Anas AlMajali, Ahmad Qaffaf, Natali Alkayid, Y. Wadhawan
{"title":"Crypto-Ransomware Detection Using Selective Hashing","authors":"Anas AlMajali, Ahmad Qaffaf, Natali Alkayid, Y. Wadhawan","doi":"10.1109/ICECTA57148.2022.9990424","DOIUrl":"https://doi.org/10.1109/ICECTA57148.2022.9990424","url":null,"abstract":"Ransomware is a malicious software that attempts to encrypt the user’s files and demand a ransom in exchange for decrypting the files. This malware may have catastrophic impacts on the availability of data and consequently on the services provided by the infected organizations and institutes. Ransomware detection has been a challenge for researchers in the past few years. In this paper, we propose a behavioral ransomware detection method that utilizes fast selective hashing techniques. By selective we mean that only few selected blocks from a file are used for similarity comparison. Our experimental results demonstrate the efficacy of the proposed method in ransonware detection in terms of detection time. For 1000 files of a total size of 20GB and a detection threshold set to five files, our proposed system is able to detect a ransomware on average within 2.76 seconds saving 99.5% of the total files without taking much of the system resources and affecting user experience.","PeriodicalId":337798,"journal":{"name":"2022 International Conference on Electrical and Computing Technologies and Applications (ICECTA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131586442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Hardware/Software Co-acceleration of Progressive Learning under Feature Dimension Variation","authors":"R. Karn, I. Elfadel","doi":"10.1109/ICECTA57148.2022.9990202","DOIUrl":"https://doi.org/10.1109/ICECTA57148.2022.9990202","url":null,"abstract":"In this paper, we address the problem of ASIC HW accelerator re-use in the case when the task-based feature set undergoes size changes. The proposed solution is a hybrid Hardware/Software (HW/SW) co-acceleration methodology for incorporating any additional features into the progressive learning model and performing inference without modifying the architecture of the HW accelerator. The co-acceleration methodology has been prototyped on an edge computing platform and compared with a HW-only acceleration in terms of inference throughput, compute resource utilization, and energy efficiency. The hybrid HW-SW co-accelerator is shown to result in a higher inference throughput while consuming less compute resources and energy than the HW-only solution. The results are further supported by using the HW accelerator’s performance counters to profile overall performance under realistic progressive-learning workloads.","PeriodicalId":337798,"journal":{"name":"2022 International Conference on Electrical and Computing Technologies and Applications (ICECTA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132548332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rayan Ajeeb, M. Madi, Olav Aaker, Efstratios Ntantis, Mahmood Sawadi Rahi
{"title":"Analytical Study of the Application of the Amorphous Core Material 2605HB1M to Reduce Core Loss in Electromagnetic Induction Motors","authors":"Rayan Ajeeb, M. Madi, Olav Aaker, Efstratios Ntantis, Mahmood Sawadi Rahi","doi":"10.1109/ICECTA57148.2022.9990362","DOIUrl":"https://doi.org/10.1109/ICECTA57148.2022.9990362","url":null,"abstract":"Due to their durable and simple manufacturing, three-phase electromagnetic induction motors presently provide even more than 90% of the mechanical power for use in industry. Many researchers have used artificial intelligence (AI) approaches to optimize electromagnetic induction motor design (TDO) and analyze performance. There are numerous methods for increasing efficiency and decreasing losses in these devices. Electromagnetic iron losses, that originate mostly within stator teeth and yoke along with the rotor yoke, are a critical element. For the convenience of modeling, electromagnetic iron losses are investigated on a 3-phase transformer rather than an electromagnetic induction motor since they both operate on electromagnetic induction and their core losses follow the same fundamental principles. This evaluation was carried out utilizing finite element methodologies with Ansys electronics desktop. A developed computational transformer model that delivers reliable data with high accuracy was proposed. The performance of the computational model was determined to match well with experimental data for a transformer with the same specifications and dimensions found in the labs of Østfold University-Collage Norway. Using the achieved computational model configuration on the Ansys electronics desktop, the core loss and efficiency of an electromagnetic induction transformer for Metglas-2605HBIM amorphous core transformer and M19 silicon steel core transformer at high and low frequencies were then examined and compared. According to the results, when used in electromagnetic induction transformers, amorphous core transformers have lower core losses, higher efficiency, and superior performance than traditional M19 silicon steel core transformers.","PeriodicalId":337798,"journal":{"name":"2022 International Conference on Electrical and Computing Technologies and Applications (ICECTA)","volume":"337 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132572564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Feedback Linearizing Speed Control Strategy for Electric Vehicle Traction Motor drives","authors":"A. Prasanthi, H. Shareef, R. Errouissi, M. Asna","doi":"10.1109/ICECTA57148.2022.9990368","DOIUrl":"https://doi.org/10.1109/ICECTA57148.2022.9990368","url":null,"abstract":"Electric vehicles (EV) are the solution that can provide a sustainable transportation alternative to reduce carbon footprints. The design of a battery-powered DC traction