Pub Date : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300071
Hind Baaqeel, Rachid Zagrouba
Due to the massive proliferation of Short Message Service (SMS), Spammers got the interest to dig their way into it in the hope to reach more targets. Spam SMS can trick mobile users into giving away their confidential information which can result in severe consequences. The seriousness of this problem has raised the need to develop an accurate Spam filtration solution. Machine learning algorithms have emerged as a great tool to classify data into labels. This description fits our case perfectly as it classifies SMS into two labels: spam or ham. This paper will tackle the SMS spam filtration solutions by introducing a hybrid system using two types of machine learning techniques: supervised & unsupervised machine learning algorithms. The new hybrid system is designed to achieve better spam filtration accuracy and F-measures
{"title":"Hybrid SMS Spam Filtering System Using Machine Learning Techniques","authors":"Hind Baaqeel, Rachid Zagrouba","doi":"10.1109/ACIT50332.2020.9300071","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300071","url":null,"abstract":"Due to the massive proliferation of Short Message Service (SMS), Spammers got the interest to dig their way into it in the hope to reach more targets. Spam SMS can trick mobile users into giving away their confidential information which can result in severe consequences. The seriousness of this problem has raised the need to develop an accurate Spam filtration solution. Machine learning algorithms have emerged as a great tool to classify data into labels. This description fits our case perfectly as it classifies SMS into two labels: spam or ham. This paper will tackle the SMS spam filtration solutions by introducing a hybrid system using two types of machine learning techniques: supervised & unsupervised machine learning algorithms. The new hybrid system is designed to achieve better spam filtration accuracy and F-measures","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124085492","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300075
Walid Elhedda, Maroua Mehri, M. Mahjoub
Many iterative supervised clustering algorithms such as K-means and its derivatives depend closely on the initial cluster center positions. In order to overcome the convergence problems inherent in the clustering algorithms (i.e., local optimum), and subsequently to avoid a drop in clustering performance, many researchers continue to propose novel efficient methods able to determine automatically the optimal cluster centers. Therefore, in this paper, we propose a simple and efficient cluster center initialization method, called hyperspace-based multi-level thresholding (HMLT). The proposed HMLT method is based on using a novel multi-level thresholding approach on the multi-dimensional representation of color images (called hyperspace). In order to show the high performance of the HMLT method, experiments have been conducted using a recent clustering method, called the hyperkernel-based intuitionistic fuzzy c-means (HKIFCM), and after initializing the cluster center positions randomly and by means of the HMLT method. The HKIFCM clustering method that its performance tightly depends on the cluster center initialization, is applied for color ancient document image denoising (i.e., separate noise from text and background). Qualitative and quantitative assessments of results are deduced from a number of ancient document images collected from two different datasets.
{"title":"A Cluster Center Initialization Method using Hyperspace-based Multi-level Thresholding (HMLT): Application to Color Ancient Document Image Denoising","authors":"Walid Elhedda, Maroua Mehri, M. Mahjoub","doi":"10.1109/ACIT50332.2020.9300075","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300075","url":null,"abstract":"Many iterative supervised clustering algorithms such as K-means and its derivatives depend closely on the initial cluster center positions. In order to overcome the convergence problems inherent in the clustering algorithms (i.e., local optimum), and subsequently to avoid a drop in clustering performance, many researchers continue to propose novel efficient methods able to determine automatically the optimal cluster centers. Therefore, in this paper, we propose a simple and efficient cluster center initialization method, called hyperspace-based multi-level thresholding (HMLT). The proposed HMLT method is based on using a novel multi-level thresholding approach on the multi-dimensional representation of color images (called hyperspace). In order to show the high performance of the HMLT method, experiments have been conducted using a recent clustering method, called the hyperkernel-based intuitionistic fuzzy c-means (HKIFCM), and after initializing the cluster center positions randomly and by means of the HMLT method. The HKIFCM clustering method that its performance tightly depends on the cluster center initialization, is applied for color ancient document image denoising (i.e., separate noise from text and background). Qualitative and quantitative assessments of results are deduced from a number of ancient document images collected from two different datasets.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124830460","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300068
Dilip Singh Sisodia, Inakollu NehaPriyanka, P. Amulya
The contemporary recommender systems are facing challenges such as noise in user's choice, scalability, cold-start problem, availability of ample choices and handling of sparse data sets. In this paper, a multistage collaborative filtering is proposed to address the issues of noise in user's choice and ample choices availability. The two-stage filtering at first stage, filtering is performed using Pearson coefficient as a similarity measure and in the second stage, the longest common subsequence (LCS) is used to do filtering. The experiments are performed using benchmark 100k movielense datasets. The performance of multistage collaborative filtering is evaluated using accuracy, precision, recall, and f-measure. The results are also compared with single stage filtering and performance of multistage collaborative filtering is significantly improved over the used datasets.
