Computer Engineering Commons^™

Ai-Assisted Reconfiguration Of Battery Packs For Cell Balancing To Extend Driving Runtime, Yuqin Weng, Cristinel Ababei

Electrical and Computer Engineering Faculty Research and Publications

State of charge (SoC) cell balancing is one of the most important roles of battery management systems (BMS). The performance and lifespan of a battery pack can be significantly degraded and reduced by the presence of imbalance in cells SoC. Recently, we have shown that using a machine learning driven battery pack reconfiguration technique based on a network of controllable switches, one can periodically change the battery pack topology to effectively achieve better cell SoC equalization. As a result, the driving runtime achieved with a better balanced battery pack is increased. In this paper, we build on these promising results …

Exploring Lstm-Based Attention Mechanisms With Pso And Grid Search Under Different Normalization Techniques For Energy Demands Time Series Forecasting, Andri Pranolo, Xiaofeng Zhou, Yingchi Mao, Bambang Widi Pratolo, Aji Prasetya Wibawa, Agung Bella Putra Utama, Abdoul Fatakhou Ba, Abdullahi Uwaisu Muhammad

Knowledge Engineering and Data Science

Advanced analytical approaches are required to accurately forecast the energy sector's rising complexity and volume of time series data. This research aims to forecast the energy demand utilising sophisticated Long Short-Term Memory (LSTM) configurations with Attention mechanisms (Att), Grid search, and Particle Swarm Optimization (PSO). In addition, the study also examines the influence of Min-Max and Z-Score normalization approaches in the preprocessing stage on the accuracy performances of the baselines and the proposed models. PSO and Grid Search techniques are used to select the best hyperparameters for LSTM models, while the attention mechanism selects the important input for the LSTM. …

Hybrid Method For User Review Sentiment Categorization In Chatgpt Application Using N-Gram And Word2vec Features, Husna Luthfiatun Nisa, Atina Ahdika

Knowledge Engineering and Data Science

The rapid development of Artificial Intelligence (AI) has significantly influenced nearly all aspects of life. One AI product widely used by people worldwide is the Chat Generative Pre-Training Transformer (ChatGPT), which can respond to questions conversationally. Although data indicates that the use of ChatGPT in Indonesia is less widespread than in other countries, a Populix survey reveals that half of the respondents have utilized ChatGPT, using AI more than once a month. This indicates its crucial role among the Indonesian population. ChatGPT is not limited to browsers; it is also available as a downloadable application on the Google Play Store. …

Convolutional Neural Network In Motion Detection For Physiotherapy Exercise Movement, Dika Fikri Laistulloh, Anik Nur Handayani, Rosa Andrie Asmara, Phillip Taw

Knowledge Engineering and Data Science

Physiotherapy focuses on movement and optimal utilization of the patient's potential. Exercise Therapy is a physiotherapy procedure that specifically focuses exercises on active and passive movements. Cerebral Palsy (CP) patients are one of the sufferers of motor disorders of the upper extremities. Cerebral Palsy (CP) patients suffer from disorders in motor functions of the upper extremities. Physiotherapy Exercise Movement has 4 categories of movement exercises for the therapy of people with upper extremity body disorders: Elbow flexor strengthening in sitting using free weights, lifting an object up, reaching diagonally in sitting, and reaching from a low surface to a high …

Optimizing Malaria Control: Granular And Cost-Effective Mosquito Habitat Index In Endemic Areas Through Satellite Imagery, Nur Ainun Daulay, Salwa Rizqina Putri, Arie Wahyu Wijayanto, Ika Yuni Wulansari

Knowledge Engineering and Data Science

Malaria, classified as a tropical disease under the Sustainable Development Goals (SDGs) indicator 3.3, remains a significant global health challenge. In this study, by taking advantage of multiple spectral composite indexes of multisource satellite imagery to capture various geospatial features relevant to the suitability of marsh mosquito habitat, we introduced the Mosquito Habitat Suitability Index (MHSI) to assess potential Anopheles mosquito breeding sites in terms of the vegetation density, water bodies, environment temperature, and humidity in any particular areas. The MHSI integrates the publicly accessible granular level of the normalized difference vegetation index, water index, land surface temperature, and moisture …

Docker Optimization Of An Automotive Sector Virtual Server Infrastructure, Leonel Hernandez, Carlos Eduardo Uc Rios

