You searched for +publisher:"Colorado School of Mines" +contributor:("Zhang, Hao").
Showing records 1 – 21 of
21 total matches.
Colorado School of Mines
1.
Limpiyapirom, Narongchai.
Improvement of features extraction of time series dataset by using autoencoder.
Degree: MS(M.S.), Computer Science, 2020, Colorado School of Mines
URL: http://hdl.handle.net/11124/175326 
► In this research, we studied how to extract features vector from the Multivariate Time Series dataset (MTS) by using various types of Autoencoder. Do the…
(more)
▼ In this research, we studied how to extract features vector from the Multivariate Time Series dataset (MTS) by using various types of Autoencoder. Do the classification method from these encoded vectors to show that the compressed data from Autoencoder still keeping enough essential features, although the size was reduced. The dataset that we used is blood measurements collected from patients after surgery; the result after measurement will represent that patients have surgical site infections or not. This dataset contains many missing data, so not just only deal with the compressing method, we are also facing with sparse data problem so that the imputation method will be performed to recover the data back. To sum up, our research will show the capability to compress features vector from sparse multivariate time series datasets while keeping enough information.
Advisors/Committee Members: Wang, Hua (advisor), Zhang, Hao (committee member), Wu, Bo (committee member).
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Limpiyapirom, N. (2020). Improvement of features extraction of time series dataset by using autoencoder. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/175326
Chicago Manual of Style (16th Edition):
Limpiyapirom, Narongchai. “Improvement of features extraction of time series dataset by using autoencoder.” 2020. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/175326.
MLA Handbook (7th Edition):
Limpiyapirom, Narongchai. “Improvement of features extraction of time series dataset by using autoencoder.” 2020. Web. 16 Apr 2021.
Vancouver:
Limpiyapirom N. Improvement of features extraction of time series dataset by using autoencoder. [Internet] [Masters thesis]. Colorado School of Mines; 2020. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/175326.
Council of Science Editors:
Limpiyapirom N. Improvement of features extraction of time series dataset by using autoencoder. [Masters Thesis]. Colorado School of Mines; 2020. Available from: http://hdl.handle.net/11124/175326
Colorado School of Mines
2.
Li, Ming.
Security and privacy on smartphones: a sensing approach.
Degree: PhD, Computer Science, 2020, Colorado School of Mines
URL: http://hdl.handle.net/11124/174214
► The technological advancements have made smartphones an indispensable component of our daily lives. Security and privacy (S&P) on smartphones has thus become an important research…
(more)
▼ The technological advancements have made smartphones an indispensable component of our daily lives. Security and privacy (S&P) on smartphones has thus become an important research topic. Since there are no universally applicable solutions to solve S&P issues on smartphones, we conduct our research in a case study manner, with a focus on smartphone sensors. We propose Spy-Phone to show how smartphones get eavesdropped by motion sensors, Ultra-Unlock to authenticate users with gestures in the air, and MoVo to protect voice authentication systems against spoofing attacks. In detail, the Spy-Phone system turns smartphones into spy bugs by performing Man-in- the-Phone attack. Such an attack is based on the fact that motion sensors (accelerometers and gyroscopes) can measure audio signals, though at a much lower sampling rate. It is a big threat to smartphone users since the phone’s operating system grants applications permissions to motion sensors automatically. Ultra-Unlock uses the microphones and speakers in smartphones to send ultrasound signals and catch users’ finger movements, then utilizes these user-specific movements to unlock the phone. It is a great alternative to the password/fingerprint authentication when users’ fingers are dirty or wet and to the face authentication when users wear masks or goggles. MoVo is a spoof-proof voice authentication system that not only authenticates users by their voices but also differentiates live people and electronic devices. In other words, attackers are unable to unlock the phone by replay attack (attackers record the victim’s voice in person or online, then replay the recording and access the victim’s devices illegally). The idea is to utilize the self demodulation effect and acoustic attenuation effect that occurred when sound signals transmit through human bodies. Motion sensors are used to catch such signals.
Advisors/Committee Members: Yang, Dejun (advisor), Camp, Tracy (committee member), Wakin, Michael B. (committee member), Zhang, Hao (committee member).
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Li, M. (2020). Security and privacy on smartphones: a sensing approach. (Doctoral Dissertation). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/174214
Chicago Manual of Style (16th Edition):
Li, Ming. “Security and privacy on smartphones: a sensing approach.” 2020. Doctoral Dissertation, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/174214.
MLA Handbook (7th Edition):
Li, Ming. “Security and privacy on smartphones: a sensing approach.” 2020. Web. 16 Apr 2021.
Vancouver:
Li M. Security and privacy on smartphones: a sensing approach. [Internet] [Doctoral dissertation]. Colorado School of Mines; 2020. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/174214.
Council of Science Editors:
Li M. Security and privacy on smartphones: a sensing approach. [Doctoral Dissertation]. Colorado School of Mines; 2020. Available from: http://hdl.handle.net/11124/174214
Colorado School of Mines
3.
Zhu, Lixiao.
Effects of proactive explanations by autonomous systems on human-robot trust.
Degree: MS(M.S.), Computer Science, 2020, Colorado School of Mines
URL: http://hdl.handle.net/11124/174193
► Human-Robot Interaction (HRI) seeks understanding, designing, and evaluating of robots for human-robot teams. Previous research has indicated that the performance of human-robot teams depends on…
(more)
▼ Human-Robot Interaction (HRI) seeks understanding, designing, and evaluating of robots for human-robot teams. Previous research has indicated that the performance of human-robot teams depends on human-robot trust, which in turn depends on appropriate robot-to-human transparency. In this thesis, we explore one strategy for improving robot transparency, proactive explanations, and its effect on the human-robot trust. We also introduce a resource management testbed, in which human participants engage in a resource management exercise while a robot teammate performs an assistive task. Our results suggest that there is a positive relationship between providing proactive explanations and human-robot trust.
Advisors/Committee Members: Williams, Thomas (advisor), Zhang, Hao (committee member), Mehta, Dinesh P. (committee member).
Subjects/Keywords: human-robot trust; human-robot interaction; proactive explanations
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Zhu, L. (2020). Effects of proactive explanations by autonomous systems on human-robot trust. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/174193
Chicago Manual of Style (16th Edition):
Zhu, Lixiao. “Effects of proactive explanations by autonomous systems on human-robot trust.” 2020. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/174193.
MLA Handbook (7th Edition):
Zhu, Lixiao. “Effects of proactive explanations by autonomous systems on human-robot trust.” 2020. Web. 16 Apr 2021.
Vancouver:
Zhu L. Effects of proactive explanations by autonomous systems on human-robot trust. [Internet] [Masters thesis]. Colorado School of Mines; 2020. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/174193.
Council of Science Editors:
Zhu L. Effects of proactive explanations by autonomous systems on human-robot trust. [Masters Thesis]. Colorado School of Mines; 2020. Available from: http://hdl.handle.net/11124/174193
Colorado School of Mines
4.
Li, Ming.
Spectrum monitoring in cognitive radio networks: a game-theoretical approach.
Degree: MS(M.S.), Electrical Engineering and Computer Science, 2015, Colorado School of Mines
URL: http://hdl.handle.net/11124/17147
► Opportunistic spectrum access is a great way to improve the spectrum utilization, but it also generates spectrum misuse problems. We employ limited number of monitors…
(more)
▼ Opportunistic spectrum access is a great way to improve the spectrum utilization, but it also generates spectrum misuse problems. We employ limited number of monitors to dynamically monitor all channels concerned, then detect and punish the malicious secondary users. The problem is which channels to monitor, how long to monitor each channel, and in which order to monitor them. We model this problem as an adversarial multi-armed bandit problem with switching costs. To solve this problem, we propose two algorithms. The first algorithm selects strategies based on monitoring history and maintains same strategy for some time to reduce switching costs. We prove its expected weak regret to be O(T
2/3) where T is the time horizon. The second algorithm is modified to have more parameters and cover all channels more efficiently. We show there exists a confidence bound of the new algorithm's weak regret (still O(T
2/3). We also simulate the algorithm with different types of adversaries. Simulation results indicate the bounds hold and our algorithms sometimes outperform the best fixed strategy.
