About the journal
The Journal of Information Systems and Telecommunication (JIST) accepts and publishes papers containing original researches and/or development results, representing an effective and novel contribution for knowledge in the area of information systems and Telecommunication. Contributions are accepted in the form of Regular papers or Correspondence. Regular papers are the ones with a well-rounded treatment of a problem area, whereas Correspondence focus on a point of a defined problem area. Under the permission of the editorial board, other kinds of papers may be published if they are found to be relevant or of interest to the readers. Responsibility for the content of the papers rests upon the Authors only. The Journal is aimed at not only a national target community, but also international audiences is taken into consideration. For this reason, authors are supposed to write in English.
This Journal is Published under scientific support of Advanced Information Systems (AIS) Research Group and Digital & Signal Processing Group, ICTRC
For further information on Article Processing Charges (APCs) policies, please visit our APC page or contact us infojist@gmail.com.
Recent Articles
-
Open Access Article
1 - FLHB-AC: Federated Learning History-Based Access Control Using Deep Neural Networks in Healthcare System
Nasibeh Mohammadi Afshin Rezakhani Hamid Haj Seyyed Javadi Parvaneh asghariIssue 46 , Vol. 12 , Spring 2024Giving access permission based on histories of access is now one of the security needs in healthcare systems. However, current access control systems are unable to review all access histories online to provide access permission. As a result, this study first proposes a MoreGiving access permission based on histories of access is now one of the security needs in healthcare systems. However, current access control systems are unable to review all access histories online to provide access permission. As a result, this study first proposes a method to perform access control in healthcare systems in real-time based on access histories and the decision of the suggested intelligent module. The data is used to train the intelligent module using the LSTM time series machine learning model. Medical data, on the other hand, cannot be obtained from separate systems and trained using different machine-learning models due to the sensitivity and privacy of medical records. As a result, the suggested solution employs the federated learning architecture, which remotely performs machine learning algorithms on healthcare systems and aggregates the knowledge gathered in the servers in the second phase. Based on the experiences of all healthcare systems, the servers communicate the learning aggregation back to the systems to control access to resources. The experimental results reveal that the accuracy of history-based access control in local healthcare systems before the application of the suggested method is lower than the accuracy of the access control in these systems after aggregating training with federated learning architecture. Manuscript profile -
Open Access Article
2 - An Acoustic Echo Canceller using Moving Window to Track Energy Variations of Double-Talk-Detector
Mouldi MAKDIR Mourad BENZIANE Mohamed BOUAMARIssue 46 , Vol. 12 , Spring 2024As a fundamental device in acoustic echo cancellation (AEC) systems, the echo canceller based on adaptive filters relies on the adaptive approximation of the echo-path. However, the adaptive filter must face the risk of divergence during the double-talk periods when the MoreAs a fundamental device in acoustic echo cancellation (AEC) systems, the echo canceller based on adaptive filters relies on the adaptive approximation of the echo-path. However, the adaptive filter must face the risk of divergence during the double-talk periods when the near-end is present. To solve this problem, the double-talk-detector (DTD) is often used to detect the double-talk periods and prevent the echo canceller from being disturbed by the other end of the speaker’s signal. In this paper, we propose a DTD based on a new method that can detect quickly and track accurately double-talk periods. It is based on the sum of energies of the estimated echo and the microphone signals which is continuously compared to the error energy. A window that moves with time and tracks energy variations of the different input signals of the DTD represents a fundamental feature of the proposed method compared to several other methods based on correlation. The goal is to outperform conventional normalized cross-correlation (NCC) methods which are well-known in terms of small steady-state misalignment and stability of decision variable. In this work, the normalized least mean squares (NLMS) algorithm is used to update the filter coefficients along speech signals which are taken from the NOIZEUS database. Efficiency of the proposed method is particularly compared to the conventional Geigel algorithm and normalized cross-correlation method (NCC) that depends on the cross-correlation between the microphone signal and the error signal of AEC. Performance evaluation is confirmed by computer simulation. Manuscript profile -
Open Access Article
3 - An Aspect-Level Sentiment Analysis Based on LDA Topic Modeling
