Journal of Theoretical and Applied Information Technology
High efficiency video coding (HEVC) is the newest video coding generation of the ITU-T and ISO/IE... more High efficiency video coding (HEVC) is the newest video coding generation of the ITU-T and ISO/IEC, which first appeared in January 2013. It has the advantage of reducing the bit rate by as much as 50 %when compared to H.264 while maintaining the same visual quality. In the last decade, authentication and copyright protection methodologies have become one of the essential items in order to protect video contents by embedding within an efficient video codec. Thus, the objective of this paper is to revise recent developments in the area of watermarking techniques for video coding schemes and their applicability to the new Standard HEVC. The results of this study provide motivation to achieve a higher embedding capacity and higher compression performance for HEVC compared to H.264/AVC especially, for low bitrate coding.
The Arabic language has many different dialects and it must be recognized before using the automa... more The Arabic language has many different dialects and it must be recognized before using the automatic speech recognition (ASR). On the other hand, it is observed in all Arab countries that the standard Arabic language is widely written and used in an official speech, newspapers, public administration, and schools but it is not used in daily conversations instead the dialect is widely spoken in daily life and rarely written. In this paper, we examine the difficult task of properly identifying various Arabic dialects and propose a system developed to identify a set of four regional and modern standard Arabic speeches, based on speech recognition using Hidden Markov Models (HMMs) algorithms. HMMs have become a very popular way to build a speech recognition system. It is set as hidden states and possibilities of transition from one state to another. Due to the similarities and differences between the Arabic dialects, speeches collected from the ADI5 datasets were retrieved from the MGB-3...
The wide technical evolution of the use of data mining technology in dealing with huge electronic... more The wide technical evolution of the use of data mining technology in dealing with huge electronic datasets is increasing day by day. This great and growing progress motivates us to employ this technology in dealing with the municipality's social data. The municipality is an organizational structure that includes a number of departments, offices and service localities that deal with sectors, citizens and businesses in a specific geographical area. Within the municipality there are areas affiliated to the municipality, which we called in Libya as "Al-Mahalla." This "Mahalla" represents an administrative division belonging to the municipality. There are social data represented in a dataset about the citizens residing in Al-Mahalla, which belongs to the municipality. The dataset holds a general statistical data on the citizens residing in the municipality, as well as the "Al-Mahalla" inhabited by the citizens. In this study, we will address the municipality of Al-Khums in Libya, as one of the municipalities in Libya as a case study. In this paper, we will use classification and clustering methods to extract knowledge from social data and predict marriage rate, death rate, poverty rate and rate of increase or decrease of citizens in the municipality, which in turn helps leaders and decision makers in the municipality to make the appropriate decision. As well as it aims to discuss the impact of the municipality's social data on the current Libyan lifestyle. We used also Weka software as a data mining solution to apply classification and clustering methods on the datasets we obtained from the municipality.
The Arabic language has many different dialects and it must be recognized before using the automa... more The Arabic language has many different dialects and it must be recognized before using the automatic speech recognition (ASR). On the other hand, it is observed in all Arab countries that the standard Arabic language is widely written and used in an official speech, newspapers, public administration, and schools but it is not used in daily conversations instead the dialect is widely spoken in daily life and rarely written. In this paper, we examine the difficult task of properly identifying various Arabic dialects and propose a system developed to identify a set of four regional and modern standard Arabic speeches, based on speech recognition using Hidden Markov Models (HMMs) algorithms. HMMs have become a very popular way to build a speech recognition system. It is set as hidden states and possibilities of transition from one state to another. Due to the similarities and differences between the Arabic dialects, speeches collected from the ADI5 datasets were retrieved from the MGB-3 challenge source. We proposed an Arabic Dialect Identification System called "Building a System for Arabic Dialects Identification based on Speech Recognition using Hidden Markov Models (HMMs)" that takes Input as speech utterances and produces output as dialect being spoken. During the training phase, speech utterances from one or more dialects were analyzed to capture the important properties of audio signals in terms of time and frequency. During the testing phase, previously unseen test utterances were utilized to the system, and the system outputs the dialect associated with the model of dialect that most closely matches the test utterance. The proposed model of the system shows promising results of the model for each dialect match.
