Статьи журнала - International Journal of Information Technology and Computer Science
Все статьи: 1165
Mining Frequent Itemsets with Weights over Data Stream Using Inverted Matrix
Статья научная
In recent years, the mining research over data stream has been prominent as they can be applied in many alternative areas in the real worlds. In this paper, we have proposed an algorithm called MFIWDSIM for mining frequent itemsets with weights over a data stream using Inverted Matrix [10]. The main idea is moving data stream to an inverted matrix saved in the computer disks so that the algorithms can mine on it many times with different support thresholds as well as alternative minimum weights. Moreover, this inverted matrix can be accessed to mine in different times for user's requirements without recalculation. By analyzing and evaluating, the MFIWDSIM can be seen as the better algorithm compared to WSWFP-stream [9] for mining frequent itemsets with weights over data stream.
Бесплатно
Mining Maximal Quasi Regular Patterns in Weighted Dynamic Networks
Статья научная
Interactions appearing regularly in a network may be disturbed due to the presence of noise or random occurrence of events at some timestamps. Ignoring them may devoid us from having better understanding of the networks under consideration. Therefore, to solve this problem, researchers have attempted to find quasi/quasi-regular patterns in non-weighted dynamic networks. To the best of our knowledge, no work has been reported in mining such patterns in weighted dynamic networks. So, in this paper we present a novel method which mines maximal quasi regular patterns on structure (MQRPS) and maximal quasi regular patterns on weight (MQRPW) in weighted dynamic networks. Also, we have provided a relationship between MQRPW and MQRPS which facilitates in the running of the proposed method only once, even when both are required and thus leading to reduction in computation time. Further, the analysis of the patterns so obtained is done to gain a better insight into their nature using four parameters, viz. modularity, cliques, most commonly used centrality measures and intersection. Experiments on Enron-email and a synthetic dataset show that the proposed method with relationship and analysis is potentially useful to extract previously unknown vital information.
Бесплатно
Mining Sequential Patterns from mFUSP - Tree
Статья научная
Mining sequential patterns from sequence database has consequential responsibility in the data mining region as it can find the association from the ordered list of events. Mining methods that predicated on the pattern growth approach, such as PrefixSpan, are well-organized enough to denude the sequential patterns, but engendering a projection database for each pattern regards as bottleneck of these methods. Lin (2008) first commenced the concept of tree structure to sequential pattern mining, which is acknowledged as Fast updated sequential pattern tree (FUSP - tree). However, link information stored in each node of FUSP - tree structure increases the complication of this method due to its link updating process. In this paper, at first, we have proposed a modified fast updated sequential pattern tree (called a mFUSP - tree) arrangement for storing the complete set of sequences with just frequent items, their frequencies and their relations among items in the given sequence into a compact data structure; excluding this tree structure avoids storing link information along to the next node of the following branch in the tree that carries the same item. Afterward, we have established by a mining method that our mFUSP - tree structure is proficient enough to ascertain out the perfect set of frequent sequential patterns from sequence databases without generating any intermediate projected tree and without calling for repeated scanning of the original database during mining. Our experimental result proves that, the performance of our proposed mFUSP - tree mining approach is a lot more trustworthy than other existing algorithms like GSP, PrefixSpan and FUSP - tree based mining.
Бесплатно
Статья научная
This study presents the results of a content analysis of 2476 tweets posted by Hillary Clinton and Donald Trump during the 2016 presidential election following their official nomination by their respective political parties. The study sought to determine whether the candidates used a focused campaign strategy in their tweets, and whether the tweets revealed priorities based on their focus and the time of the day they were posted. The results show that Clinton posted more tweets, had a more focused campaign than Trump during the same time frame.
