Anwar Rehman - Academia.edu (original) (raw)

Papers by Anwar Rehman

2017 23rd International Conference on Automation and Computing (ICAC)

The smartphones have become the basic necessity of life. Users are being authenticated on mobile ... more The smartphones have become the basic necessity of life. Users are being authenticated on mobile devices using PINs, password, swipe, etc. However, the existing authentication mechanisms are not resilient against modern security attacks. With the increase of touch devices, gesture-based authentication behaviour becomes more important. This paper analyzes the distinctness of a gesture in a touch base mobile device. Analysis show that specific user has distinct gesture of different fingers. Experimental study reveals that finger accuracy in a gesture-based authentication is increased by an individual's index finger and thumbs. Furthermore, the results show that the accuracy and efficiency of a gesture-based lock depends on the phone's position, portrait mode, left or right-handed user, and single or double hand user style.

2018 24th International Conference on Automation and Computing (ICAC), 2018

Plagiarism is an act of presenting someone else's idea, words and original work as one's ... more Plagiarism is an act of presenting someone else's idea, words and original work as one's own without acknowledging the original source. It creates many problems, especially for academic institutions and researchers. There are many plagiarism detection tools publically available which are used to overcome these problems, however these tools mainly work for particular languages like Arabic and English. In South Asian countries specifically India and Pakistan, a huge part of research content is available in Hindi and Urdu languages. Unfortunately, plagiarism detection in Urdu text cannot acquire the proper attention of research community because it has complex sentence structure and lacks linguistic resources. In this paper, we propose a novel framework for plagiarism detection specifically for Urdu language. There is no benchmark corpus available for Urdu plagiarism detection, and therefore we developed a corpus of Urdu language. We applied distance measuring method along with vector space method to measure the similarity between suspicious and source text. For evaluation purpose, we defined different classes of plagiarized text such as paraphrase, heavily plagiarized, light plagiarized and direct copy-paste. Moreover, we evaluated each class of plagiarized text in terms of precision, recall, and f-measure. The experimental results have presented that Levenshiten distance and Jaccard containment methods produced significant improvement in the performance of plagiarism detection compared with existing methods.

2018 14th International Conference on Emerging Technologies (ICET), 2018

Plagiarism, intellectual theft, and copyright violation are the most important problems for resea... more Plagiarism, intellectual theft, and copyright violation are the most important problems for researchers and academic organizations such as universities. The famous publicly available Plagiarism Detection (PD) tools are Turnitin, APlagramme, Plagscan, and Aplag and these tools use to overcome plagiarism problems. However, these tools mainly work for English, Persian and Arabic languages. Copyright and intellectual document have written in every language of the world and many South Asian countries including Pakistan and India, a huge amount of academic content is available in the Urdu language. Unfortunately, due to resources scarcity and less concentration of researcher There is no enough work has been done in Urdu PD. Capturing of plagiarism in Urdu is presented in this paper. Most existing Urdu PD systems fail to identify paraphrase plagiarism in comparison between suspicious and source text document. However, the proposed system is able to identify different types of plagiarism like sentence reordering, inert/delete inter-textual similarity and near copy similarity. The proposed system is based on a distance measuring method, structural alignment algorithm, and vector space model. The system performance is evaluated using machine learning classifiers i.e. Support Vector Machine and Naïve Bayes. The experimental results demonstrated that performance of the proposed method is improved as compared to other existing model i.e. cosine method, simple Jaccard measure.

In this paper, an energy management controller (EMC) is designed using three optimization techniq... more In this paper, an energy management controller (EMC) is designed using three optimization techniques: harmony search algorithm (HSA), firefly algorithm (FA) and enhanced differential evolution (EDE). The objectives of this work are to minimize electricity cost as well as peak to average ratio (PAR) while maintaining the user comfort (UC). Critical peak pricing (CPP) is used for the calculation of electricity bill. The trade-off between UC and electricity cost is exploited in such a way that a stability is achieved among UC and electricity price that is preferred by the consumer. Reduction in PAR is beneficial for both consumer and utility as it provides stability to the electric grid.