motor system for an electric vehicle is presented in this study. The proposed EV system consists of a battery energy source, bidirectional DC-DC converter, and traction motor. The accurate mathematical modelling of the PI-controlled bi-directional DC-DC converter is incorporated in this work to provide the desired voltage at the motor side and to maintain the power flow under steady-state and dynamic conditions. In view of the demand of explicit speed control attribute of the EV and non-linear characteristics of traction motor with overall system unpredictable disturbances, this paper also illustrates the design and modelling of feedback linearizing control with disturbance observer for the speed control of traction motor. The MATLAB/Simulink simulation model of the proposed system is developed to examine the performance of the proposed system under various operating conditions. The simulation is performed with calculated load torque with the exact velocity and acceleration rate at the traction motor which represents the exact EV dynamics. The simulation results indicate that the designed battery-powered EV with the proposed non-linear controller can follow the speed and load torque thoroughly.","PeriodicalId":337798,"journal":{"name":"2022 International Conference on Electrical and Computing Technologies and Applications (ICECTA)","volume":"402 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132033603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"UAV-to-UAV Communication Scheme for Enabling Emergency Services During Network Failure","authors":"A. Alnoman","doi":"10.1109/ICECTA57148.2022.9990222","DOIUrl":"https://doi.org/10.1109/ICECTA57148.2022.9990222","url":null,"abstract":"In this paper, a communication scheme is proposed to enable emergency services during extraordinary circumstances by allowing first responders to connect with mobile users when the cellular network fails to provide radio coverage. The proposed scheme is based on the device-to-device (D2D) communication where devices can communicate directly without involving the cellular network. In particular, unmanned aerial vehicles (UAVs) communicate in a D2D manner to form a grid of relays that provide radio access for affected users. The work aims to minimize the total delay of the multi-hop UAV-to-UAV communication path from the requesting user which is covered by one UAV to the emergency service provider that is covered by another UAV. Here, since each UAV is providing radio access to a number of mobile users, each UAV is modeled as an M/M/1 queueing system where the response time of the UAV is considered the cost of the path to that UAV. The problem of finding the minimum response time is then solved using the Dijkstra’s shortest path algorithm. Results show the effectiveness of the proposed scheme in reducing the time required to establish the multi-hop path from the mobile user to the emergency service provider.","PeriodicalId":337798,"journal":{"name":"2022 International Conference on Electrical and Computing Technologies and Applications (ICECTA)","volume":"518 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123040740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohammed Al Razehi, R. Errouissi, Mahdi Debouza, H. Shareef
{"title":"Disturbance-Observer Based control for PWM Rectifiers Under Unbalanced Grid Conditions","authors":"Mohammed Al Razehi, R. Errouissi, Mahdi Debouza, H. Shareef","doi":"10.1109/ICECTA57148.2022.9990407","DOIUrl":"https://doi.org/10.1109/ICECTA57148.2022.9990407","url":null,"abstract":"This paper presents the design and experimental validation of a current control technique for Pulse-width modulated (PWM) rectifiers under both balanced and unbalanced grid voltages. In particular, unbalanced grid voltages can cause double fundamental frequency oscillations in the DC-link voltage. These DC-link voltage oscillations can be removed by setting the grid current to accurately track a specific current reference. In this paper, the proposed controller utilizes a cascaded control scheme comprising of an outer voltage loop and an inner current loop. The outer loop controller is designed to generate the specific current reference needed to maintain the DC-link voltage constant and at its reference. The inner current loop consists of a state-feedback controller coupled with a disturbance observer to ensure accurate tracking of the current reference. The current controller is designed in the $alphabeta$ reference to ensure accurate regulation of both balanced and unbalanced grid currents needed to suppress the DC-link voltage oscillations. To validate the effectiveness of the proposed controller, experimental tests were conducted and showcased that the control scheme is able to achieve the desired control objectives with excellent results.","PeriodicalId":337798,"journal":{"name":"2022 International Conference on Electrical and Computing Technologies and Applications (ICECTA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127806814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Customized Convolutional Neural Network for Dental Bitewing Images Segmentation","authors":"W. A. Nassan, T. Bonny, K. Obaideen, A. Hammal","doi":"10.1109/ICECTA57148.2022.9990564","DOIUrl":"https://doi.org/10.1109/ICECTA57148.2022.9990564","url":null,"abstract":"Bitewing images are useful for recognizing the most common dental diseases, like tooth decay and periodontal bone loss. Besides providing important details like the condition of fillings and the presence of calculus or tartar. Due to the wide variety of topologies, the complexity of medical structures, and the poor image quality caused by problems like low contrast, noise, irregularities, and fuzzy edges borders, segmentation of dental images is difficult and often unsuccessful. Recent advances in deep learning models improve