Artificial Intelligence and Robotics Commons^™

Jsper (Just Stablediffusion Plus Easy Retraining), Adam Rusterholz, Meghan Finn, Zach Zolliecoffer, Zach Judy

ATU Scholars Symposium

JSPER is an an AI art generation Web Application that is both flexible and accessible. Our goal is to enable anyone to create and use their own customized art models, regardless of technical skill level. These models can be trained on almost anything, from a person, to an animal, to a specific object, or even style. The user only has to upload a handful of images of their subject. Then, training settings get optimized at the push of a button to match the type of subject the user is training. After training, their customized model can be used to generate …

Optimizing Campus Chat-Bot Experience Using Puaa: Integrating Large Language Model (Llm) Into University Ai Assistants, Sijan Panday, Zurab Sabakhtarishvili, Clayton Jensen

ATU Scholars Symposium

The advent of large language models (LLMs) such as Chat-GPT and Bard marks a significant milestone in knowledge acquisition, offering a streamlined alternative to the traditionally labor-intensive process of navigating through multiple checkpoints on the web. This emerging trend in LLMs renders the prevalent rule-based chatbots, commonly utilized by universities, increasingly outdated and subpar. This research project proposes integrating LLM technology into university websites, specifically targeting the needs of students seeking information about their institutions by introducing PUAA (Personal University AI Assistant). Our approach involves using the Retrieval-Augmented Generation (RAG) framework, leveraging the capabilities of the LlamaIndex in conjunction with …

Techniques To Detect Fake Profiles On Social Media Using The New Age Algorithms – A Survey, A K M Rubaiyat Reza Habib, Edidiong Elijah Akpan

ATU Scholars Symposium

This research explores the growing issue of fake accounts in Online Social Networks [OSNs]. While platforms like Twitter, Instagram, and Facebook foster connections, their lax authentication measures have attracted many scammers and cybercriminals. Fake profiles conduct malicious activities, such as phishing, spreading misinformation, and inciting social discord. The consequences range from cyberbullying to deceptive commercial practices. Detecting fake profiles manually is often challenging and causes considerable stress and trust issues for the users. Typically, a social media user scrutinizes various elements like the profile picture, bio, and shared posts to identify fake profiles. These evaluations sometimes lead users to conclude …

Anomaly Detection With Spiking Neural Networks (Snn), Shruti Bhandari, Vyshnavi Gogineni

ATU Scholars Symposium

Abstract:

Anomaly detection, the identification of rare or unusual patterns that deviate from normal behavior, is a fundamental task with wide-ranging applications across various domains. Traditional machine learning techniques often struggle to effectively capture the complex temporal dynamics present in real-world data streams. Spiking Neural Networks (SNNs), inspired by the spiking nature of biological neurons, offer a promising approach by inherently modeling temporal information through precise spike timing. In this study, we investigate the use of Spiking Neural Networks (SNNs) for detecting anomalies or unusual patterns in data. We propose an SNN model that can learn what constitutes normal …

Innovating Inventory And Alert Systems With Object Tracking, Juan Harmse, Esther Peden

Campus Research Month

Security system users require safeguarding inventory from potential theft while reducing manual tracking of physical objects. Our contribution harnesses the power of artificial intelligence and computer vision with YOLO to automate the process of tracking inventory items. The system sends alerts to the inventory manager when it detects particular events. Our approach was evaluated with KernProf profiling, interference, and orientation tests. The results were overall positive in these testing areas.

The Vulnerabilities Of Artificial Intelligence Models And Potential Defenses, Felix Iov

Cybersecurity Undergraduate Research Showcase

The rapid integration of artificial intelligence (AI) into various commercial products has raised concerns about the security risks posed by adversarial attacks. These attacks manipulate input data to disrupt the functioning of AI models, potentially leading to severe consequences such as self-driving car crashes, financial losses, or data breaches. We will explore neural networks, their weaknesses, and potential defenses. We will discuss adversarial attacks including data poisoning, backdoor attacks, evasion attacks, and prompt injection. Then, we will explore defense strategies such as data protection, input sanitization, and adversarial training. By understanding how adversarial attacks work and the defenses against them, …

Intelligent Optimization Method Of Cloud Manufacturing Swarm Based On Incomplete Information Game, Kunpeng Zhang, Yan Wang, Zhicheng Ji

Journal of System Simulation

Abstract: In the process of cloud manufacturing, the incomplete information status and the mutual competition and restriction relationship between cloud platform operator and demander lead to the difficult choice of manufacturing services. A cloud manufacturing swarm intelligent optimization method based on incomplete information game model is proposed. A static game model based on incomplete information is established for the interest competition between demand-side and cloud platform, with the goal of rationally pursuing the maximization of their own revenue function. The competition rules between demand-side and cloud platform are proposed, which are introduced into nature through Harsanyi transformation and converted into …