Sina Dami Ramin AlimardaniIssue 46 , Vol. 12 , Spring 2024Sentiment analysis is a process through which the beliefs, sentiments, allusions, behaviors, and tendencies in a written language are analyzed using Natural Language Processing (NLP) techniques. This process essentially comprises of discovering and understanding people' MoreSentiment analysis is a process through which the beliefs, sentiments, allusions, behaviors, and tendencies in a written language are analyzed using Natural Language Processing (NLP) techniques. This process essentially comprises of discovering and understanding people's positive or negative sentiments regarding a product or entity in the text. The increased significance of sentiments analysis has coincided with the growth in social media such as surveys, blogs, Twitter, etc. The present study takes advantage of the topic modeling approach based on latent Dirichlet allocation (LDA) to extract and represent the thematic features as well as a support vector machine (SVM) to classify and analyze sentiments at the aspect level. LDA seeks to extract latent topics by observing all the texts, which is accomplished by assigning the probability of each word being attributed to each topic. The important features that represent the thematic aspect of the text are extracted and fed to a support vector machine for classification through this approach. SVM is an extremely powerful classification algorithm that provides the possibility to separate complex data from one another accurately by mapping the data to a space with much larger aspects and creating an optimal hyperplane. Empirical data on real datasets indicate that the proposed model is promising and performs better compared to the baseline methods in terms of precision (with 89.78% on average), recall (with 78.92% on average), and F-measure (with 83.50% on average). Manuscript profile -
Open Access Article
4 - A Comparison Analysis of Conventional Classifiers and Deep Learning Model for Activity Recognition in Smart Homes based on Multi-label Classification
John Kasubi Manjaiah D. Huchaiah Ibrahim Gad Mohammad Kazim HooshmandIssue 46 , Vol. 12 , Spring 2024Activity Recognition is essential for exploring the various activities that humans engage in within Smart Homes in the presence of multiple sensors as residents interact with household appliances. Smart homes use intelligent IoT devices linked to residents' homes to tra MoreActivity Recognition is essential for exploring the various activities that humans engage in within Smart Homes in the presence of multiple sensors as residents interact with household appliances. Smart homes use intelligent IoT devices linked to residents' homes to track changes in human behavior as the humans interact with the home's equipment, which may improve healthcare and security issues for the residents. This study presents a research work that compares conventional classifiers such as DT, LDA, Adaboost, GB, XGBoost, MPL, KNN, and DL, focusing on recognizing human activities in Smart Homes using Activity Recognizing Ambient Sensing (ARAS). The experimental results demonstrated that DL Model outperformed with excellent accuracy compared to conventional classifiers in recognizing human activities in Smart Homes. This work proves that DL Models perform best in analyzing ARAS datasets compared to traditional machine learning algorithms. Manuscript profile -
Open Access Article
5 - Designing a Semi-Intelligent Crawler for Creating a Persian Question Answering Corpus Called Popfa
Hadi Sharifian Nasim Tohidi Chitra DadkhahIssue 46 , Vol. 12 , Spring 2024Question answering in natural language processing is an interesting field for researchers to examine their ability in solving the tough Alan Turing test. Every day computer scientists are trying hard to develop and promote question answering systems in various natural l MoreQuestion answering in natural language processing is an interesting field for researchers to examine their ability in solving the tough Alan Turing test. Every day computer scientists are trying hard to develop and promote question answering systems in various natural languages, especially English. However, in Persian, it is not easy to advance these systems. The main problem is related to low resources and not enough corpora in this language. Thus, in this paper, a Persian question answering text corpus is created, which covers a wide range of religious, midwifery, and issues related to youth marriage topics and question types commonly encountered in Persian language usage. In this regard, the most important challenge was introducing a method for data gathering in Persian as well as facilitating and expanding the data gathering process. Though, SIC (Semi-Intelligent Crawler) is proposed as a solution that can overcome the challenge and find a way to crawl the Persian websites, gather text and finally import it to a database. The outcome of this research is a corpus called Popfa, which stands for POrsesh Pasokh (question answering) in FArsi. This corpus contains more than 53,000 standard questions and answers. Besides, it has been evaluated with standard approaches. All the questions in Popfa are answered by specialists in two general topics: religious and medical questions. Therefore, researchers can now use this corpus for doing research on Persian question answering. Manuscript profile -
Open Access Article
6 - Whispered Speech Emotion Recognition with Gender Detection using BiLSTM and DCNN
