International Journal of Modern Education and Computer Science @ijmecs
Статьи журнала - International Journal of Modern Education and Computer Science
Все статьи: 1096
Performance Evaluation of Various Machine Learning Algorithms for User Story Clustering
Статья научная
In agile development, user stories are the primary method for defining requirements. These days, managing user stories effectively is difficult because software projects typically contain a large number of them. A project can involve a large amount of user stories, which should be clustered into different groups based on their functionality’s similarity for systematic requirements analysis, effective mapping to developed features, and efficient maintenance. Unfortunately, the majority of user story clustering methods now in use require a great deal of manual work, which is error-prone and time-consuming. In this research, we suggest an automated framework that uses a family of machine learning algorithms to classify user stories. First, preprocessing the data is done in order to examine user stories and extract keywords from them. After that, features are taken out, which allow user stories to be automatically grouped into distinct categories. We use four feature extraction algorithms and six clustering algorithms. According to our experimental results, K-means and BIRCH clustering outperform other clustering methods, whereas cosine similarity and distance are the best feature extraction for user stories categorization to form the more balanced clusters as they both have the standard deviation is 3.08. In case of user stories cohesion, the silhouette coefficient value is 0.225 for spectral with (cosine similarity and cosine distance feature extraction) is best outcome than other clustering algorithms. The usefulness and applicability of the suggested framework are demonstrated by this study. Additionally, it offers some useful recommendations for enhancing the effectiveness of user stories clustering, for example through parameter adjustments for enhanced feature extraction and clustering.
Бесплатно
Performance Evaluation on the Effect of Combining DCT and LBP on Face Recognition System
Статья научная
In this paper, we introduce a face recognition algorithm based on doubly truncated multivariate Gaussian mixture model with Discrete Cosine Transform (DCT) and Local binary pattern (LBP). Here, the input face image is transformed to the local binary pattern domain. The obtained local binary pattern image is divided into non-overlapping blocks. Then from each block the DCT coefficients are computed and feature vector is extracted. Assigning that the feature vector follows a doubly truncated multivariate Gaussian mixture distribution, the face image is modelled. By using the Expectation-Maximization algorithm the model parameters are estimated. The initialization of the model parameters is done by using either K-means algorithm or hierarchical clustering algorithm and moment method of estimation. The face recognition system is developed with the likelihood function under Bayesian frame. The efficiency of the developed face recognition system is evaluated by conducting experimentation with JNTUK and Yale face image databases. The performance measures like half total error rate, recognition rates are computed along with plotting the ROC curves. A comparative study of the developed algorithm with some of the earlier existing algorithm revealed that this system perform better since, it utilizes local and global information of the face.
Бесплатно
Performance enhancement of machine translation evaluation systems for English – Hindi language pair
Статья научная
Machine Translation (MT) is a programmed conversion in which computer software is utilized to convert manuscripts from one Natural Language (like English) to a different Language (such as Hindi). To process any such conversion, through human or through automatic means, the conversion must be established such that it reinstate the complete sense of a manuscript from its base (source) linguistic into the target language. In this paper, the study of prevailing evaluation systems along with assessing their performance is achieved through the similarity metrics. Moreover, the authors have also presented an improved technique of translation employing features of Natural Language Processing and consequently, to acquire an enhanced and more accurate assessing Machine Translation system, a corpus is selected and the outcomes are compared with the prevailing methods. Besides this, two well-known systems such as Google and Bing decoders are selected to inquire and to assess the study of metrics called similarity metrics through Assessment of Text Essential Characteristics score. This is found to provide more accuracy than prevailing methods. Furthermore, evaluations are tested under various metrics systems like Jaccard similarity metrics, cosine similarity metrics, and sine metrics to deliver enhanced accuracy than prevailing methods.
Бесплатно
Performing Inquisitive Study of PM Traits Desirable for Project Progress
Статья научная
The accountability of a project’s success/failure lies on shoulders of a PM (project manager). Undoubtedly, project management is tough task to bring about and this is the most challenging role within the project. The project manager role varies from project to project and may include communication & negotiation with stakeholders, along with leadership and management of the project. Therefore he must possess both hard and soft skills besides education and expertise to drive his team towards excellence. This scientific documentation presents an ideal blend of responsibilities and skills essential for a project manager to cope with the changing project environment. Technical skills necessary for an IT project manager, further elaborates this study.
