Pub Date : 2023-07-19DOI: 10.31803/tg-20220921070537
M. Zheng, H. Teng, Yi Wang
In this paper, an approach to deal with the multi-objective programming problem is regulated by means of probability-based multi-objective optimization, discrete uniform experimental design, and sequential algorithm for optimization. The probability-based method for multi-objective optimization is used to conduct conversion of the multi-objective optimization problem into a single-objective optimization one in the viewpoint of probability theory. The discrete uniform experimental design is used to supply an efficient sampling to simplify the conversion. The sequential algorithm for optimization is employed to carry out further optimization. The corresponding treatments reveal the essence of the multiobjective programming, and consideration of the simultaneous optimization of each objective of multi-objective programming problem rationally. Two examples are conducted to illuminate the rationality of the approach.
{"title":"Approach of Solving Multi-objective Programming Problem by Means of Probability Theory and Uniform Experimental Design","authors":"M. Zheng, H. Teng, Yi Wang","doi":"10.31803/tg-20220921070537","DOIUrl":"https://doi.org/10.31803/tg-20220921070537","url":null,"abstract":"In this paper, an approach to deal with the multi-objective programming problem is regulated by means of probability-based multi-objective optimization, discrete uniform experimental design, and sequential algorithm for optimization. The probability-based method for multi-objective optimization is used to conduct conversion of the multi-objective optimization problem into a single-objective optimization one in the viewpoint of probability theory. The discrete uniform experimental design is used to supply an efficient sampling to simplify the conversion. The sequential algorithm for optimization is employed to carry out further optimization. The corresponding treatments reveal the essence of the multiobjective programming, and consideration of the simultaneous optimization of each objective of multi-objective programming problem rationally. Two examples are conducted to illuminate the rationality of the approach.","PeriodicalId":43419,"journal":{"name":"TEHNICKI GLASNIK-TECHNICAL JOURNAL","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69414884","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}
Pub Date : 2023-07-19DOI: 10.31803/tg-20230518082456
S. Schmidt, Benjamin S. G. Schmidt
TPM is the foundation for JIT (Just in Time) and Lean Manufacturing and forms the basis of JIT or on-time delivery. The goal of TPM is to improve equipment effectiveness and optimize equipment performance, namely PQCDSM (Productivity, Quality, Cost and Delivery, Safety and health, environment, and Morale). Many producers have tried to transform their production system to a JIT or Lean production system with the aim of increasing productivity and quality, but thus far with little success. This contribution shows how trekking and climbing tours can be used to illustrate the application of PQCDSM-Logic in mountaineering and how this can be transferred to logistics and maintenance practice. The background is the author's decades of experience with expeditions, trekking and climbing tours, TPM implementations and interviews with numerous experts. There are many similarities between the application of PQCDSM-Logic in mountaineering and in logistics and maintenance practice, which will help both in operational practice in industry and in high mountain tours, especially regarding safety in a changing environment. Presented is the extrapolation from mountain climbing to TPM and the importance of leadership for a successful (summit climbs and the like) transformation of the production system to a JIT or Lean production system.