Hyper-Heuristic Approach With K-Means Clustering For Inter-Cell Scheduling, Yanlin Zhao, Yunna Tian

Journal of System Simulation

Abstract: According to the actual production situation of China's manufacturing industry, a hyperheuristic algorithm based on K-means clustering is proposed for inter-cell scheduling problem of flexible job-shop. K-means clustering is applied to group entities with similar attributes into the corresponding work cluster decision blocks, and the ant colony algorithm is used to select heuristic rules for each decision block. The optimal scheduling solutions are generated by using corresponding heuristic rules for scheduling of entities in each decision block. Computational results show that, the computational granularity is properly increased by the form of decision blocks, and the computational efficiency of the …

Distributed Energy Management Strategy Of Microgrid Based On Master-Slave Game, Miaomiao Ma, Hao Wang, Lipeng Dong, Xiangjie Liu

Journal of System Simulation

Abstract: Under the operation mode of power market, based on two-layer master-slave game, a distributed energy management strategy for the microgrid is proposed to tackle the conflict between the overall optimal operation of renewable microgrid and the maximum profit of each investor. To fully consider the balance between energy supply and demand, the concept of power trading agent is introduced, and an integrated demand response strategy based on consumer satisfaction and adjustable load is proposed on the user side. Considering the initiative and decision-making ability of power supply and load, the decision-making game model is established with power trading agent …

Optimization Of Urban Traffic Microsimulation Model For Carbon Emission Reduction, Bo Liu, Jianxin Lin, Yini Liu, Dong Zhang

Journal of System Simulation

Abstract: To assess the environmental benefits of transportation management or control strategies, a method to effectively integrate the micro-traffic simulation model and the micro-vehicle emission model is proposed. VISSIM platform is used to build a case micro traffic simulation model. K-means clustering method is used to divide the driving behavior into 4 types based on the acceleration and deceleration characteristics of different speed intervals of the trajectory data, and the global parameters of the simulation model are calibrated based on the driving characteristics, which quantitatively describe the total sensitivity of the parameters and the sensitivity of the interactions between the …

Modeling And Analysis Of Hybrid Traffic Flow Considering Actual Behavior Of Platoon, Xi Wang, Xiujian Yang, Xiaohan Jia, Shenyi Wang

Journal of System Simulation

Abstract: To explore the effect of actual behavior of autonomous vehicular platoon on traffic flow, aiming at the hybrid traffic flow mixed with predecessor following(PF) platoon which is modeled according to the actual control strategy, a hybrid traffic flow model is established based on cellular automata(CA) modeling method. Simulation analysis shows that the effect of platoon characteristics such as time headway, market penetration, platoon size, and control gains on hybrid traffic flow presents coupling and nonlinear properties. The spatiotemporal behavior of hybrid traffic flow with different platoon characteristics is generally much different. Reducing time headway or increasing platoon market penetration …

Dynamic Path Planning For Mobile Robot Based On Rrt* And Dynamic Window Approach, Rui Zhang, Li Zhou, Zhengyang Liu

Journal of System Simulation

Abstract: A dynamic path planning method combining RRT* and dynamic window approach(DWA) is proposed to realize the obstacle avoidance of mobile robot in complex environment of dynamic obstacles. Improved RRT* algorithm is used to generate the global optimal safe path based on the known environment information. By eliminating the dangerous nodes generated by RRT* algorithm, the security of global path is ensured. Greedy algorithm is used to remove the redundant nodes in the path to reduce the length of global path. DWA is used to track along the global optimal path planned by the improved RRT* algorithm. When static obstacles …

Collaborative Navigation Method For 5g Cluster Uav Based On Configuration Optimization, Chao Gao, Zheng Huang, Xuan Zhao, Hongxing Wang, Tao Long

Journal of System Simulation

Abstract: The existing range based cooperative navigation methods for clustered UAVs generally ignore the impact of space configuration on positioning and energy determination, which makes it difficult to obtain the accurate navigation and positioning results. In view of this, a collaborative navigation method is proposed for 5G clustered UAVs based on spatial configuration optimization. The relative ranging error model of UAVs based on 5G signals in complex environments is constructed, and the optimization strategy for collaborative navigation nodes is established based on the minimum geometric division of precision(GDOP) criterion to achieve the real-time optimization of collaborative navigation spatial configuration; A …

A Multi-Uav Collaborative Priority Coverage Search Algorithm, Xiang Yu, Qianrui Deng, Sirui Duan, Chen Jiang

