Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- China Simulation Federation (3924)
- Singapore Management University (1936)
- Old Dominion University (663)
- San Jose State University (277)
- MMU Press (252)
-
- MBZUAI (233)
- City University of New York (CUNY) (185)
- Technological University Dublin (157)
- Air Force Institute of Technology (138)
- Chapman University (128)
- Chinese Academy of Sciences (117)
- California Polytechnic State University, San Luis Obispo (116)
- University of Arkansas, Fayetteville (105)
- Edith Cowan University (101)
- Lindenwood University (97)
- Embry-Riddle Aeronautical University (94)
- University of South Florida (80)
- University of Nebraska - Lincoln (79)
- University of Kentucky (76)
- University of Malaya (72)
- University of Nevada, Las Vegas (64)
- Clemson University (63)
- Dartmouth College (62)
- University of Denver (59)
- University of Michigan Law School (59)
- Utah State University (57)
- Thomas Jefferson University (55)
- University of Texas at El Paso (55)
- New Jersey Institute of Technology (54)
- University of Central Florida (51)
- Keyword
-
- Artificial intelligence (791)
- Machine learning (695)
- Deep learning (447)
- Machine Learning (422)
- Artificial Intelligence (384)
-
- AI (242)
- Deep Learning (232)
- Computer vision (162)
- Simulation (159)
- Generative AI (143)
- Reinforcement learning (141)
- Neural networks (130)
- Large language models (111)
- Natural language processing (108)
- Natural Language Processing (104)
- Robotics (97)
- ChatGPT (91)
- Path planning (89)
- Computer Vision (86)
- Optimization (85)
- Large Language Models (83)
- Classification (76)
- Neural network (69)
- Cybersecurity (66)
- Virtual reality (65)
- Neural Networks (64)
- Reinforcement Learning (64)
- Computer Science (60)
- Deep reinforcement learning (60)
- Digital twin (58)
- Publication Year
- Publication
-
- Journal of System Simulation (3924)
- Research Collection School Of Computing and Information Systems (1697)
- Journal of Informatics and Web Engineering (252)
- Master's Projects (248)
- Theses and Dissertations (183)
-
- Computer Science Faculty Publications (128)
- Bulletin of Chinese Academy of Sciences (Chinese Version) (117)
- Faculty Scholarship (109)
- Publications and Research (100)
- Computer Vision Faculty Publications (98)
- Master's Theses (96)
- Conference papers (92)
- Electrical & Computer Engineering Faculty Publications (91)
- Machine Learning Faculty Publications (86)
- Electronic Theses and Dissertations (85)
- Faculty Publications (79)
- Research outputs 2022 to 2026 (73)
- Dissertations (71)
- USF Tampa Graduate Theses and Dissertations (67)
- Dissertations and Theses Collection (Open Access) (60)
- Articles (56)
- Dissertations, Theses, and Capstone Projects (53)
- Open Access Theses & Dissertations (51)
- Theses and Dissertations--Computer Science (48)
- Natural Language Processing Faculty Publications (46)
- Teaching and Generative AI: Pedagogical Possibilities and Productive Tensions (46)
- Graduate Theses and Dissertations (45)
- Student Works (2000-2009) (42)
- Electrical & Computer Engineering Theses & Dissertations (41)
- Graduate Theses, Dissertations, and Problem Reports (ETD) (40)
- Publication Type
- File Type
Articles 8461 - 8490 of 11649
Full-Text Articles in Entire DC Network
Study On Secrecy Capacity Of Wireless Sensor Networks Based On Amplify-And-Forward Compressed Sensing Scheme, Jianlan Guo, Yuqiang Chen, Yijun Liu
Study On Secrecy Capacity Of Wireless Sensor Networks Based On Amplify-And-Forward Compressed Sensing Scheme, Jianlan Guo, Yuqiang Chen, Yijun Liu
Journal of System Simulation
Abstract: Due to the limitation of wireless sensor nodes on computation, power energy and storage space, the security issue has become a prevalent concern in the wireless communication. A deep insight on the secrecy capacity of wireless sensor network based on the Amplify-and-Forward (AF) compressed sensing scheme was offered providing a corresponding calculable capacity threshold. Moreover, a feasible algorithm based on augmented Lagrange method for the reconstruction of communication signals was proposed. Furthermore, the impact of the secrecy capacity was discussed to various numbers of active sensor nodes, relay nodes and eavesdropper nodes. Simulation results demonstrate the validity of the …
Simulation Analysis On Ballistic Deflection Of Projectile Obliquely Penetrating Into Concrete, Jianfeng Xue, Peihui Shen, Xiaoming Wang