The importance of recommendation systems is increasing day by day due to the massive number of da... more The importance of recommendation systems is increasing day by day due to the massive number of data and information-overloaded arising from the internet. This data can be collected in predictive datasets; these datasets can be processed and analysed via data mining methods. In this paper, an efficient hybrid movie recommender system has been designed using the association rules mining technique and K-nearest neighbours (KNN) algorithm as a classification method. The K-nearest neighbours (KNN) algorithm subsystem was used to create the first candidate list through a practical MovieLens dataset, which was retrieved from the source of the NetFlix network. Beside, the Apriori algorithm subsystem is used to analyse the same dataset and create the second list. Finally, the proposed system creates a final recommended list by matching the two lists. The results of the proposed system provide better performance than the existing systems in terms of the important degree. The important degree ...
In fact, millions of people in the world speak many languages. In order to communicate with each ... more In fact, millions of people in the world speak many languages. In order to communicate with each other, it is necessary to know the language we use to perform this operation. The Arabic language has many different dialects and it must be recognized before using the automatic speech recognition (ASR). On the other hand, it is observed in all Arab countries that the standard Arabic language is widely written and used in an official speech, newspapers, public administration, and schools but it is not used in the daily conversations instead the dialect is widely spoken in daily life and rarely written. In this paper, we examine the difficult task of properly identifying various Arabic dialects and propose a system developed to identify a set of four regional and modern standard Arabic speeches, based on speech recognition using Hidden Markov Models (HMMs) algorithms. HMMs have become a very popular way to build a speech recognition system. It is set as hidden states and possibilities of...
The importance of recommendation systems is increasing day by day due to the massive number of da... more The importance of recommendation systems is increasing day by day due to the massive number of data and information-overloaded arising from the internet. This data can be collected in predictive datasets; these datasets can be processed and analysed via data mining methods. In this paper, an efficient hybrid movie recommender system has been designed using the association rules mining technique and K-nearest neighbours (KNN) algorithm as a classification method. The K-nearest neighbours (KNN) algorithm subsystem was used to create the first candidate list through a practical MovieLens dataset, which was retrieved from the source of the NetFlix network. Besides, the Apriori algorithm subsystem is used to analyse the same dataset and create the second list. Finally, the proposed system creates a final recommended list by matching the two lists. The results of the proposed system provide better performance than the existing systems in terms of the important degree. The important degree gives a better accuracy rate than the existing techniques used.
International Journal of Circuits, Systems and Signal Processing, 2022
Recently, the main critical part of all organizational data systems is the security since it is t... more Recently, the main critical part of all organizational data systems is the security since it is threatened by several network attacks which in turn influences on the world financial system. Thus, the most used system in dealing with networks problems is the Intrusion Detection System (IDS). It is used to monitor the system performance and send alerts when there is anomalous activity existence in which the administrator of the system should respond to these alerts rapidly. In this paper, we proposed a statistical Naïve Bayesian method which will be used in the Intrusion Detection Systems ( IDS) systems in different scenarios such as analyzing the HTTP service based traffic and identify the HTTP normal connections and attacks. On the other hand, a comparative study between them based on the performance parameters will be analyzed in order to determine the most effective and efficient statistical method in detecting various types of attacks.
In this paper, we propose a hybrid IBTC-DWT encoding a digital image. The method combines the sim... more In this paper, we propose a hybrid IBTC-DWT encoding a digital image. The method combines the simple computation and edge preservation prosperities of interpolative block truncation coding(IBTC) and high compression ratio of discrete wavelet transform(DWT), implemented with significantly lower coding delay than DWT alone, and to achieve a reduced bit rate is also proposed and investigated. In this hybrid IBTC-DWT algorithm, the resulting high-means and low-means sub images from IBTC algorithm are coded using DWT transform. Simulation results showed that good performance was demonstrated in terms of compression ratio, bit rate and reconstruction quality. It is generally shown that this IBTC-DWT algorithm gives good quality reconstructed images at low bit rate compared to IBTC-DCT algorithm. Key-Words: Images Compression, Block Truncation Coding, Discrete Wavelet Transform.