Electricity is a valuable resource. With the increase of population, this valuable resource is be... more Electricity is a valuable resource. With the increase of population, this valuable resource is being used inefficiently. To overcome this problem, electricity providers use various techniques like introducing different pricing schemes. In peak hours, when the usage of electricity is high, the utility increases the per unit cost. Therefore, usage of electricity in peak hours result in high electricity bills. The electricity bills can be reduced by efficiently scheduling the home appliances so that few appliances are operated during peak hours. For this purpose many techniques have been proposed. In this paper, we propose a Social Spider Algorithm (SSA) for Demand Side Management (DSM). Harmony Search Algorithm (HSA) has been adapted to evaluate the results of SSA. These algorithms schedules the appliances in such a way that the usage of electricity in peak hours is reduced. This results in reduction of electricity bill and Peak to Average Ratio (PAR).

2019 25th International Conference on Automation and Computing (ICAC), 2019

Digital text is increasing rapidly on the Internet with the excessive use of social media. For th... more Digital text is increasing rapidly on the Internet with the excessive use of social media. For this reason, it is very challenging to extract effective information from the digital text due its high dimensionality, sparseness and big data. In this paper, we study the powerful nonparametric Bayesian topic model which is Hierarchical Latent Dirichlet Allocation (hLDA). We deal the issue of learning topics hierarchies from Urdu text data. The presented Topic Model for Urdu is combined with preprocessing activities, hLDA model, and Gibbs Sampling (GS) algorithm. We present hLDA base topic model called Urdu Hierarchical Latent Dirichlet Allocation (uhLDA). Empirical study showed that uhLDA effectively learns the topics hierarchies from 5000 Urdu text documents. Furthermore, we evaluated the results using Pointwise Mutual information (PMI) and it shows that uhLDA outperforms as compared to existing standard topic model LDA.

2018 24th International Conference on Automation and Computing (ICAC), 2018

Natural Language Processing (NLP) is a branch of Artificial Intelligence to help computers manipu... more Natural Language Processing (NLP) is a branch of Artificial Intelligence to help computers manipulate and interpret human languages. In NLP, text mining is a technique to derive useful information from text. Topic Model (TM) is a statistical model to extract topics from a large collection of unlabeled text using NLP and machine learning techniques. Several effective TM are available to fulfill the needs of various languages like English, German, Arabic etc. However no compelling TM is available for poor resource South Asian language Urdu. In this research study, our focus is to work on existing TM like Latent Dirichlet Allocation (LDA) to overcome the issues of Urdu language in text mining. We studied and analyzed LDA as an unsupervised model for the Urdu topic identification. Hence, we studied LDA deeply for Urdu topic identification at two levels: Variational Bayes (VB) based LDA for Urdu (VB-ULDA) with stemmer and without stemmer. Experiments are performed on a self-created massive number of Urdu documents in four different corpora. Experimental study shows that VB-ULDA outperformed in the identification of topics from Urdu text documents as compared to existing Urdu LDA (ULDA) in terms of accuracy and efficiency and results also reveal the high impact of stemming algorithm in Urdu topic identification.

Advances on Broad-Band Wireless Computing, Communication and Applications, 2017

In this paper, performance of energy management controller (EMC) based on meta-heuristic algorith... more In this paper, performance of energy management controller (EMC) based on meta-heuristic algorithms: Harmony Search Algorithm (HSA) and Firefly Algorithm (FA) are evaluated. Critical peak pricing (CPP) scheme is implemented to calculate the electricity cost. Appliances are categorized into three groups on the basis of power consumption. Electricity cost minimization and electricity load shifting from peak hours towards off peak hours are the main objectives of the paper. In simulation results, adopted approach reduces the Peak to Average Ratio (PAR) and total electricity cost. Furthermore, HSA shows better results than FA in terms of PAR and electricity cost.