Simulation Analysis On Ballistic Deflection Of Projectile Obliquely Penetrating Into Concrete, Jianfeng Xue, Peihui Shen, Xiaoming Wang
Journal of System Simulation
Abstract: In order to study the trajectory deflection law of projectiles obliquely penetrating into concrete targets, based on the theory of rigid body kinematics and cavity expansion, the penetration motion differential equations of ogive-nosed projectile were established. The variation rules of trajectory offset and invasion depth were given in different initial conditions through the programming calculation and numerical simulation by MATALB and ANSYS-LYNA software. The calculation results agree well with experimental data. The results show that the influence of penetration depth and deflection angle increase with the oblique angle increasing. The influence of ballistic deflection decreases with the …
Writing For Each Other: Dynamic Quest Generation Using In Session Player Behaviors In Mmorpg, Sean Christopher Mendonca
Writing For Each Other: Dynamic Quest Generation Using In Session Player Behaviors In Mmorpg, Sean Christopher Mendonca
Master's Theses
Role-playing games (RPGs) rely on interesting and varied experiences to maintain player attention. These experiences are often provided through quests, which give players tasks that are used to advance stories or events unfolding in the game. Traditional quests in video games require very specific conditions to be met, and for participating members to advance them by carrying out pre-defined actions. These types of quests are generated with perfect knowledge of the game world and are able to force desired behaviors out of the relevant non-player characters (NPCs). This becomes a major issue in massive multiplayer online (MMO) when other players …
Attacking Computer Vision Models Using Occlusion Analysis To Create Physically Robust Adversarial Images, Jacobsen Loh
Attacking Computer Vision Models Using Occlusion Analysis To Create Physically Robust Adversarial Images, Jacobsen Loh
Master's Theses
Self-driving cars rely on their sense of sight to function effectively in chaotic and uncontrolled environments. Thanks to recent developments in computer vision, specifically convolutional neural networks, autonomous vehicles have developed the ability to see at or above human-level capabilities, which in turn has allowed for rapid advances in self-driving cars. Unfortunately, much like humans being confused by simple optical illusions, convolutional neural networks are susceptible to simple adversarial inputs. As there is no overlap between the optical illusions that fool humans and the adversarial examples that threaten convolutional neural networks, little is understood as to why these adversarial examples …
What Do Undergraduate Engineering Students And Preservice Teachers Learn By Collaborating And Teaching Engineering And Coding Through Robotics?, Jennifer Jill Kidd, Krishnanand Kaipa, Samuel J. Jacks, Stacie I. Ringleb, Pilar Pazos, Kristie Gutierrez, Orlando M. Ayala, Lillian Maria De Souza Almeida
What Do Undergraduate Engineering Students And Preservice Teachers Learn By Collaborating And Teaching Engineering And Coding Through Robotics?, Jennifer Jill Kidd, Krishnanand Kaipa, Samuel J. Jacks, Stacie I. Ringleb, Pilar Pazos, Kristie Gutierrez, Orlando M. Ayala, Lillian Maria De Souza Almeida
Teaching & Learning Faculty Publications
This research paper presents preliminary results of an NSF-supported interdisciplinary collaboration between undergraduate engineering students and preservice teachers. The fields of engineering and elementary education share similar challenges when it comes to preparing undergraduate students for the new demands they will encounter in their profession. Engineering students need interprofessional skills that will help them value and negotiate the contributions of various disciplines while working on problems that require a multidisciplinary approach. Increasingly, the solutions to today's complex problems must integrate knowledge and practices from multiple disciplines and engineers must be able to recognize when expertise from outside their field can …
Vision And Sensor-Based Signer-Independent Framework For Arabic Sign Language Recognition, Al-Shamayleh Ahmad Sami Abd Alkareem
Vision And Sensor-Based Signer-Independent Framework For Arabic Sign Language Recognition, Al-Shamayleh Ahmad Sami Abd Alkareem
Student Works (2020-2029)
