Computer Sciences Commons^™

Survey Of Ship Detection In Video Surveillance Based On Shallow Machine Learning, Zhenbo Bi, Shiyou Zhang, Yang Hua, Yuanhong Wu

Journal of System Simulation

Abstract: At present, detection of ship targets in video surveillance based on shallow machine learning methods is still attracting attention in the fields of underwater cultural heritage protection, marine aquaculture, maritime traffic, and port management. This paper provides a review and discussion for this kind of ship detection methods. The ship target detection based on video surveillance is divided into five parts according to the key technologies involved: preprocessing, region of interest extraction, target segmentation, ship feature extraction and ship type recognition. According to different functional modules, the core problems involved in them are pointed out, and the core ideas, …

Real-Time Simulation Technology Of Fluid-Thermo-Solid Coupling Of Hypersonic Vehicle, Yunqin Liu, Li Ni, Luming Zhao, Jinpeng Bai, Tingjun Li, Chenguang Wang

Journal of System Simulation

Abstract: The solution of the coupling characteristics of fluid-thermo-solid physics in the modeling of hypersonic vehicle is an unavoidable difficulty, and the real-time simulation of fluid-thermo-solid coupling is particularly challenging. Aiming at the conflicting problem of solution accuracy and solution efficiency in fluid-thermo-solid coupling real-time simulation, a CFD (Computational Fluid Dynamics)/ CSD (Computational Structural Dynamics)-based fluid-thermo-solid coupling characteristic solution method is established, which realizes the high-precision solution of the fluid, temperature, and structural deformation field coupling. According to the multi-condition offline solution set modeling method, by accumulating a large number of offline solutions as effective support for online …

A Data-Driven Modeling Method For Game Adversity Agent, Zeng Bi, Fang Xiao, Deshuai Kong, Xiangxiang Song, Zhengxuan Jia, Tingyu Lin

Journal of System Simulation

Abstract: Aiming at the problems of collaborative modeling of formation behavior and intelligent generation of decision-making in complex confrontation scenarios, based on the serious game to simulate the confrontation scenarios of complex maritime equipment against the air, this paper proposes a data-driven modeling method for game agent and uses a distributed modeling technology of parallel adversarial scenarios and opportunistic decision making technology of smart targets to achieve agent modeling. It provides support for the further exploration of multi-objective collaborative modeling in complex confrontation scenarios. The simulation results show that deep reinforcement learning algorithms can provide a basis for the modeling …

Research On Usv Navigation Simulation Key Technologies, Jianhai Jin, Zexing Zhou, Zhang Bo, Yihong Chen, Xizhong Wei

Journal of System Simulation

Abstract: In order to solve the problems of long test time, high cost and high risk, a general framework of simulation system for autonomous navigation test and verification of USV(Unmanned Surface Vessel) has been developed, and some key simulation technologies such as complex scenario simulation, intelligent perception, navigation simulation and environmental effect modeling are researched. the dynamic equation, kinematics equation, wind load modeling, wave surface modeling, wave drift force modeling and ocean current modeling are designed and realized. The simulation system is proved to have high accuracy and fidelity by the real ship test on the lake, which can greatly …

Kinematics Analysis And Simulation Of Automatically Tracking Dental Surgery Lamp, Zerui Jiang, Lijun Yang, Li Jun, Xiaolong Jiao, Zheng Hang

Journal of System Simulation

Abstract: In order to solve the problem that the oral surgical lamp cannot automatically adjust the irradiation posture of the surgical lamp according to the face direction and oral cavity position, a six-degree-of-freedom automatic tracking visual manipulator solution is proposed. Coordinate conversion is achieved through binocular vision to obtain three-dimensional information of oral cavity position and face normal vector. The geometric method is introduced into the kinematics calculation, and the closed solution of the inverse kinematics is obtained. The correctness is verified by the Maltab programming and the introduction of numerical values. Five-degree polynomial motion planning is performed …

Research On Digital Twin-Based Modeling And Monitoring Of Five-Axis Grinder, Xiao Tong, Haifan Jiang, Guofu Ding, Jiang Lei, Shuwen Ma