Advisors/Committee Members: Yang, Dejun (advisor), Mehta, Dinesh P. (committee member), Zhang, Hao (committee member).
Subjects/Keywords: switching cost; spectrum monitoring; multi-armed bandit problem; cognitive radio networks; Cognitive radio networks; Algorithms; Algorithms – Evaluation; Game theory
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Li, M. (2015). Spectrum monitoring in cognitive radio networks: a game-theoretical approach. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/17147
Chicago Manual of Style (16th Edition):
Li, Ming. “Spectrum monitoring in cognitive radio networks: a game-theoretical approach.” 2015. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/17147.
MLA Handbook (7th Edition):
Li, Ming. “Spectrum monitoring in cognitive radio networks: a game-theoretical approach.” 2015. Web. 16 Apr 2021.
Vancouver:
Li M. Spectrum monitoring in cognitive radio networks: a game-theoretical approach. [Internet] [Masters thesis]. Colorado School of Mines; 2015. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/17147.
Council of Science Editors:
Li M. Spectrum monitoring in cognitive radio networks: a game-theoretical approach. [Masters Thesis]. Colorado School of Mines; 2015. Available from: http://hdl.handle.net/11124/17147
Colorado School of Mines
5.
Burmeister, Joshua.
Anticipation guided proactive intention prediction for assistive robots.
Degree: MS(M.S.), Mechanical Engineering, 2017, Colorado School of Mines
URL: http://hdl.handle.net/11124/170681
► When a person is performing a task, a human observer usually makes guesses about the person's intent by considering his/her own past experiences. Humans often…
(more)
▼ When a person is performing a task, a human observer usually makes guesses about the person's intent by considering his/her own past experiences. Humans often do this when they are assisting another in completing a task. Making guesses not only involves solid evidence (observations), but also draws on anticipated evidence (intuition) to predict possible future intent. Benefits of guessing include, quick decision making, lower reliance on observations, intuitiveness, and naturalness. These benefits have inspired a proactive guess method that allows a robot to infer human intentions. These inferences are intended to be used by a robot to make predictions about the best way to assist humans. The proactive guess involves intention predictions which are guided by future-object anticipations. To collect anticipation knowledge for supporting a robot's intuition, a reinforcement learning algorithm is adopted to summarize general object usage relationships from human demonstrations. To simulate overall intention knowledge in practical human-centered situations to support observations, we adopt a multi-class support vector machine (SVM) model which integrates both solid and anticipated evidence. With experiments from five practical daily scenarios, the proactive guess method is able to reliably make proactive intention predictions with a high accuracy rate.
Advisors/Committee Members: Zhang, Xiaoli (advisor), Steele, John P. H. (committee member), Zhang, Hao (committee member).
Subjects/Keywords: assistive robots; machine learning; intention prediction; anticipation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Burmeister, J. (2017). Anticipation guided proactive intention prediction for assistive robots. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/170681
Chicago Manual of Style (16th Edition):
Burmeister, Joshua. “Anticipation guided proactive intention prediction for assistive robots.” 2017. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/170681.
MLA Handbook (7th Edition):
Burmeister, Joshua. “Anticipation guided proactive intention prediction for assistive robots.” 2017. Web. 16 Apr 2021.
Vancouver:
Burmeister J. Anticipation guided proactive intention prediction for assistive robots. [Internet] [Masters thesis]. Colorado School of Mines; 2017. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/170681.
Council of Science Editors:
Burmeister J. Anticipation guided proactive intention prediction for assistive robots. [Masters Thesis]. Colorado School of Mines; 2017. Available from: http://hdl.handle.net/11124/170681
Colorado School of Mines
6.
Reily, Brian J.
Human activity recognition and gymnastics analysis through depth imagery.
Degree: MS(M.S.), Electrical Engineering and Computer Science, 2016, Colorado School of Mines
URL: http://hdl.handle.net/11124/170153
► Depth imagery is transforming many areas of computer vision, such as object recognition, human detection, human activity recognition, and sports analysis. The goal of my…
(more)
▼ Depth imagery is transforming many areas of computer vision, such as object recognition, human detection, human activity recognition, and sports analysis. The goal of my work is twofold: (1) use depth imagery to effectively analyze the pommel horse event in men’s gymnastics, and (2) explore and build upon the use of depth imagery to recognize human activities through skeleton representation. I show that my gymnastics analysis system can accurately segment a scene based on depth to identify a ‘depth of interest’, ably recognize activities on the pommel horse using only the gymnast’s silhouette, and provide an informative analysis of the gymnast’s performance. This system runs in real-time on an inexpensive laptop, and has been built into an application in use by elite gymnastics coaches. Furthermore, I present my work expanding on a bio-inspired skeleton representation obtained through depth data. This representation outperforms existing methods in classification accuracy on benchmark datasets. I then show that it can be used to interact in real-time with a Baxter humanoid robot, and is more accurate at recognizing both complete and ongoing interactions than current state-of-the-art methods.
Advisors/Committee Members: Hoff, William A. (advisor), Zhang, Hao (advisor), Wang, Hua (committee member), Celik, Ozkan (committee member).
Subjects/Keywords: activity prediction; activity recognition; depth imagery; gymnastics; image segmentation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Reily, B. J. (2016). Human activity recognition and gymnastics analysis through depth imagery. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/170153
Chicago Manual of Style (16th Edition):
Reily, Brian J. “Human activity recognition and gymnastics analysis through depth imagery.” 2016. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/170153.
MLA Handbook (7th Edition):
Reily, Brian J. “Human activity recognition and gymnastics analysis through depth imagery.” 2016. Web. 16 Apr 2021.
Vancouver:
Reily BJ. Human activity recognition and gymnastics analysis through depth imagery. [Internet] [Masters thesis]. Colorado School of Mines; 2016. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/170153.
Council of Science Editors:
Reily BJ. Human activity recognition and gymnastics analysis through depth imagery. [Masters Thesis]. Colorado School of Mines; 2016. Available from: http://hdl.handle.net/11124/170153
Colorado School of Mines
7.
Lin, Jian.
Privacy and security in crowdsensing.
Degree: PhD, Computer Science, 2019, Colorado School of Mines
URL: http://hdl.handle.net/11124/173985
► The rapid proliferation of sensor-embedded devices has enabled crowdsensing, a new paradigm which effectively collects sensing data from pervasive users. However, both the openness of…
(more)
▼ The rapid proliferation of sensor-embedded devices has enabled crowdsensing, a new paradigm which effectively collects sensing data from pervasive users. However, both the openness of crowdsensing systems and the richness of users' submitted data raise significant concerns for privacy and security. In this thesis, we aim to identify and solve privacy and security issues in crowdsensing. Specifically, we consider three important parts in crowdsensing: task allocation, incentive mechanisms, and truth discovery. In crowdsensing systems, task allocation is used to select a proper subset of users to perform tasks. Incentive mechanisms are used to stimulate users to participate in the system. Truth discovery is used to aggregate data. We first analyze privacy issues in task allocation and incentive mechanisms raised by the inference attack in which a user is able to infer other users' sensitive information according to published information. We propose two task allocation algorithms which defend against location-inference attack. To protect users' bid privacy from inference attack, we propose two frameworks for privacy-preserving incentive mechanisms. Then, we analyze the security issues in incentive mechanisms and truth discovery raised by the Sybil attack in which a user illegitimately pretends to be multiple identities to gain benets. To deter users from conducting a Sybil attack, we propose Sybil-proof incentive mechanisms for both offline and online scenarios. Additionally, we propose a Sybil-resistant truth discovery framework to diminish the impact of the Sybil attack on the aggregated data. Both simulation and experiment results show the effectiveness of the proposed works in solving privacy and security issues in crowdsensing.
