Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- TÜBİTAK (3106)
- Embry-Riddle Aeronautical University (409)
- Missouri University of Science and Technology (335)
- Old Dominion University (319)
- Air Force Institute of Technology (129)
-
- University of New Haven (74)
- University of Nebraska - Lincoln (63)
- University of Nevada, Las Vegas (62)
- University of Dar es Salaam (55)
- Western University (36)
- University of Arkansas, Fayetteville (35)
- Chapman University (34)
- Portland State University (31)
- Loyola University Chicago (27)
- University of Kentucky (27)
- Purdue University (26)
- Wayne State University (24)
- New Jersey Institute of Technology (23)
- University of Texas at El Paso (23)
- University of Malaya (21)
- University of South Florida (21)
- California Polytechnic State University, San Luis Obispo (18)
- Michigan Technological University (18)
- South Dakota State University (15)
- Technological University Dublin (15)
- Munster Technological University (14)
- University of Denver (14)
- University of South Carolina (14)
- University of New Mexico (13)
- Washington University in St. Louis (13)
- Keyword
-
- Machine learning (152)
- Deep learning (128)
- Classification (87)
- Optimization (85)
- Genetic algorithm (61)
-
- Neural networks (54)
- Particle swarm optimization (53)
- Security (53)
- Digital forensics (48)
- Image processing (48)
- Artificial intelligence (47)
- Feature extraction (46)
- Clustering (43)
- Machine Learning (43)
- Computer vision (42)
- Wireless sensor networks (41)
- Artificial neural networks (40)
- Algorithms (37)
- Feature selection (37)
- Support vector machine (37)
- Artificial neural network (35)
- Deep Learning (35)
- Fuzzy logic (34)
- Convolutional neural network (30)
- Convolutional neural networks (30)
- Cybersecurity (30)
- Reinforcement learning (29)
- Natural language processing (28)
- Neural network (28)
- Power quality (28)
- Publication Year
- Publication
-
- Turkish Journal of Electrical Engineering and Computer Sciences (3106)
- Journal of Digital Forensics, Security and Law (290)
- Electrical and Computer Engineering Faculty Research & Creative Works (282)
- Theses and Dissertations (127)
- Electrical & Computer Engineering Theses & Dissertations (120)
-
- Electrical & Computer Engineering Faculty Publications (109)
- Annual ADFSL Conference on Digital Forensics, Security and Law (100)
- Electrical & Computer Engineering and Computer Science Faculty Publications (71)
- Tanzania Journal of Engineering and Technology (TJET) (50)
- School of Computing: Conference and Workshop Papers (44)
- Electrical and Computer Engineering Publications (36)
- Electronic Theses and Dissertations (34)
- Computer Science: Faculty Publications and Other Works (27)
- Faculty Publications (27)
- UNLV Theses, Dissertations, Professional Papers, and Capstones (26)
- Dissertations (25)
- Engineering Faculty Articles and Research (25)
- Open Access Theses & Dissertations (23)
- USF Tampa Graduate Theses and Dissertations (20)
- Chemical Engineering and Materials Science Faculty Research Publications (19)
- Computer Science Faculty Research & Creative Works (19)
- Graduate Theses and Dissertations (19)
- Computer Science Faculty Publications (18)
- Dissertations and Theses (18)
- Publications (18)
- Doctoral Dissertations (17)
- Engineering Technology Faculty Publications (16)
- Fred and Harriet Cox Senior Design Competition Projects (16)
- VMASC Publications (15)
- Electrical & Computer Engineering Faculty Research (14)
- Publication Type
- File Type
Articles 3571 - 3600 of 5275
Full-Text Articles in Computer Sciences
A Model-Based Fault Detection And Prognostics Scheme For Takagi-Sugeno Fuzzy Systems, Balaje T. Thumati, Miles A. Feinstein, S. Jagannathan
A Model-Based Fault Detection And Prognostics Scheme For Takagi-Sugeno Fuzzy Systems, Balaje T. Thumati, Miles A. Feinstein, S. Jagannathan
Electrical and Computer Engineering Faculty Research & Creative Works