Journal of System Simulation

Abstract: Aiming at the poor virtual-real interaction ability, single data presentation mode, and hysteretic abnormality handling in CNC machine tool status monitoring, a visual monitoring method for machine tool process based on digital twin is proposed, Which realizes the mapping of three subsystems of machine tool, machinery, control and electrical to the information space from three dimensions of geometry, logic and data. The verification of instructions and CNC programs, real-time status monitoring and abnormality handling during operation are carried out. A digital twin-based machine tool modeling and monitoring system is designed and developed. Taking a five-axis CNC …

Hyperspectral Rx Anomaly Detection Method Based On The Fusion Of Spatial And Spectral Feature, Liu Xuan, Xiangyang Li, He Fang, Jianwei Zhao, Fenggan Zhang

Journal of System Simulation

Abstract: To address the problem that the hyperspectral anomaly detection algorithm does not make full use of the spatial information of the hyperspectral image and the detection accuracy is limited, a FSSRX (Fusing Spatial and Spectral Reed-Xiaol) anomaly detection algorithm that fuses spatial and spectrum information is proposed to improve the accuracy of hyperspectral anomaly detection. In FSSRX algorithm, the spatial feature of hyperspectral images is firstly extracted by the EMAP(Extended Multi-attribute Profile) method and the abnormal score of each pixel in spatial features is then calculated with RX detector. Meanwhile, RX anomaly detection is carried out directly on the …

Research On Model Reuse Technology Based On Semantic Matching And Composition, Xingyu Tian, Guangxun Zeng, Yunbo Gao, Lili Ye, Guanghong Gong, Li Ni

Journal of System Simulation

Abstract: In order to solve the data barriers between the conceptual model and the simulation scenario of the combat system, the intelligent mapping and model reuse technology of the simulation scenario is researched. The conceptual model is analyzed using DOM technology. Based on the ontology theory, the knowledge base of the combat domain is constructed and the web crawler is customized to build the domain thesaurus. Through the SWRL rule library, the reasoning engine is called to realize the relational reasoning at the semantic level. An intelligent matching algorithm is designed to map the semantic relationship to the combination relationship …

Research On Cloud Tool Integration And Management Methods, Tianying Zhang, Ji Hang, Junhua Zhou, Tao Luan

Journal of System Simulation

Abstract: In response to the application needs of using professional tools to develop complex products in the fields of aerospace, aviation, weapons, ships, etc., it is urgent to implement centralized management of cloud tools and cross-professional sharing of tools through tool service-oriented methods, so as to solve issues such as inconsistent tool versions, cross-professional resource barriers, and high thresholds for tool mastery during the traditional model development process. By studying the integration and calling methods of cross-professional and different versions of self-developed tools, as well as methods of tool server operation control, authority management, etc., and taking the local …

Predictive Control Method Of Peak Hour Passenger Flow At Urban Rail Station, Xiaohe Li, Jianping Wu, Depin Peng

Journal of System Simulation

Abstract: With the rapid development of subway in China, the urban rail station, especially the transfer station, is prone to generate passenger congestion in the peak period. After analyzing the types of passenger flow in and out of the platform, a predictive control model of passenger flow is established based on the discrete linear quadratic optimal control theory. Taking Fuxingmen Station as an example, the simulation environment of the station is built by using the simulation software of Anylogic. The historical passenger flow data in peak period and the optimal passenger flow control sequence obtained by solving the passenger flow …

Study And Effect Evaluation On The Setting Of Contraflow Left-Turn At Intersections, Zhao Dan, Xuejun Niu, Shuhao Zhang, Jiaxu Wei

Journal of System Simulation

Abstract: Contraflow left-turn is one of the traffic organization ways at intersections. By analyzing the setting parameters of the contraflow left-turn, the length and the range of the contraflow left-turn lane, the constrained conditions of the contraflow left-turn are determined, and the applicable conditions are determined from the road, traffic and signal control. VISSIM software is used to analyze a road intersection, simulate and evaluate the indicators related to the intersection entrance, optimize the timing plan of contraflow left-turn lane, and validate the feasibility and advantages of contraflow left-turn lane. The results show that the intersection delays are reduced by …