Advisors/Committee Members: Yang, Dejun (advisor), Newman, Alexandra M. (committee member), Han, Qi (committee member), Zhang, Hao (committee member).
Subjects/Keywords: incentive mechanism; Sybil attack; inference attack; crowdsensing
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Lin, J. (2019). Privacy and security in crowdsensing. (Doctoral Dissertation). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/173985
Chicago Manual of Style (16th Edition):
Lin, Jian. “Privacy and security in crowdsensing.” 2019. Doctoral Dissertation, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/173985.
MLA Handbook (7th Edition):
Lin, Jian. “Privacy and security in crowdsensing.” 2019. Web. 16 Apr 2021.
Vancouver:
Lin J. Privacy and security in crowdsensing. [Internet] [Doctoral dissertation]. Colorado School of Mines; 2019. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/173985.
Council of Science Editors:
Lin J. Privacy and security in crowdsensing. [Doctoral Dissertation]. Colorado School of Mines; 2019. Available from: http://hdl.handle.net/11124/173985
Colorado School of Mines
8.
Zhang, Yuhui.
Spectrum auctions under physical interference model.
Degree: MS(M.S.), Electrical Engineering and Computer Science, 2016, Colorado School of Mines
URL: http://hdl.handle.net/11124/170308
► Spectrum auctions provide a platform for licensed spectrum users to share their underutilized spectrum with unlicensed users. Existing spectrum auctions either use the protocol interference…
(more)
▼ Spectrum auctions provide a platform for licensed spectrum users to share their underutilized spectrum with unlicensed users. Existing spectrum auctions either use the protocol interference model to characterize interference relationship as binary, or do not allow the primary and secondary users to share channels simultaneously. To ll this void, we design SPA, a spectrum single-sided auction under the physical interference model, which considers the interference to be accumulative. We prove that SPA is computationally ecient, individualrational, and truthful. Results from extensive simulation studies demonstrate that, SPA achieves higher revenue, spectrum utilization and buyer satisfaction ratio, compared with the existing auctions modied with the physical interference model.
Advisors/Committee Members: Yang, Dejun (advisor), Zhang, Hao (committee member), Mehta, Dinesh P. (committee member).
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Zhang, Y. (2016). Spectrum auctions under physical interference model. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/170308
Chicago Manual of Style (16th Edition):
Zhang, Yuhui. “Spectrum auctions under physical interference model.” 2016. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/170308.
MLA Handbook (7th Edition):
Zhang, Yuhui. “Spectrum auctions under physical interference model.” 2016. Web. 16 Apr 2021.
Vancouver:
Zhang Y. Spectrum auctions under physical interference model. [Internet] [Masters thesis]. Colorado School of Mines; 2016. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/170308.
Council of Science Editors:
Zhang Y. Spectrum auctions under physical interference model. [Masters Thesis]. Colorado School of Mines; 2016. Available from: http://hdl.handle.net/11124/170308
Colorado School of Mines
9.
Lesak, Mark C.
Odometry for autonomous navigation in GPS denied environments.
Degree: MS(M.S.), Mechanical Engineering, 2019, Colorado School of Mines
URL: http://hdl.handle.net/11124/173044
► The mining industry is dangerous and puts human lives at risk daily, including hazardous environments such as: poor air quality due to gas leaks and…
(more)
▼ The mining industry is dangerous and puts human lives at risk daily, including hazardous environments such as: poor air quality due to gas leaks and dust, unstable structural mine adits after controlled detonations or natural disasters, and possible entrapment. Robots that can safely navigate into underground mining environments can conduct reconnaissance to inspect these hazardous environments reducing the risk to human lives. This thesis presents methods to enable autonomous navigation in underground
mines, to include: 1) the system design for a flying platform, 2) computer vision techniques to extract the real-time pose of a moving robot, and 3) a Map Free LiDAR Odometry (MFLO) method. The flying platform system design focused on autonomously navigating in an underground mine. The complete system incorporates multiple sensors, an on-board embedded system, electrical connections, cabling, and an on-board power management system. Software was developed that integrates the sensors and fuses the measurements to be utilized for real-time odometry, obstacle avoidance, and control updates. A health monitor node was expanded to further ensure the safety of the aircraft. Computer vision strategies were developed to calculate the real-time pose of a moving robot with respect to a known static robot's position. The methods are: 1) ArUco Marker Identification, and 2) LED marker identification. Results are captured for both ArCuo and LED marker identification methods. Lastly, a real-time method to extract 3D ego-motion using a range flow constraint equation was developed. The method is map free, computationally light-weight, and reliable. MFLO is designed to operate in GPS-denied and light-deficient environments, making it ideal for small autonomous systems operating in underground
mines. The range flow approach presented here performs up to 0.46% position accuracy for an underground mine environment with a computation time of 20 – 96\,ms, depending on sensor resolution.
Advisors/Committee Members: Petruska, Andrew J. (advisor), Zhang, Hao (committee member), Zhang, Xiaoli (committee member).
Subjects/Keywords: ego-motion estimation; odometry; robotics; LiDAR; continuous-time; Range Flow
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Lesak, M. C. (2019). Odometry for autonomous navigation in GPS denied environments. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/173044
Chicago Manual of Style (16th Edition):
Lesak, Mark C. “Odometry for autonomous navigation in GPS denied environments.” 2019. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/173044.
MLA Handbook (7th Edition):
Lesak, Mark C. “Odometry for autonomous navigation in GPS denied environments.” 2019. Web. 16 Apr 2021.
Vancouver:
Lesak MC. Odometry for autonomous navigation in GPS denied environments. [Internet] [Masters thesis]. Colorado School of Mines; 2019. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/173044.
Council of Science Editors:
Lesak MC. Odometry for autonomous navigation in GPS denied environments. [Masters Thesis]. Colorado School of Mines; 2019. Available from: http://hdl.handle.net/11124/173044
Colorado School of Mines
10.
Liu, Rui.
Cognitive comprehension framework for human-centered situation learning and adaptation in robotics, A.
Degree: PhD, Mechanical Engineering, 2018, Colorado School of Mines
URL: http://hdl.handle.net/11124/172274
► Human-centered environment, which is defined by robots, human, and environmental conditions, is a key part of robot task executions. Accurate understanding of human-centered environment is…
(more)
▼ Human-centered environment, which is defined by robots, human, and environmental conditions, is a key part of robot task executions. Accurate understanding of human-centered environment is the precondition of successful robot executions in real-world situations. However, in practical situations, there are a lot of environment uncertainties, such as task execution dynamics, tool/human user varieties, temporal/spatial limitations and scenario unstructured characteristics. Robot task execution performances have been largely undermined when robot task execution goes from controlled lab environments to uncontrolled practical environments. To improve robot execution performances in practical human-centered environments, in this dissertation, a three-layer cognitive framework is designed to support comprehensive robot understandings for dealing with environment uncertainties, making robot to “think” like a human, instead of merely to “act” like a human. With the cognitive comprehension framework, mainly three contributions have been made: 1). by abstracting low-level executions and real-world observations of human behaviors, robot behaviors, and environment conditions, high-level cognitive understanding is generated from a human perspective, endowing robots with abstract understanding of human-centered situations, 2). by flexibly decomposing a high-level abstract goal into low-level execution details, robots are able to flexibly make plans and revise plans according to human requirements and environment condition limitations, and 3). the three-layer cognitive framework is updated and evolved as more robot commonsense knowledge is learned. In this dissertation research, this framework is cooperated with efficient robot knowledge learning methods, such as web-mining supported knowledge collection and learning from demonstrations, supporting adaptive robot executions with different domain knowledge.