Knowledge Engineering and Data Science

Server virtualization is a powerful strategy for optimizing network infrastructure. It allows multiple virtual servers to run on a single physical server, maximizing resource utilization and improving efficiency. Deploying server virtualization using Docker technology offers a lightweight and flexible approach to optimizing network infrastructure. Docker contains package applications and their dependencies, enabling consistent and efficient deployment across various environments. Specifically, optimizing virtual server infrastructure using Docker Technology in the automotive sector focuses on improving the efficiency and management of the company's virtual server resources. By implementing Docker technology, a container platform that allows the packaging and running of applications in …

Timbre Style Transfer For Musical Instruments Acoustic Guitar And Piano Using The Generator-Discriminator Model, Widean Nagari, Joan Santoso, Esther Irawati Setiawan

Knowledge Engineering and Data Science

Music style transfer is a technique for creating new music by combining the input song's content and the target song's style to have a sound that humans can enjoy. This research is related to timbre style transfer, a branch of music style transfer that focuses on using the generator-discriminator model. This exciting method has been used in various studies in the music style transfer domain to train a machine learning model to change the sound of instruments in a song with the sound of instruments from other songs. This work focuses on finding the best layer configuration in the generator- …

A Novel Approach To Defect Detection In Arabica Coffee Beans Using Deep Learning: Investigating Data Augmentation And Model Optimization, Yusriel Ardian, Novta Danyel Irawan, Sutoko Sutoko, I Nyoman Gede Arya Astawa

Knowledge Engineering and Data Science

Arabica coffee beans have valuable market worth because of their taste and quality, and there are defects like wholly and partially black beans that can lower the standards of a product, especially in the premium coffee sector. However, the manual processes used to detect the defects take an inordinate amount of time and are inefficient. This study aims to bridge the knowledge gap on the automated detection and recognition of the defects present in the Arabica coffee beans by creating and optimizing a CNN model based on a modified VGG16 architecture. The model applies data augmentation, rotation, cropping, and Bayesian …

Enhancing Information Architecture With Machine Learning For Digital Media Platforms, Taylor N. Mietzner

Honors College Theses

Modern advancements in machine learning are transforming the technological landscape, including information architecture within user experience design. With the unparalleled amount of user data generated on online media platforms and applications, an adjustment in the design process to incorporate machine learning for categorizing the influx of semantic data while maintaining a user-centric structure is essential. Machine learning tools, such as the classification and recommendation system, need to be incorporated into the design for user experience and marketing success. There is a current gap between incorporating the backend modeling algorithms and the frontend information architecture system design together. The aim of …

In-Depth Examination Of Gas Consumption In E-Will Smart Contract: A Case Study, Manal Mansour, May Salama, Hala Helmi, Mona F.M Mursi

Journal of Engineering Research

In recent years, blockchain technology, coupled with smart contracts, has played a pivotal role in the development of distributed applications. Numerous case studies have emerged, showcasing the remarkable potential of this technology across various applications. Despite its widespread adoption in the industry, there exists a significant gap between the practical implementation of blockchain and the analytical and academic studies dedicated to understanding its nuances.

This paper aims to bridge this divide by presenting an empirical case study focused on the e-will contract, with a specific emphasis on gas-related challenges. By closely examining the e-will contract case study, we seek to …

A Soft Two-Layers Voting Model For Fake News Detection, Hnin Ei Wynne, Khaing Thanda Swe

Journal of Engineering Research

The proliferation of fake news has become a complex and challenge problem in recent year, and presenting various unsolved issues within the research domain. Among these challenges, a critical concern is the development of effective models capable of accurately distinguish between fake and real news. While numerous techniques have been proposed for fake news detection, achieving optimal accuracy remains elusive. This paper introduces a novel fake news detection approach employing a two-layered weighted voting classifier. In contrast to conventional methods that assign equal weights to all classifiers, our proposed approach utilizes a selective weighting approach to solve the current issue. …

Exploring Human Aging Proteins Based On Deep Autoencoders And K-Means Clustering, Sondos M. Hammad, Mohamed Talaat Saidahmed, Elsayed A. Sallam, Reda Elbasiony

Journal of Engineering Research

Aging significantly affects human health and the overall economy, yet understanding of the underlying molecular mechanisms remains limited. Among all human genes, almost three hundred and five have been linked to human aging. While certain subsets of these genes or specific aging-related genes have been extensively studied. There has been a lack of comprehensive examination encompassing the entire set of aging-related genes. Here, the main objective is to overcome understanding based on an innovative approach that combines the capabilities of deep learning. Particularly using One-Dimensional Deep AutoEncoder (1D-DAE). Followed by the K-means clustering technique as a means of unsupervised learning. …

