Pub Date : 2022-05-28DOI: 10.1109/SETIT54465.2022.9875763
Asma Elyounsi, H. Tlijani, M. Bouhlel
In the field of ISAR Data extraction, many drawbacks appear and make this field a very challenging one. Therefore, using higher order neural networks (HONN) became an useful way to cope with problems like the inability to scale with the complexity of the problem and the sluggish converge rate that results in a lengthy training period. The Functional Link Artificial Neural Network (FLANN), a higher order neural network, was optimized in this paper using a revolutionary metaheuristic inspired by the Firefly algorithm to identify radar targets. Results from experiments demonstrate the effectiveness of the training method.
{"title":"ISAR-Image recognition using optimized HONN by a Metaheuristic algorithm","authors":"Asma Elyounsi, H. Tlijani, M. Bouhlel","doi":"10.1109/SETIT54465.2022.9875763","DOIUrl":"https://doi.org/10.1109/SETIT54465.2022.9875763","url":null,"abstract":"In the field of ISAR Data extraction, many drawbacks appear and make this field a very challenging one. Therefore, using higher order neural networks (HONN) became an useful way to cope with problems like the inability to scale with the complexity of the problem and the sluggish converge rate that results in a lengthy training period. The Functional Link Artificial Neural Network (FLANN), a higher order neural network, was optimized in this paper using a revolutionary metaheuristic inspired by the Firefly algorithm to identify radar targets. Results from experiments demonstrate the effectiveness of the training method.","PeriodicalId":126155,"journal":{"name":"2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125340741","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 : 2022-05-28DOI: 10.1109/SETIT54465.2022.9875707
S. Rovetta, Hajjam EL Hassani
: One key component of virtually all machine learning methods is optimization of some objective function. Recent methods like deep neural networks require the solution of very large problems, and there is a host of techniques that has been developed for this purpose, both with solid theoretical ground and out of hands-on experience. However, there is more to computational intelligence than just neural networks. Abstract: The Big Tech advocate the use of science to overcome the biological limits of the human body. This new world with technology, where science evolves every day to compensate the deficits of the human body, this new world will most certainly end up creating post-humans: improved men with increased capacities and life expectancy almost infinite. Man is clearly tempted to take power over the environment and over himself. We have ultra-powerful machines, IoT for data collection, storage capacity and of course algorithms, that is to say artificial intelligence. This artificial intelligence can indeed let us believe that man can take power over the environment and over himself. In recent years, machine learning has become an important solution in the healthcare industry. It allows us today to predict a decompensation several days before its occurrence and this is a reality today. Abstract: This tutorial-style presentation will start with a historic overview of Artificial Intelligence (AI), shortly going over the earlier AI waves. The focus will be on the rapid rise of AI in the last decade, narrowing it down to Deep Learning, perceived as an ubiquitous solution for a plethora of applications. This trend was/is stimulated by massive financial support and flourishing on the growth of plenty of custom AI chips. The fast pace rising start-ups in these deceptively esoteric fields will be identified, and their latest results surveyed. Currently, a key ingredient, besides new designs, is extreme ultraviolet lithography EUVL (Extreme_ultraviolet_lithography)— at the heart of fabricating the most advanced few-nanometer integrated circuits (powering cloud, fog, and edge AI & IoT, and most probably quantum computing as well). We will mention some of the technical problems faced, and go over the latest solutions (some landing the German Future Prize in Fall 2020). All of these pinpoints to a monopolistic growth potential revealing extremely stringent financial and technological constraints. Finally, we will conclude by commenting on the forthcoming growth potential of AI hardware in the wider context of rebooting and quantum computing, as seen through the expected demise of Moore’s law. Abstract: In various places of nature, we see certain patterns that repeat themselves after some scaling in size and placement or rotation. These patterns have been studied and modeled by fractal geometries like the Cantor, Koch, Peano, and Sierpinski. There, a certain dimension or angle of the object shape that is being repeated is expressed by a certain mathematica