Aniruddha Mohanty Ravindranath C. CherukuriIssue 46 , Vol. 12 , Spring 2024Emotions are human mental states at a particular instance in time concerning one’s circumstances, mood, and relationships with others. Identifying emotions from the whispered speech is complicated as the conversation might be confidential. The representation of the spee MoreEmotions are human mental states at a particular instance in time concerning one’s circumstances, mood, and relationships with others. Identifying emotions from the whispered speech is complicated as the conversation might be confidential. The representation of the speech relies on the magnitude of its information. Whispered speech is intelligible, a low-intensity signal, and varies from normal speech. Emotion identification is quite tricky from whispered speech. Both prosodic and spectral speech features help to identify emotions. The emotion identification in a whispered speech happens using prosodic speech features such as zero-crossing rate (ZCR), pitch, and spectral features that include spectral centroid, chroma STFT, Mel scale spectrogram, Mel-frequency cepstral coefficient (MFCC), Shifted Delta Cepstrum (SDC), and Spectral Flux. There are two parts to the proposed implementation. Bidirectional Long Short-Term Memory (BiLSTM) helps to identify the gender from the speech sample in the first step with SDC and pitch. The Deep Convolutional Neural Network (DCNN) model helps to identify the emotions in the second step. This implementation is evaluated with the help of wTIMIT data corpus and gives 98.54% accuracy. Emotions have a dynamic effect on genders, so this implementation performs better than traditional approaches. This approach helps to design online learning management systems, different applications for mobile devices, checking cyber-criminal activities, emotion detection for older people, automatic speaker identification and authentication, forensics, and surveillance. Manuscript profile -
Open Access Article
7 - Ensemble learning of daboosting based on deep weighting for classification of hand-written numbers in Persian
amir asil hamed Alipour Shahram mojtahedzadeh hasan AsilIssue 46 , Vol. 12 , Spring 2024Today, the hand-written data volume is huge, which prohibits these data from being manually converted into electronic files. During the past years, different types of solutions were developed to convert machine learning-based handwritten data. Each method classifies or MoreToday, the hand-written data volume is huge, which prohibits these data from being manually converted into electronic files. During the past years, different types of solutions were developed to convert machine learning-based handwritten data. Each method classifies or clusters the data according to the data type and application. In the present paper, a new approach is presented based on compound methods and deep learning for the classification of Persian handwritten data, where a deeper investigation is made of the data in basic learning by combining the Ada boosting and convolution. The present study aims at providing a new technique for classification of the images of handwritten Persian numbers. The structure of this technique is founded on Ada Boosting, which in turn, is based on weak learning. This technique improves learning by iteration of the weak learning processes and updating weights. In the meantime, the proposed method tried to employ stronger learners and present a stronger algorithm by combining these strong learners. The method was assessed on the standard Hoda dataset containing 60000 training data. The results show that the proposed method has a lower error rate than the previous methods by more than 1%. In the future, by developing basic learner, new mechanisms can be provided to improve the results by new types of learning. – Today, the hand-written data volume is huge, which prohibits these data from being manually converted into electronic files. During the past years, different types of solutions were developed to convert machine learning-based handwritten data. Each method classifies or clusters the data according to the data type and application. In the present paper, a new approach is presented based on compound methods and deep learning for the classification of Persian handwritten data, where a deeper investigation is made of the data in basic learning by combining the Ada boosting and convolution. The method was assessed on the standard Hoda dataset containing 60000 training data. The results showed that the error rate of the method has decreased by more than 1% compared to the previous methods. Manuscript profile
Most Viewed Articles
-
Open Access Article
1 - Privacy Preserving Big Data Mining: Association Rule Hiding
Golnar Assadat Afzali shahriyar mohammadiIssue 14 , Vol. 4 , Spring 2016Data repositories contain sensitive information which must be protected from unauthorized access. Existing data mining techniques can be considered as a privacy threat to sensitive data. Association rule mining is one of the utmost data mining techniques which tries to MoreData repositories contain sensitive information which must be protected from unauthorized access. Existing data mining techniques can be considered as a privacy threat to sensitive data. Association rule mining is one of the utmost data mining techniques which tries to cover relationships between seemingly unrelated data in a data base.. Association rule hiding is a research area in privacy preserving data mining (PPDM) which addresses a solution for hiding sensitive rules within the data problem. Many researches have be done in this area, but most of them focus on reducing undesired side effect of deleting sensitive association rules in static databases. However, in the age of big data, we confront with dynamic data bases with new data entrance at any time. So, most of existing techniques would not be practical and must be updated in order to be appropriate for these huge volume data bases. In this paper, data anonymization technique is used for association rule hiding, while parallelization and scalability features are also embedded in the proposed model, in order to speed up big data mining process. In this way, instead of removing some instances of an existing important association rule, generalization is used to anonymize items in appropriate level. So, if necessary, we can update important association rules based on the new data entrances. We have conducted some experiments using three datasets in order to evaluate performance of the proposed model in comparison with Max-Min2 and HSCRIL. Experimental results show that the information loss of the proposed model is less than existing researches in this area and this model can be executed in a parallel manner for less execution time Manuscript profile -
