Статьи журнала - International Journal of Information Technology and Computer Science
Все статьи: 1195
An ensemble model using a BabelNet enriched document space for twitter sentiment classification
Статья научная
With the widespread usage of social media in our daily lives, user reviews emerged as an impactful factor for numerous fields including understanding consumer attitudes, determining political tendency, revealing strengths or weaknesses of many different organizations. Today, people are chatting with their friends, carrying out social relations, shopping and following many current events through the social media. However social media limits the size of user messages. The users generally express their opinions by using emoticons, abbreviations, slangs, and symbols instead of words. This situation makes the sentiment classification of social media texts more complex. In this paper a sentiment classification model for Twitter messages is proposed to overcome this difficulty. In the proposed model first the short messages are expanded with BabelNet which is a concept network. Then the expanded and the original form of the messages are included in an ensemble learning model. Consequently we compared our ensemble model with traditional classification algorithms and observed that the F-measure value is increased.
Бесплатно
Статья научная
In today’s world tremendous amount of unstructured data, especially text, is being generated through various sources. This massive amount of data has lead the researchers to focus on employing data mining techniques to analyse and cluster them for an efficient browsing and searching mechanisms. The clustering methods like k-means algorithm perform through measuring the relationship between the data objects. Accurate clustering is based on the similarity or dissimilarity measure that is defined to evaluate the homogeneity of the documents. A variety of measures have been proposed up to this date. However, all of them are not suitable to be used in the k-means algorithm. In this paper, an extensive study is done to compare and analyse the performance of eight well-known similarity and dissimilarity measures that are applicable to the k-means clustering approach. For experiment purpose, four text document data sets are used and the results are reported.
Бесплатно
Статья научная
The transport or advection-diffusion-reaction equation is a well-known partial differential equation employed to model several types of flux problems. The cooling fin problem is a particular case of such an equation. This work presents a straightforward model for the rectangular cooling fin in a problem. The model was based on the finite differences numerical method and an efficient implementation was developed in a high-level mathematical programming language. The accuracy was evaluated with different granularity levels of meshes, and two distinct boundary conditions are compared. In the first one, only prescribed temperatures are assumed at the four tips of the domain. For the second scenario, it is assumed a heat flux at one tip of a fin with the same geometrical shape. The achieved solutions produced by the algorithm were able to depict the temperature along the whole fin surface accurately. Furthermore, the algorithm reaches relevant performance for meshes up to 4257 points where the CPU time was about 33 seconds.
Бесплатно
Статья научная
Collaborative team formation in a social network is an important aspect for solving a real-world problem that requires different expert skills to achieve it. In this paper, we propose an improved African Buffalo Optimization algorithm integrated with discrete crossover operator conjointly with swap sequence for efficient team formation whose members can assist in solving a given problem with minimum communication cost. The proposed algorithm is called Improved African Buffalo Optimization algorithm (IABO). In IABO, a new concept of swap sequence applied to improve the performance by generating better team members that cover all the required skills. To the best of our knowledge, this is the first work that considers the African Buffalo Optimization algorithm for collaborative team formation in a social network of experts. A set of experiments have been done on two popular real-world benchmark datasets (i.e., DBLP and Stack Overflow) to determine the efficiency of the proposed algorithm in team formation. The results demonstrate the effectiveness of the IABO algorithm in comparison with GA, PSO and standard African Buffalo Optimization algorithm (ABO). 10.5815/ijitcs.2018.05.02
Бесплатно
Статья научная
Significant work has already been done for complex quadratics. However, the dynamics of rational functions and their properties are equally interesting. In this paper we have generated computer images from a C++ computer program. We have then developed an artificial neural network model using predictive modeling software based on RMS type of error out of two samples of points obtained from the generated images. The imaginary part of sample II was predicted by applied the real parts of sample I and sample II to the artificial neural network. The real part of sample II was more important than the real part of sample I in predicting the imaginary part of sample II. The predicted imaginary part of sample II was then imported to Matlab Signal Processing Tool (SPTool) via Matlab workspace. We have applied a stable band pass filter to the model to eliminate noise from it for its analysis. A modulated signal produced reveals that the methodology used shall be applied to explore properties of computer generated images from the generated wavelet. We have further imported the predicted imaginary part of sample II to autoSIGNAL software for time and frequency range analysis of the continuous wavelet transform.
