Computer Engineering Commons^™

Short-Term Electricity Price Forecasting In Deregulated Electricity Market Based On Enhanced Artificial Intelligence Techniques, Pourdaryaei Alireza

Student Works (2020-2029)

Electricity price forecasting is considered as one of prime factors for operation, planning and scheduling of price-setter market participants. However, possessing time variant, non-linear and non-stationary behaviors make the electricity price a complex signal. The main challenge in this area is providing highly accurate and efficient day-ahead price forecasting. A suitable feature selection technique, which is able to model the interacting features and nonlinearities of the forecast processes, is still required although researches have been performed for day-ahead forecasting. In this research, a hybrid electricity price forecasting methodology is proposed using two-stage feature selection method and optimization using adaptive neuro-fuzzy …

Research On The Strategy Of Adaptive Uvls Based On Rtds Simulation, Zhao Dan, Man Ji, Yunling Ni, Dengxin Liu, Weidong Wang

Journal of System Simulation

Abstract: Aiming at the improvement of the slow and unstable system voltage recovery after the low voltage load shedding load protected by centralized station area, the traditional low voltage load shedding load strategy will be researched. Considering the factors such as the power shortage and the important grade of the load, the power factor of the load to be cut is introduced, and the low load shedding model is established by minimizing the amount of cut load and minimizing the reactive power. The research is transformed into a belt Constrained multi-objective optimization research. The multi- objective particle swarm optimization algorithm …

Design Of Air Defense Missile Weapon System Simulation Platform Based On Xsim Platform, Kaizhi Ruan, Qingqing Yuan, Wenhua Zhai, Zhiqiang Zhang

Journal of System Simulation

Abstract: Taking the system simulation technology which applied to the scheme argumentation, optimization design, flight test forecast, battle effectiveness evaluation of air defense missile weapon system as background, the design method of air defense missile weapon system simulation platform based on Xsim platform was put forward. The total configuration design, model design and simulation process design of the platform were discussed. An simulation platform of an air defense missile weapon system was accomplished. The result proves the platform can simulate the battle process of air defense missile weapon system, support the simulation work of air defense weapon at different …

Analysis And Optimization Of Combustion Characteristics Of Cement Kiln Cooperatively Disposing Domestic Refuse, Jingbing Wu, Hanqing Tang, Xu Jun

Journal of System Simulation

Abstract: Because the traditional methods can hardly analyze the complex combustion characteristics of cement kiln mixed with domestic refuse, a data mining technology is introduced. A domestic cement plant is selected as the object, and its operating data and relevant parameters are collected. The influence coefficient of each parameter on coal consumption and NO_x emission is analyzed by using Stability Selection algorithm. The mathematical model of coal consumption and NO_x emission is established with Random Forest algorithm, and the key optimization parameters and their optimal values are obtained by K-means clustering algorithm. The result shows that this method …

An Enhanced Multi-Modal Function Optimization Fireworks Algorithm Base On Loser-Out Tournament, Xiaoning Shen, Wang Qian, Huang Yao, You Xuan

Journal of System Simulation

Abstract: An enhanced multi-modal fireworks algorithm based on the loser-out tournament is proposed. A new position-based mapping rule is used to map the explosion sparks beyond the upper boundary of the explosion space to the area near the upper boundary, and to map the one below the lower boundary to the area near the lower boundary. A strategy which adaptively adjusts the number of explosion sparks is introduced to better balance the global and local search abilities of the algorithm. The 28 functions in the CEC2013 standard test function set are selected to the test. Experimental results show that the …

A Xor-Based Visual Cryptography Scheme For (2, N) Access Structure With Ideal Structure Division, Yuqiao Cheng, Zhengxin Fu, Bin Yu

Journal of System Simulation

Abstract: We propose a XOR-based visual cryptography scheme for (2, n) access structures. According to the definition of ideal access structure, the relationship of shares among the minimal qualified subsets is analyzed. And based on it, a division algorithm of access structures is presented with the theory of graph. By this approach, we can obtain the least number of ideal access structures. Additionally the processes of secret sharing and recovering are given. Experimental results show that this scheme can achieve a perfect secret recovery. Compared with existing schemes, the pixel expansion of our paper is the best.