Advisors/Committee Members: Zhang, Xiaoli (advisor), Zhang, Hao (committee member), King, Jeffrey C. (committee member), Stebner, Aaron P. (committee member).
Subjects/Keywords: cognitive robotics; environment adaptation; robot learning; decision making; artificial intelligence; human-robot interaction
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Liu, R. (2018). Cognitive comprehension framework for human-centered situation learning and adaptation in robotics, A. (Doctoral Dissertation). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/172274
Chicago Manual of Style (16th Edition):
Liu, Rui. “Cognitive comprehension framework for human-centered situation learning and adaptation in robotics, A.” 2018. Doctoral Dissertation, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/172274.
MLA Handbook (7th Edition):
Liu, Rui. “Cognitive comprehension framework for human-centered situation learning and adaptation in robotics, A.” 2018. Web. 16 Apr 2021.
Vancouver:
Liu R. Cognitive comprehension framework for human-centered situation learning and adaptation in robotics, A. [Internet] [Doctoral dissertation]. Colorado School of Mines; 2018. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/172274.
Council of Science Editors:
Liu R. Cognitive comprehension framework for human-centered situation learning and adaptation in robotics, A. [Doctoral Dissertation]. Colorado School of Mines; 2018. Available from: http://hdl.handle.net/11124/172274
Colorado School of Mines
11.
Osterhout, Samuel.
Design, assembly, programming, and testing of triaxially-nested Helmholtz coils, The.
Degree: MS(M.S.), Mechanical Engineering, 2018, Colorado School of Mines
URL: http://hdl.handle.net/11124/172404
► This thesis entails the full development and testing of tri-axially nested square Helmholtz coils. A novel geometric approach is presented which enables the reader to…
(more)
▼ This thesis entails the full development and testing of tri-axially nested square Helmholtz coils. A novel geometric approach is presented which enables the reader to reduce the overall size of the Helmholtz assembly without sacrificing any volume in the workspace. Included in the Appendix of this thesis are all of the mechanical and electrical drawings and bills of materials required for a full-scale reproduction of this project. There, the reader may also find a complete wiring schematic for the system. A comprehensive set of assembly and wiring instructions are provided. Two adaptations of the Biot-Savart law are developed in this paper which offer a means of calculating the B field, given the position of interest, the coil geometry, and the amount of current passing through the coil. The pseudoinverse is also used to calculate coefficients needed to calibrate the system. The Helmholtz system is capable of producing a field with a homogeneity of approximately 0.75% given a field strength to coil radius ratio of 0.219, exceeding performance criteria for typical Helmholtz coil assemblies. System performance is monitored using a three-axis hall magnetometer, the setup and results of which are presented and used to validate the system geometry and both approximation methods presented. For an outline of the overall system functionality, this paper details the structure of code written for system development and testing. This is accompanied by a discussion of the graphical user interface written for controlling and monitoring system performance.
Advisors/Committee Members: Petruska, Andrew J. (advisor), Petrella, Anthony J. (committee member), Zhang, Hao (committee member), Han, Qi (committee member).
Subjects/Keywords: gradient; homogeneous; magnetism; Helmholtz; field; magnetic
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Osterhout, S. (2018). Design, assembly, programming, and testing of triaxially-nested Helmholtz coils, The. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/172404
Chicago Manual of Style (16th Edition):
Osterhout, Samuel. “Design, assembly, programming, and testing of triaxially-nested Helmholtz coils, The.” 2018. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/172404.
MLA Handbook (7th Edition):
Osterhout, Samuel. “Design, assembly, programming, and testing of triaxially-nested Helmholtz coils, The.” 2018. Web. 16 Apr 2021.
Vancouver:
Osterhout S. Design, assembly, programming, and testing of triaxially-nested Helmholtz coils, The. [Internet] [Masters thesis]. Colorado School of Mines; 2018. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/172404.
Council of Science Editors:
Osterhout S. Design, assembly, programming, and testing of triaxially-nested Helmholtz coils, The. [Masters Thesis]. Colorado School of Mines; 2018. Available from: http://hdl.handle.net/11124/172404
Colorado School of Mines
12.
Saadatzi, Mohammadhossein.
Combined simulation of musculoskeletal biomechanics and exoskeletons.
Degree: PhD, Mechanical Engineering, 2018, Colorado School of Mines
URL: http://hdl.handle.net/11124/172541
► Wearable robots are becoming increasingly common, in both research laboratories and the industry, due to their significant potential benefits in rehabilitation engineering, assistive robotics, ergonomics,…
(more)
▼ Wearable robots are becoming increasingly common, in both research laboratories and the industry, due to their significant potential benefits in rehabilitation engineering, assistive robotics, ergonomics, and power augmentation. Thus far, design and control of these devices have primarily relied on exhaustive experimental procedures. Alternatively, combined predictive simulations of device and human musculoskeletal mechanics offer a promising approach to decreasing necessary human subject experiment scenarios and cost. In simulation, the device parameter space can be explored to determine the most promising design solutions and parameter values, which, in turn, can inform the human subject experiment design. This dissertation focuses on building a framework for combined musculoskeletal and exoskeleton dynamics for walking. In the framework, the actuation profiles of body muscles are optimized using a single-shooting method. The single-shooting method facilitates convenient consideration of human musculoskeletal system models with varying levels of complexity, various exoskeletons and controllers, and different objective functions. High-throughput computing resources are employed for the computationally-intensive optimizations in this framework. The proposed framework is used for study and design of passive exoskeletons for reducing the metabolic energy expenditure during walking. The simulation results suggest that elastic elements acting in parallel with lower-limb uniarticular muscles can reduce the metabolic cost of walking by up to 28%. These results support the use of predictive simulations as a tool for the study and conceptual design of exoskeletons and can accelerate device and control development.
Advisors/Committee Members: Silverman, Anne K. (advisor), Celik, Ozkan (committee member), Bach, Joel M. (committee member), Petrella, Anthony J. (committee member), Zhang, Hao (committee member).
Subjects/Keywords: bipedal walking; passive exoskeletons; wearable robots; metabolic energy expenditure; biomechanics; predictive simulation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Saadatzi, M. (2018). Combined simulation of musculoskeletal biomechanics and exoskeletons. (Doctoral Dissertation). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/172541
Chicago Manual of Style (16th Edition):
Saadatzi, Mohammadhossein. “Combined simulation of musculoskeletal biomechanics and exoskeletons.” 2018. Doctoral Dissertation, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/172541.
MLA Handbook (7th Edition):
Saadatzi, Mohammadhossein. “Combined simulation of musculoskeletal biomechanics and exoskeletons.” 2018. Web. 16 Apr 2021.
Vancouver:
Saadatzi M. Combined simulation of musculoskeletal biomechanics and exoskeletons. [Internet] [Doctoral dissertation]. Colorado School of Mines; 2018. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/172541.
Council of Science Editors:
Saadatzi M. Combined simulation of musculoskeletal biomechanics and exoskeletons. [Doctoral Dissertation]. Colorado School of Mines; 2018. Available from: http://hdl.handle.net/11124/172541
Colorado School of Mines
13.
Li, Songpo.
Novel intuitive human-robot interaction using 3D gaze.