TPM是JIT (Just in Time)和精益生产的基础，是JIT(准时交货)的基础。TPM的目标是提高设备效率和优化设备性能，即PQCDSM(生产力、质量、成本和交付、安全和健康、环境和士气)。许多生产商试图将他们的生产系统转变为JIT或精益生产系统，目的是提高生产率和质量，但迄今为止收效甚微。这篇文章展示了如何使用徒步旅行和登山旅行来说明PQCDSM-Logic在登山中的应用，以及如何将其转移到后勤和维护实践中。背景是作者数十年的探险、徒步旅行和登山旅行、TPM实施和对众多专家的采访经验。PQCDSM-Logic在登山中的应用与在物流和维护实践中的应用有许多相似之处，这将有助于工业和高山旅游的操作实践，特别是在不断变化的环境中的安全方面。介绍了从爬山到TPM的外推，以及领导对生产系统成功(登顶等)向JIT或精益生产系统的转变的重要性。
{"title":"PQCDSM-Logic in Maintenance (TPM) and Mountaineering","authors":"S. Schmidt, Benjamin S. G. Schmidt","doi":"10.31803/tg-20230518082456","DOIUrl":"https://doi.org/10.31803/tg-20230518082456","url":null,"abstract":"TPM is the foundation for JIT (Just in Time) and Lean Manufacturing and forms the basis of JIT or on-time delivery. The goal of TPM is to improve equipment effectiveness and optimize equipment performance, namely PQCDSM (Productivity, Quality, Cost and Delivery, Safety and health, environment, and Morale). Many producers have tried to transform their production system to a JIT or Lean production system with the aim of increasing productivity and quality, but thus far with little success. This contribution shows how trekking and climbing tours can be used to illustrate the application of PQCDSM-Logic in mountaineering and how this can be transferred to logistics and maintenance practice. The background is the author's decades of experience with expeditions, trekking and climbing tours, TPM implementations and interviews with numerous experts. There are many similarities between the application of PQCDSM-Logic in mountaineering and in logistics and maintenance practice, which will help both in operational practice in industry and in high mountain tours, especially regarding safety in a changing environment. Presented is the extrapolation from mountain climbing to TPM and the importance of leadership for a successful (summit climbs and the like) transformation of the production system to a JIT or Lean production system.","PeriodicalId":43419,"journal":{"name":"TEHNICKI GLASNIK-TECHNICAL JOURNAL","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69415025","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}
Pub Date : 2023-07-19DOI: 10.31803/tg-20230504194331
Aurelia Burinskiene, Arūnas Burinskas
The authors have investigated sustainable environment delivery systems and identified transportation lead-time investigation cases. This research study aimed to increase freight delivery lead-time and minimize distance in transportation. To reach the goal, the paper's authors, after analysis of the hierarchy of quantitative methods and models, proposed the framework for modeling freight allocation and transportation lead-time and delivered a study that includes discrete event simulation. During the simulation, various scenarios have been revised. Following the simulation mentioned above analysis, around 3.8 % of distance could be saved during freight delivery if lead-time for transportation were revised by choosing five days criteria for modeling freight allocation. The savings depend on the number of received orders from different geographic locations.
{"title":"Modelling Freight Allocation and Transportation Lead-Time","authors":"Aurelia Burinskiene, Arūnas Burinskas","doi":"10.31803/tg-20230504194331","DOIUrl":"https://doi.org/10.31803/tg-20230504194331","url":null,"abstract":"The authors have investigated sustainable environment delivery systems and identified transportation lead-time investigation cases. This research study aimed to increase freight delivery lead-time and minimize distance in transportation. To reach the goal, the paper's authors, after analysis of the hierarchy of quantitative methods and models, proposed the framework for modeling freight allocation and transportation lead-time and delivered a study that includes discrete event simulation. During the simulation, various scenarios have been revised. Following the simulation mentioned above analysis, around 3.8 % of distance could be saved during freight delivery if lead-time for transportation were revised by choosing five days criteria for modeling freight allocation. The savings depend on the number of received orders from different geographic locations.","PeriodicalId":43419,"journal":{"name":"TEHNICKI GLASNIK-TECHNICAL JOURNAL","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69414858","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}
Pub Date : 2023-07-19DOI: 10.31803/tg-20230518185836
Maja Trstenjak, Miljenko Mustapić, Petar Gregurić, Tihomir Opetuk
Industry 5.0 is a human-centred concept of industrial development towards the sustainable and resilient system presented by the European Union which aims to become the global both innovation and industrial leader. It should overcome the barriers of the previously presented Industry 4.0. This paper presents the research conducted in the 112 Croatian manufacturing companies, dealing with their awareness level of the Industry 5.0, as well as the use of green and digital elements in logistics activities. The results have shown that the awareness of the digital concept of both Industry 4.0 or 5.0 remains low, but the companies are more open towards the implementation of the green elements than the digital ones, with the potential for future development recognized.