Бесплатно
Analogue Wavelet Transform Based the Solution of the Parabolic Equation
Статья научная
In this paper we have proved that the solution of parabolic equation and its Fast Fourier Transform generate continuous wavelet transforms. Indeed, we have solved the parabolic equation using PDETool, exported its solution and coefficients to Matlab workspace. We have then imported the solution from workspace to signal processing tool. We have sampled the imported solution with the sampling frequency of 8192Hz and applied the band pass filter with that frequency. The convolution of the sampled PDE solution with the impulse response of the band pass filter has generated wavelet transform. This algorithm computes the wavelet transform either directly of via Faster Fourier Transform. The computation of the FFT of the PDE solution has produced complex wavelet.
Бесплатно
Analysing Open Source Software in Terms of Its Characteristics and Establishing New Paradigms
Статья научная
The world that we see and in which we live is driven by open source platforms. Whether we talk about Linux and Apache or Drupal and Joomla (all are open source platforms), right from the beginning the open source technology has always been influencing. If we go online and try to find out open source link, we find that it is difficult to find a site/online application without an open source connection. This paper examines Free and Open Source Software (FOSS) in an empirical setup in terms of its major characteristics i.e. Deployability and Usability. These two characteristics of FOSS are ex-tremely important from point of view of its comparison with proprietary software. The different attributes of FOSS were identified in the literature and were made part of the present study to carry out empirical analysis of FOSS. Apart from this a number of attributes were also included in this empirical study those were agreed upon by the participants while carrying out pilot study. This paper throws light on the experience of different kinds of users associated with FOSS. The statistical analysis using fisher's exact test was used to conclude the dependability of important characteristics of FOSS on each other.
Бесплатно
Analysis and Ranking of Software Reliability Models Based on Weighted Criteria Value
Статья научная
Many software reliability growth models (SRGMs) have been analyzed for measuring the growth of software reliability. Selection of optimal SRGMs for use in a particular case has been an area of interest for researchers in the field of software reliability. All existing methodologies use same weight for each comparison criterion. But in reality, it is the fact that all the parameters do not have the same priority in reliability measurement. Keeping this point in mind, in this paper, a computational methodology based on weighted criteria is presented to the problem of performance analysis of various non-homogenous Poisson process (NHPP) models. It is relatively simple and requires less calculation. A set of twelve comparison criteria has been formulated and each criterion has been assigned different weight to rank the software reliability growth models proposed during the past 30 years. Case study results show that the weighted criteria value method offers a very promising technique in software reliability growth models comparison.
Бесплатно
Статья научная
The application of modern information technologies in the oil and gas sector is constantly developing, which facilitates the acceleration of exploration and detection of oil, the increase in oil production and reduction in risks relates to health, human safety, and the environment. The Internet of things in the oil and gas sector, like in all sectors of industry, has great prospects from an economic point of view. The article is devoted to the study of the current state and avenues of solving key problems of effective and reliable functioning of the oil and gas industry as a cyber-physical system using the Internet of things in the Azerbaijani oil company SOCAR. The main technological processes and existing opportunities for the application of information technologies in the oil and gas complex are analyzed. New approaches are proposed to solve the problems in the oil and gas complex as cyber-physical system based on the smart sensors, the Internet of things, wireless networks and cloud technologies. The implementation of the proposed model is aimed at increasing the effectiveness, resource storage, exploration reliability and durability of the oil and gas complex.
Бесплатно
Analysis of MC-CDMA System in Mobile Communications
Статья научная
Wireless communication plays an important role in our daily life. One of the most important techniques which is Candidate for the fourth generation is Multicarrier Code Division Multiple Access (MC-CDMA) due to its high data rate. This research paper presents the MC-CDMA system using different modulation techniques. The variety of modulation types are depended in order to show the effects of modulation index and type on broadcasting data. The bit error rate of the system is plotted for a range of signal to noise ratio so that the effect of modulation on the MC-CDMA system will be evident. Actually, the simulation results show that QAM gives less bit error rate that makes MC-CDMA more flexible and suitable for mobile communication next generation technology. Also, the peak-to-average power (PAPR) of MC-CDMA is analyzed to show that high PAPR is the main disadvantage of MC-CDMA system then the possible solutions for this problem are discussed in this research paper.
Бесплатно
Analysis of Metric-Based Object-Oriented Code Refactoring Opportunities Identification Approaches
Статья научная
Refactoring is used to improve deteriorated software design, code and their maintainability. In object-oriented (OO) code, before refactoring is performed, its opportunities must be identified and several approaches exist this regard. Among the approaches is the software metric-based approach where quality software metrics are used. Therefore, this paper provide analysis of existing empirical studies that utilized software metrics to identify refactoring opportunities in OO software systems. We performed a comprehensive analysis on 16 studies to identify the state-of-the-practice. The focal point was on the workings, refactoring activities, the programming language and the impact on software quality. The results obtained shows approaches were not unique, each was designed either for a single refactoring activity or couple of them, move method and extract class dominated the refactorings activities, and most approaches were fully automated while few were semi-automated. Moreover, OO metrics played acritical role in both opportunities detection and factoring decisions. Based on the results, it would be beneficial if generic refactoring approach is developed that is capable of identifying needs for all refactoring activities.