Degree: PhD, Mechanical Engineering, 2017, Colorado School of Mines
URL: http://hdl.handle.net/11124/170993
► Human-centered robotics has become a new trend in robotic research in which robots closely work around humans or even directly/indirectly make contact with humans. Human-centered…
(more)
▼ Human-centered robotics has become a new trend in robotic research in which robots closely work around humans or even directly/indirectly make contact with humans. Human-centered robotics not only requires the robot to successfully and safely accomplish the given task, but also requires it to establish a rapport with humans by considering human factors. Human-robot interaction (HRI) has been an essential component in human-centered robotics due to the fundamental information exchange between the human and the robot, which plays an essential role in the task success and rapport establishment. In this dissertation, human gaze, which indicates where a person is looking, is scientifically studied as an intuitive and effective HRI modality. The gaze modality is natural and effortless to utilize, and from gaze modality, rich information about a user's mental state can be revealed. Despite the promise of gaze modality, applying gaze as an interaction modality is significantly limited by the virtual gaze tracking technology available and low-level gaze interpretation. Three-dimensional (3D) gaze tracking in real environments, which measures the 3D Cartesian location of where a person is looking, is highly desirable for intuitive and effective HRI in human-centered robotics. Employing 3D gaze as an interaction modality not only indicates the manipulation target, but also reports the location of the target and suggests how to perform the manipulation on it. The goal of this dissertation is to achieve the novel 3D-gaze-based HRI modality, with which a user can intuitively express what tasks he/she wants the robot to do by directly looking at the object of interest in the real world. In working toward this goal, the investigation concentrates on 1) the technology to accurately sense where a person is looking in real environments and 2) the method to interpret the human gaze and convert it into an effective interaction modality. This new interaction modality is expected to benefit users who have impaired mobility in their daily living as well as able-bodied users who need an additional hand in general working scenarios.
Advisors/Committee Members: Zhang, Xiaoli (advisor), Zhang, Hao (committee member), Hoff, William A. (committee member), Steele, John P. H. (committee member).
Subjects/Keywords: assistive robot; human-robot interaction; 3D gaze; intention awareness; attention awareness
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Li, S. (2017). Novel intuitive human-robot interaction using 3D gaze. (Doctoral Dissertation). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/170993
Chicago Manual of Style (16th Edition):
Li, Songpo. “Novel intuitive human-robot interaction using 3D gaze.” 2017. Doctoral Dissertation, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/170993.
MLA Handbook (7th Edition):
Li, Songpo. “Novel intuitive human-robot interaction using 3D gaze.” 2017. Web. 16 Apr 2021.
Vancouver:
Li S. Novel intuitive human-robot interaction using 3D gaze. [Internet] [Doctoral dissertation]. Colorado School of Mines; 2017. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/170993.
Council of Science Editors:
Li S. Novel intuitive human-robot interaction using 3D gaze. [Doctoral Dissertation]. Colorado School of Mines; 2017. Available from: http://hdl.handle.net/11124/170993
Colorado School of Mines
14.
Han, Fei.
Representation learning for long-term collaborative autonomy.
Degree: PhD, Computer Science, 2018, Colorado School of Mines
URL: http://hdl.handle.net/11124/172260
► Autonomy has attracted a lot of research attention over the past few decades, since it is the key capability of all autonomous systems, including unmanned…
(more)
▼ Autonomy has attracted a lot of research attention over the past few decades, since it is the key capability of all autonomous systems, including unmanned aerial vehicles (UAV), unmanned ground vehicles (UGV), unmanned surface vehicles (USV), humanoid robots, etc. Those fully or partially autonomous systems have been transforming the way people work, live, and communicate nowadays, e.g. automated AC systems in the building, robot arms manufacturing cars in the factory, etc. On the other hand, robots or intelligent agents usually do not work alone, such as assistance robots, coaching robots, self-driving cars, etc. They need to observe, learn from, and reflect with human beings. When robots enable to interact and collaborate with humans autonomously, we call it collaborative autonomy. Collaborative autonomy is a very challenging problem, which requires robots to have both great perception and decision making capabilities. It becomes even more challenging when this collaborative autonomy can be continuously performed in a long-term period, since there would be strong appearance variations of the environment, such as changes of illumination, weather, and vegetation conditions across months or even seasons. Humans can easily identify the same object and place in different times of the day, months, and seasons. However, this critical long-term perception capability is very challenging for real-world robots though it is the key to enable long-term autonomy. This research investigates the perception problems for long-term collaborative autonomy. In this dissertation, several representation learning approaches are introduced to improve the real-time perception performance of robots in the long-term period. Firstly, I introduce a 3D human skeletal representation learning approach to enable real-time robot awareness of human behaviors, which is invariant to viewpoint, human body scale and motion speed. Then, multiple representation learning approaches are presented for the long-term place recognition problem, which enables the life-long relocalization of robots with a single camera. Finally, we demonstrate that the learned representation using the approaches proposed in this dissertation can be integrated in the online robotic decision making system and enables the long-term collaborative autonomy capability.
Advisors/Committee Members: Zhang, Hao (advisor), Wang, Hua (advisor), Camp, Tracy (committee member), Zhang, Xiaoli (committee member), Yue, Chuan (committee member).
Subjects/Keywords: long-term autonomy; robotic perception; representation learning; collaborative autonomy
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Han, F. (2018). Representation learning for long-term collaborative autonomy. (Doctoral Dissertation). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/172260
Chicago Manual of Style (16th Edition):
Han, Fei. “Representation learning for long-term collaborative autonomy.” 2018. Doctoral Dissertation, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/172260.
MLA Handbook (7th Edition):
Han, Fei. “Representation learning for long-term collaborative autonomy.” 2018. Web. 16 Apr 2021.
Vancouver:
Han F. Representation learning for long-term collaborative autonomy. [Internet] [Doctoral dissertation]. Colorado School of Mines; 2018. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/172260.
Council of Science Editors:
Han F. Representation learning for long-term collaborative autonomy. [Doctoral Dissertation]. Colorado School of Mines; 2018. Available from: http://hdl.handle.net/11124/172260
Colorado School of Mines
15.
Appapogu, Rahul Dev.
Autonomous navigation in GPS denied environments using MPC and LQR with potential field based obstacle avoidance.
Degree: MS(M.S.), Mechanical Engineering, 2019, Colorado School of Mines
URL: http://hdl.handle.net/11124/172896
► Workers in mining industry are posed with hazardous environments due to the nature of the work inside a mine. Gas leaks, explosions, rock falls, entrapment,…
(more)
▼ Workers in mining industry are posed with hazardous environments due to the nature of the work inside a mine. Gas leaks, explosions, rock falls, entrapment, long exposure to dust are all potentially fatal conditions for the workers. Although solutions for the problems are being implemented, they are not sufficient and mostly are very expensive. \newline Autonomous robots can reduce the risk for miners by taking over potentially dangerous tasks for them. For instance, an autonomous robot can carry operations like air quality assessment, inspection of dangerous mine conditions and even perform search and rescue tasks in disaster situations. \newline This thesis presents robots that can traverse through the mine environment with on board sensors collecting data without any human intervention. Control and Obstacle avoidance algorithms are designed and presented in this thesis for the robots, ground and aerial platforms. A Model Predictive Control (MPC) approach is presented which includes pre-packing of necessary terms that would help decrease the computation costs. A Linear Quadratic Regulator (LQR) approach is also presented and its performance against the Model Predictive Control approach is presented in presence and absence of obstacles. A Potential Fields based obstacle avoidance approach is presented which makes use of octomaps. \newline Experimental results are promising as both aerial and ground platforms perform navigation without any GPS and avoid obstacles if any, in a simulation. Fast solve times on the order of hundreds of micro seconds are obtained and the results are compared with other existing techniques and presented. A real-time implementation of the ground robot has been made in various GPS denied environments and the results are presented. In real-time as well, the robot performs navigation avoiding obstacles in all cases.