{"title":"Use of Green Industry 5.0 Technologies in Logistics Activities","authors":"Maja Trstenjak, Miljenko Mustapić, Petar Gregurić, Tihomir Opetuk","doi":"10.31803/tg-20230518185836","DOIUrl":"https://doi.org/10.31803/tg-20230518185836","url":null,"abstract":"Industry 5.0 is a human-centred concept of industrial development towards the sustainable and resilient system presented by the European Union which aims to become the global both innovation and industrial leader. It should overcome the barriers of the previously presented Industry 4.0. This paper presents the research conducted in the 112 Croatian manufacturing companies, dealing with their awareness level of the Industry 5.0, as well as the use of green and digital elements in logistics activities. The results have shown that the awareness of the digital concept of both Industry 4.0 or 5.0 remains low, but the companies are more open towards the implementation of the green elements than the digital ones, with the potential for future development recognized.","PeriodicalId":43419,"journal":{"name":"TEHNICKI GLASNIK-TECHNICAL JOURNAL","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69415076","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}
Pub Date : 2023-07-19DOI: 10.31803/tg-20221228154330
Dea-Won Kim
The goal of text classification is to identify the category to which the text belongs. Text categorization is widely used in email detection, sentiment analysis, topic marking and other fields. However, good text representation is the point to improve the capability of NLP tasks. Traditional text representation adopts bag-of-words model or vector space model, which loses the context information of the text and faces the problems of high latitude and high sparsity,. In recent years, with the increase of data and the improvement of computing performance, the use of deep learning technology to represent and classify texts has attracted great attention. Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and RNN with attention mechanism are used to represent the text, and then to classify the text and other NLP tasks, all of which have better performance than the traditional methods. In this paper, we design two sentence-level models based on the deep network and the details are as follows: (1) Text representation and classification model based on bidirectional RNN and CNN (BRCNN). BRCNN’s input is the word vector corresponding to each word in the sentence; after using RNN to extract word order information in sentences, CNN is used to extract higher-level features of sentences. After convolution, the maximum pool operation is used to obtain sentence vectors. At last, softmax classifier is used for classification. RNN can capture the word order information in sentences, while CNN can extract useful features. Experiments on eight text classification tasks show that BRCNN model can get better text feature representation, and the classification accuracy rate is equal to or higher than that of the prior art. (2) Attention mechanism and CNN (ACNN) model uses the RNN with attention mechanism to obtain the context vector; Then CNN is used to extract more advanced feature information. The maximum pool operation is adopted to obtain a sentence vector; At last, the softmax classifier is used to classify the text. Experiments on eight text classification benchmark data sets show that ACNN improves the stability of model convergence, and can converge to an optimal or local optimal solution better than BRCNN.
{"title":"Text Classification Based on Neural Network Fusion","authors":"Dea-Won Kim","doi":"10.31803/tg-20221228154330","DOIUrl":"https://doi.org/10.31803/tg-20221228154330","url":null,"abstract":"The goal of text classification is to identify the category to which the text belongs. Text categorization is widely used in email detection, sentiment analysis, topic marking and other fields. However, good text representation is the point to improve the capability of NLP tasks. Traditional text representation adopts bag-of-words model or vector space model, which loses the context information of the text and faces the problems of high latitude and high sparsity,. In recent years, with the increase of data and the improvement of computing performance, the use of deep learning technology to represent and classify texts has attracted great attention. Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and RNN with attention mechanism are used to represent the text, and then to classify the text and other NLP tasks, all of which have better performance than the traditional methods. In this paper, we design two sentence-level models based on the deep network and the details are as follows: (1) Text representation and classification model based on bidirectional RNN and CNN (BRCNN). BRCNN’s input is the word vector corresponding to each word in the sentence; after using RNN to extract word order information in sentences, CNN is used to extract higher-level features of sentences. After convolution, the maximum pool operation is used to obtain sentence vectors. At last, softmax classifier is used for classification. RNN can capture the word order information in sentences, while CNN can extract useful features. Experiments on eight text classification tasks show that BRCNN model can get better text feature representation, and the classification accuracy rate is equal to or higher than that of the prior art. (2) Attention mechanism and CNN (ACNN) model uses the RNN with attention mechanism to obtain the context vector; Then CNN is used to extract more advanced feature information. The maximum pool operation is adopted to obtain a sentence vector; At last, the softmax classifier is used to classify the text. Experiments on eight text classification benchmark data sets show that ACNN improves the stability of model convergence, and can converge to an optimal or local optimal solution better than BRCNN.","PeriodicalId":43419,"journal":{"name":"TEHNICKI GLASNIK-TECHNICAL JOURNAL","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69415130","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}
Pub Date : 2023-07-19DOI: 10.31803/tg-20221227094126
Yangsun Lee
Abnormal behavior is called an abnormal behavior that deviates from the same normal standard as the average. The installation of public CCTVs to prevent crimes is increasing, but the crime rate is rather increasing recently. In line with this situation, artificial intelligence research using deep learning that automatically finds abnormal behavior in CCTV is increasing. Deep learning is a type of artificial intelligence designed based on artificial neural networks, and the quality of learning data is important for high accuracy in the development of artificial intelligence through deep learning. This paper verifies whether learning data for abnormal behavior detection is suitable as learning data which is being constructed using an MPED-RNN model for binary classification to determine whether there is an abnormal behavior by frame using skeleton data of a person based on an autoencoder. As a result of the experiment, the unsupervised learning-based MPED-RNN model used in this paper is not suitable for verifying images with a similar number of frames with and without abnormal behavior, such as the corresponding data, and it is judged that appropriate results can be derived only when verified with a supervised learningbased model.