Journal of System Simulation

Abstract: For the challenges such as large disaster area, uneven distribution of key areas and limited rescue time in emergency rescue, a multi-UAV collaborative priority coverage search algorithm is proposed. The search area is rasterized, and each grid is probabilistically labeled according to the disaster prediction information. The search area is divided into sub-regions of similar size and equal number of UAVs by K-means++ algorithm, and the search starting point of each sub-region is determined based on the clustering center, so that the multiple UAVs can carry out the partition cooperative search of the whole area. The score of each …

Incremental Image Dehazing Algorithm Based On Multiple Transfer Attention, Jinyang Wei, Keping Wang, Yi Yang, Shumin Fei

Journal of System Simulation

Abstract: In order to improve the processing ability of the depth-neural network dehazing algorithm to the supplementary data set, and to make the network differently process the image features of different importance to improve the dehazing ability of the network, an incremental dehazing algorithm based on multiple migration of attention is proposed. The teacher's attention generation network in the form of Encoder-Decoder extracts the multiple attention of labels and haze, which is used it as the label of the characteristic migration media network to constrain the network training to form the migration media attention as close as possible to the …

Path Planning Rapid Algorithm Based On Modified Rrt* For Unmanned Surface Vessel, Zhaozhen Jiang, Wenlong Wang, Wenqi Sun

Journal of System Simulation

Abstract: Aiming at the weak purposiveness of rapidly exploring random tree algorithm in USV path planning, a modified rapid algorithm is proposed. The artificial potential field method is improved and the force analysis in four directions is added to comprehensively calculate the resultant force on USV. The calculation method of steering angle is redefined to avoid entering the local optimal trap and can reach the target point smoothly to obtain an initial path. The initial path is used to set the random point sampling area of rapidly exploring random tree algorithm. By reducing the probability of random points generated in …

Research On Cross-Domain Unmanned Swarm Cooperative Anti-Submarine Search Method, Ning Wang, Xiaolong Liang, Jiaqiang Zhang, Yueqi Hou, Aiwu Yang

Journal of System Simulation

Abstract: For the maritime ASW search, a cross-domain unmanned swarm cooperative search method is proposed in which USVs are used as the communication relay of UAVs. The digital grid map is used to characterize the mission area and the kinematic model of cross-domain platform is constructed. The cooperative method of cross-domain unmanned systems is proposed, and the distributed information fusion mechanism of unmanned systems is designed. The search objective function for heterogeneous platforms is designed to guide the unmanned systems to make real-time decisions in search task. The simulation results show that the proposed method can be effective to the …

Simulation Verification And Decision-Making Key Technologies Of Unmanned Swarm Game Confrontation: A Survey, Xiaolong Liang, Aiwu Yang, Jiaqiang Zhang, Yueqi Hou, Ning Wang, Xiao Huang, Junbin Gong

Journal of System Simulation

Abstract: Unmanned swarm game confrontation is a new combat mode and plays a crucial role in intelligent warfare. Its core is the autonomous generation of a series of game confrontation decision sequences to "empower" the swarm. The progress of system simulation verification for the unmanned swarm game confrontation is analyzed. The key technologies of the autonomous decision-making are discussed from three aspects, technology based on expert systems and game theory, technology based on swarm intelligence and optimization theory, and technology based on neural networks and reinforcement learning. The key technology research conducted by the author's team on the autonomous decisionmaking …

Research On Integration Of Virtual-Real Hybrid Simulation Experiment Environment For Unmanned Swarm, Huijie Yang, Taoshun Xiao, Chen Wu, Lingfeng Guo

Journal of System Simulation

Abstract: Constructing the experiment environment and researching the core technology, key equipment and operation theory is the key step for the development of unmanned swarm. Based on the requirement of hybrid simulation environment for unmanned swarm, the elements of the experiment environment are analyzed, and the architecture is proposed, which is composed of common infrastructure, general experiment services, special experiment tools, security and support tool. The key experiment environment integration technology is studied from the aspects of experiment network, model data and experiment application. The feasibility of the method to construct the virtual-real hybrid simulation environment is verified by an …

Mixed-Variable Particle Swarm Optimization Algorithm Based On Competitive Coevolution, Hu Zhang, Heng Zhang, Zilu Huang, Zhe Wang, Qingpo Fu, Jin Peng, Feng Wang

Journal of System Simulation

Abstract: For the current algorithm, it is difficult to obtain the available solution due to the irregularity of problem decision space caused by the numerous mixed variable optimization problems during real industrial applications. The coevolution strategy is introduced and a mixed variable particle swarm optimization algorithm(CCPSO) based on competitive coevolution is proposed. The search direction adjustment mechanism based on tolerance is designed to judge the evolution state of particles, adaptively adjust the search direction of particles, avoid falling into local optimum, and balance the convergence and diversity of the population. The learning object generation mechanism is adopted for each particle …