Quadratic Neural Network Architecture As Evaluated Relative To Conventional Neural Network Architecture,
2022
University of South Carolina
Quadratic Neural Network Architecture As Evaluated Relative To Conventional Neural Network Architecture, Reid Taylor
Senior Theses
Current work in the field of deep learning and neural networks revolves around several variations of the same mathematical model for associative learning. These variations, while significant and exceptionally applicable in the real world, fail to push the limits of modern computational prowess. This research does just that: by leveraging high order tensors in place of 2nd order tensors, quadratic neural networks can be developed and can allow for substantially more complex machine learning models which allow for self-interactions of collected and analyzed data. This research shows the theorization and development of mathematical model necessary for such an idea to …
Development Of A Ppg Sensor Array As A Wearable Device For Monitoring Cardiovascular Metrics,
2022
Western Michigan University
Development Of A Ppg Sensor Array As A Wearable Device For Monitoring Cardiovascular Metrics, Jose Ignacio Rodriguez-Labra
Masters Theses
Wearable devices with integrated sensors for tracking human vitals are widely used for a variety of applications, including exercise, wellness, and health monitoring. Photoplethysmography (PPG) sensors use pulse oximetry to measure pulse rate, cardiac cycle, oxygen saturation, and blood flow by passing a light beam of variable wavelength through the skin and measuring its reflection. A multi-channel PPG wearable system was developed to include multiple nodes of pulse oximeters, each capable of using different wavelengths of light. The system uses sensor fusion along with a machine learning model to perform feature extraction of relevant cardiovascular metrics across multiple pulse oximeters …
Learning Domain Invariant Information To Enhance Presentation Attack Detection In Visible Face Recognition Systems,
2022
University of Nebraska-Lincoln
Learning Domain Invariant Information To Enhance Presentation Attack Detection In Visible Face Recognition Systems, Jennifer Hamblin
Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research
Face signatures, including size, shape, texture, skin tone, eye color, appearance, and scars/marks, are widely used as discriminative, biometric information for access control. Despite recent advancements in facial recognition systems, presentation attacks on facial recognition systems have become increasingly sophisticated. The ability to detect presentation attacks or spoofing attempts is a pressing concern for the integrity, security, and trust of facial recognition systems. Multi-spectral imaging has been previously introduced as a way to improve presentation attack detection by utilizing sensors that are sensitive to different regions of the electromagnetic spectrum (e.g., visible, near infrared, long-wave infrared). Although multi-spectral presentation attack …
Verifiable Searchable Encryption Framework Against Insider Keyword-Guessing Attack In Cloud Storage,
2022
Xidian University
Verifiable Searchable Encryption Framework Against Insider Keyword-Guessing Attack In Cloud Storage, Yinbin Miao, Robert H. Deng, Kim-Kwang Raymond Choo, Ximeng Liu, Hongwei Li
Research Collection School Of Computing and Information Systems
Searchable encryption (SE) allows cloud tenants to retrieve encrypted data while preserving data confidentiality securely. Many SE solutions have been designed to improve efficiency and security, but most of them are still susceptible to insider Keyword-Guessing Attacks (KGA), which implies that the internal attackers can guess the candidate keywords successfully in an off-line manner. Also in existing SE solutions, a semi-honest-but-curious cloud server may deliver incorrect search results by performing only a fraction of retrieval operations honestly (e.g., to save storage space). To address these two challenging issues, we first construct the basic Verifiable SE Framework (VSEF), which can withstand …
Improving Feature Generalizability With Multitask Learning In Class Incremental Learning,
2022
Singapore Management University
Improving Feature Generalizability With Multitask Learning In Class Incremental Learning, Dong Ma, Chi Ian Tang, Cecilia Mascolo
Research Collection School Of Computing and Information Systems
Many deep learning applications, like keyword spotting [1], [2], require the incorporation of new concepts (classes) over time, referred to as Class Incremental Learning (CIL). The major challenge in CIL is catastrophic forgetting, i.e., preserving as much of the old knowledge as possible while learning new tasks. Various techniques, such as regularization, knowledge distillation, and the use of exemplars, have been proposed to resolve this issue. However, prior works primarily focus on the incremental learning step, while ignoring the optimization during the base model training. We hypothesise that a more transferable and generalizable feature representation from the base model would …