Web usage mining (WUM) focuses on the discovering of potential knowledge from browsing patterns o... more Web usage mining (WUM) focuses on the discovering of potential knowledge from browsing patterns of the users. It leads us to find the correlation between pages in the analysis stage. The primary data source used in web usage mining is the server log-files (web-logs). Browsing web pages by the user leaves a lot of information in the log-file. Analyzing log-files information drives us to understand the behavior of the user. Web-logs include web server access logs and application server logs. Web-log is an essential part for web mining to extract the usage patterns and study the visiting characteristics of user. Our paper focus on the use of web mining techniques to classify web pages type according to user visits. This classification helps us to understand the user behavior. Also we will use some classification and association rule techniques for discovering the potential knowledge from the browsing patterns.
This paper is a comprehensive study of an Ad Hoc wireless network which is a wireless network wit... more This paper is a comprehensive study of an Ad Hoc wireless network which is a wireless network without any central controlling authority which is a collection of mobile nodes that are dynamically and arbitrarily located in such a manner that the interconnections between nodes are capable of changing on a continual basis, so nodes cooperate to route a packet. The purpose of the routing protocol is to discover rapid changes of the topology in such a way that intermediate nodes can act as routers to forward packets on behalf of the communicating pair . Route construction should be done with a minimum of overhead and bandwidth consumption. In configuration, topology management issues are even more important in the context of ad hoc wireless networks. This paper provides an overview of three routing protocols by presenting their characteristics and functionality to exchange and use different type of information (text, image, video and voice) as database, Email, video conferencing, voice, ...
The purpose of this work is to Identifying Cancer Patients using DNA Micro-Array Data that use DN... more The purpose of this work is to Identifying Cancer Patients using DNA Micro-Array Data that use DNA chains which contain informational code to composition of the human body, methods are based on the idea of selecting a gene subset to distinguish all classes, it will be more effective to solve a multi-class problem, and we will propose a genetic programming (GP) based approach to deal with the gene selection and classification tasks for biological datasets. This biological dataset will be derived from multiple biological databases. The procedure responsible for extracting datasets called DNA-Aggregator. We will design a biological aggregator, which aggregates various datasets via DNA micro-array community-developed ontology. Our aggregator is composed of modules that retrieve the data from various biological databases. It will also enable queries by other applications to recognize the genes. The genes will be categorized in groups based on a classification method, which collects simil...
This paper presents the application of Multi Layer Perceptron (MLP) Artificial Neural Network to ... more This paper presents the application of Multi Layer Perceptron (MLP) Artificial Neural Network to classification of handwritten Arabic words. Zernik Moments are used as a feature vector for each word. An efficient way to select the most suitable order of Zernik moments is also presented. The MLP is trained in a supervised fashion using the Back Propagation learning algorithm. Having being trained, the MLP is tested on different set of handwritten Arabic words that has never been seen by the MLP. Several experiments are performed to select the best MLP structure. Experimental results have shown that with the presented structure and the order of the Zernik Moments more than 87% of correct recognition was obtained.
Abstract—Lossless image compression techniques are used in digital imaging where large amount of ... more Abstract—Lossless image compression techniques are used in digital imaging where large amount of data is to be stored without compromising the image quality. The volume of data that can be compressed using lossless image compression schemes is usually much ...