Бесплатно
Analysis of Parametric & Non Parametric Classifiers for Classification Technique using WEKA
Статья научная
In the field of Machine learning & Data Mining, lot of work had been done to construct new classification techniques/ classifiers and lot of research is going on to construct further new classifiers with the help of nature inspired technique such as Genetic Algorithm, Ant Colony Optimization, Bee Colony Optimization, Neural Network, Particle Swarm Optimization etc. Many researchers provided comparative study/ analysis of classification techniques. But this paper deals with another form of analysis of classification techniques i.e. parametric and non parametric classifiers analysis. This paper identifies parametric & non parametric classifiers that are used in classification process and provides tree representation of these classifiers. For the analysis purpose, four classifiers are used in which two of them are parametric and rest of are non-parametric in nature.
Бесплатно
Статья научная
Nowadays, various Wireless Health Monitoring Systems use Internet of Things to transmit patient's data over Wireless Sensor Network and then the data is stored and processed via Cloud Computing, however, the use of different kind of Wireless Sensor on each system leads to power efficiency problem. This paper analyses and compares the consumption of power on six Wireless Health Monitoring Systems, which are invented to monitor the patient's condition and transfer the data using Wireless Sensor Network. Three different techniques are analyzed, namely GPRS/UMTS (used in one WHMS), Wi-Fi (used in one WHMS), and Bluetooth (used in four WHMS). This paper concludes that the systems that use Bluetooth as their transmission medium are more effective in reducing power consumption than the other systems that use GPRS/UMTS or Wi-Fi.
Бесплатно
Analysis of Requirement Engineering Processes, Tools/Techniques and Methodologies
Статья научная
Requirement engineering is an integral part of the software development lifecycle since the basis for developing successful software depends on comprehending its requirements in the first place. Requirement engineering involves a number of processes for gathering requirements in accordance with the needs and demands of users and stakeholders of the software product. In this paper, we have reviewed the prominent processes, tools and technologies used in the requirement gathering phase. The study is useful to perceive the current state of the affairs pertaining to the requirement engineering research and to understand the strengths and limitations of the existing requirement engineering techniques. The study also summarizes the best practices and how to use a blend of the requirement engineering techniques as an effective methodology to successfully conduct the requirement engineering task. The study also highlights the importance of security requirements as though they are part of the non-functional requirement, yet are naturally considered fundamental to secure software development.
Бесплатно
Analysis of Tandem Repeat Patterns in Nlrc4 using a Motif Model
Статья научная
Exponential accumulation of biological data requires computer scientists and bioinformaticians to improve the efficiency of computer algorithms and databases. The recent advancement of computational tools has boosted the processing capacity of enormous volume of genetic data. This research applied a computational approach to analyze the tandem repeat patterns in Nlrc4 gene. Because the protein product of Nlrc4 gene is important in detecting pathogen and triggering subsequent immune responses, the results of this genetic analysis is essential for the understanding of the genetic characteristics of Nlrc4. The study on the distribution of tandem repeats may provide insights for drug design catered for the Nlrc4-implicated diseases.
Бесплатно
Статья научная
This article explores the multifaceted challenges inherent in ensuring the cybersecurity of critical infrastructures, i.e., a linchpin of modern society and the economy, spanning pivotal sectors such as energy, transportation, and finance. In the era of accelerating digitalization and escalating dependence on information technology, safeguarding these infrastructures against evolving cyber threats becomes not just crucial but imperative. The examination unfolds by dissecting the vulnerabilities that plague critical infrastructures, probing into the diverse spectrum of threats they confront in the contemporary cybersecurity landscape. Moreover, the article meticulously outlines innovative security strategies designed to fortify these vital systems against malicious intrusions. A distinctive aspect of this work is the nuanced case study presented within the oil and gas sector, strategically chosen to illustrate the vulnerability of critical infrastructures to cyber threats. By examining this sector in detail, the article aims to shed light on industry-specific challenges and potential solutions, thereby enhancing our understanding of cybersecurity dynamics within critical infrastructures. This article contributes a comprehensive analysis of the challenges faced by critical infrastructures in the face of cyber threats, offering contemporary security strategies and leveraging a focused case study to deepen insights into the nuanced vulnerabilities within the oil and gas sector.