Open Access Article
2 - Instance Based Sparse Classifier Fusion for Speaker Verification
Mohammad Hasheminejad Hassan FarsiIssue 15 , Vol. 4 , Summer 2016This paper focuses on the problem of ensemble classification for text-independent speaker verification. Ensemble classification is an efficient method to improve the performance of the classification system. This method gains the advantage of a set of expert classifiers MoreThis paper focuses on the problem of ensemble classification for text-independent speaker verification. Ensemble classification is an efficient method to improve the performance of the classification system. This method gains the advantage of a set of expert classifiers. A speaker verification system gets an input utterance and an identity claim, then verifies the claim in terms of a matching score. This score determines the resemblance of the input utterance and pre-enrolled target speakers. Since there is a variety of information in a speech signal, state-of-the-art speaker verification systems use a set of complementary classifiers to provide a reliable decision about the verification. Such a system receives some scores as input and takes a binary decision: accept or reject the claimed identity. Most of the recent studies on the classifier fusion for speaker verification used a weighted linear combination of the base classifiers. The corresponding weights are estimated using logistic regression. Additional researches have been performed on ensemble classification by adding different regularization terms to the logistic regression formulae. However, there are missing points in this type of ensemble classification, which are the correlation of the base classifiers and the superiority of some base classifiers for each test instance. We address both problems, by an instance based classifier ensemble selection and weight determination method. Our extensive studies on NIST 2004 speaker recognition evaluation (SRE) corpus in terms of EER, minDCF and minCLLR show the effectiveness of the proposed method. Manuscript profile -
Open Access Article
3 - Node Classification in Social Network by Distributed Learning Automata
Ahmad Rahnama Zadeh meybodi meybodi Masoud Taheri KadkhodaIssue 18 , Vol. 5 , Spring 2017The aim of this article is improving the accuracy of node classification in social network using Distributed Learning Automata (DLA). In the proposed algorithm using a local similarity measure, new relations between nodes are created, then the supposed graph is partitio MoreThe aim of this article is improving the accuracy of node classification in social network using Distributed Learning Automata (DLA). In the proposed algorithm using a local similarity measure, new relations between nodes are created, then the supposed graph is partitioned according to the labeled nodes and a network of Distributed Learning Automata is corresponded on each partition. In each partition the maximal spanning tree is determined using DLA. Finally nodes are labeled according to the rewards of DLA. We have tested this algorithm on three real social network datasets, and results show that the expected accuracy of presented algorithm is achieved. Manuscript profile -
Open Access Article
4 - COGNISON: A Novel Dynamic Community Detection Algorithm in Social Network
Hamideh Sadat Cheraghchi Ali ZakerolhossieniIssue 14 , Vol. 4 , Spring 2016The problem of community detection has a long tradition in data mining area and has many challenging facet, especially when it comes to community detection in time-varying context. While recent studies argue the usability of social science disciplines for modern social MoreThe problem of community detection has a long tradition in data mining area and has many challenging facet, especially when it comes to community detection in time-varying context. While recent studies argue the usability of social science disciplines for modern social network analysis, we present a novel dynamic community detection algorithm called COGNISON inspired mainly by social theories. To be specific, we take inspiration from prototype theory and cognitive consistency theory to recognize the best community for each member by formulating community detection algorithm by human analogy disciplines. COGNISON is placed in representative based algorithm category and hints to further fortify the pure mathematical approach to community detection with stabilized social science disciplines. The proposed model is able to determine the proper number of communities by high accuracy in both weighted and binary networks. Comparison with the state of art algorithms proposed for dynamic community discovery in real datasets shows higher performance of this method in different measures of Accuracy, NMI, and Entropy for detecting communities over times. Finally our approach motivates the application of human inspired models in dynamic community detection context and suggest the fruitfulness of the connection of community detection field and social science theories to each other. Manuscript profile -
Open Access Article
5 - A Bio-Inspired Self-configuring Observer/ Controller for Organic Computing Systems