Бесплатно
Mining the Shirt Sizes for Indian Men by Clustered Classification
Статья научная
In garment production engineering, sizing system plays an important role for manufacturing of clothing. The standards for defining the size label are a critical issue. Locating the right garment size for a customer depends on the label as an interface. In this research work intend to approach that it could be used for developing sizing systems by data mining techniques applied to Indian anthropometric dataset. We propose a new approach of two-stage data mining procedure for labelling the shirt types exclusively for Indian men. In the first stage , clustering technique applied on the original dataset, to categorise the size labels. Then these clusters are used for supervised learning in the second stage for classification. A sizing system classifies a specific population into homogeneous subgroups based on some key body dimensions. The space with these dimensions gives raise to complexity for finding uniform standards. This enables us to have an interface as a communication tool among manufacturers, retailers and consumers. This sizing system is developed for the men’s age ranges between 25 and 66 years. Main attribute happens to be the chest size as clearly visible in the data set. We have obtained classifications for men’s shirt attributes based on clustering techniques.
Бесплатно
Mixed QoS Controlled Wireless Streaming Media Transmission Strategy
Статья научная
Streaming media applications is currently limited by high bandwidth requirements. It is a challenging problem to provide the required quality of service (QoS) for the efficient transmission of video data under the varying network conditions such as the time-varying packet loss and fluctuating bandwidth. On Internet the most important part for streaming media transmission application is QoS control mechanism which including two kinds of QoS control method, based on end to end and network. A wireless streaming media forward platform based on the mixed quality-of-service (QoS) control system is introduced in this paper. The theoretical knowledge related to the quality of service and mixed quality of service control of the feasibility and characteristics are analyzed, and introduced a comprehensive quality of service in theory. This system combines network control and end to end quality of service control. The network of the system is optimized to support quality of service, using the underlying network devices, network bandwidth optimization, network structure adapted to meet the both ends of the quality of service. At both ends, from the delay, jitter, etc. are adjusted, by the addition of the timestamp and other information on the dynamic adjustment of the speed of data transmission. Through improving the control of two ends QoS and media streaming forward server, the video streaming from ships on the sea is transferred to the Internet by microwave and then linked to common Internet and mobile phone users through carrier networks(wired and wireless), which realized the real time supervision.
Бесплатно
Mobile Computing Trends in Saudi Arabia: An Exploratory Study
Статья научная
The main purpose of this research was to gain an understanding of the adoption behavior of mobile computing in Saudi Arabia. In particular, it aimed to acquire new insight into mobile computing trends, specifically in Saudi Arabia, in order to develop hypotheses and formulate precise criteria for mobile computing evaluation. In order to achieve these aims, the researcher created a focus group by recruiting eight participants with solid background knowledge of usability engineering and mobile computing. The focus group proposed a four-phase process: determination, qualification, categorization and evaluation of the mobile computing applications developed by Saudi organizations. During the determination phase, two hundred and twenty seven (n=227) mobile applications were determined as having been developed by organizations in Saudi Arabia. During the qualification phase, one hundred and forty two (n=142) mobile applications were qualified. Within the categorization phase, the experts categorized only the qualified applications into a two-level categorization hierarchy. Finally, in the evaluation phase, the qualified applications were evaluated in terms of purpose, platform, visual appearance, content, organization and usability. The results herein revealed that 43% of the mobile applications in Saudi Arabia were M-Government applications, while 57% were M-Business applications. In addition, the study proposed a sample of thirty six (n=36) applications as having statistical significance from all of the mobile applications in Saudi Arabia.
Бесплатно
Mobile Phone Based RIMS for Traffic Control a Case Study of Tanzania
Статья научная
Vehicles saturation in transportation infrastructure causes traffic congestion, accidents, transportation delays and environment pollution. This problem can be resolved with proper management of traffic flow. Existing traffic management systems are challenged on capturing and processing real-time road data from wide area road networks. The main purpose of this study is to address the gap by implementing a mobile phone based Road Information Management System. The proposed system integrates three modules for data collection, storage and information dissemination. The modules works together to enable real-time traffic control. Disseminated information from the system, enables road users to adjust their travelling habit, also it allows the traffic lights to control the traffic in relation to the real-time situation occurring on the road. In this paper the system implementation and testing was performed. The results indicated that there is a possibility to track traffic data using Global Positioning System enabled mobile phones, and after processing the collected data, real-time traffic status was displayed on web interface. This enabled road users to know in advance the situation occurring on the roads and hence make proper travelling decision. Further research should consider adjusting the traffic lights control system to understand the disseminated real-time traffic information.