In this paper, a novel model-based fault detection (FD) and prediction scheme is developed for a class of Takagi-Sugeno (T-S) fuzzy systems. Unlike other FD schemes, in the proposed design, an FD observer with online fault learning capability is utilized to generate a residual which is obtained by comparing the system output with respect to the observer output. A fault is declared active if the generated residual exceeds an a priori chosen threshold. Subsequently, the fault magnitude is estimated online by using a suitable parameter update law. Upon detection, the online estimate of the fault magnitude is used in a …
Neural Network-Based Finite-Horizon Approximately Optimal Control Of Uncertain Affine Nonlinear Continuous-Time Systems, Hao Xu, Qiming Zhao, Travis Dierks, S. Jagannathan
Neural Network-Based Finite-Horizon Approximately Optimal Control Of Uncertain Affine Nonlinear Continuous-Time Systems, Hao Xu, Qiming Zhao, Travis Dierks, S. Jagannathan
Electrical and Computer Engineering Faculty Research & Creative Works
This paper develops a novel neural network (NN) based finite-horizon approximate optimal control of nonlinear continuous-time systems in affine form when the system dynamics are complete unknown. First an online NN identifier is proposed to learn the dynamics of the nonlinear continuous-time system. Subsequently, a second NN is utilized to learn the time-varying solution, or referred to as value function, of the Hamilton-Jacobi-Bellman (HJB) equation in an online and forward in time manner. Then, by using the estimated time-varying value function from the second NN and control coefficient matrix from the NN identifier, an approximate optimal control input is computed. …
File Detection On Network Traffic Using Approximate Matching, Frank Breitinger, Ibrahim Baggili
File Detection On Network Traffic Using Approximate Matching, Frank Breitinger, Ibrahim Baggili
Electrical & Computer Engineering and Computer Science Faculty Publications
In recent years, Internet technologies changed enormously and allow faster Internet connections, higher data rates and mobile usage. Hence, it is possible to send huge amounts of data / files easily which is often used by insiders or attackers to steal intellectual property. As a consequence, data leakage prevention systems (DLPS) have been developed which analyze network traffic and alert in case of a data leak. Although the overall concepts of the detection techniques are known, the systems are mostly closed and commercial. Within this paper we present a new technique for network traffic analysis based on approximate matching (a.k.a …
Quantifying Relevance Of Mobile Digital Evidence As They Relate To Case Types: A Survey And A Guide For Best Practices, Shahzad Saleem, Ibrahim Baggili, Oliver Popov
Quantifying Relevance Of Mobile Digital Evidence As They Relate To Case Types: A Survey And A Guide For Best Practices, Shahzad Saleem, Ibrahim Baggili, Oliver Popov
Electrical & Computer Engineering and Computer Science Faculty Publications
In this work, a survey was conducted to help quantify the relevance of nineteen types of evidence (such as SMS) to seven types of digital investigations associated with mobile devices (MD) (such as child pornography). 97 % of the respondents agreed that every type of digital evidence has a different level of relevance to further or solve a particular investigation. From 55 serious participants, a data set of 5,772 responses regarding the relevance of nineteen types of digital evidence for all the seven types of digital investigations was obtained. The results showed that (i) SMS belongs to the most relevant …
Detection Of Seagrass Scars Using Sparse Coding And Morphological Filter, Ender Oguslu, Sertan Erkanli, Victoria J. Hill, W. Paul Bissett, Richard C. Zimmerman, Jiang Li, Charles R. Bostater Jr. (Ed.), Stelios P. Mertikas (Ed.), Xavier Neyt (Ed.)
Detection Of Seagrass Scars Using Sparse Coding And Morphological Filter, Ender Oguslu, Sertan Erkanli, Victoria J. Hill, W. Paul Bissett, Richard C. Zimmerman, Jiang Li, Charles R. Bostater Jr. (Ed.), Stelios P. Mertikas (Ed.), Xavier Neyt (Ed.)