Hearing and speech-impairment disability is widespread throughout the world. At present, 15 million people have this disability in the Arab world, and about 86% of them come from low- and middle-income countries. Meanwhile, sign language (SL) can be classified into standard Arabic sign language (ArSL) and local Arabic sign language (LArSL). ArSL is the formal standard and is the more acceptable SL in the Arab world; it is also considered as the medium of instructions for schools and universities as well as television news, shows and programmes. With the absence of usable ArSL recognition (ArSLR) platforms, hearing- and speech-impaired people …
Integrating Finance Dictionary In Lexicon-Based Approach With Machine Learning Algorithm To Analyse The Impact Of Opec News Sentiment On Financial Market, Ling Wu
Student Works (2020-2029)
Since last few decades, machine learning algorithm which trains computers to learn from experience, is one of the most rapidly developing techniques which settles in the intersection research field of statistics and computer science. This research aims to build a properly trained machine learning classifier to study the impact of Organization of Petroleum Exporting Countries (OPEC) news sentiment on stock prices of six Malaysian public listed companies (energy sector) in the main board of Bursa Malaysia. The data used in this research are collected during the period 2012-2017. To carry out the research, firstly, lexicon-based approach is used to analyze …
Visual Commonsense R-Cnn, Tan Wang, Jianqiang Huang, Hanwang Zhang, Qianru Sun
Visual Commonsense R-Cnn, Tan Wang, Jianqiang Huang, Hanwang Zhang, Qianru Sun
Research Collection School Of Computing and Information Systems
We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). This is also …
Multi-Rate Simulation Based On Explicit-Implicit Hybrid Integration, Bingda Zhang, Chen Ming, Wang Xiao, Lanyu Wang
Multi-Rate Simulation Based On Explicit-Implicit Hybrid Integration, Bingda Zhang, Chen Ming, Wang Xiao, Lanyu Wang
Journal of System Simulation
Abstract: A multi-rate simulation method based on explicit-implicit hybrid integration algorithm for the grid-connected photovoltaic system which included power electronic devices with a variety of switching frequency was put forward. Inductances and capacitances were used to divide the grid-connected photovoltaic system into subsystems. A multi-rate interface was put forward to satisfy the request of real time. The stability criterion of the multi-rate simulation algorithm was put forward. FPGA was used as a platform to build the digital grid-connected photovoltaic system. The hardware in loop test for DC/DC and DC/AC converter controllers was conducted on this platform to verify the accuracy …
Weighted Online Estimation Of Soc Based On Adaptive Battery Model, Haohao Sun, Tinglong Pan, Dinghui Wu
Weighted Online Estimation Of Soc Based On Adaptive Battery Model, Haohao Sun, Tinglong Pan, Dinghui Wu
Journal of System Simulation
Abstract: Aiming at the problem that the traditional lithium battery model has poor adaptive ability in SOC estimation and the local estimation accuracy of the single SOC estimation algorithm is low, online identification of model parameters with Multi-Innovation Stochastic Gradient algorithm and method of weighted online estimation of SOC was proposed. The results of lithium-ion battery model parameters online identification updated in real time, realizing lithium-ion battery model adaptive. Aiming at the estimation of SOC, a method of weighted online estimation method based on the PI (proportion and integral) regulator's OCV combined with Ah (an integral method) was proposed. Weights …
Multi-Variable Modeling Research For Main-Steam Temperature Of Power Station Boiler Based On Improved Differential Evolution Algorithm, Li Qin, Zhang Hao, Daogang Peng, Yibo Guo, Nianlong Wang, Yuzhen Sun
Multi-Variable Modeling Research For Main-Steam Temperature Of Power Station Boiler Based On Improved Differential Evolution Algorithm, Li Qin, Zhang Hao, Daogang Peng, Yibo Guo, Nianlong Wang, Yuzhen Sun
Journal of System Simulation
