2024-03-28T21:12:43+04:30 http://ijict.itrc.ac.ir/browse.php?mag_id=24&slc_lang=en&sid=1
24-183 2024-03-28 10.1002
International Journal of Information and Communication Technology Research 2251-6107 2783-4425 doi 2012 4 2 Optimized Regression in Sensor Networks by Integration of Harmony Search and Particle Swarm Optimization Hadi Shakibian Nasrollah Moghadam Charkari Regression modeling in sensor networks is a difficult task due to (i) the network data is distributed among the nodes and (ii) the restricted capabilities of the sensor nodes, such as limited power supply and bandwidth capacity. Recently, some distributed approaches have been proposed based on gradient descent and Nelder-Mead simplex methods. Although in these methods, the energy consumption is low, but the accuracy is still far from the centralized approach. Also, they suffer from a high latency. In this paper, a two-fold distributed approach has been proposed for doing regression analysis in wireless sensor networks. After clustering the network, the regressor of each cluster is learned by the integration of particle swarm optimization and harmony search. Afterwards, cluster heads collaborate to construct the global network regressor using a weighted averaging combination rule. The experimental results show the proposed approach improves the accuracy and latency significantly while its energy consumption is considerably acceptable in comparison with its popular counterparts. sensor networks distributed regression particle swarm optimization harmony search multiple classifier systems 2012 6 01 1 10 http://ijict.itrc.ac.ir/article-1-183-en.pdf
24-184 2024-03-28 10.1002
International Journal of Information and Communication Technology Research 2251-6107 2783-4425 doi 2012 4 2 E-Learners’ Activity Categorization Based on Their Learning Styles Using ART Family Neural Network Gholam Ali Montazer Hessam Khoshniat Adaptive learning means providing the most appropriate learning materials and strategies considering students' characteristics. Grouping students based on their learning styles is one of the approaches which has been followed in this area. In this paper, we introduce a mechanism in which learners are divided into some categories according to their behavioral factors and interactions with the system in order to adopt the most appropriate recommendations. In the proposed approach, learners' grouping is done using ART neural network variants including Fuzzy ART, ART 2A, ART 2A-C and ART 2A-E. The clustering task is performed considering some features of learner's behavior chosen based on their learning style. Additionally, these networks identifythe number of students' categories according to the similarities among their actions during the learning processautomatically. Having employed mentioned methods in a web-based educational system and analyzed their clustering accuracy and performance, we achieved remarkable outcomes as presented in this paper. Personalized e-Learning System Adaptive Resonance Theory ART Neural Network Learning Style Intelligent Tutoring System 2012 6 01 11 26 http://ijict.itrc.ac.ir/article-1-184-en.pdf
24-185 2024-03-28 10.1002
International Journal of Information and Communication Technology Research 2251-6107 2783-4425 doi 2012 4 2 Predicting Network Attacks Using Ontology-Driven Inference Ahmad Salahi Morteza Ansarinia Graph knowledge models and ontologies are very powerful modeling and reasoning tools. We propose an effective approach to model network attacks and attack prediction which plays important roles in security management. The goals of this study are: First we model network attacks, their prerequisites and consequences using knowledge representation methods in order to provide description logic reasoning and inference over attack domain concepts. And secondly, we propose an ontology-based system which predicts potential attacks using inference and observing information which provided by sensory inputs. We generate our ontology and evaluate corresponding methods using CAPEC, CWE, and CVE hierarchical datasets. Results from experiments show significant capability improvements comparing to traditional hierarchical and relational models. Proposed method also reduces false alarms and improves intrusion detection effectiveness. Knowledge Engineering Network Security Ontology 2012 6 01 27 35 http://ijict.itrc.ac.ir/article-1-185-en.pdf
24-186 2024-03-28 10.1002