Бесплатно
Person Authentication using Relevance Vector Machine (RVM) for Face and Fingerprint
Статья научная
Multimodal biometric systems have proven more efficient in personal verification or identification than single biometric ones, so it is also a focus of this paper. Particularly, in the paper, the authors present a multimodal biometric system in which features from face and fingerprint images are extracted using Zernike Moment (ZM), the personal authentication is done using Relevance Vector Machine (RVM) and feature-level fusion technique. The proposed system has proven its remarkable ability to overcome the limitations of uni-modal biometric systems and to tolerate local variations in the face or fingerprint image of an individual. Also, the achieved experimental results have demonstrated that using RVM can assure a higher level of forge resistance and enables faster authentication than the state-of-the-art technique , namely the support vector machine (SVM).
Бесплатно
Personalized recommendation systems (PRES): a comprehensive study and research issues
Статья научная
The type of information systems used to recommend items to the users are called Recommendation systems. The concept of recommendations was seen among cavemen, ants and other creatures too. Users often rely on opinion of their peers when looking for selecting something, this usual behavior of the humans, led to the development of recommendation systems. There exist various recommender systems for various areas. The existing recommendation systems use different approaches. The applications of recommendation systems are increasing with increased use of web based search for users’ specific requirements. Recommendation techniques are employed by general purpose websites such as google and yahoo based on browsing history and other information like user’s geographical locations, interests, behavior in the web, history of purchase and the way they entered the website. Document recommendation systems recommend documents depending on the similar search done previously by other users. Clickstream data which provides information like user behavior and the path the users take are captured and given as input to document recommendation system. Movie recommendation systems and music recommendation systems are other areas in use and being researched to improve. Social recommendation is gaining the momentum because of huge volume of data generated and diverse requirements of the users. Current web usage trends are forcing companies to continuously research for best ways to provide the users with the suitable information as per the need depending on the search and preferences. This paper throws light on common strategies being followed for building recommendation systems. The study compares existing techniques and highlights the opportunities available for research in this area.
Бесплатно
Perspective of Database Services for Managing Large-Scale Data on the Cloud: A Comparative Study
Статья научная
The influx of Big Data on the Internet has become a question for many businesses of how they can benefit from big data and how to use cloud computing to make it happen. The magnitude at which data is getting generated day by day is hard to believe and is beyond the scope of a human's capability to view and analyze it and hence there is an imperative need for data management and analytical tools to leverage this big data. Companies require a fine blend of technologies to collect, analyze, visualize, and process large volume of data. Big Data initiatives are driving urgent demand for algorithms to process data, accentuating challenges around data security with minimal impact on existing systems. In this paper, we present many existing cloud storage systems and query processing techniques to process the large scale data on the cloud. The paper also explores the challenges of big data management on the cloud and related factors that encourage the research work in this field.
Бесплатно
Plants Disease Segmentation using Image Processing
Статья научная
The image segmentation performs a significant role in the field of image processing because of its wide range of applications in the agricultural fields to identify plants diseases by classifying the different diseases. Classification is a technique to classify the plants diseases on different morphological characteristics. Different classifiers are used to classify such as SVM (Support Vector Machine), K- nearest neighbor classifiers, Artificial Neural Networks, Fuzzy Logic, etc. This paper presents different image processing techniques used for the early detection of different Plants diseases by different authors with different techniques. The main focus of our work is on the critical analysis of different plants disease segmentation techniques. The strengths and limitations of different techniques are discussed in the comparative evaluation of current classification techniques. This study also presents several areas of future research in the domain of plants disease segmentation. Our focus is to analyze the best classification techniques and then fuse certain best techniques to overcome the flaws of different techniques, in the future.
Бесплатно
Pragmatic evaluation of iscrum & scrum
Статья научная
Scrum has emerged as a most adopted and most desired Agile approach that provides corporate strategic competency by laying a firm foundation for project management. Scrum, being more of a framework than a rigid methodology, offers maximum flexibility to its practitioners. However, there are several challenges confronted during its implementation for which certain researchers not only adapted, but also augmented Scrum with other Agile practices. One such effort is IScrum, an Improved Scrum process model. In this paper an empirical study has been conducted for analyzing the two models i.e. classical Agile Scrum model and IScrum process model. There are two goals of this study: first is to validate the IScrum and the second goal is to evaluate it in comparison with the traditional Scrum model. Subsequently, the study will describe and highlight which characteristics of Scrum are enhanced in IScrum. Furthermore, a survey is used to investigate the teams’ experience with both models. The results of survey and case-study have been examined and compared to find out if IScrum performs well than Scrum in software development. The outcomes advocate that the improvements were quite effective in resolving most of the problem areas. The IScrum can thus be adopted by industry practitioners as best choice.