Multimedia Tools and Applications, 2019

Nowadays, social media has become a tremendous source of acquiring user's opinions. With the adva... more Nowadays, social media has become a tremendous source of acquiring user's opinions. With the advancement of technology and sophistication of the internet, a huge amount of data is generated from various sources like social blogs, websites, etc. In recent times, the blogs and websites are the real-time means of gathering product reviews. However, excessive number of blogs on the cloud has enabled the generation of huge volume of information in different forms like attitudes, opinions, and reviews. Therefore, a dire need emerges to find a method to extract meaningful information from big data, classify it into different categories and predict end user's behaviors or sentiments. Long Short-Term Memory (LSTM) model and Convolutional Neural Network (CNN) model have been applied to different Natural Language Processing (NLP) tasks with remarkable and effective results. The CNN model efficiently extracts higher level features using convolutional layers and max-pooling layers. The LSTM model is capable to capture long-term dependencies between word sequences. In this study, we propose a hybrid model using LSTM and very deep CNN model named as Hybrid CNN-LSTM Model to overcome the sentiment analysis problem. First, we use Word to Vector (Word2Vc) approach to train initial word embeddings. The Word2Vc translates the text strings into a vector of numeric values, computes distance between words, and makes groups of similar words based on their meanings. Afterword embedding is performed in which the proposed model combines set of features that are extracted by convolution and global max-pooling layers with long term dependencies. The proposed model also uses dropout technology, normalization and a rectified linear unit for accuracy improvement. Our results show that the proposed Hybrid CNN-LSTM Model outperforms traditional deep learning and machine learning techniques in terms of precision, recall, f-measure, and accuracy. Our approach achieved competitive results using state-of-the-art techniques on the IMDB movie review dataset and Amazon movie reviews dataset.

Electricity is a controllable and convenient form of energy and it provides power to appliances. ... more Electricity is a controllable and convenient form of energy and it provides power to appliances. As the population of world is increasing, the electricity demand is also increasing which leads to energy crisis. This problem can be control by using Demand Side Management (DSM) and Energy Management Scheduler (EMS). In this paper, we design EMS for residential area using two heuristic algorithms: Bacteria Foraging Algorithm (BFA) and Social Spider Optimization (SSO) algorithm. Our main objectives are to minimize electricity cost and Peak to Average Ratio (PAR). These algorithms help to shift the load from on-peak to off-peak hours. We use Real Time Price (RTP) signal for electricity bill calculation. Simulation results demonstrate that our designed EMS achieved our objectives effectively. SSO perform better in term of PAR and User Comfort (UC).

2017 23rd International Conference on Automation and Computing (ICAC)

The smartphones have become the basic necessity of life. Users are being authenticated on mobile ... more The smartphones have become the basic necessity of life. Users are being authenticated on mobile devices using PINs, password, swipe, etc. However, the existing authentication mechanisms are not resilient against modern security attacks. With the increase of touch devices, gesture-based authentication behaviour becomes more important. This paper analyzes the distinctness of a gesture in a touch base mobile device. Analysis show that specific user has distinct gesture of different fingers. Experimental study reveals that finger accuracy in a gesture-based authentication is increased by an individual's index finger and thumbs. Furthermore, the results show that the accuracy and efficiency of a gesture-based lock depends on the phone's position, portrait mode, left or right-handed user, and single or double hand user style.

2018 24th International Conference on Automation and Computing (ICAC), 2018

Plagiarism is an act of presenting someone else's idea, words and original work as one's ... more Plagiarism is an act of presenting someone else's idea, words and original work as one's own without acknowledging the original source. It creates many problems, especially for academic institutions and researchers. There are many plagiarism detection tools publically available which are used to overcome these problems, however these tools mainly work for particular languages like Arabic and English. In South Asian countries specifically India and Pakistan, a huge part of research content is available in Hindi and Urdu languages. Unfortunately, plagiarism detection in Urdu text cannot acquire the proper attention of research community because it has complex sentence structure and lacks linguistic resources. In this paper, we propose a novel framework for plagiarism detection specifically for Urdu language. There is no benchmark corpus available for Urdu plagiarism detection, and therefore we developed a corpus of Urdu language. We applied distance measuring method along with vector space method to measure the similarity between suspicious and source text. For evaluation purpose, we defined different classes of plagiarized text such as paraphrase, heavily plagiarized, light plagiarized and direct copy-paste. Moreover, we evaluated each class of plagiarized text in terms of precision, recall, and f-measure. The experimental results have presented that Levenshiten distance and Jaccard containment methods produced significant improvement in the performance of plagiarism detection compared with existing methods.