On The Reliability Of Wearable Sensors For Assessing Movement Disorder-Related Gait Quality And Imbalance: A Case Study Of Multiple Sclerosis,
2022
University of South Florida
On The Reliability Of Wearable Sensors For Assessing Movement Disorder-Related Gait Quality And Imbalance: A Case Study Of Multiple Sclerosis, Steven Díaz Hernández
USF Tampa Graduate Theses and Dissertations
Approximately 33 million American adults had a movement disorder associated with medication use, ear infections, injury, or neurological disorders in 2008, with over 18 million people affected by neurological disorders worldwide. Physical therapists assist people with movement disorders by providing interventions to reduce pain, improve mobility, avoid surgeries, and prevent falls and secondary complications of neurodegenerative disorders. Current gait assessments used by physical therapists, such as the Multiple Sclerosis Walking Scale, provide only semi-quantitative data, and cannot assess walking quality in detail or describe how one’s walking quality changes over time. As a result, quantitative systems have grownas useful tools …
Seabem: An Artificial Intelligence Powered Web Application To Predict Cover Crop Biomass,
2022
University of Nebraska - Lincoln
Seabem: An Artificial Intelligence Powered Web Application To Predict Cover Crop Biomass, Aime Christian Tuyishime, Andrea Basche
Honors Program: Senior Projects (Public)
SEABEM, the Stacked Ensemble Algorithms Biomass Estimator Model, is a web application with a stacked ensemble of Machine Learning (ML) algorithms running on the backend to predict cover crop biomass for locations in Sub-Saharan. The SEABEM model was developed using a previously developed database of crop growth and yield that included site characteristics such as latitude, longitude, soil texture (sand, silt, and clay percentages), temperature, and precipitation. The goal of SEABEM is to provide global farmers, mainly small-scale African farmers, the knowledge they need before practicing and benefiting from cover crops while avoiding the expensive and time-consuming operations that come …
Mix Method Approach Of Measuring Vr As A Pedagogical Tool To Enhance Experimental Learning: Motivation From Literature Survey Of Previous Study,
2022
Sukkur IBA University, Pakistan.
Mix Method Approach Of Measuring Vr As A Pedagogical Tool To Enhance Experimental Learning: Motivation From Literature Survey Of Previous Study, Muhammad Mujtaba Asad, Aisha Naz Ansari, Prathamesh Churi, Antonio José Moreno Guerrero, Anas A. Salameh
Institute for Educational Development, Karachi
This research has been experimented on our previous literature review. Technological advancement has prevailed in the modern era from the 20th century. Artificial intelligence and virtual worlds have been created for rapid technological development. This paper is aimed at exploring the effect of virtual reality as a pedagogical tool for enhancing experiential learning among undergraduate students. Considering this, it was a mixed-methods study following the design of sequential exploratory–which includes qualitative followed by quantitative part. The targeted population was undergraduate students taking education programs from Public Sector Universities of Sindh. For the qualitative part, the sample of eight undergraduate students …
Barriers And Enablers For Older Adults Participating In A Home-Based Pragmatic Exercise Program Delivered And Monitored By Amazon Alexa: A Qualitative Study,
2022
Edith Cowan University
Barriers And Enablers For Older Adults Participating In A Home-Based Pragmatic Exercise Program Delivered And Monitored By Amazon Alexa: A Qualitative Study, Paul Jansons, Jackson Fyfe, Jack Dalla Via, Robin M. Daly, Eugene Gvozdenko, David Scott
Research outputs 2022 to 2026
Background: The remote delivery and monitoring of individually-tailored exercise programs using voice-controlled intelligent personal assistants (VIPAs) that support conversation-based interactions may be an acceptable alternative model of digital health delivery for older adults. The aim of this study was to evaluate the enablers and barriers for older adults participating in a home-based exercise program delivered and monitored by VIPAs. Method: This qualitative study used videoconferencing to conduct semi-structured interviews following a 12-week, prospective single-arm pilot study in 15 adults aged 60 to 89 years living alone in the community. All participants were prescribed an individualized, brief (10 min, 2–4 times …
A Combined Approach For Private Indexing Mechanism,
2022
University of Mumbai
A Combined Approach For Private Indexing Mechanism, Pranita Maruti Desai Ms., Vijay Maruti Shelake Mr.