Gigacollector: A Real-Time, Temporally Coherent Framework Forwi-Fi Environment Control, Data Collection, And Ml Inference, An Vu

Computer Science and Engineering Master's Theses

Wi-Fi is the primary wireless communication method for the majority of devices in both residential and commercial settings. The number of devices continues to increase, making latency, bandwidth, and security difficult to manage and balance to provide satisfactory performance for all users. Novel methods that rely on the collection of data from the networking stack have been developed in research settings to analyze and predict key parameters and network state to improve communication efficiency. However, crucial processes such as experimentation, data collection, and performance analysis have often been performed manually on offline data.

This thesis presents GigaCollector, a scalable end-to-end …

Human Motion-Inspired Inverse Kinematics Algorithm For A Robotics-Based Human Upper Body Model, Urvish Trivedi

USF Tampa Graduate Theses and Dissertations

The goal of this research is to develop a human motion-inspired inverse kinematics algorithm framework specifically designed for a Robotics-Based Human Upper Body Model (RHUBM). This framework offers solutions to challenges in various fields. In humanoid robotics, the framework addresses the problem of unnatural robot movement by enabling the development of motion planning algorithms that incorporate human-like movements. For prosthetics, the framework tackles the challenge of amputee difficulty in learning and controlling prosthetics by providing a user-friendly interface that predicts and visualizes upper limb movements, enabling learning and practice. In rehabilitation therapy, the framework tackles …

Revolutionizing Feature Selection: A Breakthrough Approach For Enhanced Accuracy And Reduced Dimensions, With Implications For Early Medical Diagnostics, Shabia Shabir Khan, Majid Shafi Kawoosa, Bonny Bannerjee, Subhash C. Chauhan, Sheema Khan

Research Symposium

Background: The system's performance may be impacted by the high-dimensional feature dataset, attributed to redundant, non-informative, or irrelevant features, commonly referred to as noise. To mitigate inefficiency and suboptimal performance, our goal is to identify the optimal and minimal set of features capable of representing the entire dataset. Consequently, the Feature Selector (Fs) serves as an operator, transforming an m-dimensional feature set into an n-dimensional feature set. This process aims to generate a filtered dataset with reduced dimensions, enhancing the algorithm's efficiency.

Methods: This paper introduces an innovative feature selection approach utilizing a genetic algorithm with an ensemble crossover operation …

Exploring The Use Of Enhanced Swad Towards Building Learned Models That Generalize Better To Unseen Sources, Brandon M. Weinhofer

USF Tampa Graduate Theses and Dissertations

Deep learning models, typically, take significant time to train. Classifier ensembles are areliable way to increase classifier accuracy and perhaps generalizability to unseen sources of data. These classifiers can be combined with a simple voting scheme. The problem is that having multiple models can very heavily increase training time. Snapshot ensembles have been shown to provide a boost in performance by creating an ensemble of classifiers with different weights during the training of a single deep learned model. This can somewhat solve the problem of the increased training time as you do not have to train separate models. As Machine …

Comparing Anova And Powershap Feature Selection Methods Via Shapley Additive Explanations Of Models Of Mental Workload Built With The Theta And Alpha Eeg Band Ratios, Bujar Raufi, Luca Longo

Articles

Background: Creating models to differentiate self-reported mental workload perceptions is challenging and requires machine learning to identify features from EEG signals. EEG band ratios quantify human activity, but limited research on mental workload assessment exists. This study evaluates the use of theta-to-alpha and alpha-to-theta EEG band ratio features to distinguish human self-reported perceptions of mental workload. Methods: In this study, EEG data from 48 participants were analyzed while engaged in resting and task-intensive activities. Multiple mental workload indices were developed using different EEG channel clusters and band ratios. ANOVA’s F-score and PowerSHAP were used to extract the statistical features. At …

Uav Swarm Obstacle Avoidance Algorithm Based On Visual Field And Velocity Guidance, Xueqi Gui, Chuntao Li