Study On Hardware-In-Loop Simulation Of Space-Feed Low-Frequency Guidance With Turntable External, Linpeng Wang, Chaolei Wang, Yuting Dai

Journal of System Simulation

Abstract: Low-frequency detection, tracking and guidance of stealthy targets need new requirements for hardware-in-loop simulation verification technology. Turntable built-in usually produces electromagnetic interference to seeker. A turntable external method for space- feed low-frequency guidance of hardware in- loop simulation system is proposed. The space-feed low-frequency guidance simulation model is established, and the influence of turntable electromagnetic interference on the seeker is completely eliminated by the turntable external. The simulation environment of non-inertial space motion is constructed to solve the information fusion problem of multiple spaces for hardware-in-loop simulation. The feasibility of the simulation method is verified. The results show that …

Study On Three-Dimensional Scene Sar Radio Frequency Simulation Technology, Guijie Diao, Ni Hong, Yang Liang

Journal of System Simulation

Abstract: Synthetic Aperture Radar (SAR) radio frequency simulation technology for three-dimensional scene is significant for SAR system test and the research of signal processing algorithms. A SAR radio frequency signal simulation is the core technology. Based on preliminary SAR frequency simulation scheme, a real-time SAR radio frequency signal simulation method for three-dimensional scene is proposed, and key parameters such as backward scattering coefficient, range between radar and target, shielding factor, antenna pattern weighting factor are calculated in real time according to the flight path information of SAR radar platform. Finally, the test results proved the validity of the method.

Matching Between Mac Address And Object Based On Rssi Change Sequence, Zhang Liang, Kaifeng Hao

Journal of System Simulation

Abstract: The connection between real people and the MAC of the communications device is of high value to public and network security. A better solution was proposed to improve the existing methods. MAC and real-time RSSI changes of the communication device were obtained by multiple Wi-Fi probes, then the RSSI status change sequence was constructed. The distance between object and multiple Wi-Fi probes was obtained by the object tracking, and the sequence of distance state change was constructed. After two kinds of sequences were compared, the optimal result was selected as the matching result between the moving object and the …

State Of Charge Estimation Of The Lithium-Ion Battery Based On Improved Extended Kalman Particle Filter Algorithm, Xia Fei, Zhicheng Wang, Shuotao Hao, Daogang Peng, Beili Yu, Yimin Huang

Journal of System Simulation

Abstract: The three order Thevenin model of 18650 Lithium-Ion battery is established based on the experimental data of UTS divided capacity tester. The extended kalman filtering (EKF) algorithm is adopted as the important density function of particle filter (PF) algorithm, and the extended Kalman particle filter (EKPF) algorithm is formed. The sample degradation and lack of diversity in the re-sampling stage of EKPF algorithm is optimized by an improved re-sampling algorithm which based on a weight sorting and survival of the fittest particles. The improved EKPF algorithm is applied to estimate the State of Charge (SOC) of the three order …

Curvature-Based Bp Algorithm Optimization And Its Application In Fnn, Weili Xiong, Wenxin Sun, Xudong Shi

Journal of System Simulation

Abstract: In order to improve the optimization efficiency of BP algorithm affected by the selection of step size, a step size optimization BP algorithm based on curvature information is proposed and applied to the training process of FNN (Fuzzy Neural Network). Reference to Newton's method, The gradient of the cost function and the curvature information in the direction are calculated to determine the direction and magnitude of the parameter adjustment in each iteration. This method only needs to consider the two order information of the gradient direction, so it does not need the storage and processing of Hessian matrix. The …

Low-Complexity Apit Algorithm And Its Opnet Simulation Of Underwater Acoustic Sensor Networks, Jiahui Xu, Keyu Chen, En Chen