2018 14th International Conference on Emerging Technologies (ICET), 2018

Plagiarism, intellectual theft, and copyright violation are the most important problems for resea... more Plagiarism, intellectual theft, and copyright violation are the most important problems for researchers and academic organizations such as universities. The famous publicly available Plagiarism Detection (PD) tools are Turnitin, APlagramme, Plagscan, and Aplag and these tools use to overcome plagiarism problems. However, these tools mainly work for English, Persian and Arabic languages. Copyright and intellectual document have written in every language of the world and many South Asian countries including Pakistan and India, a huge amount of academic content is available in the Urdu language. Unfortunately, due to resources scarcity and less concentration of researcher There is no enough work has been done in Urdu PD. Capturing of plagiarism in Urdu is presented in this paper. Most existing Urdu PD systems fail to identify paraphrase plagiarism in comparison between suspicious and source text document. However, the proposed system is able to identify different types of plagiarism like sentence reordering, inert/delete inter-textual similarity and near copy similarity. The proposed system is based on a distance measuring method, structural alignment algorithm, and vector space model. The system performance is evaluated using machine learning classifiers i.e. Support Vector Machine and Naïve Bayes. The experimental results demonstrated that performance of the proposed method is improved as compared to other existing model i.e. cosine method, simple Jaccard measure.

In this paper, an energy management controller (EMC) is designed using three optimization techniq... more In this paper, an energy management controller (EMC) is designed using three optimization techniques: harmony search algorithm (HSA), firefly algorithm (FA) and enhanced differential evolution (EDE). The objectives of this work are to minimize electricity cost as well as peak to average ratio (PAR) while maintaining the user comfort (UC). Critical peak pricing (CPP) is used for the calculation of electricity bill. The trade-off between UC and electricity cost is exploited in such a way that a stability is achieved among UC and electricity price that is preferred by the consumer. Reduction in PAR is beneficial for both consumer and utility as it provides stability to the electric grid.

Electricity is a valuable resource. With the increase of population, this valuable resource is be... more Electricity is a valuable resource. With the increase of population, this valuable resource is being used inefficiently. To overcome this problem, electricity providers use various techniques like introducing different pricing schemes. In peak hours, when the usage of electricity is high, the utility increases the per unit cost. Therefore, usage of electricity in peak hours result in high electricity bills. The electricity bills can be reduced by efficiently scheduling the home appliances so that few appliances are operated during peak hours. For this purpose many techniques have been proposed. In this paper, we propose a Social Spider Algorithm (SSA) for Demand Side Management (DSM). Harmony Search Algorithm (HSA) has been adapted to evaluate the results of SSA. These algorithms schedules the appliances in such a way that the usage of electricity in peak hours is reduced. This results in reduction of electricity bill and Peak to Average Ratio (PAR).

2019 25th International Conference on Automation and Computing (ICAC), 2019

Digital text is increasing rapidly on the Internet with the excessive use of social media. For th... more Digital text is increasing rapidly on the Internet with the excessive use of social media. For this reason, it is very challenging to extract effective information from the digital text due its high dimensionality, sparseness and big data. In this paper, we study the powerful nonparametric Bayesian topic model which is Hierarchical Latent Dirichlet Allocation (hLDA). We deal the issue of learning topics hierarchies from Urdu text data. The presented Topic Model for Urdu is combined with preprocessing activities, hLDA model, and Gibbs Sampling (GS) algorithm. We present hLDA base topic model called Urdu Hierarchical Latent Dirichlet Allocation (uhLDA). Empirical study showed that uhLDA effectively learns the topics hierarchies from 5000 Urdu text documents. Furthermore, we evaluated the results using Pointwise Mutual information (PMI) and it shows that uhLDA outperforms as compared to existing standard topic model LDA.

