International Journal of Information Technology and Computer Science @ijitcs
Статьи журнала - International Journal of Information Technology and Computer Science
Все статьи: 1227
Predicting the Occurrence of Cerebrovascular Accident in Patients using Machine Learning Technique
Статья научная
Cerebrovascular disease commonly known as stroke is the third leading cause of disability and mortality in the world. In recent years, technological advancements have transformed the way information is acquired and how problems are solved in diverse fields of human endeavors, including the medical and healthcare sectors. Machine Learning (ML) and data driven techniques have gain prominence in problem solving and have been deployed in the prediction of the occurrences of stroke. This work explores the application of supervised machine learning algorithms for the prediction of stroke, emphasizing the critical need for early prediction to enhance preventive measures. A comprehensive comparison of classification (Support Vector Machine and Random Forest) and regression (Logistic Regression) algorithms was conducted, with concerns on binary stroke outcome (likelihood of stroke and no stroke) data utilizing dataset from the International Stroke Trial database. The Synthetic Minority Oversampling Technique (SMOTE) and K-fold cross validation were used to balance and address the class imbalance in the datasets. The subsequent model comparison demonstrated distinct strengths and weaknesses among the three models. Random Forest (RF) exhibited high accuracy score of 89%, Support Vector Machine (SVM) and Logistic Regression (LR) showed 86% accuracy. LR demonstrated the most balanced predictive performance, achieving high precision for stroke cases and reasonable recall for both classes.
Бесплатно
Prediction Model of the Stock Market Index Using Twitter Sentiment Analysis
Статья научная
Stock market prediction has been an interesting research topic for many years. Finding an efficient and effective means of predicting the stock market found its way in different social networking platforms such as Twitter. Studies have shown that public moods and sentiments can affect one's opinion. This study explored the tweets of the Filipino public and its possible effects on the movement of the closing Index of the Philippine Stock Exchange. Sentiment Analysis was used in processing individual tweets and determining its polarity - either positive or negative. Tweets were given a positive and negative probability scores depending on the features that matched the trained classifier. Granger causality testing identified whether or not the past values of the Twitter time series were useful in predicting the future price of the PSE Index. Two prediction models were created based on the p-values and regression algorithms. The results suggested that the tweets collected using geo location and local news sources proved to be causative of the future values of the Philippine Stock Exchange closing Index.
Бесплатно
Prediction Models for Diabetes Mellitus Incidence
Статья научная
Diabetes mellitus is an incurable disease with global prevalence and exponentially increasing incidence. It is one of the greatest health hazards of the twenty-first century which poses a great economic threat on many nations. The premise behind effective disease management in healthcare system is to ensure coordinated intervention targeted towards reducing the incidence of such disease. This paper presents an approach to reducing the incidence of diabetes by predicting the risk of diabetes in patients. Diabetes mellitus risk prediction model was developed using supervised machine learning algorithms of Naïve Bayes, Support Vector Machine and J48 Decision Tree. The decision tree was able to give a prediction accuracy of 95.09% using rules of prediction that give acceptable results, that is, the model was approximately 95% accurate. The easy-to-understand rules of prediction got from J48 decision tree make it excellent in developing predictive models.
Бесплатно
Prediction and monitoring agents using weblogs for improved disaster recovery in cloud
Статья научная
Disaster recovery is a continuous dilemma in cloud platform. Though sudden scaling up and scaling down of user’s resource requests is available, the problem of servers down still persists getting users locked at vendor’s end. This requires such a monitoring agent which will reduce the chances of disaster occurrence and server downtime. To come up with an efficient approach, previous researchers’ techniques are analyzed and compared regarding prediction and monitoring of outages in cloud computing. A dual functionality Prediction and Monitoring Agent is proposed to intelligently monitor users’ resources requests and to predict coming surges in web traffic using Linear Regression algorithm. This solution will help to predict the user’s future requests’ behavior, to monitor current progress of resources’ usage, server virtualization and to improve overall disaster recovery process in Cloud Computing.
Бесплатно
Статья научная
Pharmacy handles all the medicine needed in the hospital that consists of vast amount of records. These produce large scale of datasets that are complex to manage and thereby need tools and technique to easily process, interpret, forecast and predict future consumption. Due to this, the method of predicting and forecasting stock consumption using Data Mining technique in hospital pharmacy is not be a surprising issue. Thus, this research investigated the potential applicability of data mining technology to predict the Anti-Retroviral drugs consumption for pharmacy based up on patient's history datasets of Jugal hospital, Harar, Ethiopia. The methodology used for this research is based on Knowledge Discovery in Database which had mostly relied on using the decision tree algorithms specifically M5P model tree. WEKA software, a data-mining tool were used for interpreting, evaluating and predicting from large datasets. Result with the data set suggests that tree based modeling approach can effectively be used in predicting the consumption of ARV drugs.