In fact, millions of people in the world speak many languages. In order to communicate with each ... more In fact, millions of people in the world speak many languages. In order to communicate with each other, it is necessary to know the language we use to perform this operation. The Arabic language has many different dialects and it must be recognized before using the automatic speech recognition (ASR). On the other hand, it is observed in all Arab countries that the standard Arabic language is widely written and used in an official speech, newspapers, public administration, and schools but it is not used in the daily conversations instead the dialect is widely spoken in daily life and rarely written. In this paper, we examine the difficult task of properly identifying various Arabic dialects and propose a system developed to identify a set of four regional and modern standard Arabic speeches, based on speech recognition using Hidden Markov Models (HMMs) algorithms. HMMs have become a very popular way to build a speech recognition system. It is set as hidden states and possibilities of transition from one state to another. Due to the similarities and differences between the Arabic dialects, speeches collected from the ADI5 datasets were retrieved from the MGB-3 challenge source. We proposed an Arabic Dialect Identification System called "Building a System for Arabic Dialects Identification based on Speech Recognition using Hidden Markov Models (HMMs)" that takes Input as speech utterances and produces output as dialect being spoken. During the training phase, speech utterances from one or more dialects were analyzed to capture the important properties of audio signals in terms of time and frequency. During the testing phase, previously unseen test utterances were utilized to the system, and the system outputs the dialect associated with the model of dialect that most closely matches the test utterance. The proposed model of the system shows promising results of the model for each dialects match.
International Journal of Circuits, Systems and Signal Processing, 2022
Recently, the main critical part of all organizational data systems is the security since it is t... more Recently, the main critical part of all organizational data systems is the security since it is threatened by several network attacks which in turn influences on the world financial system. Thus, the most used system in dealing with networks problems is the Intrusion Detection System (IDS). It is used to monitor the system performance and send alerts when there is anomalous activity existence in which the administrator of the system should respond to these alerts rapidly. In this paper, we proposed a statistical Naïve Bayesian method which will be used in the Intrusion Detection Systems (IDS) systems in different scenarios such as analyzing the HTTP service based traffic and identify the HTTP normal connections and attacks. On the other hand, a comparative study between them based on the performance parameters will be analyzed in order to determine the most effective and efficient statistical method in detecting various types of attacks.
Journal of Theoretical and Applied Information Technology
High efficiency video coding (HEVC) is the newest video coding generation of the ITU-T and ISO/IE... more High efficiency video coding (HEVC) is the newest video coding generation of the ITU-T and ISO/IEC, which first appeared in January 2013. It has the advantage of reducing the bit rate by as much as 50 %when compared to H.264 while maintaining the same visual quality. In the last decade, authentication and copyright protection methodologies have become one of the essential items in order to protect video contents by embedding within an efficient video codec. Thus, the objective of this paper is to revise recent developments in the area of watermarking techniques for video coding schemes and their applicability to the new Standard HEVC. The results of this study provide motivation to achieve a higher embedding capacity and higher compression performance for HEVC compared to H.264/AVC especially, for low bitrate coding.
The Arabic language has many different dialects and it must be recognized before using the automa... more The Arabic language has many different dialects and it must be recognized before using the automatic speech recognition (ASR). On the other hand, it is observed in all Arab countries that the standard Arabic language is widely written and used in an official speech, newspapers, public administration, and schools but it is not used in daily conversations instead the dialect is widely spoken in daily life and rarely written. In this paper, we examine the difficult task of properly identifying various Arabic dialects and propose a system developed to identify a set of four regional and modern standard Arabic speeches, based on speech recognition using Hidden Markov Models (HMMs) algorithms. HMMs have become a very popular way to build a speech recognition system. It is set as hidden states and possibilities of transition from one state to another. Due to the similarities and differences between the Arabic dialects, speeches collected from the ADI5 datasets were retrieved from the MGB-3...