Journal of System Simulation

Abstract: Due to the energy limitations of underwater acoustic sensor networks, low-complexity location algorithms are more suitable for underwater acoustic sensor networks. The traditional APIT algorithm can obtain better location accuracy with less control overhead, which is beneficial to the location of underwater sensor networks, but it has high complexity and large redundancy errors. This paper proposes a low-complexity APIT algorithm replaced the traditional grid SCAN algorithm with a point scanning method, and builds an underwater acoustic sensor network environment on the OPNET platform, and elaborates the implementation process of the location algorithm in underwater sensor network. Simulation results …

Study On Infrared Radiation Of Nmp Recovery System In Lithium Battery Pole Piece, Yanjun Xiao, Yang Huan, Yanping Kang

Journal of System Simulation

Abstract: The structure design of the NMP recovery system in the lithium battery pole piece coating process has many technology difficulties, including the vacuum and infrared radiation heating technology. For vacuum system, after the analysis of its impact on the coating process, and the drying needs of the NMP recovery system, through the analytic hierarchy process, the most suitable infrared radiation heater type can be determined. The process of recovering gaseous NMP is numerically simulated, and the simulation results of the system flow performance are obtained. The parameters of the drying time, arrangement mode and other parameters are determined by …

Research On The Mvc-Based Generation Of Test Paper And The Algorithm Of Subjective Criterion, Cuicui Zhang, Guoxiang Zhou, Yu Lei, Shi Lei, Qingqing Wang

Journal of System Simulation

Abstract: At home and abroad, the formed test system has a mature algorithm to the objective problem. However, there are still some problems in the subjective questioning. Therefore, it is feasible to design a MVC(Model View Controller) framework for the dynamic generation of papers, and to propose an automatic algorithm. In the paper volume generation system, the paper page is generated dynamically by the distributed view and the component loading technique. In the subjective automatic questioning algorithm, a bidirectional traversal space model algorithm is proposed, which uses the key words bidirectional matching and vector space model to calculate the answer …

Research On Evacuation Simulation Method Considering Social Behavior, Yuanyuan Deng, Liping Zheng, Ruiwen Cai

Journal of System Simulation

Abstract: In an emergency evacuation scenario, the typical social attributes of an individual impact their evacuation behavior. Two kinds of social factors, such as individual familiarity to the environment and the individual group, are introduced and applied in crowd evacuation simulation. An evacuation simulation method is proposed. The real-time collision avoidance technique of RVO library is used to simulate the dynamic motion of the population. The local target points and its selection mechanism are used to simulate the different social behaviors of the population. Experiments show that the familiarity to the environment and group factors have influence on the evacuation …

Research On Flexray Network Optimization Based On Switched Message Scheduling Algorithm, Yinan Xu, Xiangqi Kong, Mengzhuo Liu

Journal of System Simulation

Abstract: The development of vehicle electronic technology needs advanced in-vehicle communication network. Because of the high transmission speed, reliability and the flexible topology structure, the FlexRay network has become the most popular in-vehicle communication protocol in recent years. In order to meet the demand of network development, a scheduling algorithm based on switched FlexRay network was designed, and a new method that could calculate the Static segment and the worst case response time of Dynamic segment was put forward. The result of the simulation experiment shows that the transmission speed improves 26%, the slot number decreases by 44% and …

Cruise Missile Path Planning Based On Aco Algorithm And Bezier Curve Optimization, Shi Yan, Lihua Zhang, Shouquan Dong, Jue Wang

Journal of System Simulation

Abstract: For the low-altitude penetration of cruise missile, there is a large number of steering points and a larger steering angle in missile path planning based on ant colony algorithm. In order to solve this problem, a three-dimensional path planning method based on ant colony algorithm and Bezier curve optimization is proposed. The planning path node generated by ant colony algorithm was used as the control point to generate the flight path of Bezier curve, and then the curve was changed to be broken lines path. In order to avoid the unnavigable section, using the breadth first search algorithm to …

Research On Active Training Compliance Control Of Ankle Rehabilitation Robot, Yanbin Liu, Xiangyuan Pang, Yanbin Zhang, Bingjing Guo, Jianhai Han

