Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science最新文献

{"title":"Using Deep Learning for Efficient Diagnoses of COVID-19, Viral\u0000Illnesses (Other than COVID-19), and Bacterial Illnesses","authors":"V. Addala","doi":"10.11159/icbes21.112","DOIUrl":"https://doi.org/10.11159/icbes21.112","url":null,"abstract":"According to the World Health Organization the COVID-19 pandemic has killed more than 3.3 million people worldwide. Efficiently and accurately diagnosing people with COVID-19 is essential to help slow down the spread of the virus. Although swab tests do exist, they are not easily accessible in underdeveloped areas, whereas Chest X-Ray scanning has been available before the pandemic. However, there is a lack of radiologists to analyze and diagnose illnesses from Chest X-Rays. This is why this research aimed to use deep learning for efficient and automated diagnoses of COVID-19, Viral (Other than COVID-19), and Bacterial illnesses via Chest X-Ray images. Since the deep learning models had to analyze images, a CNN (Convolutional Neural Network) was built. There were three different CNN architectures fine-tuned and trained on real-time patient data. Out of all three fine-tuned CNN models, the VGG-16 fine-tuned CNN model received the highest testing accuracy of 92.34% when tested on 977 images. This means that when given a new image, the model was able to correctly classify it in one of the four different classes 92.43% of the time. Further improvements will be made to this project in order to make it into an actual usable platform.","PeriodicalId":433404,"journal":{"name":"Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129561180","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":"Aerial Display Using Lenticular Lenses","authors":"K. Yanaka, Kouki Shibata, Toshiaki Yamanouchi","doi":"10.11159/mhci21.301","DOIUrl":"https://doi.org/10.11159/mhci21.301","url":null,"abstract":"An aerial display that can float a two-dimensional image or a three-dimensional object in an empty space is important as a noncontact interface. Aerial displays have two types: a reflection type that uses a mirror and a refraction type that involves a lens. The latter has the advantage of being easily miniaturized because the path of light does not bend much. The method using two commercially available lenticular lenses is inexpensive. However, the principle of the method is not yet fully understood. In this study, the rules of light rays passing through the lens were applied to explain this principle clearly. For further confirmation, a simulation was performed. Results revealed that the lens group consisting of two convex lenses arranged at the interval of twice the focal length as well as the lens group consisting of three convex lenses arranged at intervals the focal length reflected parallel rays coming from an angle as if they were mirrors. When the number of lenses was set to 3, the viewing range widened.","PeriodicalId":433404,"journal":{"name":"Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130739433","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":"Deep Learning-based Electric Appliances Identification from their Switching-On Current Waveforms","authors":"Yassine Chemingui, A. Gastli, Mahdi Houchati","doi":"10.11159/cist21.110","DOIUrl":"https://doi.org/10.11159/cist21.110","url":null,"abstract":"The field of non-intrusive load monitoring offers a multitude of methods for investigating and diagnosing energy demand per appliance. Thus, energy-aware strategies can be derived and implemented. With the widespread of smart meters, the rich information of the main current variation is within reach for many households. Through continuous analysis of the main current waveform, switchingon loads can be identified, and energy-saving practices can be devised. This paper proposes a deep learning model, a Convolutional Siamese neural network for appliance classification based on the WHITED raw high-frequency current dataset. The model is trained on pairs of appliance, measuring their similarity. Based on that, the appliance is identified. With minimal data preprocessing, an F1 macro measure of 0.95 was achieved on the training appliances, and a 0.79 score on previously unseen devices.","PeriodicalId":433404,"journal":{"name":"Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133480296","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":"How Can Machine Learning Help Computer Vision in the Next Decade?","authors":"M. Welling","doi":"10.11159/mvml21.003","DOIUrl":"https://doi.org/10.11159/mvml21.003","url":null,"abstract":"","PeriodicalId":433404,"journal":{"name":"Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117231294","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 Novel Optical Coherence Tomography for Non-Destructive Characterisation of Electrical-Thermal-Mechanical Deformation of Bonding Wires","authors":"Zhiyi Zhao, Zijian Zhang, Yaochun Shen","doi":"10.11159/eee21.001","DOIUrl":"https://doi.org/10.11159/eee21.001","url":null,"abstract":"Bonding wire is one of the most failure-prone components of power electronics modules, and silicone gel is usually employed to encase bonding wires. In this talk I will report the use of optical coherence tomography (OCT) technique to precisely measure the electrical–thermal–mechanical (ETM) deformation of bonding wires under silicone gel. A spectral-domain line-field OCT system was developed to capture the whole cross-sectional image of the bonding wire sample in a single-shot fashion without the need of any mechanical scanning. The time-resolved displacement/deformation of the bonding wire under silicone gel can be measured with sub-nanometre sensitivity by extracting the phase information recorded in the raw OCT spectrogram. The achieved temporal resolution is 2.5 ms for monitoring the ETM deformation dynamics of the bonding wire. We found that the ETM deformation of the gel-encased bonding wire was about three times smaller than that of the bare bonding wire. These experimental results suggest that the spectral-domain line-field OCT could be a useful analytical tool for studying the time-dependent ETM deformation of bonding wires encased by silicone gel.","PeriodicalId":433404,"journal":{"name":"Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science","volume":"260 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133987065","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":"Model of Magnetic Spherical Micro-Robot Motion in Soft Media","authors":"Yulia Malkova, Sijie Ran, G. Friedman","doi":"10.11159/icbes21.111","DOIUrl":"https://doi.org/10.11159/icbes21.111","url":null,"abstract":"Extended Abstract Millimeter-sized robots are of growing importance for various medical applications involving minimally invasive surgical practices. Such miniature devices could play an important role temporarily during procedures such as laparoscopic and endoscopic techniques or as long-term implants for applications such as drug delivery and neural probes and stimulators. One common difficulty in most of these minimally invasive techniques is insertion of the small device into the target region in the body. In soft tissue insertion, one may often desire to move the device along certain trajectory which may be curved. One method of insertion along curved trajectory may involve pulling the device via magnetic force. However, the movement trajectory depends not only on the applied magnetic force but also on the tissue reaction force. The goal of the presented work is to develop an appropriate model of the tissue reaction force during movement of a small magnetically actuated untethered device in order to plan and control the trajectory of its motion. There are no macroscopic soft non-linear tissue reaction models, so we would like to propose one. This model takes irreversible energy losses into consideration by presenting medium reaction force or yield force, which depends on the direction of motion with respect to the previous trajectory. By introducing anisotropy direction, the anisotropy force is included in the model. This force plays a major role when solid attempts to translate in the vicinity of the previous pathway, associated with cracks, medium formations, or tissue fracturing around the moving sphere. However, the model ignores any elastic deformations since elastic deformations are small in comparison to sphere position translational changes. By establishing these forces and knowing relations between them, defining a local anisotropy direction as a state variable, it's possible to predict a trajectory of a moving magnetic sphere. Additional focus of the presented work is to test the abovepresented model for different cases and simulate them using MATLAB programming language.","PeriodicalId":433404,"journal":{"name":"Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122691180","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":"Detecting Emotional Contagion in OSS Projects","authors":"Rashmi Dhakad, L. Benedicenti","doi":"10.11159/cist21.301","DOIUrl":"https://doi.org/10.11159/cist21.301","url":null,"abstract":"In recent times, due to an increase of open source software working models, the behaviour and emotional affective state of developers are becoming increasingly relevant as a subject of research in the software engineering community. One important aspect of such research is emotional contagion: the phenomenon by which the affective state of an individual is transferred to another one through communications. In this paper, propose a simple model that determines the presence of emotional contagion, negative or positive, in an open source project in order to enrich the set of tools used to help the developers..","PeriodicalId":433404,"journal":{"name":"Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116800025","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":"Magnetic Resonance Spectroscopy Signal Analysis Based on Fingerprinting Dictionary Approaches","authors":"Iurii Venglovskyi","doi":"10.11159/icbes21.114","DOIUrl":"https://doi.org/10.11159/icbes21.114","url":null,"abstract":"Magnetic resonance spectroscopy (MRS) is a technique applicable in medical diagnosis or research, which has the unique capability to give non-invasive access to the biochemical content (metabolites) of scanned organs. Up to recent times, all the proposed methods solved metabolite quantification as an optimization problem attempting to minimize the difference between the data and a given parameterized model function. This paper proposes quantification of metabolites in MR spectroscopic imaging using a fingerprinting