Бесплатно
Prediction of Defect Prone Software Modules using MLP based Ensemble Techniques
Статья научная
Prediction of defect prone software modules is now considered as an important activity of software quality assurance. This approach uses the software metrics to predict whether the developed module is defective or not. This research presents MLP based ensemble classification framework to predict the defect prone software modules. The framework predicts the defective modules by using three dimensions: 1) Tuned MLP, 2) Tuned MLP with Bagging 3) Tuned MLP with Boosting. In first dimension only the MLP is used for the classification after optimization. In second dimension, the optimized MLP is integrated with bagging technique. In third dimension, the optimized MLP is integrated with boosting technique. Four publically available cleaned NASA MDP datasets are used for the implementation of proposed framework and the performance is evaluated by using F-measure, Accuracy, Roc Area and MCC. The performance of the proposed framework is compared with ten widely used supervised classification techniques by using Scott-Knott ESD test and the results reflects the high performance of the proposed framework.
Бесплатно
Prediction of Missing Values for Decision Attribute
Статья научная
The process of determining missing values in information system is an important issue for decision making especially when the missing values are in the decision attribute. The main goal for this paper is to introduce algorithm for finding missing values of decision attribute. Our approach is depending on distance function between existing values. These values can be calculated by distance function between the conditions attributes values for the complete information system and incomplete information system. This method can deal with the repeated small distance by eliminating a condition attribute which has the smallest effect on the complete information system. This algorithm will be discussed in detail with an example of a case study.
Бесплатно
Preference-Based Web Service Composition: Case-Based Planning Approach
Статья научная
Web service selection is an indispensable process for web service composition. However it became a difficult task as many web services are increased on the web and mostly they offer similar functionalities, which service will be the best. User preferences are the key to retain only the best services for the composition. In this paper, we have proposed a web service composition model based on user preferences. To improve the process of web service composition we propose a case-based planning approach with user preferences which uses successful experiences in past to solve similar problems. In this paper we integrate user preferences in the phase of selection, adaptation and planning. Our main contributions are a new method of case retrieval, an extended algorithm of adaptation and planning with user preferences. Results obtained offer more than a solution to the user and taking both functional and non-functional requirements.
Бесплатно
Primary-Backup Access Control Scheme for Securing P2P File-Sharing Systems
Статья научная
Peer-to-peer (P2P) file-sharing systems have gained large interests among the internet users. However, wide-scale applications of P2P file-sharing technologies are constrained by the limitations associated with the sophisticated control mechanisms. Moreover, the decentralized and anonymous characteristics of P2P environments make it more difficult to control accesses on the shared resources, especially for using traditional access control methods. To overcome these limitations, we propose a role-based access control architecture for P2P file-sharing systems that supports autonomous decisions and centralized controls. The architecture integrates policies of credential, identity and role-based access control models to provide scalable, efficient and fault-tolerant access control services. Furthermore, we employ the primary-backup (PB) scheme to preserve P2P decentralized structure and peers’ autonomy property while enabling collaboration between peers. In particular, we propose a method for setting up interoperating relationships between domains by role mappings and resolve two kinds of interoperability conflicts while mapping roles from foreign domain to local domain without centralized authority. We believe that the proposed architecture is realistic, efficient and can provide controlled communications between peers.
Бесплатно
Статья научная
The study is devoted to assessing the risks of cyber threats in the future based on expert sampling patterns. One of the key problems of modern cybersecurity is the dynamic nature of threats that change under the influence of technological progress and socio-economic factors. In this context, the authors consider a methodological approach that involves the use of a multi-level analysis of expert opinions. The main emphasis is placed on taking into account the different points of view, experience and professional activities of experts from the public, private and academic sectors. An important stage of the study is the procedure of data cleaning to form a representative sample that takes into account only logically consistent responses of experts. The paper focuses on the integration of the expert sample patterns‘ features. The key differences in threat assessments between different groups of experts depending on their professional role and experience are identified. This made it possible to formulate comprehensive recommendations for strategic cyber risk management focused on both short-term and long-term priorities. The study makes a significant contribution to understanding the peculiarities of cyber risk assessment through the use of multivariate analysis of expert opinions. The proposed methodology allows not only to improve the quality of forecasts of future cyber threats, but also contributes to the creation of adaptive cybersecurity strategies that take into account the specifics of each sector. The findings of the study emphasize the importance of a multidimensional approach to analyzing cyber threats, taking into account the specifics of each expert group. Integration of assessments and consideration of local peculiarities are key to the development of adaptive and effective cyber defense strategies focused on global and local challenges.