Journal of System Simulation

Abstract: In the future aerial combat of multiple unmanned aerial vehicles (UAVs), the safe flight of UAV swarm in unknown airspace is an important content of swarm research. In view of avoiding obstacles and maintaining behavior in the UAV swarm system, this paper presents a UAV swarm collision avoidance algorithm based on visual field and velocity guidance (VFVG). The swarm adaptive communication topology mechanism is designed based on the visual field method. Combined with the principle of far attraction and near repulsion and the consensus method, the mechanism can accelerate the transmission of obstacle avoidance information among UAV swarms while …

Modeling And Optimization Of Smart Warehouse Order Sorting Considering Splitting Strategy, Yuze Xu, Linxuan Zhang, Hui Li, Ming Ge, Wanyi He

Journal of System Simulation

Abstract: For an automatic vehicle sorting problem involving mixed sorting of two types of orders, an order splitting strategy and a method for batch adjustment of sub-orders after splitting are proposed by considering the phenomena of blockage of automatic guided vehicles (AGVs) and idleness of manual collection stations in the order sorting process. In addition, with the optimization objective of minimizing the total order completion time, an order sorting integer planning model with order splitting is established. An improved discrete grey wolf optimization algorithm is proposed to jointly optimize the three sub-problems of order batching, batch sorting, and product unloading …

Construction Of Machine Learning Data Set For Analyzing The Replay Of The Wargaming, Dayong Zhang, Jingyu Yang, Jun Ma, Chenye Song

Journal of System Simulation

Abstract: The first problem to be solved in the application of machine learning to the analysis of the replay of the wargaming is the construction of data sets. Due to the standardization requirements of machine learning for data structure, as well as the limitations of computing power and storage, building a machine learning data set through the wargaming data still faces many problems in terms of how to describe the wargaming situation, how to describe the wargaming process, how to handle high dimensional data, and how to prevent data distortion. To solve these problems, this paper constructs a mapping model …

Gesture Recognition For Dynamic Vision Sensor Based On Multi-Dimensional Projection Spatiotemporal Event Frame, Lai Kang, Yakun Zhang

Journal of System Simulation

Abstract: Vision-based gesture recognition is a commonly used means of human-computer interaction in the fields of virtual reality and game simulation. In practical applications, rapid changes in gesture movements will lead to blurred imaging with traditional RGB cameras or depth cameras, which brings great challenges to gesture recognition. To solve the above problems, a dynamic visual data gesture recognition method based on a multi-dimensional projection spatiotemporal event frame (STEF) is proposed by a using dynamic vision sensor to capture high-speed gesture movement information. The spatiotemporal information is embedded in the data projection surface and fused to form a multidimensional projection …

Multi-Agent Path Planning With Obstacle Penalty Factor, Xingyu Yan, Dayan Li, Niya Wang, Kaixiang Zhang, Jianlin Mao

Journal of System Simulation

Abstract: In light load environments, complex obstacle areas will exacerbate local conflicts between agents, leading to a decrease in path solving efficiency. This paper proposes a multi-agent path planning (MAPF) method with obstacle penalty factors in light load environments. First, in the low-level single machine planning process based on the conflict-based search (CBS) algorithm framework, by judging the distribution type of surrounding obstacles that are about to expand the agent's position, corresponding obstacle penalty factors are assigned to them; then, the penalty factors in the path planning process are accumulated and used as the heuristic value of single machine planning …

Research On Optimization Design Method Of Waverider Forebody/Bump Profile Of Aircraft, Jialin Qiu, Jun Huang, Peng Shu, Qingfeng Wang, Zhiqin Liu, Wenyou Qiao

Journal of System Simulation

Abstract: The waverider forebody and Bump profile of aircraft are two classic cases reflecting the waverider idea in aircraft component design. They can effectively improve the overall aerodynamic performance of aircraft and have become the core technology of aircraft overall design. In order to seek the optimal design of the waverider forebody and Bump profile to improve the efficiency of aircraft design, an optimization design method for the waverider forebody and Bump profile is proposed in this paper. The initial waverider forebody and Bump profile are generated by the osculating cone theory and conical flow field, and the aerodynamic performance …

Research On Hybrid Solution Algorithm For Layout Problem Of Rectangular Parts With Multiple Constraints, Ye Liu, Weixi Ji, Xuan Su, Hongxuan Zhao

Journal of System Simulation

Abstract: A hybrid algorithm based on a cutting and matching algorithm and an improved ant colony algorithm was proposed to solve the layout problem of rectangular parts in the process of wood and glass blanking. A layout optimization model was established to maximize the mean square utilization and the remaining processing time; the ant colony algorithm was used as the layout sequence algorithm to determine the layout sequence of some parts and meet the processing time constraint. In order to improve the search efficiency of the ant colony algorithm, an adaptive pheromone updating strategy was proposed, and a hybrid mutation …