{"title":"Longest Common Subsequence based Multistage Collaborative Filtering for Recommender Systems","authors":"Dilip Singh Sisodia, Inakollu NehaPriyanka, P. Amulya","doi":"10.1109/ACIT50332.2020.9300068","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300068","url":null,"abstract":"The contemporary recommender systems are facing challenges such as noise in user's choice, scalability, cold-start problem, availability of ample choices and handling of sparse data sets. In this paper, a multistage collaborative filtering is proposed to address the issues of noise in user's choice and ample choices availability. The two-stage filtering at first stage, filtering is performed using Pearson coefficient as a similarity measure and in the second stage, the longest common subsequence (LCS) is used to do filtering. The experiments are performed using benchmark 100k movielense datasets. The performance of multistage collaborative filtering is evaluated using accuracy, precision, recall, and f-measure. The results are also compared with single stage filtering and performance of multistage collaborative filtering is significantly improved over the used datasets.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128968678","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300086
Shynar Mussiraliyeva, M. Bolatbek, B. Omarov, Zhanar Medetbek, G. Baispay, R. Ospanov
Due to the activity of terrorist propaganda on the Internet and social networks, as well as given the high dynamics of the emergence of new sites and accounts of extremist orientation, it is important to quickly detect content that demonstrates a tendency to extremism in the prevention of extremist and terrorist activities. This article is intended to explore the possibilities of automatic recognition of extremist content using machine learning from this point of view. This article is devoted to the application of machine learning methods for solving the problem of security, in part-countering terrorism and extremism using information from the Internet.
{"title":"On Detecting Online Radicalization and Extremism Using Natural Language Processing","authors":"Shynar Mussiraliyeva, M. Bolatbek, B. Omarov, Zhanar Medetbek, G. Baispay, R. Ospanov","doi":"10.1109/ACIT50332.2020.9300086","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300086","url":null,"abstract":"Due to the activity of terrorist propaganda on the Internet and social networks, as well as given the high dynamics of the emergence of new sites and accounts of extremist orientation, it is important to quickly detect content that demonstrates a tendency to extremism in the prevention of extremist and terrorist activities. This article is intended to explore the possibilities of automatic recognition of extremist content using machine learning from this point of view. This article is devoted to the application of machine learning methods for solving the problem of security, in part-countering terrorism and extremism using information from the Internet.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127140150","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300063
N. Jaafar, N. A. Ismail, Yusman Azimi Yusoff
In Muslim life, there is an important ritual that they need to do in their daily lives, a prayer known as salat. There was evidence that showed performing salat correctly is good for better health. This paper developed a motion recognition system for salat movement using a cooperative multisensor approach based on salat law. Existing work in this related field could recognize a few salat movements; however, they could not cover salat movements based on salat law by using a single camera. This paper presents the motion recognition system's usability study, named SalatLab using a cooperative multisensor approach. In this paper, the user's error rate was evaluated by the SalatLab prototype and tutor-based method to test if the proposed system can bridge the gap in assessing user error. The experiment was conducted to evaluate the user error rate in salat activity by comparing it with the traditional tutor-based methodology. Success scores in recognizing salat movement and user acceptance of the proposed prototype have also been evaluated. The results show a significant difference in error rate and success score assessed by the proposed system and tutor-based. However, the proposed prototype was accepted by the user and received good feedback.