Бесплатно
Prioritization of Barriers to Digitization for Circular Systems using Analytical Hierarchy Process
Статья научная
The increasing urgency for sustainable practices has motivated this research to explore the barriers hindering the adoption of digital technologies in circular systems. As industries seek to leverage IoT for enhanced efficiency and sustainability, understanding these barriers is crucial for effective implementation. This study employs a comprehensive, multi–dimensional approach, integrating insights from a literature review and expert interviews with industry professionals. Key findings reveal that technological complexity and high initial costs are the most significant barriers, highlighting the need for targeted strategies to address these challenges. Additional barriers include regulatory compliance issues and unclear return on investment, which further complicate the adoption process. The study's conclusion emphasizes that overcoming these barriers is essential for facilitating the successful integration of digital technologies in circular economies. Furthermore, the research identifies the necessity for future investigations into the interactions between these barriers and the effectiveness of various interventions. The novelty of this study lies in its holistic examination of the multifaceted barriers, combining qualitative insights with a structured analytical framework. This approach not only contributes to the existing literature on Digitization but also offers practical implications for stakeholders aiming to enhance sustainability and efficiency in their operations. By addressing the identified challenges, organizations can pave the way for a more circular and resilient future, ultimately driving innovation and growth in the rapidly evolving digital landscape.
Бесплатно
Priority Based New Approach for Correlation Clustering
Статья научная
Emerging source of Information like social network, bibliographic data and interaction network of proteins have complex relation among data objects and need to be processed in different manner than traditional data analysis. Correlation clustering is one such new style of viewing data and analyzing it to detect patterns and clusters. Being a new field, it has lot of scope for research. This paper discusses a method to solve problem of chromatic correlation clustering where data objects as nodes of a graph are connected through color-labeled edges representing relations among objects. Purposed heuristic performs better than the previous works.
Бесплатно
Priority Based Uplink Scheduling Scheme for WiMAX Service Classes
Статья научная
IEEE 802.16 standard supports five different service classes in order to support different needs of the mobile users with different QoS criteria. But, this standard doesn’t specify admission control and scheduling mechanisms and so far many solutions are proposed in the science world. In this paper we propose priority based uplink scheduling scheme for IEEE 802.16 standard that improves the QoS performances of the five WiMAX service classes, especially of the ertPS service class. Simulation experiments and analysis are done choosing the most adequate WiMAX simulator and the ns-2 simulation tool. Traffic load of the ertPS connections is changed from low to high in order to perform detailed performance analysis of the results. Results given in average delay, average jitter and average throughput are evaluated and compared with so far known uplink scheduling mechanism. The results show that our proposed uplink scheduling scheme based on the priority of the service classes improves the QoS performances especially in high loaded scenarios.
Бесплатно
Processing of Satellite Digital Images for Mapping Atmospheric Transmissivity in Bangladesh
Статья научная
This study investigates the potential of determining atmospheric transmissivity (τ) from NOAA-AVHRR satellite images using a simple methodology. Using this method, hourly transmissivity values over the land surface area of Bangladesh has been determined. The spatio-temporal distribution of τ has been studied by constructing monthly average maps for the whole country for one complete year (February 2005 to January 2006). Yearly average map has been prepared by integrating monthly average maps. Geographical distribution of τ exhibits patterns and trends. It is observed that the value of τ varies from 0.3 to 0.65 with the average maximum value in the month of April and minimum value in the month of November. It is also observed that for western parts of the country, which is the drought prone area, transmissivity values are little bit higher than that at the eastern parts. Relatively lower values of τ in the dry months (November to January) may be due to the effect of particulate or chemical pollution in the atmosphere.
Бесплатно
Статья научная
Software process improvement (SPI) is an important requirement in a software company. The search for better approach brought different kinds of models with multiple sets of principles for SPI to be founded. The framework is proposed to mainly address an alternative way of achieving a better process capability. The approach focuses on the implementation of SPI which can seamlessly align with the organization nature, day to day business activities, and financial capability. The paper provides the detailed implementation guideline and application of the framework through case study results. The case study is performed in a software development unit placed under academic institution. The unit is founded specifically for application development for internal and external customers. The case study is designed to be implemented in two software development projects in the development unit. From the ongoing case study, the results from the first project which is completed in six iterations are presented in this paper. Considering SPI implementation, the development team followed the framework and associated procedures throughout the development process. The results obtained in terms of aligning SPI to the daily development task and CMMI KPAs capability improvement achieved showed promising results.