Advisors/Committee Members: Petruska, Andrew J. (advisor), Steele, John P. H. (advisor), Zhang, Hao (committee member), Zhang, Xiaoli (committee member).
Subjects/Keywords: linear quadratic regulator; obstacle avoidance; autonomous navigation; potential fields; model predictive control
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Appapogu, R. D. (2019). Autonomous navigation in GPS denied environments using MPC and LQR with potential field based obstacle avoidance. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/172896
Chicago Manual of Style (16th Edition):
Appapogu, Rahul Dev. “Autonomous navigation in GPS denied environments using MPC and LQR with potential field based obstacle avoidance.” 2019. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/172896.
MLA Handbook (7th Edition):
Appapogu, Rahul Dev. “Autonomous navigation in GPS denied environments using MPC and LQR with potential field based obstacle avoidance.” 2019. Web. 16 Apr 2021.
Vancouver:
Appapogu RD. Autonomous navigation in GPS denied environments using MPC and LQR with potential field based obstacle avoidance. [Internet] [Masters thesis]. Colorado School of Mines; 2019. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/172896.
Council of Science Editors:
Appapogu RD. Autonomous navigation in GPS denied environments using MPC and LQR with potential field based obstacle avoidance. [Masters Thesis]. Colorado School of Mines; 2019. Available from: http://hdl.handle.net/11124/172896
Colorado School of Mines
16.
Li, Shuang.
Optimization for high-dimensional analysis and estimation in signal processing and machine learning.
Degree: PhD, Electrical Engineering, 2020, Colorado School of Mines
URL: http://hdl.handle.net/11124/174160
► High-dimensional signal analysis and estimation appears in many signal processing and machine learning applications, including modal analysis, airborne radar system demixing, parameter estimation in spectrally…
(more)
▼ High-dimensional signal analysis and estimation appears in many signal processing and machine learning applications, including modal analysis, airborne radar system demixing, parameter estimation in spectrally sparse signals, and simultaneous blind deconvolution and phase retrieval. The underlying low-dimensional structure in these high-dimensional signals inspires us to develop optimality guarantees as well as some optimization-based techniques for the fundamental problems in signal processing and machine learning.In many applications, high-dimensional signals often have a certain concise representation, which is a linear combination of a small number of atoms in a dictionary with elements drawn from the signal space. In compressive sensing,L1-minimization is a widely used framework to find the sparse representations of a signal. It has recently been shown that atomic norm minimization (ANM), which is a generalization of L1-minimization, is an efficient and powerful way for exactly recovering unobserved time-domain samples and identifying unknown frequencies in signals having sparse frequency spectra, namely, finding a concise representation for spectrally sparse signals. This new technique works on a continuous dictionary and can completely avoid the effects of basis mismatch, which can plague conventional grid-based compressive sensing techniques.Almost every problem in the fields of signal processing and machine learning can be formulated as either a convex or non-convex optimization problem. With convex formulations, we can get guaranteed global optimality but we often encounter problems with large size. Though non-convex optimization often lacks global optimality, it can have much lower computational and storage complexity. The objective of this dissertation is to (i) analyze and estimate high-dimensional signals or parameters with convex optimization-based techniques; (ii) analyze and estimate high-dimensional signals or parameters with non-convex optimization-based techniques; (iii) generalize the ideas and techniques used in optimization to differentiable games, which are games with continuous decision variables and differentiable cost functions, and have been gradually adapted to model many signal processing, communication, and networking problems in the last two decades.Our main contributions include a new (i) method to estimate the modal parameters in modal analysis, non-asymptotic bound on the sample complexity of modal analysis with random temporal compression, and non-asymptotic bound on the recovery error of an atomic norm denoising problem in the multiple measurement vector setting; (ii) analysis for the airborne radar system demixing problem, where the received signal consists of contributions from targets, jammers, and clutter; (iii) optimization-based perspective on the classical MUSIC algorithm that could lead to future developments and understanding, and non-asymptotic theoretical guarantees for the proposed algorithms; (iv) non-asymptotic theoretical bound on the mean square error of atomic…
Advisors/Committee Members: Wakin, Michael B. (advisor), Tang, Gongguo (advisor), Zhang, Hao (committee member), Tenorio, Luis (committee member), Vincent, Tyrone (committee member), Nayeri, Payam (committee member), Constantine, Paul G. (committee member).
Subjects/Keywords: signal processing; machine learning
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Li, S. (2020). Optimization for high-dimensional analysis and estimation in signal processing and machine learning. (Doctoral Dissertation). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/174160
Chicago Manual of Style (16th Edition):
Li, Shuang. “Optimization for high-dimensional analysis and estimation in signal processing and machine learning.” 2020. Doctoral Dissertation, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/174160.
MLA Handbook (7th Edition):
Li, Shuang. “Optimization for high-dimensional analysis and estimation in signal processing and machine learning.” 2020. Web. 16 Apr 2021.
Vancouver:
Li S. Optimization for high-dimensional analysis and estimation in signal processing and machine learning. [Internet] [Doctoral dissertation]. Colorado School of Mines; 2020. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/174160.
Council of Science Editors:
Li S. Optimization for high-dimensional analysis and estimation in signal processing and machine learning. [Doctoral Dissertation]. Colorado School of Mines; 2020. Available from: http://hdl.handle.net/11124/174160
Colorado School of Mines
17.
Zhao, Rui.
Vulnerability exploration and data protection in end-user applications.
Degree: PhD, Electrical Engineering and Computer Science, 2016, Colorado School of Mines
URL: http://hdl.handle.net/11124/170631
► Using different end-user applications on personal computers and mobile devices has become an integral part of our daily lives. For example, we use Web browsers…
(more)
▼ Using different end-user applications on personal computers and mobile devices has become an integral part of our daily lives. For example, we use Web browsers and mobile applications to perform many important tasks such as Web browsing, banking, shopping, and bill-paying. However, due to the security vulnerabilities in many applications and also due to the lack of security knowledge or awareness of end users, users’ sensitive data may not be properly protected in those applications and can be leaked to attackers resulting in severe consequences such as identity theft, financial loss, and privacy leakage. Therefore, exploring potential vulnerabilities and protecting sensitive data in end-user applications are of great need and importance. In this dissertation, we explore the vulnerabilities in both end-user applications and end users. In terms of end-user applications, we focus on Web browsers, browser extensions, stand-alone applications, and mobile applications by manually or automatically exploring their vulnerabilities and by proposing new data protection mechanisms. Specifically, we (1) investigate vulnerabilities of the password managers in the five most popular Web browsers, (2) investigate vulnerabilities of two commercial browser extension and cloud based password managers, (3) propose a framework for automatic detection of information leakage vulnerabilities in browser extensions, (4) propose a secure cloud storage middleware for end-user applications, and (5) investigate cross-site input inference attacks on mobile Web users. In terms of end users, we focus on phishing attacks by investigating users’ susceptibility to both traditional phishing and Single Sign-On phishing. Specifically, we (6) explore the feasibility of creating extreme phishing attacks and evaluate the effectiveness of such phishing attacks. By conducting these research projects, we expect to advance the scientific and technological understanding on protecting users’ sensitive data in applications, and make users’ online experience more secure and enjoyable.
Advisors/Committee Members: Yue, Chuan (advisor), Zhang, Xiaoli (committee member), Han, Qi (committee member), Mehta, Dinesh P. (committee member), Wang, Hua (committee member), Zhang, Hao (committee member).
