2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)最新文献_第6页

Bot Detection Using Machine Learning Algorithms on Social Media Platforms 在社交媒体平台上使用机器学习算法进行机器人检测

2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA) Pub Date : 2020-11-25 DOI: 10.1109/CITISIA50690.2020.9371778

Sainath Gannarapu, A. Dawoud, Rasha S. Ali, Ali A. Alwan

{"title":"Bot Detection Using Machine Learning Algorithms on Social Media Platforms","authors":"Sainath Gannarapu, A. Dawoud, Rasha S. Ali, Ali A. Alwan","doi":"10.1109/CITISIA50690.2020.9371778","DOIUrl":"https://doi.org/10.1109/CITISIA50690.2020.9371778","url":null,"abstract":"Using bots in social media is a significant concern for information validity and authenticity. Currently, there are several solutions for bots detection. However, the accuracy of the detection still needs improvement. The main aim of this paper is to introduce an automatic mechanism for the detection and removal of bots that exist on social media platforms. The research has the purpose of removing the non-genuine accounts, their related information, and the data which are posted by them and to make these platforms free of misleading information. Bots detection and removal will increase the authenticity of the contents presented on different social media platforms. Also, It will improve the level of privacy and authenticity of these platforms and related users. The research uses the bot detection technique based on machine learning algorithms. The components of the study are data, feature selection, and bot detection. The research performs web development and hosting on the collected data with a machine-learning algorithm to perform bot detection in social media networks. The proposed system provides a more accurate and effective system for bot detection using machine learning. The research utilizes various approaches and mechanisms that lead to the enhanced efficiency of bot detection and removals.","PeriodicalId":145272,"journal":{"name":"2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116602803","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

Deep learning for ovarian follicle (OF) classification and counting: displaced rectifier linear unit (DReLU) and network stabilization through batch normalization (BN) 深度学习用于卵巢卵泡(OF)分类和计数:置换整流线性单元(DReLU)和通过批归一化(BN)实现网络稳定

2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA) Pub Date : 2020-11-25 DOI: 10.1109/CITISIA50690.2020.9371844

Mekhriniso Abdukodirova, S. Abdullah, A. Alsadoon, P. Prasad

{"title":"Deep learning for ovarian follicle (OF) classification and counting: displaced rectifier linear unit (DReLU) and network stabilization through batch normalization (BN)","authors":"Mekhriniso Abdukodirova, S. Abdullah, A. Alsadoon, P. Prasad","doi":"10.1109/CITISIA50690.2020.9371844","DOIUrl":"https://doi.org/10.1109/CITISIA50690.2020.9371844","url":null,"abstract":"Background and aim: Diagnosis and treatment of female infertility conditions would help future reproductive planning. Although current deep learning frameworks are able to classify and separately count all types at high accuracy, these solutions suffer from a misclassification error and a high computation complexity due to a positive bias effect and an internal covariate shift. The objective of this paper is to increase the classification accuracy of OFs and to reduce the computational costs of classification via deep learning (DL). Methodology: our framework for follicle classification and counting (FCaC) uses filter-based segmentation. A new method is also proposed to accelerate learning and to normalize the input layer by adjusting and scaling the activations. Our method uses a modified activation function (MAF)- displaced rectifier linear unit (DReLU) and batch normalization (BN) in Feature Extraction and Classification. Therefore, faster and more stable training is achieved by modifying input distribution of an activation function (AF). Results: The proposed system was able to obtain a mean classification accuracy of 97.614%, which is 2.264% more accurate classification than the state-of-the-art. Furthermore, the model processes a single WSI 30% faster (in 10.23 seconds compared to 14.646 seconds processing time of the existing solutions). Conclusion: The proposed system focuses on processing histology images with an accurate classification. It is also faster, has an accelerated convergence and enhanced learning thanks to BN and the EAF. We considered a positive bias effect and internal covariate shift as the main aspects to improve the classification performance.","PeriodicalId":145272,"journal":{"name":"2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124465966","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: 0

A Decentralised Land Sale and Ownership Tracking System using Blockchain technology 采用区块链技术的分散式土地买卖及业权追踪系统

2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA) Pub Date : 2020-11-25 DOI: 10.1109/CITISIA50690.2020.9371777

Mahsa Mohaghegh, A. Panikkar

引用次数: 0

Authentication in E-Health Services 电子医疗服务中的身份验证

2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA) Pub Date : 2020-11-25 DOI: 10.1109/CITISIA50690.2020.9371820