Programmable And Scalable Bit-Sliced Vlsi Architecture For Decision Tree Based Machine Learning Edge Inference, Raaga Sai Somesula

USF Tampa Graduate Theses and Dissertations

As the volume and diversity of Internet-of-Things (IoT) data continues to grow, traditional cloud-based processing methods face significant challenges, including latency, bandwidth constraints, and privacy concerns. Our research focuses on employing decision trees (DTs) as an intelligent filtering mechanism on the edge. Preliminary comparisons across four datasets revealed DTs are significantly more efficient than multilayer perceptrons (MLP), saving 97-98\% in area and power, leading to the selection of DT for our proposed architecture for lightweight IoT devices. We propose a novel programmable and scalable custom application specific integrated circuit (ASIC) architecture designed for Decision Tree based ML inference. Each bit-slice …

Human Action Recognition Based On Skeleton Edge Information Under Projection Subspace, Benyue Su, Peng Zhang, Bangguo Zhu, Mengjuan Guo, Min Sheng

Journal of System Simulation

Abstract: In recent years, human action recognition based on skeleton data has received a lot of attention in the fields of computer vision and human-computer interaction. Most of the existing methods focus on modeling the skeleton points in the original 3D coordinate space. However, skeleton points ignore the physical chain structure of the human body itself, which makes it difficult to portray the local correlation of human motion. In addition, due to the diversity of camera views, it is difficult to explore the comprehensive representation of actions in different views under the original point-based 3D space. In view of this, …

Three-Dimensional Path Planning Of Uav Based On All Particles Driving Wild Horse Optimizer Algorithm, Gaoyang Li, Xiangfeng Li, Kang Zhao, Yuchao Jin, Zhidong Yi, Dunwen Zuo

Journal of System Simulation

Abstract: In view of large calculation amounts and difficult convergence in the unmanned aerial vehicle (UAV) path planning, a path planning method based on all particles driving wild horse optimizier (APDWHO) was proposed. A three-dimensional environment model and path cost model were established, by which the path planning problem was transformed into a multi-dimensional function optimization problem. An adaptive neighborhood search strategy (ANSS) was adopted to improve the exploitation ability of the algorithm. The Gaussian random walk strategy was used to search the historical optimal position of the individual to improve the exploration ability of the algorithm. Since the ANSS …

3d Streamline Visualization Method Based On Clustering Fusion, Xuqiang Shao, Ya Cheng, Yizhong Jin

Journal of System Simulation

Abstract: In order to solve the problems of incomplete feature extraction, continuity destruction of flow field by visual results, and poor representation of streamline caused by unstable clustering division when the clustering method is used to realize 3D streamline visualization. A 3D streamline visualization method based on clustering fusion is proposed. It consists of a distance measurement method between features and a clustering fusion method, which takes the inter-feature distance and spatial distance as the similarity between streamlines for clustering and then performs weighted merging and subdivision of the obtained clustering result. The method has been tested on data sets …

Planning Modeling And Optimization Algorithm For 5g Indoor Distribution System, Shaoda Zeng, Hailin Liu

Journal of System Simulation

Abstract: Most of the new services in 5G mobile communication technologies, including smart homes, smart factories, and virtual reality, take place in indoor scenes. Therefore, how to quickly plan and build a 5G indoor distribution system with low construction cost and low power loss is of great significance for telecom operators. This paper establishes a mathematical planning model of a 5G indoor distribution system, which is closer to the actual scenario. The model aims to minimize the deployment cost and the maximum output signal power deviation between antennas, and the constraint is to meet the expected output signal power of …

Formation Strategy Of Hybrid Obstacle Avoidance Algorithm For Multiple Mobile Robots, Fulin Liu, Qingxin Li

Journal of System Simulation

Abstract: For the obstacle avoidance problem of multiple mobile robots in the unknown static obstacle environment, this paper proposed a formation strategy of a hybrid obstacle avoidance algorithm for multiple mobile robots, ensuring that multiple mobile robots do not collide during operation, can maintain the formation to the maximum extent in the unknown static obstacle environment for effective obstacle avoidance, and can reach the designated target point in a short time. Based on the leaderfollower method and artificial potential field (APF) method, the formation strategy divided the robots in the system into the leader robot and the follower robot. According …