{"title":"Tutorials Speakers of SETIT 2022","authors":"S. Rovetta, Hajjam EL Hassani","doi":"10.1109/SETIT54465.2022.9875707","DOIUrl":"https://doi.org/10.1109/SETIT54465.2022.9875707","url":null,"abstract":": One key component of virtually all machine learning methods is optimization of some objective function. Recent methods like deep neural networks require the solution of very large problems, and there is a host of techniques that has been developed for this purpose, both with solid theoretical ground and out of hands-on experience. However, there is more to computational intelligence than just neural networks. Abstract: The Big Tech advocate the use of science to overcome the biological limits of the human body. This new world with technology, where science evolves every day to compensate the deficits of the human body, this new world will most certainly end up creating post-humans: improved men with increased capacities and life expectancy almost infinite. Man is clearly tempted to take power over the environment and over himself. We have ultra-powerful machines, IoT for data collection, storage capacity and of course algorithms, that is to say artificial intelligence. This artificial intelligence can indeed let us believe that man can take power over the environment and over himself. In recent years, machine learning has become an important solution in the healthcare industry. It allows us today to predict a decompensation several days before its occurrence and this is a reality today. Abstract: This tutorial-style presentation will start with a historic overview of Artificial Intelligence (AI), shortly going over the earlier AI waves. The focus will be on the rapid rise of AI in the last decade, narrowing it down to Deep Learning, perceived as an ubiquitous solution for a plethora of applications. This trend was/is stimulated by massive financial support and flourishing on the growth of plenty of custom AI chips. The fast pace rising start-ups in these deceptively esoteric fields will be identified, and their latest results surveyed. Currently, a key ingredient, besides new designs, is extreme ultraviolet lithography EUVL (Extreme_ultraviolet_lithography)— at the heart of fabricating the most advanced few-nanometer integrated circuits (powering cloud, fog, and edge AI & IoT, and most probably quantum computing as well). We will mention some of the technical problems faced, and go over the latest solutions (some landing the German Future Prize in Fall 2020). All of these pinpoints to a monopolistic growth potential revealing extremely stringent financial and technological constraints. Finally, we will conclude by commenting on the forthcoming growth potential of AI hardware in the wider context of rebooting and quantum computing, as seen through the expected demise of Moore’s law. Abstract: In various places of nature, we see certain patterns that repeat themselves after some scaling in size and placement or rotation. These patterns have been studied and modeled by fractal geometries like the Cantor, Koch, Peano, and Sierpinski. There, a certain dimension or angle of the object shape that is being repeated is expressed by a certain mathematica","PeriodicalId":126155,"journal":{"name":"2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128109449","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 : 2022-05-28DOI: 10.1109/SETIT54465.2022.9875932
Amit Kumar Bhuyan, H. Dutta, S. Biswas
This paper presents a computationally efficient and accurate speech segmentation framework suitable for speaker diarization. The proposed approach solves the problem of increased false positive rate in order to compensate for reduced false negative rate during speaker change detection in the existing methods in literature. In this new approach, speaker change point detection is biased around detected quasi-silences, which reduces the severity of the trade-off between the missed detection and false detection rates. Additionally, the computational overhead is reduced due to the fact that the segmentation related processing happens only around the detected quasi-silences as opposed to during the entire speech signal. The change point detection accuracy of the proposed quasi-silence-based method is compared with the WinGrow method from literature that uses Bayesian Information Criterion (BIC) recursively. The results show a considerable improvement in the reduction of false positive rate at the segmentation stage while reducing the computational overhead. The proposed mechanism’s improved accuracy and reduced computation makes it a candidate for real-time speaker diarization especially when run on low-power embedded devices.