Бесплатно
Статья научная
Model-driven testing is a method to verify the requirement specification of the system through UML models. Cuckoo search (CS) algorithm is based on the brooding characteristics of cuckoo birds. The test case generation process is used to identify the test cases with resources with critical domain requirements. This proposed paper emphasizing on the generation and optimization of test cases or test data using cuckoo search technique through a case study, i.e., the withdrawal operation in a Bank ATM and it also describes the generation of test cases from UML behavioral diagram like activity diagram, possible test paths are also generated through activity diagram graph.
Бесплатно
Modeling Truncated Loss Data of Operational Risk in E-banking
Статья научная
Operational risk is an important risk component for financial institutions, especially in E-banking. Large amount of capital that are assigned to decrease this risk are evidence to this subject. One of the most important factors for modeling operational risk to estimate capital charge is loss data collections of banks. But sometimes for reasons like decreasing the costs, banks save only the losses above some determined thresholds at their database. For achieving accurate capital charge, this threshold should be considered in determining capital charge. This paper focuses on modeling truncated loss data above some given threshold. We discuss several statistical methods for modeling truncated data, and suggest the best one for modeling truncated loss data. We have tested our suggested model for some operational loss data samples. Our results indicate that our approach can be useful for increasing accuracy of estimating operational risk capital charge in E-banking.
Бесплатно
Modeling of seamless vertical handover mechanism using demanded resource identification & mapping
Статья научная
One of the prominent challenges for offering seamless communication system while performing vertical handover in heterogeneous network is to relay the communication without identifying the accurate demands of the resources as well as quality of services for the newly moved node. After reviewing the existing literatures, it was found that there is a potential research gap in addressing this problem of seamless vertical handover. Therefore, the proposed manuscript addresses this problem by introducing a novel analytical model which is capable of formulating a precise decision for controlling the selection /dropping of the data packets on the basis of dynamic state of the network condition. The proposed system contributes faster processing by arbitrarily selecting the packets to be forwarded with a very unique and simple resource management. The study outcome of proposed system highlights an increased throughput and reduced length of queue along with better fairness control to offer seamless vertical handover.
Бесплатно
Статья научная
A new form of wireless sensor networks is emerging as an important component of the Internet of Things (IoT) where camera devices are interconnected and endowed with an IP address to form visual sensor networks. The applications of these networks span from smart parking systems in smart cities, video surveillance for security systems to healthcare monitoring and many others which are emerging from niche areas. The management of such sensor networks will require meeting a higher quality of service (QoS) constraints than demanded from traditional sensor networks. While many works have focused only on energy efficiency as a way of providing QoS in sensor networks, we consider a novel modelling approach where local optimizations implemented on the sensor nodes are translated into pheromone distribution used in ant colony optimization for path computation. We propose a routing protocol called the multipath ant colony optimization (MACO) that finds QoS-aware routing paths for the sensor readings from source nodes to the sink by relying on four local parameters: the link cost, the remaining energy of neighboring nodes, sensor nodes location information and the amount of data a neighbor node is currently processing. Finally, we propose an architecture for integrating sensor data with the cloud computing. Simulation results reveal the relative efficiency of the newly proposed approach compared to selected related routing protocols in terms of several QoS metrics. These include the network energy efficiency, delay and throughput.
Бесплатно
Modern Platform for Parallel Algorithms Testing: Java on Intel Xeon Phi
Статья научная
Parallel algorithms are popular method of increasing system performance. Apart from showing their properties using asymptotic analysis, proof-of-concept implementation and practical experiments are often required. In order to speed up the development and provide simple and easily accessible testing environment that enables execution of reliable experiments, the paper proposes a platform with multi-core computational accelerator: Intel Xeon Phi, and modern programming language: Java. The article includes the description of integration Java with Xeon Phi, as well as detailed information about all of the software components. Finally, the set of tests proves, that proposed platform is able to prepare reliable experiments of parallel algorithms implemented in modern programming language.