International Journal of Information and Communication Technology Research 2251-6107 2783-4425 doi 2012 4 2 Performance Improvement of Language Identification Using Transcription Based Sequential Approaches & Sequential Kernels Based SVM Seyed Abbas Hosseini Amereei Mohammad Mehdi Homayounpour In this paper a generative frontend based on both phonetic and prosodic features, and also a couple of approaches based on phonetic transcription- Aggregated Phone Recognizer followed by Language Models (APRLM) and Generalized Phone Recognizer followed by Language Models (GPRLM), are investigated. APRLM and GPRLM have few disadvantages since they need phonetic transcription of speech data, and also they use fewer level of information while the generative frontend built upon an ensemble of Gaussian densities uses prosodic and phonetic information altogether. Furthermore, no transcription of speech data is needed in Support Vector Machine (SVM)- based approaches, and they showed better performances in our experiments too. In addition, APRLM and GPRLM are more time consuming than SVM-based approaches. We used Mel-Frequency Cepstral Coefficients (MFCC) in APRLM and GPRLM, and Shifted Delta Cepstrum (SDC) and Pitch Contour Polynomial Approximation (PCPA) features in SVM-based methods. Probabilistic Sequence Kernel (PSK) and Generalized Linear Discriminant Sequence (GLDS) kernels are used in SVM experiments. SVM using GLDS and PSK kernels outperforms GMM in all our LID experiments conducted by applying PCPA features and LID performance improved about 2.1% and 5.9% respectively. The combination of Probabilistic Characteristic Vector using PCPA (PCV-PCPA) and Probabilistic Characteristic Vector using SDC (PCV-SDC) provides further improvements. Language Identification Probabilistic Characteristic Vector Pitch Contour Polynomial Approximation Probabilistic Sequence Kernel Generalized Linear Discriminant Analysis APRLM GPRLM 2012 6 01 37 45 http://ijict.itrc.ac.ir/article-1-186-en.pdf
24-187 2024-03-28 10.1002
International Journal of Information and Communication Technology Research 2251-6107 2783-4425 doi 2012 4 2 E-business Integrated Test Framework Model Pasha Vejdan Tamar Abbas Asosheh There is an increasing need for an integrated test framework which can do conformance and interoperability testing in all layers of e-business standards without any dependence on a specific standard. In this paper a knowledge framework was provided for designing a model for e-business integrated testing by combining identified design factors from testing experience and conducting the CEN (European Committee for Standardization) GITB (Global Interoperability Test Bed) project feasibility study. Also, it was shown that abstracting of test scenarios in a modular manner makes them easily understandable, independent from test beds and standards and, furthermore, more reusable. Embedding a test case tool in the test framework provides the capability of automatic generation of executable test cases, and simultaneously makes them more manageable. A modular test bed design, by considering some interfaces to pluggable adaptors and applying event driven execution model, make it configurable and applicable to the various test types. By embedding management components into the test bed, more controlling and monitoring were provided over the test and its steps as, functional requirements for the current test beds. E-business Test Framework Interoperability Test Conformance Test Test Case Test Bed 2012 6 01 47 60 http://ijict.itrc.ac.ir/article-1-187-en.pdf
24-188 2024-03-28 10.1002
International Journal of Information and Communication Technology Research 2251-6107 2783-4425 doi 2012 4 2 Ontological Modeling of Radio Frequency Identification(RFID)Attacks Ahmad Salahi Mahshid Delavar Advances in RFID technology has led to increasing usage of these systems in various applications such as supply chain management, object identification and so on. At the same time, security attacks against these systems have also grown. Employing a common vocabulary for the sensors of RFID intrusion detection systems will be useful for collaborating with each other in identifying security incidents. Ontological approach for defining RFID attacks can obtain this common vocabulary that is understandable for both humans and software agents. In this paper, an ontological modeling of RFID attacks is presented. RFID Attack Ontology Modeling Intrusion Detection System Security 2012 6 01 61 70 http://ijict.itrc.ac.ir/article-1-188-en.pdf
24-189 2024-03-28 10.1002
International Journal of Information and Communication Technology Research 2251-6107 2783-4425 doi 2012 4 2 Data Mining in the E-Learning Systems: A Virtual University Case Study Behrouz Minaei Bidgoli SSeyed Hassan Hani Vahid Ghanbari Virtual learning environments provide the opportunity for the students to learn educational materials in educational institutions from different parts and places and with no requirement to physical presence. Over the time, a host of different information related to students, the content of teaching and learning and the interactions among them are recorded in virtual learning systems database that one of the most important of such information is how the students use the system. In this article, we will review the articles that have paid attention to this subject and a classification of the performed activities in this field and would be provided; in continue, some examples of these activities have been applied to the data from Imam Khomeini virtual university. Data mining Educational systems Web mining Web-based educational systems 2012 6 01 71 81 http://ijict.itrc.ac.ir/article-1-189-en.pdf