Abstract: By analyzing the factors which affected the main-steam temperature, a multi-variable model was introduced to overcome the bad result of single variable cascade control. An improved differential evolution algorithm was proposed including mutation strategies random selection, crossover ratio and mutation ratio adaptive adjustment, which was used for closed-loop identification of main-steam multi-variable transfer function model. The principle and method how to obtain valid identification data from power plant distributed control system history database was introduced, and the data from some 1 000 MW coal-fired power plant was used to identify and verify the main-steam temperature multi-variable model, …
Research On Wavelength Routing Algorithm Based On Multi-Service In Satellite Optical Networks, Qingli Liu, Junfei Yao, Zhiguo Liu
Research On Wavelength Routing Algorithm Based On Multi-Service In Satellite Optical Networks, Qingli Liu, Junfei Yao, Zhiguo Liu
Journal of System Simulation
Abstract: An optical wavelength routing algorithm for satellite networks based on multi-service was proposed, in order to solve the problem of low utilization rate of wavelengths, slow convergence and low efficiency of satellite optical networks. In this algorithm, it divided the area of the satellite network and updated the link in the area to improve the convergence speed of algorithm. Different services were assigned different wavelength sets to satisfy requirement of different service. According to the initial link weight, which included wavelength remain number and transmission delay, it changed link weight dynamically to achieve network load balancing and rational use …
Performance Analysis On Multiuser Untrusted Amplify-And-Forward Relay Networks, Deng Dan, Zhou Wen
Performance Analysis On Multiuser Untrusted Amplify-And-Forward Relay Networks, Deng Dan, Zhou Wen
Journal of System Simulation
Abstract: The effect of the untrusted relaying node was investigated on the secrecy outage probability (SOP) of amplify-and-forward (AF) relay networks in the presence of direct links and multiple users. In the considered system, the best user was selected according a certain criterion. It transmitted signals to the destination node with the aid of the untrusted relaying node. To reduce the useful information leakage, three selection criteria were proposed based on the channel state information of the direct and/or relaying link. The closed-form analytical SOP and the corresponding asymptotic expressions were derived. Computer simulation was conducted to validate the theoretical …
Modeling And Simulation Of Mooring Force Prediction Based On Improved Ga-Bp Network, Shifeng Li, Zhanzhi Qiu
Modeling And Simulation Of Mooring Force Prediction Based On Improved Ga-Bp Network, Shifeng Li, Zhanzhi Qiu
Journal of System Simulation
Abstract: According to the mooring security and early warning control requirement of the large open sea terminal, a ship mooring force prediction model based on genetic algorithm and BP network was studied. Environmental dynamic factors were considered and a model structure was determined by a weight statistics method; the learning method was improved by individual parent information and contemporary individual local gradient information; according to the improved model, a ship mooring force prediction method of the open sea terminal was proposed. The simulation results show that the performance of the prediction model has improved in the iteration number, …
Intensity Analysis And Fatigue Life Simulation For Connecting Bolt Of Shearer Machine Body, Zhiyong Hao, Yaolong Lei, Mao Jun, Yuan Zhi
Intensity Analysis And Fatigue Life Simulation For Connecting Bolt Of Shearer Machine Body, Zhiyong Hao, Yaolong Lei, Mao Jun, Yuan Zhi
Journal of System Simulation
Abstract: To obtain the cutting load spectrum of themachine body connecting bolt, the method of merging unknown quantities and multi calculation combined with the test experiments of shear mechanical properties was used to solve the overdetermined equations of shearer left haulage unit spatial mechanical model The cutting load spectrum of the machine body connecting bolt was taken to run PSD analysis, and the rainflow counting method was used to script the load spectrum. The frequency domain characteristics and time domain continuation characteristics were therefore obtained. The static analysis and fatigue life simulation analysis combined with the bolt load …
Application Of Weighted Dynamic Svdd In Nonlinear Process Monitoring, Yanhong Xie, Chengao Sun, Li Yuan
Application Of Weighted Dynamic Svdd In Nonlinear Process Monitoring, Yanhong Xie, Chengao Sun, Li Yuan
Journal of System Simulation