Бесплатно
Modified Binary Exponential Backoff Algorithm to Minimize Mobiles Communication Time
Статья научная
The field of Wireless Local Area Networks (LANs) is expanding rapidly as a result of advances in digital communications, portable computers, and semiconductor technology. The early adopters of this technology have primarily been vertical application that places a premium on the mobility offered by such systems. Binary Exponential Backoff (BEB) refers to a collision resolution mechanism used in random access MAC protocols. This algorithm is used in Ethernet (IEEE 802.3) wired LANs. In Ethernet networks, this algorithm is commonly used to schedule retransmissions after collisions. The paper’s goal is to minimize the time transmission cycle of the information between mobiles moving in a Wi-Fi by changing the BEB algorithm. The Protocol CSMA / CA manage access to the radio channel by performing an arbitration based on time. This causes many problems in relation to time transmission between mobiles moving in a cell 802.11. what we have done show that the protocol using CSMA / CA access time believed rapidly when the number of stations and / or the network load increases or other circumstances affects the network..
Бесплатно
Morphotactics of Manipuri Adjectives: A Finite-State Approach
Статья научная
This paper presents a constrained finite-state model to represent the morphotactic rule of Manipuri adjective word forms. There is no adjective word category in Manipuri language. By rule this category is derived from verb roots with the help of some selected affixes applicable only to verb roots. The affixes meant for the purpose and the different rules for adjective word category formation are identified. Rules are composed for describing the simple agglutinative morphology of this category. These rules are combined to describe the more complex morphotactic structures. Finite-state machine is used to describe the concatenation rules and corresponding non-deterministic and deterministic automaton are developed for ease of computerization. A root lexicon of verb category words is used along with an affix dictionary in a database. The system is capable to analyze and recognize a certain word as adjective by observing the morpheme concatenation rule defined with the help of finite-state networks.
Бесплатно
Статья научная
To achieve successful reusability of components a disciplined development approach is required which is the component based software engineering(CBSE).The software component selection is a vital part of this approach. It consists of defining an evaluation criteria based on user requirements and depending on this the repository is searched and shortlisted components are presented to the user. Due to availability of large number of components offering same type of functionality it is difficult to select a particular component based on available description. This paper presents a multiobjective optimization model for component selection purpose and solves it using preemptive goal programming approach by using an optimization tool LINDO. Subsequently, an illustrative case study is given where the components are taken from an online repository and goal programming is applied for getting the most optimal component. However, this model is applicable when the repository is small but for larger set of components it needs to be validated.
Бесплатно
Multi Objective Test Suite Reduction for GUI Based Software Using NSGA-II
Статья научная
Regression Testing is a performed to ensure modified code does not have any unintended side effect on the software. If regression testing is performed with retest-all method it will be very time consuming as testing activity. Therefore test suite reduction methods are used to reduce the size of original test suite. Objective of test suite reduction is to reduce those test cases which are redundant or less important in their fault revealing capability. Test suite reduction can only be used when time is critical to run all test cases and selective testing can only be done. Various methods exist in the literature related to test suite reduction of traditional software. Most of the methods are based of single objective optimization. In case of multi objective optimization of test suite, usually researchers assign different weight values to different objectives and combine them as single objective. However in test suite reduction multiple Pareto-optimal solutions are present, it is difficult to select one test case over other. Since GUI based software is our concern there exist very few reduction techniques and none of them consider multiple objective based reduction. In this work we propose a new test suite reduction technique based on two objectives, event weight and number of faults identified by test case. We evaluated our results for 2 different applications and we achieved 20% reduction in test suite size for both applications. In Terp Paint 3.0 application compromise 15.6% fault revealing capability and for Notepad 11.1% fault revealing capability is reduced.