OES Faculty Publications
We present a two-step algorithm for the detection of seafloor propeller seagrass scars in shallow water using panchromatic images. The first step is to classify image pixels into scar and non-scar categories based on a sparse coding algorithm. The first step produces an initial scar map in which false positive scar pixels may be present. In the second step, local orientation of each detected scar pixel is computed using the morphological directional profile, which is defined as outputs of a directional filter with a varying orientation parameter. The profile is then utilized to eliminate false positives and generate the final …
Mobile Indoor Positioning For Augmented Reality Systems, Robert B. Glass
Mobile Indoor Positioning For Augmented Reality Systems, Robert B. Glass
Theses and Dissertations
This thesis explores the creation and setup of a prototype that allows users of the device to interact within an indoor real world environment and a virtual environment simultaneously using high-tech common technology. The prototype is comprised of a small mobile device such as a cellular mobile phone, Raspberry Pi computer, a battery powered handheld Pico projector, and software developed for the Android OS. The software can easily be ported to other mobile and non-mobile operating systems. The mobile device must contain accelerometer, magnetometer, and gyroscope embedded sensors as well as 802.11 wireless network chip. The prototype software implements an …
Optimal Fuzzy Load Frequency Controller With Simultaneous Auto-Tuned Membership Functions And Fuzzy Control Rules, Abas Ali Zamani, Ehsan Bijami, Farid Sheikholeslam, Bahram Jafrasteh
Optimal Fuzzy Load Frequency Controller With Simultaneous Auto-Tuned Membership Functions And Fuzzy Control Rules, Abas Ali Zamani, Ehsan Bijami, Farid Sheikholeslam, Bahram Jafrasteh
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, an auto-tuned fuzzy load frequency controller (FLFC)-based artificial bee colony (ABC) algorithm is developed to quench the deviations in the frequency and tie-line power due to load disturbances in an interconnected power system. Optimal tuning of membership functions (MFs) and fuzzy control rules is very important to improve the design performance and achieve a satisfactory level of robustness for a particular operation. In this work, to reduce the fuzzy system design effort and take large parametric uncertainties into account, a new systematic and simultaneous tuning method is developed for designing MFs and fuzzy rules. For this, the …
Btsql: Nested Bitemporal Relational Database Query Language, Canan Atay, Abdullah Uz Tansel
Btsql: Nested Bitemporal Relational Database Query Language, Canan Atay, Abdullah Uz Tansel
Turkish Journal of Electrical Engineering and Computer Sciences
A nested bitemporal relational data model and its query language are implemented. The bitemporal atom (BTA) is the fundamental construct to represent temporal data and it contains 5 components: a value, the lower and upper bounds of valid time, and the lower and upper bounds of the recoding time. We consider 2 types of data structures for storing BTAs: 1) string representation and 2) abstract data-type representation. We also develop a preprocessor for translating a bitemporal structured query language (BtSQL) statement into standard SQL statements. The BtSQL includes the select, insert, delete, and update statements of the SQL, extended for …
Wireless Sensor Localization Using Enhanced Dv-Aoa Algorithm, Peter Brida, Juraj Machaj, Jozef Benikovsky
Wireless Sensor Localization Using Enhanced Dv-Aoa Algorithm, Peter Brida, Juraj Machaj, Jozef Benikovsky
Turkish Journal of Electrical Engineering and Computer Sciences
In this paper, we deal with the improvement of the positioning accuracy of distance vector (DV)-based positioning algorithms, which use angular information DV- angle of arrival (AoA). This algorithm belongs to an ad-hoc positioning system. We focus on the improvement of the algorithm and its enhanced version is presented. The angular information of particular nodes is obtained and processed by the original algorithm; however, the final position estimation is determined by the proposed novel algorithm using only a subset of all intersections. We assign weights to the individual intersections according to their positions and the positions of the RNs. For …
A Reduced Probabilistic Neural Network For The Classification Of Large Databases, Abdelhadi Lotfi, Abdelkader Benyettou
A Reduced Probabilistic Neural Network For The Classification Of Large Databases, Abdelhadi Lotfi, Abdelkader Benyettou
Turkish Journal of Electrical Engineering and Computer Sciences
The probabilistic neural network (PNN) is a special type of radial basis neural network used mainly for classification problems. Due to the size of the network after training, this type of network is usually used for problems with a small-sized training dataset. In this paper, a new training algorithm is presented for use with large training databases. Application to the handwritten digit database shows that the reduced PNN performs better than the standard PNN for all of the studied cases with a big gain in size and processing speed. This new type of neural network can be used easily for …