{"title":"A Study on Verification of CCTV Image Data through Unsupervised Learning Model of Deep Learning","authors":"Yangsun Lee","doi":"10.31803/tg-20221227094126","DOIUrl":"https://doi.org/10.31803/tg-20221227094126","url":null,"abstract":"Abnormal behavior is called an abnormal behavior that deviates from the same normal standard as the average. The installation of public CCTVs to prevent crimes is increasing, but the crime rate is rather increasing recently. In line with this situation, artificial intelligence research using deep learning that automatically finds abnormal behavior in CCTV is increasing. Deep learning is a type of artificial intelligence designed based on artificial neural networks, and the quality of learning data is important for high accuracy in the development of artificial intelligence through deep learning. This paper verifies whether learning data for abnormal behavior detection is suitable as learning data which is being constructed using an MPED-RNN model for binary classification to determine whether there is an abnormal behavior by frame using skeleton data of a person based on an autoencoder. As a result of the experiment, the unsupervised learning-based MPED-RNN model used in this paper is not suitable for verifying images with a similar number of frames with and without abnormal behavior, such as the corresponding data, and it is judged that appropriate results can be derived only when verified with a supervised learningbased model.","PeriodicalId":43419,"journal":{"name":"TEHNICKI GLASNIK-TECHNICAL JOURNAL","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69415064","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}
Pub Date : 2023-07-19DOI: 10.31803/tg-20230511175500
Lara Kuhlmann, M. Pauly
Sales forecasts are essential for a smooth workflow and cost optimization. Usually, they are assessed using statistical error measures, which might be misleading in a business context. This paper proposes a new dynamic systems model for an economic evaluation of sales forecasts. The model describes the development of the inventory level over time and derives the resulting overstock and shortage costs. It is tested on roughly 3,000 real-world time series and compared with the commonly used approach based on statistical measures. The experiments show that different statistical measures have no coherent evaluation, making their usage even less suitable for a practical economic application.
{"title":"A Dynamic Systems Model for an Economic Evaluation of Sales Forecasting Methods","authors":"Lara Kuhlmann, M. Pauly","doi":"10.31803/tg-20230511175500","DOIUrl":"https://doi.org/10.31803/tg-20230511175500","url":null,"abstract":"Sales forecasts are essential for a smooth workflow and cost optimization. Usually, they are assessed using statistical error measures, which might be misleading in a business context. This paper proposes a new dynamic systems model for an economic evaluation of sales forecasts. The model describes the development of the inventory level over time and derives the resulting overstock and shortage costs. It is tested on roughly 3,000 real-world time series and compared with the commonly used approach based on statistical measures. The experiments show that different statistical measures have no coherent evaluation, making their usage even less suitable for a practical economic application.","PeriodicalId":43419,"journal":{"name":"TEHNICKI GLASNIK-TECHNICAL JOURNAL","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69414951","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}
Pub Date : 2023-07-19DOI: 10.31803/tg-20230518081537
Lars Tasche, Maximilian Bähring, Benno Gerlach
Current trends in urban areas pose several challenges to city logistics stakeholders while also offering opportunities for optimization. With its analytics, modelling and simulation capabilities, the Digital Supply Chain Twin (DSCT) technology provides a possibility to optimize urban logistics processes. However, a number of barriers have limited the implementation of holistic DSCTs so far. An integrative, collaborative platform could decrease these barriers. By applying design science research methodology and expert interviews, this paper develops an architecture for a high-level cross-institutional platform for the generation of DSCTs. This framework includes a modular design of the platform through eight functional modules. The platform can facilitate the implementation of DSCTs for urban stakeholders and thus optimize urban logistics processes.