Бесплатно
Multi Population Hybrid Genetic Algorithms for University Course Timetabling Problem
Статья научная
University course timetabling is one of the important and time consuming issues that each University is involved with it at the beginning of each. This problem is in class of NP-hard problem and is very difficult to solve by classic algorithms. Therefore optimization techniques are used to solve them and produce optimal or near optimal feasible solutions instead of exact solutions. Genetic algorithms, because of multidirectional search property of them, are considered as an efficient approach for solving this type of problems. In this paper three new hybrid genetic algorithms for solving the university course timetabling problem (UCTP) are proposed: FGARI, FGASA and FGATS. In proposed algorithms, fuzzy logic is used to measure violation of soft constraints in fitness function to deal with inherent uncertainly and vagueness involved in real life data. Also, randomized iterative local search, simulated annealing and tabu search are applied, respectively, to improve exploitive search ability and prevent genetic algorithm to be trapped in local optimum. The experimental results indicate that the proposed algorithms are able to produce promising results for the UCTP.
Бесплатно
Multi-Factor Authentication for Improved Enterprise Resource Planning Systems Security
Статья научная
Universities across the globe have increasingly adopted Enterprise Resource Planning (ERP) systems, a software that provides integrated management of processes and transactions in real-time. These systems contain lots of information hence require secure authentication. Authentication in this case refers to the process of verifying an entity’s or device’s identity, to allow them access to specific resources upon request. However, there have been security and privacy concerns around ERP systems, where only the traditional authentication method of a username and password is commonly used. A password-based authentication approach has weaknesses that can be easily compromised. Cyber-attacks to access these ERP systems have become common to institutions of higher learning and cannot be underestimated as they evolve with emerging technologies. Some universities worldwide have been victims of cyber-attacks which targeted authentication vulnerabilities resulting in damages to the institutions reputations and credibilities. Thus, this research aimed at establishing authentication methods used for ERPs in Kenyan universities, their vulnerabilities, and proposing a solution to improve on ERP system authentication. The study aimed at developing and validating a multi-factor authentication prototype to improve ERP systems security. Multi-factor authentication which combines several authentication factors such as: something the user has, knows, or is, is a new state-of-the-art technology that is being adopted to strengthen systems’ authentication security. This research used an exploratory sequential design that involved a survey of chartered Kenyan Universities, where questionnaires were used to collect data that was later analyzed using descriptive and inferential statistics. Stratified, random and purposive sampling techniques were used to establish the sample size and the target group. The dependent variable for the study was limited to security rating with respect to realization of confidentiality, integrity, availability, and usability while the independent variables were limited to adequacy of security, authentication mechanisms, infrastructure, information security policies, vulnerabilities, and user training. Correlation and regression analysis established vulnerabilities, information security policies, and user training to be having a higher impact on system security. The three variables hence acted as the basis for the proposed multi-factor authentication framework for improve ERP systems security.
Бесплатно
Multi-Feature Segmentation and Cluster based Approach for Product Feature Categorization
Статья научная
At a recent time, the web has become a valuable source of online consumer review however as the number of reviews is growing in high speed. It is infeasible for user to read all reviews to make a valuable or satisfying decision because the same features, people can write it contrary words or phrases. To produce a useful summary of domain synonyms words and phrase, need to be a group into same feature group. We focus on feature-based opinion mining problem and this paper mainly studies feature based product categorization from the number of users - generated review available on the different website. First, a multi-feature segmentation method is proposed which segment multi-feature review sentences into the single feature unit. Second part of speech dictionary and context information is used to consider the irrelevant feature identification, sentiment words are used to identify the polarity of feature and finally an unsupervised clustering based product feature categorization method is proposed. Clustering is unsupervised machine learning approach that groups feature that have a high degree of similarity in a same cluster. The proposed approach provides satisfactory results and can achieve 100% average precision for clustering based product feature categorization task. This approach can be applicable to different product.
Бесплатно