Journal of System Simulation

Abstract: In order to ensure that ankle rehabilitation robot can accurately supply arbitrary characteristic training force for patient during active training, the pneumatic muscle redundant parallel driving ankle rehabilitation robot was taken as research objects, the zero error force tracking method and the compliance control strategy for active training were researched. The dynamics model of the ankle rehabilitation robot were set up, based on the impedance control theory, the trajectory planning method for the zero error force tracking was researched, and based on the Lyapunov’s stability theory, the pneumatic muscle redundant parallel driving compliance control strategy was proposed. Rehabilitation training …

Deep Siamese Neural Networks For Facial Expression Recognition In The Wild, Wassan Hayale

Electronic Theses and Dissertations

The variation of facial images in the wild conditions due to head pose, face illumination, and occlusion can significantly affect the Facial Expression Recognition (FER) performance. Moreover, between subject variation introduced by age, gender, ethnic backgrounds, and identity can also influence the FER performance. This Ph.D. dissertation presents a novel algorithm for end-to-end facial expression recognition, valence and arousal estimation, and visual object matching based on deep Siamese Neural Networks to handle the extreme variation that exists in a facial dataset. In our main Siamese Neural Networks for facial expression recognition, the first network represents the classification framework, where we …

Facial Action Unit Detection With Deep Convolutional Neural Networks, Siddhesh Padwal

Electronic Theses and Dissertations

The facial features are the most important tool to understand an individual's state of mind. Automated recognition of facial expressions and particularly Facial Action Units defined by Facial Action Coding System (FACS) is challenging research problem in the field of computer vision and machine learning. Researchers are working on deep learning algorithms to improve state of the art in the area. Automated recognition of facial action units has man applications ranging from developmental psychology to human robot interface design where companies are using this technology to improve their consumer devices (like unlocking phone) and for entertainment like FaceApp. Recent studies …

Automated Recognition Of Facial Affect Using Deep Neural Networks, Behzad Hasani

Electronic Theses and Dissertations

Automated Facial Expression Recognition (FER) has been a topic of study in the field of computer vision and machine learning for decades. In spite of efforts made to improve the accuracy of FER systems, existing methods still are not generalizable and accurate enough for use in real-world applications. Many of the traditional methods use hand-crafted (a.k.a. engineered) features for representation of facial images. However, these methods often require rigorous hyper-parameter tuning to achieve favorable results.

Recently, Deep Neural Networks (DNNs) have shown to outperform traditional methods in visual object recognition. DNNs require huge data as well as powerful computing units …

Edge-Cloud Computing For Iot Data Analytics: Embedding Intelligence In The Edge With Deep Learning, Ananda Mohon M. Ghosh, Katarina Grolinger

Electrical and Computer Engineering Publications

Rapid growth in numbers of connected devices including sensors, mobile, wearable, and other Internet of Things (IoT) devices, is creating an explosion of data that are moving across the network. To carry out machine learning (ML), IoT data are typically transferred to the cloud or another centralized system for storage and processing; however, this causes latencies and increases network traffic. Edge computing has the potential to remedy those issues by moving computation closer to the network edge and data sources. On the other hand, edge computing is limited in terms of computational power and thus is not well suited for …

Deep Learning For Load Forecasting With Smart Meter Data: Online Adaptive Recurrent Neural Network, Mohammad Navid Fekri, Harsh Patel, Katarina Grolinger, Vinay Sharma

Electrical and Computer Engineering Publications

No abstract provided.

A Comprehensive And Modular Robotic Control Framework For Model-Less Control Law Development Using Reinforcement Learning For Soft Robotics, Charles Sullivan

Open Access Theses & Dissertations

Soft robotics is a growing field in robotics research. Heavily inspired by biological systems, these robots are made of softer, non-linear, materials such as elastomers and are actuated using several novel methods, from fluidic actuation channels to shape changing materials such as electro-active polymers. Highly non-linear materials make modeling difficult, and sensors are still an area of active research. These issues have rendered typical control and modeling techniques often inadequate for soft robotics. Reinforcement learning is a branch of machine learning that focuses on model-less control by mapping states to actions that maximize a specific reward signal. Reinforcement learning has …