Faults Identification In Three-Phase Induction Motors Using Support Vector Machines, Rama Hammo
Faults Identification In Three-Phase Induction Motors Using Support Vector Machines, Rama Hammo
Master of Technology Management Plan II Graduate Projects
Induction motor is one of the most important motors used in industrial applications. The operating conditions may sometime lead the machine into different fault situations. The main types of external faults experienced by these motors are over loading, single phasing, unbalanced supply voltage, locked rotor, phase reversal, ground fault, under voltage and over voltage. The machine should be shut down when a fault is experienced to avoid damage and for the safety of the workers. Computer based relays monitor the machine and disconnect it during the faults. The relay logic used to identify these faults requires sophisticated signal processing techniques …
Sensor Selection And Integration To Improve Video Segmentation In Complex Environments, Adam R. Reckley, Wei-Wen Hsu, Chung-Hao Chen, Gangfeng Ma, E-Wen Huang
Sensor Selection And Integration To Improve Video Segmentation In Complex Environments, Adam R. Reckley, Wei-Wen Hsu, Chung-Hao Chen, Gangfeng Ma, E-Wen Huang
Electrical & Computer Engineering Faculty Publications
Background subtraction is often considered to be a required stage of any video surveillance system being used to detect objects in a single frame and/or track objects across multiple frames in a video sequence. Most current state-of-the-art techniques for object detection and tracking utilize some form of background subtraction that involves developing a model of the background at a pixel, region, or frame level and designating any elements that deviate from the background model as foreground. However, most existing approaches are capable of segmenting a number of distinct components but unable to distinguish between the desired object of interest and …
Using Internet Artifacts To Profile A Child Pornography Suspect, Marcus K. Rogers, Kathryn C. Seigfried-Spellar
Using Internet Artifacts To Profile A Child Pornography Suspect, Marcus K. Rogers, Kathryn C. Seigfried-Spellar
Journal of Digital Forensics, Security and Law
Digital evidence plays a crucial role in child pornography investigations. However, in the following case study, the authors argue that the behavioral analysis or “profiling” of digital evidence can also play a vital role in child pornography investigations. The following case study assessed the Internet Browsing History (Internet Explorer Bookmarks, Mozilla Bookmarks, and Mozilla History) from a suspected child pornography user’s computer. The suspect in this case claimed to be conducting an ad hoc law enforcement investigation. After the URLs were classified (Neutral; Adult Porn; Child Porn; Adult Dating sites; Pictures from Social Networking Profiles; Chat Sessions; Bestiality; Data Cleaning; …
On Cyber Attacks And Signature Based Intrusion Detection For Modbus Based Industrial Control Systems, Wei Gao, Thomas H. Morris
On Cyber Attacks And Signature Based Intrusion Detection For Modbus Based Industrial Control Systems, Wei Gao, Thomas H. Morris
Journal of Digital Forensics, Security and Law
Industrial control system communication networks are vulnerable to reconnaissance, response injection, command injection, and denial of service attacks. Such attacks can lead to an inability to monitor and control industrial control systems and can ultimately lead to system failure. This can result in financial loss for control system operators and economic and safety issues for the citizens who use these services. This paper describes a set of 28 cyber attacks against industrial control systems which use the MODBUS application layer network protocol. The paper also describes a set of standalone and state based intrusion detection system rules which can be …
Idiographic Digital Profiling: Behavioral Analysis Based On Digital Forensics, Chad M. Steel
Idiographic Digital Profiling: Behavioral Analysis Based On Digital Forensics, Chad M. Steel
Journal of Digital Forensics, Security and Law
Idiographic digital profiling (IDP) is the application of behavioral analysis to the field of digital forensics. Previous work in this field takes a nomothetic approach to behavioral analysis by attempting to understand the aggregate behaviors of cybercriminals. This work is the first to take an idiographic approach by examining a particular subject's digital footprints for immediate use in an ongoing investigation. IDP provides a framework for investigators to analyze digital behavioral evidence for the purposes of case planning, subject identification, lead generation, obtaining and executing warrants, and prosecuting offenders.
