2022 International Conference on Intelligent Systems and Computer Vision (ISCV)最新文献_第7页

Detection of toxicity in social media based on Natural Language Processing methods 基于自然语言处理方法的社交媒体毒性检测

2022 International Conference on Intelligent Systems and Computer Vision (ISCV) Pub Date : 2022-05-18 DOI: 10.1109/ISCV54655.2022.9806096

Mohammed Taleb, Alami Hamza, Mohamed Zouitni, Nabil Burmani, Said Lafkiar, Noureddine En-Nahnahi

{"title":"Detection of toxicity in social media based on Natural Language Processing methods","authors":"Mohammed Taleb, Alami Hamza, Mohamed Zouitni, Nabil Burmani, Said Lafkiar, Noureddine En-Nahnahi","doi":"10.1109/ISCV54655.2022.9806096","DOIUrl":"https://doi.org/10.1109/ISCV54655.2022.9806096","url":null,"abstract":"Comments on important websites, such as popular news portals or social media platforms, are among the main ways of virtual interaction. Unfortunately, the behavior of users on these websites often becomes rude or disrespectful, by spreading toxic comments which can muddle the proper functioning of these sites. The aim of this research is to detect these toxic comments, and to find parts, toxic spans, of these comments to which toxicity can be attributed. Thus, we explored and compared various classifiers belonging to three categories “Machine Learning, Ensemble Learning and Deep Learning” and using different text representations. For detecting toxic spans in the comments, we applied an unsupervised method, we apply the Local Interpretable Model-Agnostic Explanations (LIME).The measures we used to evaluate our methods are accuracy, recall, and Fl-score. Our experiments showed that deep learning models performed unquestionably in the task of detecting toxic comments. The LSTM models with the Globe representation and LSTM with FastText were able to produce a higher F1 and accuracy compared to the other models used. For Toxic spans detction, the higher scores were obtained when combining LIME with classifier LSTM(GloVe) with an accuracy of 98% to identify the toxic spans.","PeriodicalId":426665,"journal":{"name":"2022 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128634066","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}

引用次数: 2

Multi-criteria optimization for optimal nutrition of Moroccan diabetics : *Note: Sub-titles are not captured in Xplore and should not be used 摩洛哥糖尿病患者最佳营养的多标准优化:*注:在Xplore中不捕获字幕，不应使用

2022 International Conference on Intelligent Systems and Computer Vision (ISCV) Pub Date : 2022-05-18 DOI: 10.1109/ISCV54655.2022.9806093

A. Ahourag, K. E. Moutaouakil, S. Chellak, H. Baizri, M. Cheggour

引用次数: 0

A Study of Bidirectional Encoder Representations from Transformers for Sequential Recommendations 面向顺序推荐的互感器双向编码器表示研究

2022 International Conference on Intelligent Systems and Computer Vision (ISCV) Pub Date : 2022-05-18 DOI: 10.1109/ISCV54655.2022.9806062

Amine Kheldouni, J. Boumhidi

引用次数: 0

Advanced Financial Data Processing and Labeling Methods for Machine Learning 机器学习的高级金融数据处理和标记方法

2022 International Conference on Intelligent Systems and Computer Vision (ISCV) Pub Date : 2022-05-18 DOI: 10.1109/ISCV54655.2022.9806060

Samira Bounid, Mohammed Oughanem, Salman Bourkadi

引用次数: 5

On The Formalization of The TOGAF Content MetaModel Using Ontologies 基于本体的TOGAF内容元模型形式化研究

2022 International Conference on Intelligent Systems and Computer Vision (ISCV) Pub Date : 2022-05-18 DOI: 10.1109/ISCV54655.2022.9806063

Bouchra El Idrissi, Chadia Tetou, Karim Doumi

引用次数: 0

Face information forensics analysis based on facial aging: A Survey 基于面部老化的人脸信息取证分析研究进展

2022 International Conference on Intelligent Systems and Computer Vision (ISCV) Pub Date : 2022-05-18 DOI: 10.1109/ISCV54655.2022.9806126