Variety Recognition Based On Deep Learning And Double-Sided Characteristics Of Maize Kernel, Feng Xiao, Zhang Hui, Zhou Rui, Qiao Lu, Wei Dong, Dandan Li, Yuyao Zhang, Guoqing Zheng

Journal of System Simulation

Abstract: In order to construct a maize kernel variety recognition model with high recognition accuracy and suitable for mobile phone application, a mobile phone is used to obtain maize kernel double-sided (embryonic and non-embryonic) images. Based on the lightweight convolutional neural network MobileNetV2 and transfer learning, a maize kernel image variety recognition model is constructed. In view of the existing research methods are mainly for single-sided recognition of maize kernel variety, the performance of single-sided and double-sided characteristics modeling and recognition is compared. The results show that the double-sided recognition accuracy of maize kernel double-sided characteristics modeling is 99.83%, which …

Self-Relabeling For Noise-Tolerant Retina Vessel Segmentation Through Label Reliability Estimation, Jiacheng Li, Ruirui Li, Ruize Han, Song Wang

Faculty Publications

Background Retinal vessel segmentation benefits significantly from deep learning. Its performance relies on sufficient training images with accurate ground-truth segmentation, which are usually manually annotated in the form of binary pixel-wise label maps. Manually annotated ground-truth label maps, more or less, contain errors for part of the pixels. Due to the thin structure of retina vessels, such errors are more frequent and serious in manual annotations, which negatively affect deep learning performance.

Methods In this paper, we develop a new method to automatically and iteratively identify and correct such noisy segmentation labels in the process of network training. We consider …

Human Interaction With Fake News, Autumn Woodson, Sampath Jayarathna (Mentor)

Computer & Information Science: Research Experiences for Undergraduates in Disinformation Detection and Analytics

No abstract provided.

Measuring And Comparing Social Bias In Static And Contextual Word Embeddings, Alan Cueva Mora

Dissertations

Word embeddings have been considered one of the biggest breakthroughs of deep learning for natural language processing. They are learned numerical vector representations of words where similar words have similar representations. Contextual word embeddings are the promising second-generation of word embeddings assigning a representation to a word based on its context. This can result in different representations for the same word depending on the context (e.g. river bank and commercial bank). There is evidence of social bias (human-like implicit biases based on gender, race, and other social constructs) in word embeddings. While detecting bias in static (classical or non-contextual) word …

Nlp@Vcu: Crop Characteristic Extraction Framework, Cora Lewis, Bridget Mcinnes, Getiria Onsongo

Summer REU Program

We developed a crop characteristic extraction framework. Starting from a custom SpaCy named entity recognition model, we added pre-trained word embeddings and a part-of-speech based entity expansion post-processing step. Then, we implemented an evaluation framework that functioned as a 5-fold cross validation wrapper for SpaCy custom training. Preliminary results showed improvement in the extraction framework after these additions.

Classification Of Electropherograms Using Machine Learning For Parkinson’S Disease, Soroush Dehghan

Electronic Theses and Dissertations

Parkinson’s disease (PD) is a neurodegenerative movement disorder that progresses gradually over time. The onset of symptoms in people who are suffering from PD can vary from case to case, and it depends on the progression of the disease in each patient. The PD symptoms gradually develop and exacerbate the patient’s movements throughout time. An early diagnosis of PD could improve the outcomes of treatments and could potentially delay the progression of this disorder and that makes discovering a new diagnostic method valuable. In this study, I investigate the feasibility of using a machine learning (ML) approach to classify PD …

Data Analytics And Visualization For Virtual Simulation, Sri Lekha Koppaka

Browse all Theses and Dissertations

Healthcare organizations attract a diversity of caregivers and patients by providing essential care. While interacting with people of various races, ethnicity, and economical background, caregivers need to be empathetic and compassionate. Proper training and exposure are needed to understand the patient’s background and handle different situations and provide the best care for the patient. With social determinants of health (SDOH) as the basis, the thesis focuses on providing exposure through “Wright LIFE (Lifelike Immersion for Equity) - A simulation-based training tool” to two such scenarios covering patients from the LGBTQIA+ community & autism spectrum disorder (ASD). This interactive tool helps …