Бесплатно
Pronunciation Proficiency Evaluation based on Discriminatively Refined Acoustic Models
Статья научная
The popular MLE (Maximum Likelihood Estimation) is a generative approach for acoustic modeling and ignores the information of other phones during training stage. Therefore, the MLE-trained acoustic models are confusable and unable to distinguish confusing phones well. This paper introduces discriminative measures of minimum phone/word error (MPE/MWE) to refine acoustic models to deal with the problem. Experiments on the database of 498 people’s live Putonghua test indicate that: 1) Refined acoustic models are more distinguishable than conventional MLE ones; 2) Even though training and test are mismatch, they still perform significantly better than MLE ones in pronunciation proficiency evaluation. The final performance has approximately 4.5% relative improvement.
Бесплатно
Proposal of Implicit Coordination Model for Performance Enhancement Using Sprint Zero
Статья научная
Scrum model always welcome the new requirements from customer at any stage of software development. This situation creates problem for development team to meet estimated timelines. The Scrum development team is always under heavy workload and stress because of this situation. A high level of coordination among team members is required in order to overcome this work pressure and meet quality demands within estimated time and cost. Scrum model emphasis to coordinate through communication to cope with changing requirements. Scrum development is facing new challenges to meet high quality demands with critical timeline environment. The ability of a team to act intelligently in such situation is gaining key position for the survival and success of an organization. The goal of this paper is to highlight the role of implicit coordination helping the software development team members to act intelligently in time demand environment to achieve common goals. Implicit coordination among team members during sprint zero development can show significant improvement in team performance. This will help to achieve high quality product under heavy workload within estimated time period. A survey is conducted to validate the research i.e., implicit coordination has strong impact for successful implementation of Scrum methodology.
Бесплатно
Proposal of New PRORISK Model for GSD Projects
Статья научная
The level of complexity and risks associated with software are increasing exponentially because of competing environment especially in geographically distributed projects. Global software development (GSD) face challenges like distance, communication and coordination challenges. The coordination and communication challenges are the main causes of failure in GSD. Project Oriented Risk Management (PRORISK) is one of the models to address the importance of risk management and project management processes in standard software projects. However, existing model is not proposed to handle GSD associated risks. This warrants the proposal of new PRORISK model to manage the risks of GSD. Survey is used as a research design to validate the proposed solution. We anticipate that the proposed solution will help the software companies to cater the risks associated with GSD.
Бесплатно
Provisioning quality of service for multimedia applications in cloud computing
Статья научная
Since the last decade, many new trends have been introduced to access network technologies and services through internet. Cloud computing is one of those significant technologies that reduce the cost and increase the productivity by providing a variety of services. Recently, cloud computing based system is primarily used for multimedia applications. Over the cloud computing, multimedia applications has some significant quality of service (QoS) requirements such as bandwidth, jitter, latency etc. But due to some limitations in services providing, it is constantly complex to make selection for an appropriate service. Keeping in view the provision of multimedia services through cloud computing, many different concepts and approaches that provide better cloud services under the constraints of QoS attributes have been described in the literature. The goal of this paper is to assess the applicability and provision of multimedia applications over cloud computing through enhanced quality of service. We have identified the primary quality of service msetrics evaluation of multimedia services over cloud computing. Furthermore, under these metrics we evaluated the existing approaches that provide multimedia related services with their strengths and limitations. This evaluation approach could provide the service that can provide better QoS in multimedia applications over cloud computing.
Бесплатно
Статья научная
Microwave-Induced Thermo-Acoustic Tomograp- phy (MITAT) has attracted more concerns in recent years in biomedical imaging field. It has both the high contrast of the microwave imaging and the high resolution of ultrasound imaging. As compared to optoacoustics, which uses instead a pulsed light for evoking optoacoustic response, thermo-aco- ustic imaging has the advantage of deeper tissue penetration, attaining the potential for wider clinical dissemination, especially for malignant tumors. In this paper, the induced thermo-acoustic wave propagating in a mimic biologic tissue is simulated by numeric method Pseudo-Spectrum Time Domain (PSTD). Due to the excellent performance in noise- depress and the stability for the fluctuation of the model parameters, Time Reversal Mirror (TRM) imaging technique is studied computationally for the simulative received therm- o-acoustic signals. Some thermo-acoustic objects with differ- ent initial pressure distribution are designed and imaged by TRM technique to represent the complex biologic tissue case in a random media. The quality of images generated by TRM technique based on PSTD method hints the potential of the MITAT technique.
Бесплатно