Abstract: Due to the complexity of the chemical process, the data are often characterized by dynamics and correlation between sequences. Traditional support vector data description (SVDD) methods are difficult to guarantee real-time monitoring online. A Weighted-Dynamic-SVDD (WDSVDD) method was proposed to monitor fault in real time online. The dynamic method was introduced, and the correlation between the data was considered. The weighted information was used to highlight the useful information. The model was established by using SVDD method, and the online real-time fault monitoring was realized. The method not only overcomes the adverse effect of non-Gaussian and nonlinearity, but …
Research On One-Cycle Controlled Bi-Directional Dc-Dc Converter Based On Switch Capacitor Network, Chen Lei, Tinglong Pan, Yanxia Shen, Dinghui Wu, Zhicheng Ji
Research On One-Cycle Controlled Bi-Directional Dc-Dc Converter Based On Switch Capacitor Network, Chen Lei, Tinglong Pan, Yanxia Shen, Dinghui Wu, Zhicheng Ji
Journal of System Simulation
Abstract: According to the switch capacitor network working characteristics of discharging in series, charging in parallel, a high ratio bidirectional DC-DC converter based on switch capacitor network was proposed. In order to improve the converter's ability of resist input voltage disturbance and dynamic response speed, an improved method was focused on which combined the advantage of one-cycle control and the output voltage feedback compensation control, which could realize inhibition the input voltage perturbation in one cycle and improve the converter's resistance ability of load disturbance. The operating principle and control characteristics of the new converter were analyzed. The improved one-cycle …
Simulation On Waste Heat And Water Recovery System Of Flue Gas In Plant Boiler, Jinping Wang, Deng Yu, Bin Li, Zhu Rui
Simulation On Waste Heat And Water Recovery System Of Flue Gas In Plant Boiler, Jinping Wang, Deng Yu, Bin Li, Zhu Rui
Journal of System Simulation
Abstract: To further improve economy of power plant, the waste heat and water recovery system was put forward. The mathematical model of the gas cooler was established, and the simulation model of this system was built. This simulation model was integrated into the simulation system of a 350mw heating unit, and the simulation experiment was carried out. The influences caused by the introduction of the flue gas waste heat and water recovery system to thermal power unit were analyzed. The dynamic characteristics of the flue gas waste heat and water recovery system based on the valve perturbation experiments were …
Modeling And Simulation For Inter-Harmonics Of Double Pwm Ac Speed Control System For Port Bridge Crane, Wenhuan Yang, Dirui Yang, Ronggao Li
Modeling And Simulation For Inter-Harmonics Of Double Pwm Ac Speed Control System For Port Bridge Crane, Wenhuan Yang, Dirui Yang, Ronggao Li
Journal of System Simulation
Abstract: When the total capacity of double PWM reversible speed control system in distribution network accounts for a larger proportion of power grid capacity, the power quality pollution, or even voltage flicker is generated by interharmonics of double PWM system. Therefore the stable operation of the power grid is affected. Based on the studies on bridge crane system in Shanghai Deep water Port area, a mathematical model of multi-quadrant double PWM reversible speed control system was established. In accordance with the operating characteristics of motor, the inter-harmonic currents, injected into grid were simulated at different speeds respectively in the power …
Closing The Data-Decisions Loop: Deploying Artificial Intelligence For Dynamic Resource Management, Pradeep Varakantham
Closing The Data-Decisions Loop: Deploying Artificial Intelligence For Dynamic Resource Management, Pradeep Varakantham
Asian Management Insights
Improving predictions and allocations to determine the optimal matching of demand and supply in a dynamic, uncertain future.
Free Space Detection And Trajectory Planning For Autonomous Robot, Zachary Ross Winger
Free Space Detection And Trajectory Planning For Autonomous Robot, Zachary Ross Winger
Computer Science and Software Engineering
Autonomous robots need to know what is around them and where it is safe for them to move to. Because having this ability is so important, Dr. Seng and myself have created a model to predict the free space in front of his autonomous robot, Herbie. We then use this prediction to enforce a driving policy to ensure Herbie drives around safely.