{"title":"Unsupervised Quasi-Silence based Speech Segmentation for Speaker Diarization","authors":"Amit Kumar Bhuyan, H. Dutta, S. Biswas","doi":"10.1109/SETIT54465.2022.9875932","DOIUrl":"https://doi.org/10.1109/SETIT54465.2022.9875932","url":null,"abstract":"This paper presents a computationally efficient and accurate speech segmentation framework suitable for speaker diarization. The proposed approach solves the problem of increased false positive rate in order to compensate for reduced false negative rate during speaker change detection in the existing methods in literature. In this new approach, speaker change point detection is biased around detected quasi-silences, which reduces the severity of the trade-off between the missed detection and false detection rates. Additionally, the computational overhead is reduced due to the fact that the segmentation related processing happens only around the detected quasi-silences as opposed to during the entire speech signal. The change point detection accuracy of the proposed quasi-silence-based method is compared with the WinGrow method from literature that uses Bayesian Information Criterion (BIC) recursively. The results show a considerable improvement in the reduction of false positive rate at the segmentation stage while reducing the computational overhead. The proposed mechanism’s improved accuracy and reduced computation makes it a candidate for real-time speaker diarization especially when run on low-power embedded devices.","PeriodicalId":126155,"journal":{"name":"2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"272 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122773846","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 : 2022-05-28DOI: 10.1109/SETIT54465.2022.9875810
Hendel Mounia
This paper outlines the adopted methodology to construct an intelligent system, which is able to detect and to discriminate between short circuit faults in high voltage power lines (220 kV, 50 Hz) with a length of 300 km. Based on the current study, two approaches for feature extraction are presented and compared. Firstly, the voltage and current signals are decomposed into 20 ms segments, and two distinct sets of descriptors are then calculated; The first one, consists on a set of 102 morphological, and the second one, consists on a set of 12 electrical parameters. Finally, two direct probabilistic multiclass support vector machines (M-SVM) are trained separately to discriminate between 10 short-circuit faults plus a normal case, each of them receives as inputs one of the previously calculated sets.The study shows that the obtained results are very satisfactory, however, the M-SVM presents higher accuracy when it’s trained by morphological parameters; with a classification rates of 96.74% and 91.23% for the first and second method respectively
{"title":"A comparative Study Between Electrical and Morphological Features for Short-Circuit Faults Detection and Discrimination in Power Grid Lines","authors":"Hendel Mounia","doi":"10.1109/SETIT54465.2022.9875810","DOIUrl":"https://doi.org/10.1109/SETIT54465.2022.9875810","url":null,"abstract":"This paper outlines the adopted methodology to construct an intelligent system, which is able to detect and to discriminate between short circuit faults in high voltage power lines (220 kV, 50 Hz) with a length of 300 km. Based on the current study, two approaches for feature extraction are presented and compared. Firstly, the voltage and current signals are decomposed into 20 ms segments, and two distinct sets of descriptors are then calculated; The first one, consists on a set of 102 morphological, and the second one, consists on a set of 12 electrical parameters. Finally, two direct probabilistic multiclass support vector machines (M-SVM) are trained separately to discriminate between 10 short-circuit faults plus a normal case, each of them receives as inputs one of the previously calculated sets.The study shows that the obtained results are very satisfactory, however, the M-SVM presents higher accuracy when it’s trained by morphological parameters; with a classification rates of 96.74% and 91.23% for the first and second method respectively","PeriodicalId":126155,"journal":{"name":"2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122824656","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 : 2022-05-28DOI: 10.1109/SETIT54465.2022.9875563
Nessrine Raggad, Nouha Arfaoui
Fake news corresponds to distributed information which is not true. It becomes popularized during the 2016 U.S. elections. With the spread of COVID-19 and becoming an epidemic, much information is exchanged around the world. A part of this information is fake having a negative impact on mental health and psychological well-being of people. Because of the importance of this issue, we propose in this work applying several machine learning algorithms to detect COVID-19 fake news. We propose, also, several metrics to evaluate those models and to choose the best among them. Compared to the existing works, we use four classes: Fake, Mostly Fake, True and Mostly True.