Journal of Digital Forensics, Security and Law
Private indexing is a set of approaches for analyzing research data that are similar or resemble similar ones. This is used in the database to keep track of the keys and their values. The main subject of this research is private indexing in record linkage to secure the data. Because unique personal identification numbers or social security numbers are not accessible in most countries or databases, data linkage is limited to attributes such as date of birth and names to distinguish between the number of records and the real-life entities they represent. For security reasons, the encryption of these identifiers …
New Embedded Simulation Technology For Smart Internet Of Things,
2022
1.State Key Laboratory of Complex Product Intelligent Manufacturing System Technology, Beijing Institute of Electronic System Engineering, Beijing 100854, China;2.Beijing Complex Product Advanced Manufacturing Engineering Research Center, Beijing Simulation Center, Beijing 100854, China;3.Science and Technology on Special Simulation Laboratory, Beijing Simulation Center, Beijing 100854, China;4.Engineering Research Center of Complex Product Advanced Manufacturing Systems, Ministry of Education, Beihang University, Beijing 100191, China;
New Embedded Simulation Technology For Smart Internet Of Things, Bohu Li, Xudong Chai, Lin Zhang, Duzheng Qing, Guoqiang Shi, Tingyu Lin, Liqin Guo, Chen Yang, Mu Gu, Zhengxuan Jia, Hui Gong, Zhen Tang
Journal of System Simulation
Abstract: Human society in the new development era and journey is facing the new situation. The operation paradigm, technology and ecosystem of industries related to the national economy and people's livelihood、national security are changing significantly towards the digital, networked, cloud-based and intelligent "Smart Internet of Things". The new embedded simulation technology, with the capabilities of online and continuous analysis, cognition, learning, decision-making, operation and optimization,is urgently needed for the development of "Smart Internet of Things". "Smart Internet of Things" is briefly introduced and the connotation, characteristics and application mode of the new embedded simulation technology are proposed and its architecture, …
Research On Integrated Scheduling Of Agv And Machine In Flexible Job Shop,
2022
School of Information Engineering, Ningxia University, Yinchuan 750021, China;
Research On Integrated Scheduling Of Agv And Machine In Flexible Job Shop, Kui Chen, Li Bi, Wenya Wang
Journal of System Simulation
Abstract: Aiming at the flexible job shop scheduling problem with AGV (automated guided vehicle), a dual resource integrated scheduling optimization model with the objective of minimizing makespan is established. In the process of population initialization, a heuristic initialization method is proposed to improve the quality of population initial solution and accelerate the convergence speed of the algorithm. A hybrid discrete particle swarm optimization algorithm that can effectively avoid premature maturation is proposed by combining the competitive learning mechanism and the random restart mechanism to address the disadvantages of discrete particle swarm algorithms that are prone to premature maturation. Simulation experiments …
Cause Analysis Of Vocs Hazards In Related Areas Based On Object Function Petri Net,
2022
Management College, Xi′an University of Architecture & Technology, Xi′an 710055, China;
Cause Analysis Of Vocs Hazards In Related Areas Based On Object Function Petri Net, Guangqiu Huang, Tiantian Wu
Journal of System Simulation
Abstract: The multi-resolution formal description based on discrete event system specification (DEVS) has the ability of hierarchical and structured description, but the description of the intelligent behavior inside the module is relatively lacking, while Agent-based modeling can describe the characteristics of individual perception, behavior, communication, cooperation, learning and evolution. Under the framework of multi-resolution modeling, DEVS and Agent model descriptions are combined to provide the description capabilities for events, behaviors, mechanisms, etc. Based on the description of multi-resolution DEVS models, a formal model description method with coupling closure is proposed, which includes the description of the multi-resolution entity-level atomic model …
Research On Algebraic Loop Of Synchronous Generator Simulation Based On Simulink,
2022
1.School of Automation, Northwestern Polytechnical University, Xi'an 710129, China;
Research On Algebraic Loop Of Synchronous Generator Simulation Based On Simulink, Shuang Wang, Zhaohui Gao, Siyu Chen, Xiao Tang, Zhan Xi
Journal of System Simulation
Abstract: The problem of algebraic loop is common in Simulink simulation. The existence of algebraic loop will reduce the speed and accuracy of simulation, and even lead to errors in simulation results. Taking the simulation of synchronous generator as an example, the problem of algebraic loop and its elimination method in Simulink simulation are discussed. Starting from the analysis of the basic equations of synchronous generator, the cause of algebraic loop in simulation is discussed, the influence of the algebraic loop on the system simulation is pointed out, using disassembly method and transformation method, focusing on eliminating the algebraic loop, …
Research On 3d Path Planning Algorithm Based On Fast Rrt Algorithm,
2022
School of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an 710000, China;
Research On 3d Path Planning Algorithm Based On Fast Rrt Algorithm, Zhaoqiang Li, Shiyu Zhang
Journal of System Simulation