Design And Implementation Of Spatial Augmented Reality In Large Scene, Shuiying Ge, Shuman Liu, Shibiao Xu, Xiaopeng Zhang
Design And Implementation Of Spatial Augmented Reality In Large Scene, Shuiying Ge, Shuman Liu, Shibiao Xu, Xiaopeng Zhang
Journal of System Simulation
Abstract: To get long distance marker recognition in Augmented Reality, three software development toolkits were used to construct the long distance marker-less registration technology based on depth sensor, and develop a new augmented reality system based on PC platform. The tracking system was constructed by Kinect and camera. Defects in the single camera tracking system for long distance tracking were improved, and human-computer interaction in Augmented Reality was realized. By the detailed description of the main function modules, such as position calibration module, maker-less virtual-real registration module, and natural interaction module, the system design concept was introduced. Experiment results show …
Solving Flexible Job-Shop Scheduling Problem By Improved Chicken Swarm Optimization Algorithm, Shipeng Xu, Dinghui Wu, Kong Fei, Zhicheng Ji
Solving Flexible Job-Shop Scheduling Problem By Improved Chicken Swarm Optimization Algorithm, Shipeng Xu, Dinghui Wu, Kong Fei, Zhicheng Ji
Journal of System Simulation
Abstract: To solve the flexible job-shop scheduling problem (FJSP) more effectively, an improved chicken swarm optimization (ICSO) algorithm was proposed. A flexible job-shop scheduling model was established for the purpose of minimizing the machine makespan. The improved chicken swarm optimization algorithm was presented. Algorithm improved the update formula of chicks and combined the advantages of simulated annealing algorithm and dynamic inertia cosine weight strategy, which achieved an effective balance of global search and local exploration. According to simulating and testing four standard functions and a flexible job shop scheduling model and compared with particle swarm optimization (PSO) and chicken swarm …
Study On Balanced Energy-Consumption Routing Protocol Of Airfield Single-Lamp Monitoring System, Gao Mei, Bingyuan Wang, Dandan Zhang, Zhaorong Sun
Study On Balanced Energy-Consumption Routing Protocol Of Airfield Single-Lamp Monitoring System, Gao Mei, Bingyuan Wang, Dandan Zhang, Zhaorong Sun
Journal of System Simulation
Abstract: To extend the sensor node lifetime and balance the energy consumption of the wireless sensor network, on the basis of the protocols AL-CAME (Airfield lighting-clustering algorithm based on max energy) and ECOMP (Efficient cluster-based communication protocol), a clustered hierarchy protocol of balanced energy-consumption was proposed for the airfield single-lamp monitoring system. According to the protocol, every two sensor nodes formed a cluster, and the node with the highest remaining energy was elected to be cluster head which was responsible for data aggregation within the cluster. The balanced routing algorithm was adopted in data-transmission from cluster head to …
Study For Solar Seasonal Storage System In Transition Season, Liu Long
Study For Solar Seasonal Storage System In Transition Season, Liu Long
Journal of System Simulation
Abstract: The COP (Coefficient of Performance) of the GSHP system has decreased gradually year after year caused by imbalance energy loads especially in heating-dominated climate zones. The solar thermal energy storage system in transition season can solve the problems effectively. The practice of solar seasonal storage was carried out and supplied by a practical project. TRNSYS 16 was used to simulate the solar energy storage experiment process. The correctness of the model was verified by the experimental data and the simulation results were corrected. Results shows that the simulated results and the measured data were well matched with …
Robotic Manipulator's Visual Servo Control Based On Echo State Networks, Guoyou Li, Xiafei Su, Xiaolei Qin, Xiangxue Shi
Robotic Manipulator's Visual Servo Control Based On Echo State Networks, Guoyou Li, Xiafei Su, Xiaolei Qin, Xiangxue Shi
Journal of System Simulation
Abstract: The inaccuracy in robotic manipulator modeling, which due to the nonlinear and strong coupling of robotic manipulator itself, cannot be ignored on the study of the robotic manipulator control problem. Aiming at the inaccuracy in robotic manipulator modeling, this study led echo state network in the visual servo control system of robotic manipulator. In order to achieve the robotic manipulator positioning control, this study used the echo state network to identify inaccurate item and compensates the uncertainties of the model in the control law. The simulation model of the simulated system was built with MATLAB simulation software. The …