Subjects/Keywords: protection; vulnerability; security; applications
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Zhao, R. (2016). Vulnerability exploration and data protection in end-user applications. (Doctoral Dissertation). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/170631
Chicago Manual of Style (16th Edition):
Zhao, Rui. “Vulnerability exploration and data protection in end-user applications.” 2016. Doctoral Dissertation, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/170631.
MLA Handbook (7th Edition):
Zhao, Rui. “Vulnerability exploration and data protection in end-user applications.” 2016. Web. 16 Apr 2021.
Vancouver:
Zhao R. Vulnerability exploration and data protection in end-user applications. [Internet] [Doctoral dissertation]. Colorado School of Mines; 2016. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/170631.
Council of Science Editors:
Zhao R. Vulnerability exploration and data protection in end-user applications. [Doctoral Dissertation]. Colorado School of Mines; 2016. Available from: http://hdl.handle.net/11124/170631
Colorado School of Mines
18.
Liu, Kai.
Study of non-negative matrix factorizations: foundations, methods, algorithms, and applications, A.
Degree: PhD, Computer Science, 2019, Colorado School of Mines
URL: http://hdl.handle.net/11124/173252
► Machine learning problems generally could be categorized into three: supervised, semi-supervised and unsupervised learning problems. In supervised learning problems, there are labels or output which…
(more)
▼ Machine learning problems generally could be categorized into three: supervised, semi-supervised and unsupervised learning problems. In supervised learning problems, there are labels or output which could be utilized to do classification or regression, while there are no labels or output in unsupervised learning. Clustering is one major topic in unsupervised learning, that given some data, we need to cluster the data into several groups. Among the methods in clustering, K-means is one of the most popular one, which is simple yet efficient. Non-negative matrix factorization (bf{NMF}) is a classical mathematical problem which aims to give two non-negative matrices F and G so that FG approximate the given nonnegative matrix X. Due to its elegant formulation, bf{NMF} has been a hot topic for the past decade, and it has been proved that bf{NMF} could also do clustering which is equivalent to K-means and give more details. Different form some existing matrix factorization methods such as bf{SVD}, bf{QR}, bf{LU} \etc, bf{NMF} has an advantage in interpretation. In real world, there are some data naturally to be nonnegative, such as the connection between people, image pixels range from 0 to 255 \etc. Existing factorization methods could not guarantee the factor matrices to be nonnegative which fails in interpretation. From the perspective of feature learning F , if some face images are given for clustering, the negative data in F is meaningless. While from the perspective of membership matrix G, some operations are only additive, for example: any color could be generated from Red, Green and Blue, the ratio of Red, Green and Blue should be non-negative. Similar situations include the function of some certain Genetics to some certain disease. Some important work has been done for the past years: basic bf{NMF} (bf{BNMF}) is proposed to give F, G with a rigid decrease in loss function with updates by making use of a method named Auxiliary Function while the nonnegative properties could be guaranteed. Graph NMF (bf{GNMF}) makes use of both intra data and inter correlation between data which is widely used for manifold data clustering. Tri-factorization has also been proposed to cluster the data and feature simultaneously which has been studied widely for the past several years. Besides the methods mentioned above, some constraint in bf{NMF} has been proposed, such as the orthogonality of membership matrix G to get a unique solution; also sparsity ratio constraint is studied with rigorous mathematical analysis and proof. However, most of the previous methods are based on Multiplicative Updating Algorithm (bf{MUA}) in bf{BNMF} which is suffered from some disadvantages: poor local minimum, time consuming, difficult to solve non-convex norm objective function or penalty. Moreover, in real experiments, there are many soft-clustering cases which is ambiguous for clustering. More importantly, though the orthogonality constraint is proposed to get rid…
Advisors/Committee Members: Wang, Hua (advisor), Tang, Gongguo (committee member), Mehta, Dinesh P. (committee member), Zhang, Hao (committee member), Williams, Thomas (committee member), Kim, Eunhye (committee member).
Subjects/Keywords: machine learning
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Liu, K. (2019). Study of non-negative matrix factorizations: foundations, methods, algorithms, and applications, A. (Doctoral Dissertation). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/173252
Chicago Manual of Style (16th Edition):
Liu, Kai. “Study of non-negative matrix factorizations: foundations, methods, algorithms, and applications, A.” 2019. Doctoral Dissertation, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/173252.
MLA Handbook (7th Edition):
Liu, Kai. “Study of non-negative matrix factorizations: foundations, methods, algorithms, and applications, A.” 2019. Web. 16 Apr 2021.
Vancouver:
Liu K. Study of non-negative matrix factorizations: foundations, methods, algorithms, and applications, A. [Internet] [Doctoral dissertation]. Colorado School of Mines; 2019. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/173252.
Council of Science Editors:
Liu K. Study of non-negative matrix factorizations: foundations, methods, algorithms, and applications, A. [Doctoral Dissertation]. Colorado School of Mines; 2019. Available from: http://hdl.handle.net/11124/173252
19.
Zhang, Ziling.
Applied machine learning for multi-sensory robot perception.
Degree: MS(M.S.), Computer Science, 2019, Colorado School of Mines
URL: http://hdl.handle.net/11124/174011
► In recent years, advances in autonomous robotics have begun to transform how we work and live. Unmanned Aerial Vehicles (UAV) and Unmanned Ground Vehicles are…
(more)
▼ In recent years, advances in autonomous robotics have begun to transform how we work and live. Unmanned Aerial Vehicles (UAV) and Unmanned Ground Vehicles are helping us to deliver goods, conduct surveys of construction sites, and perform search and rescue alongside first responders. However, designing robots with this level of autonomy is often challenging due to the complexity of the real-world environment. Multi-sensory perception is a critical component to address this challenge and develop robust autonomous robotic systems. By combining multiple inputs from sensors, the system can eliminate a single point of failure from sensor degradation and generate new insights to make better decisions integrating information from dierent sensor modalities. Recent breakthroughs in Machine Learning, especially the Deep Neural Network(DNN) based deep learning perception pipelines have been proven effective in a number of robot perception tasks. However, the significant computation cost for Deep Neural Networks is prohibiting their deployment on a robot system with limited power budget and real-time performance requirement. It is important to bridge this gap by optimization to deploy state-of-the-art machine learning models to a real-world robot systems. This work investigates the viability to develop robust multi-sensory robot perception systems enhanced by machine learning models in three different chapters. First, I explore the effectiveness of DNN perception pipelines in object detection and semantic segmentation tasks, then experiment on various model optimization techniques to enhance the efficiency of these perception models, achieving real-time performance on robot system with a limited power budget. Then I elucidate the design and implementation of a thermal sensing robot system that performs sensor fusion of a thermal camera and an RGB-Depth Camera to automatically track occupants in a building, measuring their forehead temperature, providing fine-grain information for better decision making in intelligent Air Conditioning (AC) system. Finally, I explore camera pose estimation using rectangular to spherical image matching, enabling a robot to quickly grasp a scene with spherical camera, and allow other robots to localize themselves within the scene by matching rectangular sensor images to the spherical image.
Advisors/Committee Members: Zhang, Hao (advisor), Petruska, Andrew J. (committee member), Williams, Thomas (committee member).
Subjects/Keywords: machine learning; sensor fusion; multi-sensory perception; edge computing
…41
Figure 4.2
A spherical image captured in Colorado School of Mines…
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Zhang, Z. (2019). Applied machine learning for multi-sensory robot perception. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/174011
Chicago Manual of Style (16th Edition):
Zhang, Ziling. “Applied machine learning for multi-sensory robot perception.” 2019. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/174011.