Abstract: RRT (rapidly exploring random tree) algorithm is a sampling-based path planning algorithm, which can search a path in high-dimensional environment. The traditional RRT algorithm has the problems of low node utilization and large amount of calculation. To solve these problems, the fast RRT* (Quick RRT*) algorithm is improved by optimizing the strategy of reselection of parent node and pruning range, improving the sampling method and introducing adaptive step size, which makes the algorithm time-consuming and path length shorter. At the same time, the node connection screening strategy is added to eliminate the excessive turning angle in the path. …
Simulation Of Robust Optimal Synchronization Control For Direct Drive H-Type Motion Platform,
2022
School of Electrical Engineering, Shenyang University of Technology, Shenyang 110870, China;
Simulation Of Robust Optimal Synchronization Control For Direct Drive H-Type Motion Platform, Limei Wang, Hongyan Yao, Kang Zhang
Journal of System Simulation
Abstract: Cell manufacturing is an important organizational form of modern production systems. In scheduling of cell manufacturing systems, machine failures or interruptions are very common in practice, meanwhile the waste due to energy consumption during machine idle time cannot be ignored. Hence the relevant research is with strong significance. This paper considers the problems of machine interruption and energy consumption in cell scheduling, and developed an integer programming model to minimize the makespan as well as the cost of energy consumption during machine idling and the interruption cost. A mixed optimization method is proposed based on improved wolf pack algorithm …
Electronic Solid Waste Prediction Based On Intelligent Optimization Grey Model,
2022
Key Laboratory for Advanced Process Control of Light Industry of Ministry of Education, Jiangnan University, Wuxi 214122, China;
Electronic Solid Waste Prediction Based On Intelligent Optimization Grey Model, Xiaoan Sun, Xiaoli Luan, Fei Liu
Journal of System Simulation
Abstract: Aiming at the problems of complex modeling mechanism and low modeling accuracy in the prediction of electronic solid waste production, an intelligent modeling method combining fractional order multiple gray model and neural network compensation model is proposed. Particle swarm optimization is used to optimize the accumulative order and background parameters of the gray model to maximize the performance of the gray model. BP neural network is used to compensate the error of gray modeling and improve the prediction accuracy of solid waste production. The effectiveness of the proposed method is verified by Washington state electronic solid waste data. The …
Modeling Time Series Using Multi-Modality Fuzzy Cognitive Maps,
2022
1.School of Control Science and Engineering, Dalian University of Technology, Dalian 116023, China;
Modeling Time Series Using Multi-Modality Fuzzy Cognitive Maps, Guoliang Feng, Wei Lu, Jianhua Yang
Journal of System Simulation
Abstract: A multi-modality modeling method for time series data based on fuzzy cognitive maps is proposed to address the problem that a single model is difficult to accurately reflect the multi-modal characteristics of time series.The bootstrap method is used to select multiple sub-sequences from the original time serieswhich contain the diverse modality in the original time series. The fuzzy cognitive map sub-models are constructed on each sub-sequencesrespectively. The formed sub-models are further merged by means of granular computing method and the merging performance with different weighting strategies is analyzed. The developed multi-modal model not only has prediction abilities at …
Research On Optimization Of Network Resource Utilization In Static Segment Of Flexray Bus,
2022
China North Vehicle Research Institute, Beijing 100072, China;
Research On Optimization Of Network Resource Utilization In Static Segment Of Flexray Bus, Xinhang He, Erkang Li, Hongchao Zhang
Journal of System Simulation
Abstract: In order to improve the utilization of the network resources of the FlexRay bus, the network is optimized for static segment scheduling. The FlexRay communication mechanism is analyzed, the message model is established and the calculation method of bandwidth loss is derived, while considering the protocol overhead and network idling, taking the number of static frames and the length of the static frame payload as design variables, the overall optimal packaging scheme is obtained by solving this multi-objective optimization problem. This solution is finally applied to the vehicle chassis integrated control system for simulation analysis and verification. The results …
Job Shop Rescheduling Under Recessive Disturbance Based On Digital Twin,
2022
1.Key Laboratory of Advanced Process Control for Light Industry, Jiangnan University, Wuxi 214122, China;
Job Shop Rescheduling Under Recessive Disturbance Based On Digital Twin, Dinghui Wu, Tongrui Zhang, Xiuli Zhang
Journal of System Simulation
Abstract: A new shop rescheduling model driven by digital twin is proposed to solve the problems of disturbance cumulative rescheduling. A scheduling parameter updating method is proposed and a random probability distribution is used to describe the distribution of scheduling parameters to improve the accuracy of scheduling parameters. An implicit disturbance detection model is built based on Siamese Network using real-time data as input to realize the start time of rescheduling. The sample data for scheduling knowledge mining are extracted from the historical scheduling scenarios. Through the Pseudo-Siamese CNN, the mapping relationship between the Process state and machine state is …