2018 24th International Conference on Automation and Computing (ICAC), 2018

Natural Language Processing (NLP) is a branch of Artificial Intelligence to help computers manipu... more Natural Language Processing (NLP) is a branch of Artificial Intelligence to help computers manipulate and interpret human languages. In NLP, text mining is a technique to derive useful information from text. Topic Model (TM) is a statistical model to extract topics from a large collection of unlabeled text using NLP and machine learning techniques. Several effective TM are available to fulfill the needs of various languages like English, German, Arabic etc. However no compelling TM is available for poor resource South Asian language Urdu. In this research study, our focus is to work on existing TM like Latent Dirichlet Allocation (LDA) to overcome the issues of Urdu language in text mining. We studied and analyzed LDA as an unsupervised model for the Urdu topic identification. Hence, we studied LDA deeply for Urdu topic identification at two levels: Variational Bayes (VB) based LDA for Urdu (VB-ULDA) with stemmer and without stemmer. Experiments are performed on a self-created massive number of Urdu documents in four different corpora. Experimental study shows that VB-ULDA outperformed in the identification of topics from Urdu text documents as compared to existing Urdu LDA (ULDA) in terms of accuracy and efficiency and results also reveal the high impact of stemming algorithm in Urdu topic identification.

Advances on Broad-Band Wireless Computing, Communication and Applications, 2017

In this paper, performance of energy management controller (EMC) based on meta-heuristic algorith... more In this paper, performance of energy management controller (EMC) based on meta-heuristic algorithms: Harmony Search Algorithm (HSA) and Firefly Algorithm (FA) are evaluated. Critical peak pricing (CPP) scheme is implemented to calculate the electricity cost. Appliances are categorized into three groups on the basis of power consumption. Electricity cost minimization and electricity load shifting from peak hours towards off peak hours are the main objectives of the paper. In simulation results, adopted approach reduces the Peak to Average Ratio (PAR) and total electricity cost. Furthermore, HSA shows better results than FA in terms of PAR and electricity cost.

Multimedia Tools and Applications, 2019

Nowadays, social media has become a tremendous source of acquiring user's opinions. With the adva... more Nowadays, social media has become a tremendous source of acquiring user's opinions. With the advancement of technology and sophistication of the internet, a huge amount of data is generated from various sources like social blogs, websites, etc. In recent times, the blogs and websites are the real-time means of gathering product reviews. However, excessive number of blogs on the cloud has enabled the generation of huge volume of information in different forms like attitudes, opinions, and reviews. Therefore, a dire need emerges to find a method to extract meaningful information from big data, classify it into different categories and predict end user's behaviors or sentiments. Long Short-Term Memory (LSTM) model and Convolutional Neural Network (CNN) model have been applied to different Natural Language Processing (NLP) tasks with remarkable and effective results. The CNN model efficiently extracts higher level features using convolutional layers and max-pooling layers. The LSTM model is capable to capture long-term dependencies between word sequences. In this study, we propose a hybrid model using LSTM and very deep CNN model named as Hybrid CNN-LSTM Model to overcome the sentiment analysis problem. First, we use Word to Vector (Word2Vc) approach to train initial word embeddings. The Word2Vc translates the text strings into a vector of numeric values, computes distance between words, and makes groups of similar words based on their meanings. Afterword embedding is performed in which the proposed model combines set of features that are extracted by convolution and global max-pooling layers with long term dependencies. The proposed model also uses dropout technology, normalization and a rectified linear unit for accuracy improvement. Our results show that the proposed Hybrid CNN-LSTM Model outperforms traditional deep learning and machine learning techniques in terms of precision, recall, f-measure, and accuracy. Our approach achieved competitive results using state-of-the-art techniques on the IMDB movie review dataset and Amazon movie reviews dataset.

Electricity is a controllable and convenient form of energy and it provides power to appliances. ... more Electricity is a controllable and convenient form of energy and it provides power to appliances. As the population of world is increasing, the electricity demand is also increasing which leads to energy crisis. This problem can be control by using Demand Side Management (DSM) and Energy Management Scheduler (EMS). In this paper, we design EMS for residential area using two heuristic algorithms: Bacteria Foraging Algorithm (BFA) and Social Spider Optimization (SSO) algorithm. Our main objectives are to minimize electricity cost and Peak to Average Ratio (PAR). These algorithms help to shift the load from on-peak to off-peak hours. We use Real Time Price (RTP) signal for electricity bill calculation. Simulation results demonstrate that our designed EMS achieved our objectives effectively. SSO perform better in term of PAR and User Comfort (UC).