Sabin Shahi, Margaret Redestowicz, N. Costadopoulos

{"title":"Authentication in E-Health Services","authors":"Sabin Shahi, Margaret Redestowicz, N. Costadopoulos","doi":"10.1109/CITISIA50690.2020.9371820","DOIUrl":"https://doi.org/10.1109/CITISIA50690.2020.9371820","url":null,"abstract":"E-health services are a modern technology that stores the health records of patients and allows medical practitioners to retrieve them remotely. E-health services have provided high-level availability and good support for medical services, but a secured authentication mechanism is vital for the protection of this sensitive information. The main concern for e-health services is that the information is transmitted through a public transmission medium and the existing authentication mechanism fails to secure the user identity and is vulnerable to different network attacks. The main aim of this paper is to provide a review of different types of authentication mechanisms used in e-health services along with their implemented technologies and provide an overall framework for future research. This report will compare and contrast the currently available authentication mechanisms of e-health services along with their data input, processing, outcome, and the recent technologies implemented in the system. Through this report, the reader will be able to gain an overview of all the existing authentication protocols based on their techniques, methods, and algorithms for improving the security of e-health services and to secure the patient data.","PeriodicalId":145272,"journal":{"name":"2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129236785","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

Review of scalable privacy protection techniques in mobile crowdsensing service for security of data 移动众测服务中数据安全的可扩展隐私保护技术综述

2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA) Pub Date : 2020-11-25 DOI: 10.1109/CITISIA50690.2020.9371826

Jinfeng Su, Sreekar Konda, Mohammad Momani

{"title":"Review of scalable privacy protection techniques in mobile crowdsensing service for security of data","authors":"Jinfeng Su, Sreekar Konda, Mohammad Momani","doi":"10.1109/CITISIA50690.2020.9371826","DOIUrl":"https://doi.org/10.1109/CITISIA50690.2020.9371826","url":null,"abstract":"Mobile crowdsensing is a service based on a group of different individuals that have a device. The MCS (Mobile crowdsensing) is used for communication and transferring of data. It is capable of sensing and computing such data that are based on some information such as measuring, mapping, analyzing, and estimating. It can be used for effective decision-making in-crowd. The data generated in by crowd is used for task generation, and the task is assigned to different users and requesters. Due to numerous jobs, there can be a situation of task similarity generates, which may affect the privacy of users or workers in crowdsensing. The problem of privacy can be solved with the help of privacy protection techniques in crowdsensing. This work aims to propose a system based MCS technique for Privacy protection of data with proper scalability. CPP (Crowdsensing Privacy Protection) taxonomy is used that is based on the comprehensiveness and fitness of good. The usefulness of the proposed arrangement is explained by ordering 30 state-of-the-art solutions. Improved consequences are based on extraordinary assets and diminish of different MCS privacy protection techniques. It can be concluded that by employing the MCS privacy protection system for securing user data based on detection and learning algorithms with accurate dimensions. This research investigates the current innovations and techniques in the field of MCS for scalable privacy protection. Different relevant algorithms are used for effective decision making for users and requestors of MCS.","PeriodicalId":145272,"journal":{"name":"2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)","volume":"26 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132955325","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: 0

CITISIA 2020 Committees CITISIA 2020 委员会

2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA) Pub Date : 2020-11-25 DOI: 10.1109/citisia50690.2020.9371794

引用次数: 0

IoT for Smart Learning/Education 物联网智能学习/教育

2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA) Pub Date : 2020-11-25 DOI: 10.1109/CITISIA50690.2020.9371774

Sabin Shrestha, Fatima Furqan

{"title":"IoT for Smart Learning/Education","authors":"Sabin Shrestha, Fatima Furqan","doi":"10.1109/CITISIA50690.2020.9371774","DOIUrl":"https://doi.org/10.1109/CITISIA50690.2020.9371774","url":null,"abstract":"Internet of Things, has opened many new possibilities in the world of technology. The interconnection among sensors, wearables, mobile devices, etc. is used to collect data. The collected data is processed and analyzed on fog and cloud through various algorithms to obtain an efficient solution to diverse problems. IoT has a wide range of spectrum for its implementation, and several industries have already started deploying a smart and efficient ecosystem. The Education sector is among these industries. There are many implementations of IoT for Smart Learning such as the use of smart boards in the classrooms, mobile applications allowing impromptu access to learning resources anywhere. These advancements are only the tip of the iceberg. The network of smart things can be utilized to make the learning process even smarter and more efficient. Even though the classes are equipped with smart devices, it is hard for educators to attend each student individually and find out the areas where they are facing problems, as every individual has a different learning pattern. Keeping track of the students and to assist them individually requires a lot of time and effort. The level of difficulty increases further when face-to-face learning is switched to online learning. The research focuses on enhancing the online learning and teaching experience through the implementation of IoT using available devices, sensors, and other technologies such as machine learning and artificial intelligence.","PeriodicalId":145272,"journal":{"name":"2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130591488","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: 5

Political Arabic Articles Classification Based on Machine Learning and Hybrid Vector 基于机器学习和混合向量的阿拉伯政治文章分类