Coverage Guided Differential Adversarial Testing Of Deep Learning Systems, Jianmin Guo, Houbing Song, Yue Zhao, Yu Jiang

Publications

Deep learning is increasingly applied to safety-critical application domains such as autonomous cars and medical devices. It is of significant importance to ensure their reliability and robustness. In this paper, we propose DLFuzz, the coverage guided differential adversarial testing framework to guide deep learing systems exposing incorrect behaviors. DLFuzz keeps minutely mutating the input to maximize the neuron coverage and the prediction difference between the original input and the mutated input, without manual labeling effort or cross-referencing oracles from other systems with the same functionality. We also design multiple novel strategies for neuron selection to improve the neuron coverage. The …

Deep Learning For Digitized Histology Image Analysis, Sudhir Sornapudi

Doctoral Dissertations

“Cervical cancer is the fourth most frequent cancer that affects women worldwide. Assessment of cervical intraepithelial neoplasia (CIN) through histopathology remains as the standard for absolute determination of cancer. The examination of tissue samples under a microscope requires considerable time and effort from expert pathologists. There is a need to design an automated tool to assist pathologists for digitized histology slide analysis. Pre-cervical cancer is generally determined by examining the CIN which is the growth of atypical cells from the basement membrane (bottom) to the top of the epithelium. It has four grades, including: Normal, CIN1, CIN2, and CIN3. In …

Fast Decision-Making Under Time And Resource Constraints, Kyle Gabriel Lassak

Graduate Theses, Dissertations, and Problem Reports (ETD)

Practical decision makers are inherently limited by computational and memory resources as well as the time available in which to make decisions. To cope with these limitations, humans actively seek methods which limit their resource demands by exploiting structure within the environment and exploiting a coupling between their sensing and actuation to form heuristics for fast decision-making. To date, such behavior has not been replicated in artificial agents. This research explores how heuristics may be incorporated into the decision-making process to quickly make high-quality decisions through the analysis of a prominent case study: the outfielder problem. In the outfielder problem, …

Compound Vision Approach For Autonomous Vehicles Navigation, Michael Mikhael

Open Access Theses & Dissertations

An analogy can be made between the sensing that occurs in simple robots and drones and that in insects and crustaceans, especially in basic navigation requirements. Thus, an approach in robots/drones based on compound eye vision could be useful. In this research, several image processing algorithms were used to detect and track moving objects starting with images upon which a grid (compound eye image) was superimposed, including contours detection, the second moments of those contours along with the grid applied to the original image, and Fourier Transforms and inverse Fourier Transforms. The latter also provide information about scene or camera …

Comparison Of Object Detection And Patch-Based Classification Deep Learning Models On Mid- To Late-Season Weed Detection In Uav Imagery, Arun Narenthiran Veeranampalayam Sivakumar, Jiating Li, Stephen Scott, Eric T. Psota, Amit J. Jhala, Joe D. Luck, Yeyin Shi

Department of Agricultural and Biological Systems Engineering: Faculty Publications

Mid- to late-season weeds that escape from the routine early-season weed management threaten agricultural production by creating a large number of seeds for several future growing seasons. Rapid and accurate detection of weed patches in field is the first step of site-specific weed management. In this study, object detection-based convolutional neural network models were trained and evaluated over low-altitude unmanned aerial vehicle (UAV) imagery for mid- to late-season weed detection in soybean fields. The performance of two object detection models, Faster RCNN and the Single Shot Detector (SSD), were evaluated and compared in terms of weed detection performance using mean …

Red Blood Cell Segmentation And Classification From Microscopic Images Using Machine Learning, Korranat Naruenatthanaset

Chulalongkorn University Theses and Dissertations (Chula ETD)

Red blood cell morphology analysis plays an essential role in diagnosing many diseases caused by RBC disorders. This manual inspection is a long process and requires practice and experience. Since recent computer vision and image processing in the medical imaging area can provide efficient tools, it can help hematologists to automatically analyze images from a microscope in a reduced time and cost. This research presents a new method to segment and classify RBCs from blood smear images. The process started from data collection, which a new application was created for precisely labeling. The normalization was done to reduce the color …