Marem H. Abdulabas, Noor D. Al-Shakarchy

{"title":"Face information forensics analysis based on facial aging: A Survey","authors":"Marem H. Abdulabas, Noor D. Al-Shakarchy","doi":"10.1109/ISCV54655.2022.9806126","DOIUrl":"https://doi.org/10.1109/ISCV54655.2022.9806126","url":null,"abstract":"Face recognition systems are now confronted with the problem of “aging”. The difficulty arises from age-related biological changes, which might result in considerable differences in face traits between two photographs obtained at various ages of the same individual. Because the face is the area of the body that is most impacted by aging, the extraction of strong facial traits for age-invariant face recognition is becoming increasingly important, especially when there are huge age disparities between the same person’s face photos. Face Age Progression (FAP) is the process of synthesizing face photos while simulating aging processes to anticipate an individual’s future look. The production of age-progressed face photographs has advantages for a variety of applications; Face recognition methods, private investigators, and entertainment content are just a few examples, particularly for recognizing and protecting missing abducted children using childhood photographs or Alzheimer’s people. Deep generative networks’ success recently, in particular, has considerably improved the maturity level of face’s qualities pictures about visual clarity, aging correctness, as well as identity preservation. This paper present a comparison of contemporary approaches to face age growth deep learning-based for both adulthood and youth face aged, face age progression FAP is classified into three rising concepts: translation-based, condition-based, & sequence-based. This paper provides a complete overview of one of the most frequently used methods of achievement assessment and a comprehensive list of available datasets.","PeriodicalId":426665,"journal":{"name":"2022 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130708581","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}

引用次数: 1

Monitoring Photovoltaic Panels Using the ESP32 Microcontroller via low-power Bluetooth Communication 利用ESP32单片机通过低功耗蓝牙通信监控光伏板

2022 International Conference on Intelligent Systems and Computer Vision (ISCV) Pub Date : 2022-05-18 DOI: 10.1109/ISCV54655.2022.9806084

Zaidan Didi, Ikram Azam

{"title":"Monitoring Photovoltaic Panels Using the ESP32 Microcontroller via low-power Bluetooth Communication","authors":"Zaidan Didi, Ikram Azam","doi":"10.1109/ISCV54655.2022.9806084","DOIUrl":"https://doi.org/10.1109/ISCV54655.2022.9806084","url":null,"abstract":"In In this paper, we propose a method based on Internet of Objects technology to transmit and monitor in real-time the main parameters of a photovoltaic panel thanks to a low communication Bluetooth communication link, this research mainly consists in integrating and taking full advantage of the ESP32 microcontroller as well as the current sensor and a Bluetooth module. In our study, we will create and initialize a low-consumption Bluetooth communication link to transmit the main parameters of a photovoltaic panel to a paired smartphone device via this Bluetooth link. As the first step in our study, we will use a current sensor to measure the exact value of the intensity of the electric current flowing from the photovoltaic panel, note here, that to reduce measurement errors, we will integrate a voltage divider instead of a voltage sensor to measure the voltage between the terminals of the photovoltaic panel. Then we will use the measured quantities to calculate the other two quantities (power and energy).Finally, we are going to send the four quantities in real-time via this low consumption Bluetooth communication. Note that for better readability, the different values sent are displayed on an LCD screen and the ESP32 serial monitor as well as on a paired smartphone device that receives the data.On the other hand, our project has been implemented and tested with efficiency and without any errors, which shows that our design has succeeded in transmitting data through this low consumption Bluetooth link.","PeriodicalId":426665,"journal":{"name":"2022 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124810172","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}

引用次数: 3

FSMC for PWM rotor side converter in DFIG-based wind turbine system 基于dfig的风力发电系统中PWM转子侧变换器的FSMC

2022 International Conference on Intelligent Systems and Computer Vision (ISCV) Pub Date : 2022-05-18 DOI: 10.1109/ISCV54655.2022.9806083

Hamza Es-Sarraj, A. E. Bakri, R. M. Alaoui, I. Boumhidi

引用次数: 1

Design of Observer for Cardiovascular Anomalies Detection: an LMI approach 心血管异常检测的观测器设计:LMI方法

2022 International Conference on Intelligent Systems and Computer Vision (ISCV) Pub Date : 2022-05-18 DOI: 10.1109/ISCV54655.2022.9806114

El Khaloufi Ghizlane, Chaibi Noreddine, B. Sadek, El-Jimi Driss, Boumhidi Ismail

引用次数: 0

ISCV 2022 Cover Page ISCV 2022封面

2022 International Conference on Intelligent Systems and Computer Vision (ISCV) Pub Date : 2022-05-18 DOI: 10.1109/iscv54655.2022.9806132

引用次数: 0