Computer Enabled Interventions To Communication And Behavioral Problems In Collaborative Work Environments, Ashutosh Shivakumar

Browse all Theses and Dissertations

Task success in co-located and distributed collaborative work settings is characterized by clear and efficient communication between participating members. Communication issues like 1) Unwanted interruptions and 2) Delayed feedback in collaborative work based distributed scenarios have the potential to impede task coordination and significantly decrease the probability of accomplishing task objective. Research shows that 1) Interrupting tasks at random moments can cause users to take up to 30% longer to resume tasks, commit up to twice the errors, and experience up to twice the negative effect than when interrupted at boundaries 2) Skill retention in collaborative learning tasks improves with …

Topological Hierarchies And Decomposition: From Clustering To Persistence, Kyle A. Brown

Browse all Theses and Dissertations

Hierarchical clustering is a class of algorithms commonly used in exploratory data analysis (EDA) and supervised learning. However, they suffer from some drawbacks, including the difficulty of interpreting the resulting dendrogram, arbitrariness in the choice of cut to obtain a flat clustering, and the lack of an obvious way of comparing individual clusters. In this dissertation, we develop the notion of a topological hierarchy on recursively-defined subsets of a metric space. We look to the field of topological data analysis (TDA) for the mathematical background to associate topological structures such as simplicial complexes and maps of covers to clusters in …

Virtual Reality-Based Serious Role-Playing Games As Digital Experiential Learning Tools To Deliver Healthcare Skills Through Mobile Devices, Dixit Bharatkumar Patel

Browse all Theses and Dissertations

Inadequate professional training and practices related to health care may result in severe complications to care experiences and outcomes. Moreover, healthcare professionals are as susceptible to the possibility of implicit biases as any other group. Importantly, the health care training is critical and challenging as minor prejudicial beliefs have an adverse influence or serious consequences on patients' health outcomes. Thus, facilitating serious role-playing virtual care practices along with raising awareness of healthcare professionals about the enduring impact of implicit/explicit biases and Social Determinants of Health (SDH) on health outcomes assist to advance the patient-provider relation, care experiences (e.g., healthcare experience …

Segmentation Of Intracranial Structures From Noncontrast Ct Images With Deep Learning, Evan Porter

Wayne State University Dissertations

Presented in this work is an investigation of the application of artificially intelligent algorithms, namely deep learning, to generate segmentations for the application in functional avoidance radiotherapy treatment planning. Specific applications of deep learning for functional avoidance include generating hippocampus segmentations from computed tomography (CT) images and generating synthetic pulmonary perfusion images from four-dimensional CT (4DCT).A single institution dataset of 390 patients treated with Gamma Knife stereotactic radiosurgery was created. From these patients, the hippocampus was manually segmented on the high-resolution MR image and used for the development of the data processing methodology and model testing. It was determined that …

Automatically Inferring Image Bases Of Arm32 Binaries, Daniel T. Chong

Browse all Theses and Dissertations

Reverse engineering tools rely on the critical image base value for tasks such as correctly mapping code into virtual memory for an emulator or accurately determining branch destinations for a disassembler. However, binaries are often stripped and therefore, do not explicitly state this value. Currently available solutions for calculating this essential value generally require user input in the form of parameter configurations or manual binary analysis, thus these methods are limited by the experience and knowledge of the user. In this thesis, we propose a user-independent solution for determining the image base of ARM32 binaries and describe our implementation. Our …

There From The Beginning: The Women Of Los Alamos National Laboratory Supporting National And International Nuclear Security, Olga Martin, Laura Mcclellan, Octavio Ramos, Heather Quinn

International Journal of Nuclear Security

From the beginning of the Manhattan Project in the early 1940s, the women of what would become Los Alamos National Laboratory (LANL) worked in technical positions alongside their male counterparts, played a key role as computers, and worked in administrative jobs as secretaries, phone operators, bookkeepers, and on behalf of the U.S. Army in the Women’s Army Corps.