On Identities In Modern Networks, Libor Polcak, Radek Hranick, Tomas Martınek
On Identities In Modern Networks, Libor Polcak, Radek Hranick, Tomas Martınek
Journal of Digital Forensics, Security and Law
Communicating parties inside computer networks use different kind of identifiers. Some of these identifiers are stable, e.g., logins used to access a specific service, some are only temporary, e.g., dynamically assigned IP addresses. This paper tackles several challenges of lawful interception that emerged in modern networks. The main contribution is the graph model that links identities learnt from various sources distributed in a network. The inferred identities result into an interception of more detailed data in conformance with the issued court order. The approach deals with network address translation, short-lived identifiers and simultaneous usage of different identities. The approach was …
Exploring Forensic Implications Of The Fusion Drive, Shruti Gupta, Marcus Rogers
Exploring Forensic Implications Of The Fusion Drive, Shruti Gupta, Marcus Rogers
Journal of Digital Forensics, Security and Law
This paper explores the forensic implications of Apple’s Fusion Drive. The Fusion Drive is an example of auto-tiered storage. It uses a combination of a flash drive and a magnetic drive. Data is moved between the drives automatically to maximize system performance. This is different from traditional caches because data is moved and not simply copied. The research included understanding the drive structure, populating the drive, and then accessing data in a controlled setting to observe data migration strategies. It was observed that all the data is first written to the flash drive with 4 GB of free space always …
Multi-Stakeholder Case Prioritization In Digital Investigations, Joshua I. James
Multi-Stakeholder Case Prioritization In Digital Investigations, Joshua I. James
Journal of Digital Forensics, Security and Law
This work examines the problem of case prioritization in digital investigations for better utilization of limited criminal investigation resources. Current methods of case prioritization, as well as observed prioritization methods used in digital forensic investigation laboratories are examined. After, a multi-stakeholder approach to case prioritization is given that may help reduce reputational risk to digital forensic laboratories while improving resource allocation. A survey is given that shows differing opinions of investigation priority between Law Enforcement and the public that is used in the development of a prioritization model. Finally, an example case is given to demonstrate the practicality of the …
An Efficient Similarity Digests Database Lookup – A Logarithmic Divide & Conquer Approach, Frank Breitinger, Christian Rathgeb, Harald Baier
An Efficient Similarity Digests Database Lookup – A Logarithmic Divide & Conquer Approach, Frank Breitinger, Christian Rathgeb, Harald Baier
Journal of Digital Forensics, Security and Law
Investigating seized devices within digital forensics represents a challenging task due to the increasing amount of data. Common procedures utilize automated file identification, which reduces the amount of data an investigator has to examine manually. In the past years the research field of approximate matching arises to detect similar data. However, if n denotes the number of similarity digests in a database, then the lookup for a single similarity digest is of complexity of O(n). This paper presents a concept to extend existing approximate matching algorithms, which reduces the lookup complexity from O(n) to O(log(n)). Our proposed approach is based …
Table Of Contents
Journal of Digital Forensics, Security and Law
No abstract provided.
From The Editor, Ibrahim Baggili
From The Editor, Ibrahim Baggili
Journal of Digital Forensics, Security and Law
In this issue we have three papers that have made the cut. The first paper titled “The Cost of Privacy: Riley v. California’s Impact on Cell Phone Searches” is timely. In 2014 there was a unanimous decision that requires a warrant for all cell phone searches. This has some strong implications on the forensic analysis of mobile phones, and to that end, this article discusses and summarizes this legal precedent with its practical implications.
Leveraging Decentralization To Extend The Digital Evidence Acquisition Window: Case Study On Bittorrent Sync, Mark Scanlon, Jason Farina, Nhien A. Khac, Tahar Kechadi
Leveraging Decentralization To Extend The Digital Evidence Acquisition Window: Case Study On Bittorrent Sync, Mark Scanlon, Jason Farina, Nhien A. Khac, Tahar Kechadi
Journal of Digital Forensics, Security and Law
File synchronization services such as Dropbox, Google Drive, Microsoft OneDrive, Apple iCloud, etc., are becoming increasingly popular in today’s always-connected world. A popular alternative to the aforementioned services is BitTorrent Sync. This is a decentralized/cloudless file synchronization service and is gaining significant popularity among Internet users with privacy concerns over where their data is stored and who has the ability to access it. The focus of this paper is the remote recovery of digital evidence pertaining to files identified as being accessed or stored on a suspect’s computer or mobile device. A methodology for the identification, investigation, recovery and verification …
Book Review: The X-Ways Forensics Practitioner's Guide, Linda Lau
Book Review: The X-Ways Forensics Practitioner's Guide, Linda Lau
Journal of Digital Forensics, Security and Law
Brett Shavers is a former law enforcement officer, a digital forensics examiner, an adjunct instructor, and a frequent speaker at many conferences. After writing his first book, titled Placing the Suspect Behind the Keyboard: Using Digital Forensics and Investigative Techniques to Identify Cybercrime Suspects, he co-wrote his 2nd book with Eric Zimmerman and Jimmy Weg, who is a knowledgeable technical editor. Both Brett and Eric are experts in cyber forensics, with many years of law enforcement experience at both the state and federal levels.
The Cost Of Privacy: Riley V. California’S Impact On Cell Phone Searches, Jennifer L. Moore, Jonathan Langton, Joseph Pochron
The Cost Of Privacy: Riley V. California’S Impact On Cell Phone Searches, Jennifer L. Moore, Jonathan Langton, Joseph Pochron
Journal of Digital Forensics, Security and Law
Riley v. California is the United States Supreme Court’s first attempt to regulate the searches of cell phones by law enforcement. The 2014 unanimous decision requires a warrant for all cell phone searches incident to arrest absent an emergency. This work summarizes the legal precedent and analyzes the limitations and practical implications of the ruling. General guidelines for members of the criminal justice system at all levels consistent with the Supreme Court’s decision are provided.