Бесплатно
Analyzing Cost Parameters Affecting Map Reduce Application Performance
Статья научная
Recently, big data analysis has become an imperative task for many big companies. Map-Reduce, an emerging distributed computing paradigm, is known as a promising architecture for big data analytics on commodity hardware. Map-Reduce, and its open source implementation Hadoop, have been extensively accepted by several companies due to their salient features such as scalability, elasticity, fault-tolerance and flexibility to handle big data. However, these benefits entail a considerable performance sacrifice. The performance of a Map-Reduce application depends on various factors including the size of the input data set, cluster resource settings etc. A clear understanding of the factors that affect Map-Reduce application performance and the cost associated with those factors is required. In this paper, we study different performance parameters and an existing Cost Optimizer that computes the cost of Map-Reduce job execution. The cost based optimizer also considers various configuration parameters available in Hadoop that affect performance of these programs. This paper is an attempt to analyze the Map-Reduce application performance and identifying the key factors affecting the cost and performance of executing Map-Reduce applications.
Бесплатно
Статья научная
This study presents a comprehensive assessment of the test performance of Bachelor of Science in Information Technology (BSIT) students in the System Integration and Architecture (SIA) course, coupled with a meticulous examination of the quality of test questions, aiming to lay the groundwork for enhancing the assessment tool. Employing a cross-sectional research design, the study involved 200 fourth-year students enrolled in the course. The results illuminated a significant discrepancy in scores between upper and lower student cohorts, highlighting the necessity for targeted interventions, curriculum enhancements, and assessment refinements, particularly for those in the lower-performing group. Further examination of the item difficulty index of the assessment tool unveiled the need to fine-tune certain items to better suit a broader spectrum of students. Nevertheless, the majority of items were deemed adequately aligned with their respective difficulty levels. Additionally, an analysis of the item discrimination index identified 25 items suitable for retention, while 27 items warranted revision, and 3 items were suitable for removal, as per the analysis outcomes. These insights provide a valuable foundation for improving the assessment tool, thereby optimizing its capacity to evaluate students' acquired knowledge effectively. The study's novel contribution lies in its integration of both student performance assessment and evaluation of assessment tool quality within the BSIT program, offering actionable insights for improving educational outcomes. By identifying challenges faced by BSIT students and proposing targeted interventions, curriculum enhancements, and assessment refinements, the research advances our understanding of effective assessment practices. Furthermore, the detailed analysis of item difficulty and discrimination indices offers practical guidance for enhancing the reliability and validity of assessment tools in the BSIT program. Overall, this research contributes to the existing body of knowledge by providing empirical evidence and actionable recommendations tailored to the needs of BSIT students, promoting educational quality and student success in Information Technology.
Бесплатно
Analyzing the Impact of Prosodic Feature (Pitch) on Learning Classifiers for Speech Emotion Corpus
Статья научная
Emotion plays a significant role in human perception and decision making whereas, prosodic features plays a crucial role in recognizing the emotion from speech utterance. This paper introduces the speech emotion corpus recorded in the provincial languages of Pakistan: Urdu, Balochi, Pashto Sindhi and Punjabi having four different emotions (Anger, Happiness, Neutral and Sad). The objective of this paper is to analyze the impact of prosodic feature (pitch) on learning classifiers (adaboostM1, classification via regression, decision stump, J48) in comparison with other prosodic features (intensity and formant) in term of classification accuracy using speech emotion corpus recorded in the provincial languages of Pakistan. Experimental framework evaluated four different classifiers with the possible combinations of prosodic features with and without pitch. An experimental study shows that the prosodic feature (pitch) plays a vital role in providing the significant classification accuracy as compared to prosodic features excluding pitch. The classification accuracy for formant and intensity either individually or with any combination excluding pitch are found to be approximately 20%. Whereas, pitch gives classification accuracy of around 40%.
Бесплатно
Статья научная
This paper illustrates a comparison study for control of highly non-linear Double Inverted Pendulum (DIP) on cart. A Matlab-Simulink model of DIP has been built using Newton's second law. The Neuro-fuzzy controllers stabilizes pendulums at vertical position while cart moves in horizontal direction. This study proposes two soft-computing techniques namely Fuzzy logic reasoning and Neural networks (NN's) for control of DIP systems. The results shows that Fuzzy controllers provides better results as compared to NN's controllers in terms of settling time (sec), maximum overshoot (degree) and steady state error. The regression (R) and mean square error (MSE) values obtained after training of Neural network were satisfactory. The simulation results proves the validity of proposed techniques.
Бесплатно