Throughout the history of the Laboratory, women experts at LANL helped establish and lead important national and international security programs, with careers in science, technology, engineering, and mathematics. Over time, the women of Los Alamos have come together under various Employee Resource …

Machine Learning In Requirements Elicitation: A Literature Review, Cheligeer Cheligeer, Jingwei Huang, Guosong Wu, Nadia Bhuiyan, Yuan Xu, Yong Zeng

Engineering Management & Systems Engineering Faculty Publications

A growing trend in requirements elicitation is the use of machine learning (ML) techniques to automate the cumbersome requirement handling process. This literature review summarizes and analyzes studies that incorporate ML and natural language processing (NLP) into demand elicitation. We answer the following research questions: (1) What requirement elicitation activities are supported by ML? (2) What data sources are used to build ML-based requirement solutions? (3) What technologies, algorithms, and tools are used to build ML-based requirement elicitation? (4) How to construct an ML-based requirements elicitation method? (5) What are the available tools to support ML-based requirements elicitation methodology? Keywords …

A Probabilistic Perspective Of Human-Machine Interaction, Mustafa Canan, Mustafa Demir, Samuel Kovacic

Engineering Management & Systems Engineering Faculty Publications

Human-machine interaction (HMI) has become an essential part of the daily routine in organizations. Although the machines are designed with state-of-the-art Artificial Intelligence applications, they are limited in their ability to mimic human behavior. The human-human interaction occurs between two or more humans; when a machine replaces a human, the interaction dynamics are not the same. The results indicate that a machine that interacts with a human can increase the mental uncertainty that a human experiences. Developments in decision sciences indicate that using quantum probability theory (QPT) improves the understanding of human decision-making than merely using classical probability theory (CPT). …

Ransombuster Iot: A Intrusion Detection And Dataset Creation Tool For Ransomware Attacks Within Iot Networks, Jackson M. Walker

Cybersecurity Undergraduate Research Showcase

The proposed research follows the design-science guidelines(Hevner, 2004). This paper uses these design-science methods for developing the guidelines for the implementation of the proposed architecture, understanding previous research contributions, and evaluating of research. This paper proposes a network artifact for studying ransomware IoT intrusion detection techniques and offers a proposed network architecture to serve as a framework for creating a publicly available dataset for IoT research on ransomware.

Deepfakes: Ai Technology Of The Future, Hosanna Root

Cybersecurity Undergraduate Research Showcase

Deepfakes technology’s danger stems from its ability to create realistic but fake synthesized media that people often identify as something that is real. With this powerful technology in the wrong hands, deepfakes can cause devastating havoc through information warfare, election campaign disruptions, and more, creating distrust in society. Disinformation is already rampant today, even without wide deployments of deepfakes, which is concerning given the fact that deepfakes’ nefarious full potentials are yet to be reached.

Security Issues With Network Connected Scada Systems, Chad Holm

Cybersecurity Undergraduate Research Showcase

The use of Supervisory Control and Data Acquisition (SCADA) systems has become common place and are being used in several different industries. These have evolved as the technology has progressed. The use of Internet of Things (IOT) devices makes for less human intervention to run daily operations in these industries. This can also allow hackers to gain access to these devices due to security holes that are overlooked. There have several different ways that have been exploited on SCADA networks and the goal is to recognize and secure them so hackers cannot gain access to them.

Corporate Cybersecurity In The Context Of M&A Transactions, Cameron Beck

Cybersecurity Undergraduate Research Showcase

The rapid rise of digital devices has unlocked a new dimension of innovation and prosperity in the 21st century. Computers are now an integrated and ubiquitous part of our global culture. You would be hard-pressed to walk into any given room without several computer chips humming inaudibly inside the machines that facilitate our modern world. Even lightbulbs and doorbells are connected to the Internet, capturing information from the world around them and sending that information to the Cloud. The Internet expands access to communication, international marketplaces, entertainment, professional resources, and nearly every book in the world.