假新闻对应的是不真实的散布信息。它在2016年美国大选期间变得流行起来。随着COVID-19的传播并成为流行病，世界各地交换了大量信息。这些信息中的一部分是虚假的，对人们的精神健康和心理健康产生了负面影响。由于这个问题的重要性，我们在这项工作中建议应用几种机器学习算法来检测COVID-19假新闻。我们还提出了几个指标来评估这些模型并从中选择最好的模型。与现有作品相比，我们使用了四个类:Fake, most Fake, True和most True。
{"title":"Machine Learning Algorithms For COVID-19 Fake News Detection","authors":"Nessrine Raggad, Nouha Arfaoui","doi":"10.1109/SETIT54465.2022.9875563","DOIUrl":"https://doi.org/10.1109/SETIT54465.2022.9875563","url":null,"abstract":"Fake news corresponds to distributed information which is not true. It becomes popularized during the 2016 U.S. elections. With the spread of COVID-19 and becoming an epidemic, much information is exchanged around the world. A part of this information is fake having a negative impact on mental health and psychological well-being of people. Because of the importance of this issue, we propose in this work applying several machine learning algorithms to detect COVID-19 fake news. We propose, also, several metrics to evaluate those models and to choose the best among them. Compared to the existing works, we use four classes: Fake, Mostly Fake, True and Mostly True.","PeriodicalId":126155,"journal":{"name":"2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129899783","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 : 2022-05-28DOI: 10.1109/SETIT54465.2022.9875567
S. S. Boudouh, M. Bouakkaz
Breast cancer is the second leading cause of death among women. Mammogram images are the widely utilized method to identify breast cancer at an early stage. In this study, we implemented a convolutional neural network that classifies mammogram images into normal and abnormal(tumor) with 100% accuracy. The dataset was collected from the Mammographic Image Analysis Society MiniMammographic Database (MiniMIAS) and due to a shortage of abnormal mammography, 92 images were added from the Chinese Mammography Database (CMMD), which only contains abnormal mammogram images. The dataset was pre-processed using several filters in order to extract the ROI (Region Of Interest) and eliminate any noises, resulting in better images for training, which were shown to be effective based on the results. The dataset was split into 75%, 5%, and 20% as training, validation, and testing sets respectively. The proposed model was trained, then evaluated using a test set with 100% accuracy.
{"title":"Breast Tumor Detection In Mammogram Images Using Convolutional Neural Networks","authors":"S. S. Boudouh, M. Bouakkaz","doi":"10.1109/SETIT54465.2022.9875567","DOIUrl":"https://doi.org/10.1109/SETIT54465.2022.9875567","url":null,"abstract":"Breast cancer is the second leading cause of death among women. Mammogram images are the widely utilized method to identify breast cancer at an early stage. In this study, we implemented a convolutional neural network that classifies mammogram images into normal and abnormal(tumor) with 100% accuracy. The dataset was collected from the Mammographic Image Analysis Society MiniMammographic Database (MiniMIAS) and due to a shortage of abnormal mammography, 92 images were added from the Chinese Mammography Database (CMMD), which only contains abnormal mammogram images. The dataset was pre-processed using several filters in order to extract the ROI (Region Of Interest) and eliminate any noises, resulting in better images for training, which were shown to be effective based on the results. The dataset was split into 75%, 5%, and 20% as training, validation, and testing sets respectively. The proposed model was trained, then evaluated using a test set with 100% accuracy.","PeriodicalId":126155,"journal":{"name":"2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130800950","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 : 2022-05-28DOI: 10.1109/SETIT54465.2022.9875521
Prerna Sharma, K. Sharma
Complications in pregnancies can be due to various reasons like health issues with mother or conditions that can hamper the development of the fetus which can later affect the health of the baby. CTG performed at the time of high risk pregnancies can timely identify those associated complications. Fetuses with deficient oxygen amount are more susceptible to fetal distress which can also be fatal. This paper puts forward Grey Wolf Optimization Algorithm and Whale Optimization Algorithm for optimal feature selection from the dataset of cardiotocography. Features selected by GWO and WOA are 4 and 7 respectively. GWO and WOA efficiently select optimal reduced set of features for classification of state of the fetus under normal, suspect and pathologic with an accuracy of 98.74% and 98.11% respectively.