Бесплатно
Статья научная
Predicting College placements based on academic performance is critical to supporting educational institutions and students in making informed decisions about future career paths. The present research investigates the use of Machine Learning (ML) algorithms to predict college students' placements using academic performance data. The study makes use of a dataset that includes a variety of academic markers, such as grades, test scores, and extracurricular activities, obtained from a varied sample of college students. To create predictive models, the study analyses numerous ML algorithms, including Logistic Regression, Gaussian Naive Bayes, Random Forest, Support Vector Machine, and K-Nearest Neighbour. The predictive models are evaluated using performance criteria such as accuracy, precision, recall, and F1-score. The most effective machine learning method for forecasting students' placements based on academic achievement is identified through a comparative study. The findings show that Random Forest approaches have the potential to effectively forecast college student placements. The findings show that academic factors such as grades and test scores have a considerable impact on prediction accuracy. The findings of this study could be beneficial to educational institutions, students, and career counsellors.
Бесплатно
Статья научная
Education is one of the necessities of an individual’s life, as it enhances the self-morality and nobility that leads one towards the challenging pathways of the competitive world. In the agricultural based country, education is scarce among the children of the farmers as they suffer from poverty. After affecting with COVID-19, study dropout rate of farmers’ children is increased. We collected raw data from rural areas of different countries, and pre-processed this data before applying the machine learning algorithm to improve the performance. We used advanced machine learning models to predict whether farmer’s children will run or drop out of their education. Based on the outcomes it was viewed that, machine learning strategies substantiate to be suitable in this area. This research proposes preventive steps for dropping out of the farmers' children. It also shows that, the Random Forest being the highest reliable model for foreseeing dropout rate and education level.
Бесплатно
Статья научная
In online education through web conference tools, teachers cannot grasp students' states by watching their behaviors like in an offline classroom. Each student also cannot be affected by others' good behavior. This paper proposes a prediction method of the student effort through acceleration sensors and a heart rate sensor worn on a student's body, and a local camera. The effort is expressed by the levels of concentration, excitation, and bodily action. A Random Forest regression model is used to predict each level from the sensor and camera data. Exhibiting the prediction result brings visibility of student states like offline. We verified the effectiveness of the prediction model through an experiment. We built the Random Forest regression prediction models from the sensors, camera, and student effort data obtained by actual lectures. In the case of building one prediction model for one lecture/one subject, the average R2 values were 0.953, 0.925, and 0.930 in the concentration, excitation, and bodily action, respectively. The R2 was -0.835 when one prediction model trained by one lecture's data is applied for another lecture's prediction. That was 0.285 when one model by 4 subjects' data is applied for prediction for the rest 1 subject. It means that the prediction model has high accuracy but is dependent on individual persons and lectures, which forces a burden to individual student to collect initial training data for individual lecture to build a prediction model. We also found that the acceleration data are the most important features. It implies the effectiveness of using acceleration sensors to predict student effort.
Бесплатно
Predicting Student Program Completion Using Naïve Bayes Classification Algorithm
Статья научная
Data mining approaches provide different educational institutions opportunities to find hidden patterns from the data stored in the database. Many researchers have used these data to develop a model that would assist the institution administrators in decision-making. This study was performed to predict student program completion using the Naïve Bayes classifier technique. The dataset utilized in this study was obtained from Bulacan State University – Sarmiento Campus in the Philippines under BS Information Technology program from five-year graduates’ data for Academic Year 2012-2016. This dataset was pre-processed, cleansed, transformed, and balanced before constructing the model. Ten predictors were used for predicting student completion. The feature selection technique was used to filter and evaluate the significance of each factor. The significant variables assessed by the feature selection technique (Weight by Correlation) were the final parameters in creating the model. The Naïve Bayes classifier was applied to predict the students’ completion using the 70:30 ratios for training and testing dataset distribution. Correlation analysis identified the weight of individual attributes to the label attribute. From 10 possible predictor variables, only four (4) predictor variables were selected after correlation analysis. The identified significant attributes affecting program completion, namely (in order of significance): parents' monthly income, mother and father's educational attainment, and High School GPA attributes. The significant attributes identified in correlation analysis splitted into 70% training data or 447 records and 30% testing data or 191 records. There were 84 out of 191 data samples, or 44% of students were predicted to complete the program. On the other hand, 107 out of 191 data samples, or 56%, were predicted as not completing the program. The accuracy values performed an 84% rating with 80.46% class precision, and 83.33% class recall in the testing dataset (n=191). The outcomes of this study have a significant impact on HEIs, particularly on college completion rates. This study shall be highly significant and beneficial specifically to university administrators as this be a tool for them to identify students who will complete college based on variables included in the model.