Quantifying Relevance Of Mobile Digital Evidence As They Relate To Case Types: A Survey And A Guide For Best Practice, Shahzad Saleem, Ibrahim Baggili, Oliver Popov
Quantifying Relevance Of Mobile Digital Evidence As They Relate To Case Types: A Survey And A Guide For Best Practice, Shahzad Saleem, Ibrahim Baggili, Oliver Popov
Journal of Digital Forensics, Security and Law
In this work, a survey was conducted to help quantify the relevance of nineteen types of evidence (such as SMS) to seven types of digital investigations associated with mobile devices (MD) (such as child pornography). 97 % of the respondents agreed that every type of digital evidence has a different level of relevance to further or solve a particular investigation. From 55 serious participants, a dataset of 5,772 responses regarding the relevance of nineteen types of digital evidence for all the seven types of digital investigations was obtained. The results showed that (i) SMS belongs to the most relevant type …
Table Of Contents
Journal of Digital Forensics, Security and Law
No abstract provided.
Developing A Conceptual Framework For Modeling Deviant Cyber Flash Mob: A Socio-Computational Approach Leveraging Hypergraph Constructs, Samer Al-Khateeb, Nitin Agarwal
Developing A Conceptual Framework For Modeling Deviant Cyber Flash Mob: A Socio-Computational Approach Leveraging Hypergraph Constructs, Samer Al-Khateeb, Nitin Agarwal
Journal of Digital Forensics, Security and Law
In a Flash Mob (FM) a group of people get together in the physical world perform an unpredicted act and disperse quickly. Cyber Flash Mob (CFM) is the cyber manifestation of flash mob coordinated primarily using social media. Deviant Cyber Flash Mob (or, DCFM) is a special case of CFM, which is categorized as the new face of transnational crime organizations (TCOs). The DCFM phenomenon can be considered as a form of a cyber-collective action that is defined as an action aiming to improve group’s conditions (such as, status or power). In this paper, we conduct a conceptual analysis of …
Cervical Cancer Histology Image Feature Extraction And Classification, Peng Guo
Cervical Cancer Histology Image Feature Extraction And Classification, Peng Guo
Masters Theses
"Cervical cancer, the second most common cancer affecting women worldwide and the most common in developing countries can be cured if detected early and treated. Expert pathologists routinely visually examine histology slides for cervix tissue abnormality assessment. In previous research, an automated, localized, fusion-based approach was investigated for classifying squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN) based on image analysis of 62 digitized histology images obtained through the National Library of Medicine. In this research, CIN grade assessments from two pathologists are analyzed and are used to facilitate atypical cell concentration feature development …
Adaptive Resonance Theory And Diffusion Maps For Clustering Applications In Pattern Analysis, Donald C. Wunsch, David J. Morris, Rui Xu
Adaptive Resonance Theory And Diffusion Maps For Clustering Applications In Pattern Analysis, Donald C. Wunsch, David J. Morris, Rui Xu
Electrical and Computer Engineering Faculty Research & Creative Works
Adaptive Resonance is primarily a theory that learning is regulated by resonance phenomena in neural circuits. Diffusion maps are a class of kernel methods on edge-weighted graphs. While either of these approaches have demonstrated success in image analysis, their combination is particularly effective. These techniques are reviewed and some example applications are given.
Fixed Final-Time Near Optimal Regulation Of Nonlinear Discrete-Time Systems In Affine Form Using Output Feedback, Qiming Zhao, Hao Xu, S. Jagannathan
Fixed Final-Time Near Optimal Regulation Of Nonlinear Discrete-Time Systems In Affine Form Using Output Feedback, Qiming Zhao, Hao Xu, S. Jagannathan
Electrical and Computer Engineering Faculty Research & Creative Works
In this paper, the fixed final-time near optimal output regulation of affine nonlinear discrete-time systems with unknown system dynamics is considered. First, a neural network (NN)-based observer is proposed to reconstruct both the system state vector and control coefficient matrix. Next, actor-critic structure is utilized to approximate the time-varying solution of the Hamilton-Jacobi-Bellman (HJB) equation or value function. To satisfy the terminal constraint, a new error term is defined and incorporated in the NN update law so that the terminal constraint error is also minimized over time. A NN with constant weights and time-dependent activation function is employed to approximate …