The wide technical evolution of the use of data mining technology in dealing with huge electronic... more The wide technical evolution of the use of data mining technology in dealing with huge electronic datasets is increasing day by day. This great and growing progress motivates us to employ this technology in dealing with the municipality's social data. The municipality is an organizational structure that includes a number of departments, offices and service localities that deal with sectors, citizens and businesses in a specific geographical area. Within the municipality there are areas affiliated to the municipality, which we called in Libya as "Al-Mahalla." This "Mahalla" represents an administrative division belonging to the municipality. There are social data represented in a dataset about the citizens residing in Al-Mahalla, which belongs to the municipality. The dataset holds a general statistical data on the citizens residing in the municipality, as well as the "Al-Mahalla" inhabited by the citizens. In this study, we will address the municipality of Al-Khums in Libya, as one of the municipalities in Libya as a case study. In this paper, we will use classification and clustering methods to extract knowledge from social data and predict marriage rate, death rate, poverty rate and rate of increase or decrease of citizens in the municipality, which in turn helps leaders and decision makers in the municipality to make the appropriate decision. As well as it aims to discuss the impact of the municipality's social data on the current Libyan lifestyle. We used also Weka software as a data mining solution to apply classification and clustering methods on the datasets we obtained from the municipality.
The Arabic language has many different dialects and it must be recognized before using the automa... more The Arabic language has many different dialects and it must be recognized before using the automatic speech recognition (ASR). On the other hand, it is observed in all Arab countries that the standard Arabic language is widely written and used in an official speech, newspapers, public administration, and schools but it is not used in daily conversations instead the dialect is widely spoken in daily life and rarely written. In this paper, we examine the difficult task of properly identifying various Arabic dialects and propose a system developed to identify a set of four regional and modern standard Arabic speeches, based on speech recognition using Hidden Markov Models (HMMs) algorithms. HMMs have become a very popular way to build a speech recognition system. It is set as hidden states and possibilities of transition from one state to another. Due to the similarities and differences between the Arabic dialects, speeches collected from the ADI5 datasets were retrieved from the MGB-3 challenge source. We proposed an Arabic Dialect Identification System called "Building a System for Arabic Dialects Identification based on Speech Recognition using Hidden Markov Models (HMMs)" that takes Input as speech utterances and produces output as dialect being spoken. During the training phase, speech utterances from one or more dialects were analyzed to capture the important properties of audio signals in terms of time and frequency. During the testing phase, previously unseen test utterances were utilized to the system, and the system outputs the dialect associated with the model of dialect that most closely matches the test utterance. The proposed model of the system shows promising results of the model for each dialect match.
The importance of recommendation systems is increasing day by day due to the massive number of da... more The importance of recommendation systems is increasing day by day due to the massive number of data and information-overloaded arising from the internet. This data can be collected in predictive datasets; these datasets can be processed and analysed via data mining methods. In this paper, an efficient hybrid movie recommender system has been designed using the association rules mining technique and K-nearest neighbours (KNN) algorithm as a classification method. The K-nearest neighbours (KNN) algorithm subsystem was used to create the first candidate list through a practical MovieLens dataset, which was retrieved from the source of the NetFlix network. Beside, the Apriori algorithm subsystem is used to analyse the same dataset and create the second list. Finally, the proposed system creates a final recommended list by matching the two lists. The results of the proposed system provide better performance than the existing systems in terms of the important degree. The important degree ...
In fact, millions of people in the world speak many languages. In order to communicate with each ... more In fact, millions of people in the world speak many languages. In order to communicate with each other, it is necessary to know the language we use to perform this operation. The Arabic language has many different dialects and it must be recognized before using the automatic speech recognition (ASR). On the other hand, it is observed in all Arab countries that the standard Arabic language is widely written and used in an official speech, newspapers, public administration, and schools but it is not used in the daily conversations instead the dialect is widely spoken in daily life and rarely written. In this paper, we examine the difficult task of properly identifying various Arabic dialects and propose a system developed to identify a set of four regional and modern standard Arabic speeches, based on speech recognition using Hidden Markov Models (HMMs) algorithms. HMMs have become a very popular way to build a speech recognition system. It is set as hidden states and possibilities of...