{"title":"Optimized Classification of fetal state health using GWO and WOA","authors":"Prerna Sharma, K. Sharma","doi":"10.1109/SETIT54465.2022.9875521","DOIUrl":"https://doi.org/10.1109/SETIT54465.2022.9875521","url":null,"abstract":"Complications in pregnancies can be due to various reasons like health issues with mother or conditions that can hamper the development of the fetus which can later affect the health of the baby. CTG performed at the time of high risk pregnancies can timely identify those associated complications. Fetuses with deficient oxygen amount are more susceptible to fetal distress which can also be fatal. This paper puts forward Grey Wolf Optimization Algorithm and Whale Optimization Algorithm for optimal feature selection from the dataset of cardiotocography. Features selected by GWO and WOA are 4 and 7 respectively. GWO and WOA efficiently select optimal reduced set of features for classification of state of the fetus under normal, suspect and pathologic with an accuracy of 98.74% and 98.11% respectively.","PeriodicalId":126155,"journal":{"name":"2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132997304","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 : 2022-05-28DOI: 10.1109/SETIT54465.2022.9875851
Bouchareb Ilhem
The recognition of the interrelationship between science and mathematics led to the creation of a new concept called artificial intelligence (AI) which contributed to solve many outstanding problems. Artificial Intelligence is the new frontier of health research and development. In this paper Artificial Intelligence challenges Alzheimer. The aim of this study is to use artificial intelligence tools to track various Alzheimer’s stages and symptoms over time and according to the patients. In order to achieve this efficient pattern recognition intelligent system based time-frequency representation-neural networks (RTF-NNT) extracts and classifies a large number of Alzheimer’s features. Each of them is associated, or not, with a pathological state, which makes it possible to automatically classify patients in diagnostic categories. This intelligent system also allows enriching the health database; which areas are altered? Which patients develop Alzheimer’s disease? How long? So much data will be crossed then in the hope of "predicting the evolution of neurodegenerative diseases, such as Alzheimer’s, at very early stages, ten or twenty years. As a stimulating result, AI tools can be adopted to promote health, reduce the time and early automatic detection of Alzheimer’s. Refine the diagnosis and predict the evolution.
{"title":"Pattern Recognition Intelligent System Based RTF-NNT For Early Detection: Application on Alzheimer","authors":"Bouchareb Ilhem","doi":"10.1109/SETIT54465.2022.9875851","DOIUrl":"https://doi.org/10.1109/SETIT54465.2022.9875851","url":null,"abstract":"The recognition of the interrelationship between science and mathematics led to the creation of a new concept called artificial intelligence (AI) which contributed to solve many outstanding problems. Artificial Intelligence is the new frontier of health research and development. In this paper Artificial Intelligence challenges Alzheimer. The aim of this study is to use artificial intelligence tools to track various Alzheimer’s stages and symptoms over time and according to the patients. In order to achieve this efficient pattern recognition intelligent system based time-frequency representation-neural networks (RTF-NNT) extracts and classifies a large number of Alzheimer’s features. Each of them is associated, or not, with a pathological state, which makes it possible to automatically classify patients in diagnostic categories. This intelligent system also allows enriching the health database; which areas are altered? Which patients develop Alzheimer’s disease? How long? So much data will be crossed then in the hope of \"predicting the evolution of neurodegenerative diseases, such as Alzheimer’s, at very early stages, ten or twenty years. As a stimulating result, AI tools can be adopted to promote health, reduce the time and early automatic detection of Alzheimer’s. Refine the diagnosis and predict the evolution.","PeriodicalId":126155,"journal":{"name":"2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133373298","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 : 2022-05-28DOI: 10.1109/SETIT54465.2022.9875760
Mohamed Achref Azzabi, Manel Khadraoui
B2B software purchase is an important decision as it results in a long commitment with the seller including important direct and indirect costs. One relatively new software is the employee recognition software. It promises a large-scale individualized follow-up. The purchase process of this product leads the buyer to take into consideration different features that may be specific to this purchase. This study aims to determine the factors that influence the purchase process involving B2B buyers of employee recognition software. Therefore, qualitative interviews were conducted with professional experience leading participants from 7 countries. Data analysis resulted in 28 codes organized into 4 themes that describe the different factors considered by the buyers for the information search and evaluation of alternatives. These themes are (1) Purchase Process Obstacles; (2) Marketing and communication needs; (3) Initial software search and (4) Buyer’s evaluation criteria. Our study results in the suggestion of a revised decision making process taking into consideration the dynamic nature of the relationships between the steps.