2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA) Pub Date : 2020-11-25 DOI: 10.1109/CITISIA50690.2020.9371791

D. Abd, A. Sadiq, A. Abbas

{"title":"Political Arabic Articles Classification Based on Machine Learning and Hybrid Vector","authors":"D. Abd, A. Sadiq, A. Abbas","doi":"10.1109/CITISIA50690.2020.9371791","DOIUrl":"https://doi.org/10.1109/CITISIA50690.2020.9371791","url":null,"abstract":"Recently, there was substantial growth in the opinion data and the number of weblogs in the world wide web (WWW). The capability for automatically determining an article’s political orientation might be of high importance in various fields ranging from academia to security. Yet, sentiment classification related to the weblog posts (especially the political ones), has been more complex in comparison to sentiment classification related to the conventional text. In the presented study, supervised machine learning along with feature extraction methods Term Frequency (TF) and five grams (unigram, bigram, trigram, 4-gram, and 5-gram) were combined to generate a hybrid vector that applied for the process of classification. Besides, for investigation purposes, Support Vector Machine (SVM), Naive Bayes (NB), KNearest Neighbor (KNN), and Decision Tree (DT) for the supervised machine learning were used. After conducting the tests, the results indicated that the NB with unigram provided results with accuracy (93.548%). Thus, the NB is extremely acceptable in the presented model.","PeriodicalId":145272,"journal":{"name":"2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131157244","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

A Novel Solution For Anti-Money Laundering System 反洗钱系统的新解决方案

2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA) Pub Date : 2020-11-25 DOI: 10.1109/CITISIA50690.2020.9371840

M. Thi, Chandana Withana, N. Quynh, N. Q. Vinh

{"title":"A Novel Solution For Anti-Money Laundering System","authors":"M. Thi, Chandana Withana, N. Quynh, N. Q. Vinh","doi":"10.1109/CITISIA50690.2020.9371840","DOIUrl":"https://doi.org/10.1109/CITISIA50690.2020.9371840","url":null,"abstract":"In the age of unpredictable fluctuations of technology, disorganized detection has been recently figured out in most of present-day anti-money laundering systems. These obstacles are attributed to certain reasons associated with applying handcrafted manipulation in the long list of principles and having the shortage of real datasets about banking purchasers or the customers’ information. This article demonstrates such an innovative approach to evaluate the data in terms of suspicious behaviors, clients’ relationships, the awareness for the customers retrieval from the financial sector in social media platforms. The applicable datasets consisting of above 20000 sample records on Kaggle is the main resource for our service. Each entry was compiled from content of collected documents and was attached to the descriptions measuring positivity or negativity in catching money laundering. They were used to qualify the model in AutoML supplied by Google Cloud Artificial Intelligence. After having been satisfied the sentiment standard with a performance accuracy approximately 0.85, we attempted to forecast the sentimental design for all searched outcomes connected with the clients to distinguish badly known companies. The output is a beneficial tool for the companies getting used to realizing unauthorized clients. In other words, instead of having no information about new clients in Know Your Customer of anti-money laundering inspections, it is more helpful to utilize this service without wasting too much time and money for a huge number of other sites out there.","PeriodicalId":145272,"journal":{"name":"2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131221891","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

A Review of Blockchain-based on IoT applications (challenges and future research directions) 基于区块链的物联网应用综述(挑战与未来研究方向)

2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA) Pub Date : 2020-11-25 DOI: 10.1109/CITISIA50690.2020.9371814

Walid K. A. Hasan, Albahlool M Abood, Mostafa Habbal

{"title":"A Review of Blockchain-based on IoT applications (challenges and future research directions)","authors":"Walid K. A. Hasan, Albahlool M Abood, Mostafa Habbal","doi":"10.1109/CITISIA50690.2020.9371814","DOIUrl":"https://doi.org/10.1109/CITISIA50690.2020.9371814","url":null,"abstract":"Internet of Things is defined as the framework of interconnected computing systems, mechanical and digital appliances, objects, animals, or people that are equipped with specific identifiers as well as the ability to transfer data over networks. Such devices will not require human-to-human or human-to-computer interaction. This technology has emerged with a Blockchain, which has been used in cryptocurrency, to enhance the performance of security and decrease costs. Although emerging Blockchain with IoT has improved the entire system design. It still faces a number of issues relevant to time latency, anonymity, power efficiency, and big data. Blockchain has been used in various applications such as Healthcare, smart homes, and smart cities. In this paper, we will briefly define the idea of Blockchain including the definition of Blockchain, its types, advantages, and disadvantages, and then present some challenges of Blockchain-based applications on the Internet of things where we focus on Healthcare, smart homes, and smart cities. Finally, some future work direction will be introduced.","PeriodicalId":145272,"journal":{"name":"2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129554745","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