The importance of recommendation systems is increasing day by day due to the massive number of da... more The importance of recommendation systems is increasing day by day due to the massive number of data and information-overloaded arising from the internet. This data can be collected in predictive datasets; these datasets can be processed and analysed via data mining methods. In this paper, an efficient hybrid movie recommender system has been designed using the association rules mining technique and K-nearest neighbours (KNN) algorithm as a classification method. The K-nearest neighbours (KNN) algorithm subsystem was used to create the first candidate list through a practical MovieLens dataset, which was retrieved from the source of the NetFlix network. Besides, the Apriori algorithm subsystem is used to analyse the same dataset and create the second list. Finally, the proposed system creates a final recommended list by matching the two lists. The results of the proposed system provide better performance than the existing systems in terms of the important degree. The important degree gives a better accuracy rate than the existing techniques used.
International Journal of Circuits, Systems and Signal Processing, 2022
Recently, the main critical part of all organizational data systems is the security since it is t... more Recently, the main critical part of all organizational data systems is the security since it is threatened by several network attacks which in turn influences on the world financial system. Thus, the most used system in dealing with networks problems is the Intrusion Detection System (IDS). It is used to monitor the system performance and send alerts when there is anomalous activity existence in which the administrator of the system should respond to these alerts rapidly. In this paper, we proposed a statistical Naïve Bayesian method which will be used in the Intrusion Detection Systems ( IDS) systems in different scenarios such as analyzing the HTTP service based traffic and identify the HTTP normal connections and attacks. On the other hand, a comparative study between them based on the performance parameters will be analyzed in order to determine the most effective and efficient statistical method in detecting various types of attacks.
In this paper, we propose a hybrid IBTC-DWT encoding a digital image. The method combines the sim... more In this paper, we propose a hybrid IBTC-DWT encoding a digital image. The method combines the simple computation and edge preservation prosperities of interpolative block truncation coding(IBTC) and high compression ratio of discrete wavelet transform(DWT), implemented with significantly lower coding delay than DWT alone, and to achieve a reduced bit rate is also proposed and investigated. In this hybrid IBTC-DWT algorithm, the resulting high-means and low-means sub images from IBTC algorithm are coded using DWT transform. Simulation results showed that good performance was demonstrated in terms of compression ratio, bit rate and reconstruction quality. It is generally shown that this IBTC-DWT algorithm gives good quality reconstructed images at low bit rate compared to IBTC-DCT algorithm. Key-Words: Images Compression, Block Truncation Coding, Discrete Wavelet Transform.
Web usage mining (WUM) focuses on the discovering of potential knowledge from browsing patterns o... more Web usage mining (WUM) focuses on the discovering of potential knowledge from browsing patterns of the users. It leads us to find the correlation between pages in the analysis stage. The primary data source used in web usage mining is the server log-files (web-logs). Browsing web pages by the user leaves a lot of information in the log-file. Analyzing log-files information drives us to understand the behavior of the user. Web-logs include web server access logs and application server logs. Web-log is an essential part for web mining to extract the usage patterns and study the visiting characteristics of user. Our paper focus on the use of web mining techniques to classify web pages type according to user visits. This classification helps us to understand the user behavior. Also we will use some classification and association rule techniques for discovering the potential knowledge from the browsing patterns.
This paper is a comprehensive study of an Ad Hoc wireless network which is a wireless network wit... more This paper is a comprehensive study of an Ad Hoc wireless network which is a wireless network without any central controlling authority which is a collection of mobile nodes that are dynamically and arbitrarily located in such a manner that the interconnections between nodes are capable of changing on a continual basis, so nodes cooperate to route a packet. The purpose of the routing protocol is to discover rapid changes of the topology in such a way that intermediate nodes can act as routers to forward packets on behalf of the communicating pair . Route construction should be done with a minimum of overhead and bandwidth consumption. In configuration, topology management issues are even more important in the context of ad hoc wireless networks. This paper provides an overview of three routing protocols by presenting their characteristics and functionality to exchange and use different type of information (text, image, video and voice) as database, Email, video conferencing, voice, ...