the performance of analyzing dental images. In this study, we build a customized Convolutional neural network (CNN) to segment the bitewing image. The bitewing radiographs, which will be used as input to the CNN model, are imported into MATLAB where the image is first enhanced before being segmented to create a binary mask image that excludes the background from the original images. Those masks are used as a target for the deep learning model. By training the proposed system with 456 bitewing images, the best accuracy we achieved on unseen images is 97.3% of accuracy, 88.27% of Fl-score.","PeriodicalId":337798,"journal":{"name":"2022 International Conference on Electrical and Computing Technologies and Applications (ICECTA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116702221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Boudal Niang, Ismaila Diakhate, A. Kora, R. M. Faye, Cheikh Saliou Mbacke Babou
{"title":"Improvement of the energy consumption of the IoT/M2M communication system embedded in pirogues on the West African coast","authors":"Boudal Niang, Ismaila Diakhate, A. Kora, R. M. Faye, Cheikh Saliou Mbacke Babou","doi":"10.1109/ICECTA57148.2022.9990289","DOIUrl":"https://doi.org/10.1109/ICECTA57148.2022.9990289","url":null,"abstract":"The uses of telecommunications and information technologies (ICT) are changing the daily lives of millions of Africans. The investigation exercises are centered on the vitality utilization of the framework of observing, observation, and security of the little conventional pirogue utilized by anglers whereas permitting way better administration of sea assets. The solution of energy-efficient is based on a low-cost integrated device using mobile technology for the data transfer network. Otherwise, the aim of this paper is to bring energy improvements to the solution “Tracking, Safety of the Small Pirogue and Monitoring of Ocean Natural Resource in West Africa Coast”. The firefly algorithm is used to cluster the pirogues and the Dijkstra algorithm for the feedback of information to the Senegalese coast guard. To begin with, the vitality commitment of this arrangement will be compared with LEACH, TEEN, and DEEC optimization strategies. This comparison appeared that on more than 10000 transmission towers the proposed strategy appears way better execution compared to other strategies in terms of vitality expended and amount of data transported within the pirogues network. Moment, the arrangement will be compared with other angling arrangements in terms of control, programmed distinguishing proof, security, reasonableness, and energy autonomy.","PeriodicalId":337798,"journal":{"name":"2022 International Conference on Electrical and Computing Technologies and Applications (ICECTA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124106687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Iftikhar Ahmad, Abdulla Bushlaibi, A. Abdelrhman, S. A. Imam, Mahmood Hammad, R. Muhammad
{"title":"Experimental Investigations for Performance Improvement of Solar Cell using Phase Change Material","authors":"Iftikhar Ahmad, Abdulla Bushlaibi, A. Abdelrhman, S. A. Imam, Mahmood Hammad, R. Muhammad","doi":"10.1109/ICECTA57148.2022.9990227","DOIUrl":"https://doi.org/10.1109/ICECTA57148.2022.9990227","url":null,"abstract":"In this research paper, an initial trial has been carried out to investigate the performance enhancement of solar cells using phase change material (PCM). The performance enhancement was judged by the virtue of open circuit voltage (OCV) and power output analysis. Two monocrystalline solar cells have been used to support the initial claim, where one cell has been cooled with the help of PCM while the second one was left to the ambient conditions. The key parameter involved and measured in the present study were solar irradiance, solar cell temperature, OCV, and output power. The OCVs and power outputs of both solar cells were compared with one another. A significant improvement has been observed in both OCV and power of the cooled solar cell as compared to the uncooled one. This study provides a foundation to investigate the power enhancement of solar cells further by using other effective cooling techniques.","PeriodicalId":337798,"journal":{"name":"2022 International Conference on Electrical and Computing Technologies and Applications (ICECTA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121863498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Machine Learning Models for Salary Prediction Dataset using Python","authors":"Reham Kablaoui, A. Salman","doi":"10.1109/ICECTA57148.2022.9990316","DOIUrl":"https://doi.org/10.1109/ICECTA57148.2022.9990316","url":null,"abstract":"In today’s world, salary is the primary source of motivation for many regular employees, which makes salary prediction very important for both employers and employees. It helps employers and employees to make estimations of the expected salary. Fortunately, technological advancements like Data Science and Machine Learning (ML) have made salary prediction more realistic. In this paper, we exploit the benefits of data science to collect a 20,000+ dataset of salaries in the USA. We then apply three supervised ML techniques to the obtained datasets to produce salary prediction. The learning models are linear regression, random forest, and neural networks. The output of the three models is analyzed and compared to show the following; neural network outperforms the other ML models for better accuracy with accuracy level 83.2%, and linear regression has the fastest time of 0.363s for training the model.","PeriodicalId":337798,"journal":{"name":"2022 International Conference on Electrical and Computing Technologies and Applications (ICECTA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126461828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}