{"title":"Digital Supply Chain Twins in Urban Logistics System","authors":"Lars Tasche, Maximilian Bähring, Benno Gerlach","doi":"10.31803/tg-20230518081537","DOIUrl":"https://doi.org/10.31803/tg-20230518081537","url":null,"abstract":"Current trends in urban areas pose several challenges to city logistics stakeholders while also offering opportunities for optimization. With its analytics, modelling and simulation capabilities, the Digital Supply Chain Twin (DSCT) technology provides a possibility to optimize urban logistics processes. However, a number of barriers have limited the implementation of holistic DSCTs so far. An integrative, collaborative platform could decrease these barriers. By applying design science research methodology and expert interviews, this paper develops an architecture for a high-level cross-institutional platform for the generation of DSCTs. This framework includes a modular design of the platform through eight functional modules. The platform can facilitate the implementation of DSCTs for urban stakeholders and thus optimize urban logistics processes.","PeriodicalId":43419,"journal":{"name":"TEHNICKI GLASNIK-TECHNICAL JOURNAL","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69415015","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}
Pub Date : 2023-07-18DOI: 10.31803/tg-20220828220446
A. Yasar
Covid-19 virus has led to a tremendous pandemic in more than 200 countries across the globe, leading to severe impacts on the lives and health of a large number of people globally. The emergence of Omicron (SARS-CoV-2), which is a coronavirus 2 variant, an acute respiratory syndrome which is highly mutated, has again caused social limitations around the world because of infectious and vaccine escape mutations. One of the most significant steps in the fight against covid-19 is to identify those who were infected with the virus as early as possible, to start their treatment and to minimize the risk of transmission. Detection of this disease from radiographic and radiological images is perhaps one of the quickest and most accessible methods of diagnosing patients. In this study, a computer aided system based on deep learning is proposed for rapid diagnosis of COVID-19 from chest x-ray images. First, a dataset of 5380 Chest x-ray images was collected from publicly available datasets. In the first step, the deep features of the images in the dataset are extracted by using the dataset pre-trained convolutional neural network (CNN) model. In the second step, Differential Evolution (DE), Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) algorithms were used for feature selection in order to find the features that are effective for classification of these deep features. Finally, the features obtained in two stages, Decision Tree (DT), Naive Bayes (NB), support vector machine (SVM), k-Nearest Neighbours (k-NN) and Neural Network (NN) classifiers are used for binary, triple and quadruple classification. In order to measure the success of the models objectively, 10 folds cross validation was used. As a result, 1000 features were extracted with the SqueezeNet CNN model. In the binary, triple and quadruple classification process using these features, the SVM method was found to be the best classifier. The classification successes of the SVM model are 96.02%, 86.84% and 79.87%, respectively. The results obtained from the classification process with deep feature extraction were achieved by selecting the features in the proposed method in less time and with less features. While the performance achieved is very good, further analysis is required on a larger set of COVID-19 images to obtain higher estimates of accuracy.