{"title":"A New Approach in Islamic Learning: Performance Evaluation of Motion Recognition System for Salat Movement","authors":"N. Jaafar, N. A. Ismail, Yusman Azimi Yusoff","doi":"10.1109/ACIT50332.2020.9300063","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300063","url":null,"abstract":"In Muslim life, there is an important ritual that they need to do in their daily lives, a prayer known as salat. There was evidence that showed performing salat correctly is good for better health. This paper developed a motion recognition system for salat movement using a cooperative multisensor approach based on salat law. Existing work in this related field could recognize a few salat movements; however, they could not cover salat movements based on salat law by using a single camera. This paper presents the motion recognition system's usability study, named SalatLab using a cooperative multisensor approach. In this paper, the user's error rate was evaluated by the SalatLab prototype and tutor-based method to test if the proposed system can bridge the gap in assessing user error. The experiment was conducted to evaluate the user error rate in salat activity by comparing it with the traditional tutor-based methodology. Success scores in recognizing salat movement and user acceptance of the proposed prototype have also been evaluated. The results show a significant difference in error rate and success score assessed by the proposed system and tutor-based. However, the proposed prototype was accepted by the user and received good feedback.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127279750","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300078
Deivanai Gurusamy, Sadik Abas
Wireless Sensor Network (WSN) has evolved as a key technology and has brought about a few changes in how the network is being adopted for modern applications. Despite the considerable growth and success, the limitation in the energy of sensor nodes persists. Researches have been rising to mitigate energy consumption by various energy management approaches, and the most efficient among them is clustering. Clustering groups the nodes according to their similarities or other parameters and helps to utilize the energy efficiently. However, it cannot wholly reduce energy consumption, so the WSN now adapts the advancement of energy harvesting (EH) and takes the new shape called EH-WSN. Energy harvesting converts the ambient energy into electrical energy and power the sensor nodes. By exploiting the recharging capabilities of this new technique, the network's lifetime is significantly increased. The performance enhancement is also crucial; hence, the energy harvesting nodes are clustered, and efficient clustering algorithms are being developed. This paper presents the clustering algorithms that have been developed newly and revised for EH-WSN. The parameters considered and that differ from the traditional clustering are analyzed. Further, the comparison among those approaches has facilitated the paper to bring out the challenges and future research directions in the clustering algorithms for EH-WSN.
{"title":"Modified Clustering Algorithms for Energy Harvesting Wireless Sensor Networks- A Survey","authors":"Deivanai Gurusamy, Sadik Abas","doi":"10.1109/ACIT50332.2020.9300078","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300078","url":null,"abstract":"Wireless Sensor Network (WSN) has evolved as a key technology and has brought about a few changes in how the network is being adopted for modern applications. Despite the considerable growth and success, the limitation in the energy of sensor nodes persists. Researches have been rising to mitigate energy consumption by various energy management approaches, and the most efficient among them is clustering. Clustering groups the nodes according to their similarities or other parameters and helps to utilize the energy efficiently. However, it cannot wholly reduce energy consumption, so the WSN now adapts the advancement of energy harvesting (EH) and takes the new shape called EH-WSN. Energy harvesting converts the ambient energy into electrical energy and power the sensor nodes. By exploiting the recharging capabilities of this new technique, the network's lifetime is significantly increased. The performance enhancement is also crucial; hence, the energy harvesting nodes are clustered, and efficient clustering algorithms are being developed. This paper presents the clustering algorithms that have been developed newly and revised for EH-WSN. The parameters considered and that differ from the traditional clustering are analyzed. Further, the comparison among those approaches has facilitated the paper to bring out the challenges and future research directions in the clustering algorithms for EH-WSN.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127583560","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9299965
D. Protić, M. Stankovic
Anomaly-based intrusion detection classifiers detect the notion of normality and classify both intrusion and/or misuse as either 'normal' or 'anomaly'. In complex computer networks, the number of the training records is often large which makes the evaluation of the classifiers computationally expensive. In this paper we present a feature selection and instances normalization algorithm that reduces the dimensionality of the dataset size, decrease processing time and increase accuracy of two classifier models, namely weighted k-Nearest Neighbor (wk-NN) and Feedforward Neural Network (FNN). The experiments are conducted on three daily records of the real computer network traffic data derived from the Kyoto 2006+ dataset. The results show high accuracy of both wk-NN and FNN classifiers but variations in mutual decisions on detected anomalies. Variations are determined with the novel hybrid model by performing logical exclusive or operation to the predicted outcomes. Improvement in the anomaly detection ranges from 0.67% to 8.08%.