Ali Tarihi Hassan Haghighi Fereidoon Shams AlieeIssue 15 , Vol. 4 , Summer 2016The increase in the complexity of computer systems has led to a vision of systems that can react and adapt to changes. Organic computing is a bio-inspired computing paradigm that applies ideas from nature as solutions to such concerns. This bio-inspiration leads to the MoreThe increase in the complexity of computer systems has led to a vision of systems that can react and adapt to changes. Organic computing is a bio-inspired computing paradigm that applies ideas from nature as solutions to such concerns. This bio-inspiration leads to the emergence of life-like properties, called self-* in general which suits them well for pervasive computing. Achievement of these properties in organic computing systems is closely related to a proposed general feedback architecture, called the observer/controller architecture, which supports the mentioned properties through interacting with the system components and keeping their behavior under control. As one of these properties, self-configuration is desirable in the application of organic computing systems as it enables by enabling the adaptation to environmental changes. However, the adaptation in the level of architecture itself has not yet been studied in the literature of organic computing systems. This limits the achievable level of adaptation. In this paper, a self-configuring observer/controller architecture is presented that takes the self-configuration to the architecture level. It enables the system to choose the proper architecture from a variety of possible observer/controller variants available for a specific environment. The validity of the proposed architecture is formally demonstrated. We also show the applicability of this architecture through a known case study. Manuscript profile -
Open Access Article
6 - Publication Venue Recommendation Based on Paper’s Title and Co-authors Network
Ramin Safa Seyed Abolghassem Mirroshandel Soroush Javadi Mohammad AziziIssue 21 , Vol. 6 , Winter 2018Information overload has always been a remarkable topic in scientific researches, and one of the available approaches in this field is employing recommender systems. With the spread of these systems in various fields, studies show the need for more attention to applying MoreInformation overload has always been a remarkable topic in scientific researches, and one of the available approaches in this field is employing recommender systems. With the spread of these systems in various fields, studies show the need for more attention to applying them in scientific applications. Applying recommender systems to scientific domain, such as paper recommendation, expert recommendation, citation recommendation and reviewer recommendation, are new and developing topics. With the significant growth of the number of scientific events and journals, one of the most important issues is choosing the most suitable venue for publishing papers, and the existence of a tool to accelerate this process is necessary for researchers. Despite the importance of these systems in accelerating the publication process and decreasing possible errors, this problem has been less studied in related works. So in this paper, an efficient approach will be suggested for recommending related conferences or journals for a researcher’s specific paper. In other words, our system will be able to recommend the most suitable venues for publishing a written paper, by means of social network analysis and content-based filtering, according to the researcher’s preferences and the co-authors’ publication history. The results of evaluation using real-world data show acceptable accuracy in venue recommendations. Manuscript profile -
Open Access Article
7 - Using Residual Design for Key Management in Hierarchical Wireless Sensor Networks
Vahid Modiri Hamid Haj Seyyed Javadi Amir Masoud Rahmani Mohaddese AnzaniIssue 29 , Vol. 8 , Winter 2020Combinatorial designs are powerful structures for key management in wireless sensor networks to address good connectivity and also security against external attacks in large scale networks. Many researchers have used key pre-distribution schemes using combinatorial stru MoreCombinatorial designs are powerful structures for key management in wireless sensor networks to address good connectivity and also security against external attacks in large scale networks. Many researchers have used key pre-distribution schemes using combinatorial structures in which key-rings, are pre-distributed to each sensor node before deployment in a real environment. Regarding the restricted resources, key distribution is a great engagement and challenging issue in providing sufficient security in wireless sensor networks. To provide secure communication, a unique key should be found from their stored key-rings. Most of the key pre-distribution protocols based on public-key mechanisms could not support highly scalable networks due to their key storage overhead and communication cost that linearly increasing. In this paper, we introduce a new key distribution approach for hierarchical clustered wireless sensor networks. Each cluster has a construction that contains new points or that reinforces and builds upon similar ideas of their head clusters. Based on Residual Design as a powerful algebraic combinatorial architecture and hierarchical network model, our approach guarantees good connectivity between sensor nodes and also cluster heads. Compared with similar existing schemes, our approach can provide sufficient security no matter if the cluster head or normal sensor node is compromised Manuscript profile -
Open Access Article
8 - Short Time Price Forecasting for Electricity Market Based on Hybrid Fuzzy Wavelet Transform and Bacteria Foraging Algorithm