{"title":"Wrapper and Hybrid Feature Selection Methods Using Metaheuristic Algorithm for Chest X-Ray Images Classification","authors":"A. Yasar","doi":"10.31803/tg-20220828220446","DOIUrl":"https://doi.org/10.31803/tg-20220828220446","url":null,"abstract":"Covid-19 virus has led to a tremendous pandemic in more than 200 countries across the globe, leading to severe impacts on the lives and health of a large number of people globally. The emergence of Omicron (SARS-CoV-2), which is a coronavirus 2 variant, an acute respiratory syndrome which is highly mutated, has again caused social limitations around the world because of infectious and vaccine escape mutations. One of the most significant steps in the fight against covid-19 is to identify those who were infected with the virus as early as possible, to start their treatment and to minimize the risk of transmission. Detection of this disease from radiographic and radiological images is perhaps one of the quickest and most accessible methods of diagnosing patients. In this study, a computer aided system based on deep learning is proposed for rapid diagnosis of COVID-19 from chest x-ray images. First, a dataset of 5380 Chest x-ray images was collected from publicly available datasets. In the first step, the deep features of the images in the dataset are extracted by using the dataset pre-trained convolutional neural network (CNN) model. In the second step, Differential Evolution (DE), Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) algorithms were used for feature selection in order to find the features that are effective for classification of these deep features. Finally, the features obtained in two stages, Decision Tree (DT), Naive Bayes (NB), support vector machine (SVM), k-Nearest Neighbours (k-NN) and Neural Network (NN) classifiers are used for binary, triple and quadruple classification. In order to measure the success of the models objectively, 10 folds cross validation was used. As a result, 1000 features were extracted with the SqueezeNet CNN model. In the binary, triple and quadruple classification process using these features, the SVM method was found to be the best classifier. The classification successes of the SVM model are 96.02%, 86.84% and 79.87%, respectively. The results obtained from the classification process with deep feature extraction were achieved by selecting the features in the proposed method in less time and with less features. While the performance achieved is very good, further analysis is required on a larger set of COVID-19 images to obtain higher estimates of accuracy.","PeriodicalId":43419,"journal":{"name":"TEHNICKI GLASNIK-TECHNICAL JOURNAL","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69414870","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}
Pub Date : 2023-07-18DOI: 10.31803/tg-20220819001236
Seda Ermis, Murat Demirci
In this study, various Rectangular Microstrip Antenna (RMA) designs operating at 28 GHz frequency for 5G-communication system are performed. All designs are generated and analyzed using a 3D electromagnetic simulation program, ANSYS HFSS (High-Frequency Structure Simulator). Single and array type RMA designs are constructed by using non-contact inset-fed feeding technique. Subsequently, the bandwidth of RMAs is increased by slotting on the ground surface, and adding a parasitic element to the antenna structure. Because of these analyses, for single type RMA, the bandwidth increases from 2.09 GHz to 3.45 GHz. Moreover, for 1 × 2 and 1 × 4 array type RMAs, very wide bandwidths of 7.53 GHz and 4.53 GHz, respectively, are obtained by applying bandwidth enhancement techniques. The success of the study has been demonstrated by comparing outputs of the designs with the some similar, experimental or simulation studies published in the literature.
{"title":"Improving the Performance of Patch Antenna by Applying Bandwidth Enhancement Techniques for 5G Applications","authors":"Seda Ermis, Murat Demirci","doi":"10.31803/tg-20220819001236","DOIUrl":"https://doi.org/10.31803/tg-20220819001236","url":null,"abstract":"In this study, various Rectangular Microstrip Antenna (RMA) designs operating at 28 GHz frequency for 5G-communication system are performed. All designs are generated and analyzed using a 3D electromagnetic simulation program, ANSYS HFSS (High-Frequency Structure Simulator). Single and array type RMA designs are constructed by using non-contact inset-fed feeding technique. Subsequently, the bandwidth of RMAs is increased by slotting on the ground surface, and adding a parasitic element to the antenna structure. Because of these analyses, for single type RMA, the bandwidth increases from 2.09 GHz to 3.45 GHz. Moreover, for 1 × 2 and 1 × 4 array type RMAs, very wide bandwidths of 7.53 GHz and 4.53 GHz, respectively, are obtained by applying bandwidth enhancement techniques. The success of the study has been demonstrated by comparing outputs of the designs with the some similar, experimental or simulation studies published in the literature.","PeriodicalId":43419,"journal":{"name":"TEHNICKI GLASNIK-TECHNICAL JOURNAL","volume":null,"pages":null},"PeriodicalIF":1.2,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69414766","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：