{"title":"B2B buyers’ purchase process of an employee recognition software: A qualitative study","authors":"Mohamed Achref Azzabi, Manel Khadraoui","doi":"10.1109/SETIT54465.2022.9875760","DOIUrl":"https://doi.org/10.1109/SETIT54465.2022.9875760","url":null,"abstract":"B2B software purchase is an important decision as it results in a long commitment with the seller including important direct and indirect costs. One relatively new software is the employee recognition software. It promises a large-scale individualized follow-up. The purchase process of this product leads the buyer to take into consideration different features that may be specific to this purchase. This study aims to determine the factors that influence the purchase process involving B2B buyers of employee recognition software. Therefore, qualitative interviews were conducted with professional experience leading participants from 7 countries. Data analysis resulted in 28 codes organized into 4 themes that describe the different factors considered by the buyers for the information search and evaluation of alternatives. These themes are (1) Purchase Process Obstacles; (2) Marketing and communication needs; (3) Initial software search and (4) Buyer’s evaluation criteria. Our study results in the suggestion of a revised decision making process taking into consideration the dynamic nature of the relationships between the steps.","PeriodicalId":126155,"journal":{"name":"2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"263 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132700225","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 : 2022-05-28DOI: 10.1109/SETIT54465.2022.9875544
H. Chebi
In this paper, a method based on Dragonfly algorithm (DA) inspired by the motion and behaviors (dynamic or static) of artificial in environment is proposed to solve the optimal camera placement (OCP) problem. Ensuring illustration coverage of the surveillance space with a maximum area and minimum number of sensors is required. To ensure the maximum visual coverage, the utilitarian and homogeneous hypotheses are determined, attracting the characteristics of the sensor. In full, six evolutionary type algorithms based on nature inspired Meta heuristic algorithms, DA, Binary dragonfly algorithm (BDA), Particle Swarm Optimization (PSO), Chaotic dragonfly algorithm (CDA), Adaptive dragonfly algorithm (ADA), and GA are adapted to solve this optimal problem of surveillance camera placement based on maximum visual coverage. The proposed algorithms are applicable for all types of surveillance areas with predefined camera locations. In pole climbing scenarios, the location is not predefined and based upon the surveillance requirements the cameras move automatically. The most important in this work is to show a new adaptation of Dragonfly algorithm for optimization (OCP). His has proven its efficiency and superiority compared too many well-experienced meta-heuristics available in the literature.
本文提出了一种基于蜻蜓算法(Dragonfly algorithm, DA)的基于环境中人工物体运动和行为(动态或静态)的方法来解决最佳摄像机放置(OCP)问题。需要以最大的面积和最少的传感器数量确保监视空间的插图覆盖。为了确保最大的视觉覆盖范围，确定了功利和均匀的假设，吸引了传感器的特征。基于自然启发的元启发式算法、DA、二进制蜻蜓算法(BDA)、粒子群算法(PSO)、混沌蜻蜓算法(CDA)、自适应蜻蜓算法(ADA)和遗传算法，采用六种进化型算法来解决基于最大视觉覆盖的监控摄像机布局优化问题。所提出的算法适用于所有类型的具有预定义摄像机位置的监视区域。在爬杆场景中，位置不是预先定义的，而是根据监控要求自动移动摄像机。本工作最重要的是提出了一种新的蜻蜓优化算法(Dragonfly algorithm for optimization, OCP)。与文献中许多经验丰富的元启发式方法相比，他的方法已经证明了它的有效性和优越性。
{"title":"Proposed and application of the Dragonfly algorithm for the camera placement problem","authors":"H. Chebi","doi":"10.1109/SETIT54465.2022.9875544","DOIUrl":"https://doi.org/10.1109/SETIT54465.2022.9875544","url":null,"abstract":"In this paper, a method based on Dragonfly algorithm (DA) inspired by the motion and behaviors (dynamic or static) of artificial in environment is proposed to solve the optimal camera placement (OCP) problem. Ensuring illustration coverage of the surveillance space with a maximum area and minimum number of sensors is required. To ensure the maximum visual coverage, the utilitarian and homogeneous hypotheses are determined, attracting the characteristics of the sensor. In full, six evolutionary type algorithms based on nature inspired Meta heuristic algorithms, DA, Binary dragonfly algorithm (BDA), Particle Swarm Optimization (PSO), Chaotic dragonfly algorithm (CDA), Adaptive dragonfly algorithm (ADA), and GA are adapted to solve this optimal problem of surveillance camera placement based on maximum visual coverage. The proposed algorithms are applicable for all types of surveillance areas with predefined camera locations. In pole climbing scenarios, the location is not predefined and based upon the surveillance requirements the cameras move automatically. The most important in this work is to show a new adaptation of Dragonfly algorithm for optimization (OCP). His has proven its efficiency and superiority compared too many well-experienced meta-heuristics available in the literature.","PeriodicalId":126155,"journal":{"name":"2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132047847","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：