{"title":"A Hybrid Model for Anomaly-Based Intrusion Detection in Complex Computer Networks","authors":"D. Protić, M. Stankovic","doi":"10.1109/ACIT50332.2020.9299965","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9299965","url":null,"abstract":"Anomaly-based intrusion detection classifiers detect the notion of normality and classify both intrusion and/or misuse as either 'normal' or 'anomaly'. In complex computer networks, the number of the training records is often large which makes the evaluation of the classifiers computationally expensive. In this paper we present a feature selection and instances normalization algorithm that reduces the dimensionality of the dataset size, decrease processing time and increase accuracy of two classifier models, namely weighted k-Nearest Neighbor (wk-NN) and Feedforward Neural Network (FNN). The experiments are conducted on three daily records of the real computer network traffic data derived from the Kyoto 2006+ dataset. The results show high accuracy of both wk-NN and FNN classifiers but variations in mutual decisions on detected anomalies. Variations are determined with the novel hybrid model by performing logical exclusive or operation to the predicted outcomes. Improvement in the anomaly detection ranges from 0.67% to 8.08%.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126254158","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 : 2020-11-28DOI: 10.1109/ACIT50332.2020.9300074
Maida Ahtesham, N. Bawany, Kiran Fatima
House prices are a significant impression of the economy, and its value ranges are of great concerns for the clients and property dealers. Housing price escalate every year that eventually reinforced the need of strategy or technique that could predict house prices in future. There are certain factors that influence house prices including physical conditions, locations, number of bedrooms and others. Traditionally predictions are made on the basis of these factors. However such prediction methods require an appropriate knowledge and experience regarding this domain. Machine Learning techniques have been a significant source of advanced opportunities to analyze, predict and visualize housing prices. In this paper, Gradient Boosting Model XGBoost is utilized to predict housing prices. Publicly available dataset containing 38,961 records of Karachi city is attained from an Open Real Estate Portal of Pakistan. Lot of work has been done in predicting house prices across many countries, however very limited amount of work has been done for predicting house prices in Pakistan. Our proposed house price prediction model is able to predict 98% accuracy.
{"title":"House Price Prediction using Machine Learning Algorithm - The Case of Karachi City, Pakistan","authors":"Maida Ahtesham, N. Bawany, Kiran Fatima","doi":"10.1109/ACIT50332.2020.9300074","DOIUrl":"https://doi.org/10.1109/ACIT50332.2020.9300074","url":null,"abstract":"House prices are a significant impression of the economy, and its value ranges are of great concerns for the clients and property dealers. Housing price escalate every year that eventually reinforced the need of strategy or technique that could predict house prices in future. There are certain factors that influence house prices including physical conditions, locations, number of bedrooms and others. Traditionally predictions are made on the basis of these factors. However such prediction methods require an appropriate knowledge and experience regarding this domain. Machine Learning techniques have been a significant source of advanced opportunities to analyze, predict and visualize housing prices. In this paper, Gradient Boosting Model XGBoost is utilized to predict housing prices. Publicly available dataset containing 38,961 records of Karachi city is attained from an Open Real Estate Portal of Pakistan. Lot of work has been done in predicting house prices across many countries, however very limited amount of work has been done for predicting house prices in Pakistan. Our proposed house price prediction model is able to predict 98% accuracy.","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126842407","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 : 2020-11-28DOI: 10.1109/acit50332.2020.9300076
{"title":"Copyright","authors":"","doi":"10.1109/acit50332.2020.9300076","DOIUrl":"https://doi.org/10.1109/acit50332.2020.9300076","url":null,"abstract":"","PeriodicalId":193891,"journal":{"name":"2020 21st International Arab Conference on Information Technology (ACIT)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121522698","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：