The purpose of this work is to Identifying Cancer Patients using DNA Micro-Array Data that use DN... more The purpose of this work is to Identifying Cancer Patients using DNA Micro-Array Data that use DNA chains which contain informational code to composition of the human body, methods are based on the idea of selecting a gene subset to distinguish all classes, it will be more effective to solve a multi-class problem, and we will propose a genetic programming (GP) based approach to deal with the gene selection and classification tasks for biological datasets. This biological dataset will be derived from multiple biological databases. The procedure responsible for extracting datasets called DNA-Aggregator. We will design a biological aggregator, which aggregates various datasets via DNA micro-array community-developed ontology. Our aggregator is composed of modules that retrieve the data from various biological databases. It will also enable queries by other applications to recognize the genes. The genes will be categorized in groups based on a classification method, which collects simil...
This paper presents the application of Multi Layer Perceptron (MLP) Artificial Neural Network to ... more This paper presents the application of Multi Layer Perceptron (MLP) Artificial Neural Network to classification of handwritten Arabic words. Zernik Moments are used as a feature vector for each word. An efficient way to select the most suitable order of Zernik moments is also presented. The MLP is trained in a supervised fashion using the Back Propagation learning algorithm. Having being trained, the MLP is tested on different set of handwritten Arabic words that has never been seen by the MLP. Several experiments are performed to select the best MLP structure. Experimental results have shown that with the presented structure and the order of the Zernik Moments more than 87% of correct recognition was obtained.
Abstract—Lossless image compression techniques are used in digital imaging where large amount of ... more Abstract—Lossless image compression techniques are used in digital imaging where large amount of data is to be stored without compromising the image quality. The volume of data that can be compressed using lossless image compression schemes is usually much ...
In fact, millions of people in the world speak many languages. In order to communicate with each ... more In fact, millions of people in the world speak many languages. In order to communicate with each other, it is necessary to know the language we use to perform this operation. The Arabic language has many different dialects and it must be recognized before using the automatic speech recognition (ASR). On the other hand, it is observed in all Arab countries that the standard Arabic language is widely written and used in an official speech, newspapers, public administration, and schools but it is not used in the daily conversations instead the dialect is widely spoken in daily life and rarely written. In this paper, we examine the difficult task of properly identifying various Arabic dialects and propose a system developed to identify a set of four regional and modern standard Arabic speeches, based on speech recognition using Hidden Markov Models (HMMs) algorithms. HMMs have become a very popular way to build a speech recognition system. It is set as hidden states and possibilities of transition from one state to another. Due to the similarities and differences between the Arabic dialects, speeches collected from the ADI5 datasets were retrieved from the MGB-3 challenge source. We proposed an Arabic Dialect Identification System called "Building a System for Arabic Dialects Identification based on Speech Recognition using Hidden Markov Models (HMMs)" that takes Input as speech utterances and produces output as dialect being spoken. During the training phase, speech utterances from one or more dialects were analyzed to capture the important properties of audio signals in terms of time and frequency. During the testing phase, previously unseen test utterances were utilized to the system, and the system outputs the dialect associated with the model of dialect that most closely matches the test utterance. The proposed model of the system shows promising results of the model for each dialects match.
International Journal of Circuits, Systems and Signal Processing, 2022
Recently, the main critical part of all organizational data systems is the security since it is t... more Recently, the main critical part of all organizational data systems is the security since it is threatened by several network attacks which in turn influences on the world financial system. Thus, the most used system in dealing with networks problems is the Intrusion Detection System (IDS). It is used to monitor the system performance and send alerts when there is anomalous activity existence in which the administrator of the system should respond to these alerts rapidly. In this paper, we proposed a statistical Naïve Bayesian method which will be used in the Intrusion Detection Systems (IDS) systems in different scenarios such as analyzing the HTTP service based traffic and identify the HTTP normal connections and attacks. On the other hand, a comparative study between them based on the performance parameters will be analyzed in order to determine the most effective and efficient statistical method in detecting various types of attacks.
Uploads
Papers by Zakaria Zubi