A Machine Learning Approach For Vulnerability Curation, Yang Chen, Andrew E. Santosa, Ming Yi Ang, Abhishek Sharma, Asankhaya Sharma, David Lo
A Machine Learning Approach For Vulnerability Curation, Yang Chen, Andrew E. Santosa, Ming Yi Ang, Abhishek Sharma, Asankhaya Sharma, David Lo
Research Collection School Of Computing and Information Systems
Software composition analysis depends on database of open-source library vulerabilities, curated by security researchers using various sources, such as bug tracking systems, commits, and mailing lists. We report the design and implementation of a machine learning system to help the curation by by automatically predicting the vulnerability-relatedness of each data item. It supports a complete pipeline from data collection, model training and prediction, to the validation of new models before deployment. It is executed iteratively to generate better models as new input data become available. We use self-training to significantly and automatically increase the size of the training dataset, opportunistically …
Knowledge Enhanced Neural Fashion Trend Forecasting, Yunshan Ma, Yujuan Ding, Xun Yang, Lizi Liao, Wai Keung Wong, Tat-Seng Chua
Knowledge Enhanced Neural Fashion Trend Forecasting, Yunshan Ma, Yujuan Ding, Xun Yang, Lizi Liao, Wai Keung Wong, Tat-Seng Chua
Research Collection School Of Computing and Information Systems
Fashion trend forecasting is a crucial task for both academia andindustry. Although some efforts have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal thereal fashion trends. Towards insightful fashion trend forecasting,this work focuses on investigating fine-grained fashion element trends for specific user groups. We first contribute a large-scale fashion trend dataset (FIT) collected from Instagram with extracted time series fashion element records and user information. Furthermore, to effectively model the time series data of fashion elements with rather complex patterns, we propose a Knowledge Enhanced …
Self-Trained Deep Ordinal Regression For End-To-End Video Anomaly Detection, Guansong Pang, Cheng Yan, Chunhua Shen, Anton Van Den Hengel, Xiao Bai
Self-Trained Deep Ordinal Regression For End-To-End Video Anomaly Detection, Guansong Pang, Cheng Yan, Chunhua Shen, Anton Van Den Hengel, Xiao Bai
Research Collection School Of Computing and Information Systems
Depression is among the most prevalent mental disorders, affecting millions of people of all ages globally. Machine learning techniques have shown effective in enabling automated detection and prediction of depression for early intervention and treatment. However, they are challenged by the relative scarcity of instances of depression in the data. In this work we introduce a novel deep multi-task recurrent neural network to tackle this challenge, in which depression classification is jointly optimized with two auxiliary tasks, namely one-class metric learning and anomaly ranking. The auxiliary tasks introduce an inductive bias that improves the classification model’s generalizability on small depression …
Learning Transferable Deep Convolutional Neural Networks For The Classification Of Bacterial Virulence Factors, Dandan Zheng, Guansong Pang, Bo Liu, Lihong Chen, Jian Yang
Learning Transferable Deep Convolutional Neural Networks For The Classification Of Bacterial Virulence Factors, Dandan Zheng, Guansong Pang, Bo Liu, Lihong Chen, Jian Yang
Research Collection School Of Computing and Information Systems
Motivation: Identification of virulence factors (VFs) is critical to the elucidation of bacterial pathogenesis and prevention of related infectious diseases. Current computational methods for VF prediction focus on binary classification or involve only several class(es) of VFs with sufficient samples. However, thousands of VF classes are present in real-world scenarios, and many of them only have a very limited number of samples available.Results: We first construct a large VF dataset, covering 3446 VF classes with 160 495 sequences, and then propose deep convolutional neural network models for VF classification. We show that (i) for common VF classes with sufficient samples, …