method, whose function is based on the creation of a dictionary of linear combinations of metabolite signals. Experimental results demonstrate the accuracy of the proposed method, compared to data obtained by a standard quantification method (QUEST), on concentration estimates of 8 metabolites from signals with macromolecule background and noise. The prototype results indicate that the concept of MR fingerprinting dictionary, useful also for preparing data for machine learning, can serve as an alternative method for metabolite quantification by NMR signal analysis.","PeriodicalId":433404,"journal":{"name":"Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122048645","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":"Processing Natural Language Queries in Semantic Web\u0000Applications","authors":"N. Zlatareva, Devansh Amin","doi":"10.11159/cist21.108","DOIUrl":"https://doi.org/10.11159/cist21.108","url":null,"abstract":"SPARQL is a powerful query language for an ever-growing number of Semantic Web applications. Using it, however, requires familiarity with the language which is not to be expected from the general web user. This drawback has led to the development of Question-Answering (QA) systems that enable users to express their information needs in natural language. This paper presents a novel dependency-based framework for translating natural language queries into SPARQL queries, which is based on the idea of syntactic parsing. The translation process involves the following five steps: extraction of the entities, extraction of the predicate, categorization of the query’s type, resolution of lexical and semantic gaps between user query and domain ontology vocabularies; and construction of the SPARQL query. The proposed framework was tested on our closed-domain student advisory application intended to provide students with advice and recommendations about curriculum and scheduling matters. The advantage of our approach is that it requires neither any laborious feature engineering, nor complex model mapping of a query expressed in natural language to a SPARQL query template, and thus it can be easily adapted to a variety of domains.","PeriodicalId":433404,"journal":{"name":"Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125381581","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":"Electrophoretic Deposition of Chitosan/Eudragit E 100/AgNPs Coatings for Controlled Release of Antibacterial Substance","authors":"Łukasz Pawłowski, A. Zieliński","doi":"10.11159/icbes21.120","DOIUrl":"https://doi.org/10.11159/icbes21.120","url":null,"abstract":"The development of bacterial infection of the tissues surrounding an implant is one of the leading causes of implant surgery failure. In order to prevent the deposition of bacteria on the implant surface and the formation of biofilm, coatings that exhibit antibacterial properties are manufactured. However, the problem is the controlled release of the therapeutic substance from the coating over the extended life of the implant [1], [2]. Usually, the active substance is released immediately when the implant is inserted into an environment simulating human body fluids, which results in burst release phenomenon, namely, the release of a large dose of active substance in a short period of time, which may result in a toxic effect. Unfortunately, chitosan, one of the most commonly used biopolymers in controlled drug delivery systems, is unstable in neutral pH environments, readily absorbs water, and swells, resulting in rapid release of the therapeutic agent. Therefore, it is necessary to limit the dissolution rate of the chitosan coating at neutral pH. Previous studies [3] have confirmed that the addition of Eudragit E 100, a cationic copolymer based on dimethylaminoethyl methacrylate, butyl methacrylate, and methyl methacrylate in a 2:1:1 ratio, to chitosan coatings significantly reduced the degradation of these coatings in artificial saliva solution at neutral pH while maintaining high sensitivity to pH drop. Hence, a biopolymer matrix of this type should provide a good carrier for an active substance, such as metallic nanoparticles with antibacterial activity, which will be released only when inflammation of peri-implant tissues occurs. The scientific objective of this study was to fabricate a smart composite coating of chitosan/Eudragit E 100/silver nanoparticles (chit/EE100/AgNPs) on grade 2 titanium surface using variable deposition parameters such as AgNPs concentration, voltage, and deposition time by the electrophoretic method. The determinant of the process of creating such composite coatings with EE100 by electrophoretic method on the surface of Ti grade 2 has not been determined yet. No publication concerning investigations of coatings containing chitosan/EE100 with silver nanoparticles has been found. The microstructure, surface roughness, thickness, chemical and phase composition, mechanical and electrochemical properties, silver release rate at different pH, and wettability of the produced coatings were investigated...","PeriodicalId":433404,"journal":{"name":"Proceedings of the 7th World Congress on Electrical Engineering and Computer Systems and Science","volume":"197 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116794411","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}