keyvan Borna Sepideh PalizdarIssue 16 , Vol. 4 , Autumn 2016Predicting the price of electricity is very important because electricity can not be stored. To this end, parallel methods and adaptive regression have been used in the past. But because dependence on the ambient temperature, there was no good result. In this study, lin MorePredicting the price of electricity is very important because electricity can not be stored. To this end, parallel methods and adaptive regression have been used in the past. But because dependence on the ambient temperature, there was no good result. In this study, linear prediction methods and neural networks and fuzzy logic have been studied and emulated. An optimized fuzzy-wavelet prediction method is proposed to predict the price of electricity. In this method, in order to have a better prediction, the membership functions of the fuzzy regression along with the type of the wavelet transform filter have been optimized using the E.Coli Bacterial Foraging Optimization Algorithm. Then, to better compare this optimal method with other prediction methods including conventional linear prediction and neural network methods, they were analyzed with the same electricity price data. In fact, our fuzzy-wavelet method has a more desirable solution than previous methods. More precisely by choosing a suitable filter and a multiresolution processing method, the maximum error has improved by 13.6%, and the mean squared error has improved about 17.9%. In comparison with the fuzzy prediction method, our proposed method has a higher computational volume due to the use of wavelet transform as well as double use of fuzzy prediction. Due to the large number of layers and neurons used in it, the neural network method has a much higher computational volume than our fuzzy-wavelet method. Manuscript profile -
Open Access Article
9 - The Innovation Roadmap and Value Creation for Information Goods Pricing as an Economic Commodity
Hekmat Adelnia Najafabadi Ahmadreza Shekarchizadeh Akbar Nabiollahi Naser Khani Hamid RastegariIssue 26 , Vol. 7 , Spring 2019Nowadays, most books and information resources or even movies and application programs are produced and reproduced as information goods. Regarding characteristics of information goods, its cost structure and market, the usual and traditional pricing methods for such com MoreNowadays, most books and information resources or even movies and application programs are produced and reproduced as information goods. Regarding characteristics of information goods, its cost structure and market, the usual and traditional pricing methods for such commodity are not useful and the information goods pricing has undergone innovative approaches. The purpose of product pricing is to find an optimal spot for maximizing manufacturers' profits and consumers' desirability. Undoubtedly, in order to achieve this goal, it is necessary to adopt appropriate strategies and implement innovative strategies. Innovative strategies and tactics reflect the analysis of market share, customer behavior change, pattern of cost, customer preferences, quick response to customer needs, market forecast, appropriate response to market changes, customer retention, discovery of their specific requirements, cost reduction and customer satisfaction increase. In this research, 32 papers have been selected among 540 prestigious articles to create a canvas containing more than 20 possible avenues for innovations in the field of information goods pricing, which can be used in the companies producing information goods, regardless of their size, nationality, and type of information goods they produce. Introduction of some key ideas on how to increase both profits and customer satisfaction and also three open issues for future research in the field of information goods pricing is one of the achievements of this research. Manuscript profile -
Open Access Article
10 - DBCACF: A Multidimensional Method for Tourist Recommendation Based on Users’ Demographic, Context and Feedback
Maral Kolahkaj Ali Harounabadi Alireza Nikravan shalmani Rahim ChinipardazIssue 24 , Vol. 6 , Autumn 2018By the advent of some applications in the web 2.0 such as social networks which allow the users to share media, many opportunities have been provided for the tourists to recognize and visit attractive and unfamiliar Areas-of-Interest (AOIs). However, finding the appropr MoreBy the advent of some applications in the web 2.0 such as social networks which allow the users to share media, many opportunities have been provided for the tourists to recognize and visit attractive and unfamiliar Areas-of-Interest (AOIs). However, finding the appropriate areas based on user’s preferences is very difficult due to some issues such as huge amount of tourist areas, the limitation of the visiting time, and etc. In addition, the available methods have yet failed to provide accurate tourist’s recommendations based on geo-tagged media because of some problems such as data sparsity, cold start problem, considering two users with different habits as the same (symmetric similarity), and ignoring user’s personal and context information. Therefore, in this paper, a method called “Demographic-Based Context-Aware Collaborative Filtering” (DBCACF) is proposed to investigate the mentioned problems and to develop the Collaborative Filtering (CF) method with providing personalized tourist’s recommendations without users’ explicit requests. DBCACF considers demographic and contextual information in combination with the users' historical visits to overcome the limitations of CF methods in dealing with multi- dimensional data. In addition, a new asymmetric similarity measure is proposed in order to overcome the limitations of symmetric similarity methods. The experimental results on Flickr dataset indicated that the use of demographic and contextual information and the addition of proposed asymmetric scheme to the similarity measure could significantly improve the obtained results compared to other methods which used only user-item ratings and symmetric measures. Manuscript profile