MLA Handbook (7th Edition):
Zhang, Ziling. “Applied machine learning for multi-sensory robot perception.” 2019. Web. 16 Apr 2021.
Vancouver:
Zhang Z. Applied machine learning for multi-sensory robot perception. [Internet] [Masters thesis]. Colorado School of Mines; 2019. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/174011.
Council of Science Editors:
Zhang Z. Applied machine learning for multi-sensory robot perception. [Masters Thesis]. Colorado School of Mines; 2019. Available from: http://hdl.handle.net/11124/174011
20.
Nahman, Zachary S.
Robot learning for loop closure detection and SLAM.
Degree: MS(M.S.), Computer Science, 2019, Colorado School of Mines
URL: http://hdl.handle.net/11124/173999
► Robotics and autonomy continues to be a key research and development focus around the world. Robots are increasingly prevalent in everyday life. From manufacturing, home…
(more)
▼ Robotics and autonomy continues to be a key research and development focus around the world. Robots are increasingly prevalent in everyday life. From manufacturing, home cleaning, to self-driving vehicles, robots are an ever-present reality with demonstrated ca- pability to increase quality of life for humans. As more and more robots exist surrounding humans, it becomes increasingly critical that robots can accurately sense and reason about the environment. The functionality of a robot building a map of its environment and lo- cating itself constantly within the map is known as Simultaneous Localization and Mapping (SLAM). SLAM is a difficult problem, and can be especially challenging when environmental appearance changers occur or when a GPS signal is not available. However, it’s within these challenging environments where the use of robots is critical. Consider a partially collapsed underground mine environment. If the environment is potentially dangerous, it doesn’t make sense to risk human life to enter the mine to perform search and rescue. If robots can be enabled to operate in challenging environments such as collapsed
mines, human life can be saved. This Master’s thesis addresses the problem of increasing the effectiveness of SLAM in these challenging environments. First, I describe a data structure capable of capturing environmental metadata for semantic description overlay to augment mapping capability. Secondly, I introduce a novel loop closure detection technique that utilizes robot learning to understand complex environments. These efforts combined contribute to increasing the effectiveness of SLAM in GPS-denied environments or environments with varying lighting conditions.
Advisors/Committee Members: Zhang, Hao (advisor), Petruska, Andrew J. (committee member), Wu, Bo (committee member).
Subjects/Keywords: loop closure detection; point clouds; SLAM; mapping; computer vision; robotics
…robot
exploring Colorado School of Mines’ Brown Hall 2nd floor in a big loop. The data set… …Computer Science, Colorado School of
Mines
2
Secondary researcher and author, Graduate Student… …Department of Computer Science, Colorado School of
Mines
3
Assistant Professor, Department of… …Computer Science, Colorado School of Mines
11
using 3D point cloud data and is capable of…
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Nahman, Z. S. (2019). Robot learning for loop closure detection and SLAM. (Masters Thesis). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/173999
Chicago Manual of Style (16th Edition):
Nahman, Zachary S. “Robot learning for loop closure detection and SLAM.” 2019. Masters Thesis, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/173999.
MLA Handbook (7th Edition):
Nahman, Zachary S. “Robot learning for loop closure detection and SLAM.” 2019. Web. 16 Apr 2021.
Vancouver:
Nahman ZS. Robot learning for loop closure detection and SLAM. [Internet] [Masters thesis]. Colorado School of Mines; 2019. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/173999.
Council of Science Editors:
Nahman ZS. Robot learning for loop closure detection and SLAM. [Masters Thesis]. Colorado School of Mines; 2019. Available from: http://hdl.handle.net/11124/173999
21.
Fisher, Wendy D.
Machine learning for the automatic detection of anomalous events.
Degree: PhD, Computer Science, 2017, Colorado School of Mines
URL: http://hdl.handle.net/11124/170968
► In this dissertation, we describe our research contributions for a novel approach to the application of machine learning for the automatic detection of anomalous events.…
(more)
▼ In this dissertation, we describe our research contributions for a novel approach to the application of machine learning for the automatic detection of anomalous events. We work in two different domains to ensure a robust data-driven workflow that could be generalized for monitoring other systems. Specifically, in our first domain, we begin with the identification of internal erosion events in earth dams and levees (EDLs) using geophysical data collected from sensors located on the surface of the levee. As EDLs across the globe reach the end of their design lives, effectively monitoring their structural integrity is of critical importance. The second domain of interest is related to mobile telecommunications, where we investigate a system for automatically detecting non-commercial base station routers (BSRs) operating in protected frequency space. The presence of non-commercial BSRs can disrupt the connectivity of end users, cause service issues for the commercial providers, and introduce significant security concerns. We provide our motivation, experimentation, and results from investigating a generalized novel data-driven workflow using several machine learning techniques. In Chapter 2, we present results from our performance study that uses popular unsupervised clustering algorithms to gain insights to our real-world problems, and evaluate our results using internal and external validation techniques. Using EDL passive seismic data from an experimental laboratory earth embankment, results consistently show a clear separation of events from non-events in four of the five clustering algorithms applied. The results from experimenting with our BSR data, using various system information (SI) and system information blocks (SIBs), show we can make a clear distinction between commercial and non-commercial scans in both Universal Mobile Telephone System (UMTS) and Long Term Evolution (LTE); more work is needed to understand whether non-commercial BSRs can be discovered in the Global System for Mobile Communications (GSM) analysis. We also investigate and provide results on using ASN.1 encoded LTE data as input to our machine learning algorithms; we use encoded data to eliminate the need for extensive feature selection and manual analysis that could potentially introduce bias. Chapter 3 uses a multivariate Gaussian machine learning model to identify anomalies in our experimental data sets. For the EDL work, we used experimental data from two different laboratory earth embankments. Additionally, we explore five wavelet transform methods for signal denoising. The best performance is achieved with the Haar wavelets. We achieve up to 97.3% overall accuracy and less than 1.4% false negatives in anomaly detection. Using the BSR scans, we continue to see that the GSM broadcast messages are not suitable for our anomaly detection system. However, the multivariate Gaussian approach with the UMTS, LTE, and ANS.1 encoded LTE scans were successful in separating commercial from non-commercial BSRs with 100% overall accuracy. In Chapter…
Advisors/Committee Members: Camp, Tracy (advisor), Wang, Hua (committee member), Krzhizhanovskaya, Valeria (committee member), Zhang, Hao (committee member), Navidi, William Cyrus (committee member), Stone, Kerri (committee member).
Subjects/Keywords: BSR detection; machine learning; earth dam and levee; anomaly detection
…former M.S.
student, at the Colorado School of Mines, for their assistance in collecting the…
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Fisher, W. D. (2017). Machine learning for the automatic detection of anomalous events. (Doctoral Dissertation). Colorado School of Mines. Retrieved from http://hdl.handle.net/11124/170968
Chicago Manual of Style (16th Edition):
Fisher, Wendy D. “Machine learning for the automatic detection of anomalous events.” 2017. Doctoral Dissertation, Colorado School of Mines. Accessed April 16, 2021.
http://hdl.handle.net/11124/170968.
MLA Handbook (7th Edition):
Fisher, Wendy D. “Machine learning for the automatic detection of anomalous events.” 2017. Web. 16 Apr 2021.
Vancouver:
Fisher WD. Machine learning for the automatic detection of anomalous events. [Internet] [Doctoral dissertation]. Colorado School of Mines; 2017. [cited 2021 Apr 16].
Available from: http://hdl.handle.net/11124/170968.
Council of Science Editors:
Fisher WD. Machine learning for the automatic detection of anomalous events. [Doctoral Dissertation]. Colorado School of Mines; 2017. Available from: http://hdl.handle.net/11124/170968
. 
Open Access Theses and Dissertations