Бесплатно
Статья научная
This study compared two neural network models (Multilayer Perceptron and Generalized Regression Neural Network) with a view to identifying the best model for predicting students’ academic performance based on single performance factor. Only academic factor (students’ results) was considered as the single performance factor of the study. One cohort of graduated students’ academic data was collected from the Computer Science and Engineering Department of Obafemi Awolowo University, Nigeria using documents and records technique. The models were simulated using MATLAB version 2015a and evaluated using mean square error, receiver operating characteristics and accuracy as the performance metrics. The results obtained show that although Multilayer Perceptron had prediction accuracy of 75%, Generalized Regression Neural Network had a better accuracy. The response time of Generalized Regression Neural Network (0.016sec) was faster than Multilayer Perceptron (0.03sec) and its memory consumption size (5kb) lower than that of Multilayer Perceptron (8kb). The simulated models were further compared with t-test method using a confidence interval of 95%. The attained t-test result from p-value (0.6854) suggests acceptance of null hypothesis, which shows that there is no significant difference between the predicted Grade Point Average and the actual Grade Point Average. The findings therefore reveal that the overall performance of Generalized Regression Neural Network outperforms the Multilayer Perceptron model with an accuracy of 95%. The study concluded that Generalized Regression Neural Network model which was simulated and with 95 % accuracy could be deployed by educationists to predict students’ academic performance using single performance factor.
Бесплатно
Predictive Model for Academic Training Course Recommendations Based on Machine Learning Algorithms
Статья научная
Given the significance of online education, a recommendation system provides a good opportunity to advise the most suitable courses according to their interest and preferences. This study proposes an academic training course recommendation that applies machine learning algorithms to provide the most appropriate 21st century learning based on individual preferences. To address the issue of imbalanced classification, the eight development skills are grouped into three skill categories during the preprocessing stage. In the classification step, several machine learning algorithms, including Decision Tree, Random Forest, Gradient Boosting, and Backpropagation Neural Network, are used to create a predictive model, which is then compared to the results of Logistic Regression. These machine learning algorithms predict the skill group based on the teacher preference data, which results in the suggestion of training courses that are customized to the teacher's profile. According to the experimental results, all machine learning algorithms showed superior prediction performance than Logistic Regression. The Backpropagation Neural Network exhibits high precision, reaching up to 78%, and demonstrates the best performance for the testing data. This research demonstrates that machine learning algorithms significantly improve the accuracy and efficiency of the training course recommendation. On this basis, this training course recommendation system will be advantageous to both the teachers looking for up- and reskilling training courses for 21st century learning. Additionally, it will be appropriate for training course designers to establish training courses that develop 21st-century learning in accordance with participants’ interests and professional development.
Бесплатно
Predictive analytic game-based model for Yoruba language learning evaluation
Статья научная
Be it indigenous or foreign language, languages are core for communicating messages from one person to another or group of persons. Primarily, it is learnt at home, schools, through the media like television and radio programmes. However, most of these language-teaching approaches do not measure the percentage growth of people who have gained the knowledge of the language over the years; they also lack the capacity to foretell the range of people that will acquire the knowledge of the language in the latest future. This is because several of the language teaching aids do not have the required dataset to describe and effectively predict the state of the language (a category of people who can speak and write the language) now, and against the future. Here, the research proposed an analytic game based model for Yoruba language evaluation. The essence is first to ascertain the user’s initial knowledge of a language, train users through difference fun filled game stages and levels, evaluate the user at the end of every level and analyse the clustered dataset of users game points to describe and predict the state of the language by using a dual level predictive analytics technique.
Бесплатно
Статья научная
Literature show that there are limited factors for existing models in e-learning systems’ adoption. This has raised an increasing sensible debate about factors affecting successful adoption of e-leaning systems in universities in developing world particularly in Tanzania. This preliminary study aimed at exploring multiple factors for successful adoption of e-learning systems in universities in learner perspective, using DeLone and McLean (2003) IS success model as a base model. This study was conducted by collecting data randomly, using the questionnaire from students of Open Universities of Tanzania (OUT) with response rate of 0.83 in a cross-sectional study and later analyzed through content validity, reliability, and criterion-based predictive validity. The preliminary analysis shows that there are twelve distinctive factors affecting e-learning systems’ adoption in universities in Tanzania. This finding suggests more empirical research studies to follow it up, to cement and generalize this case and validate the proposed model in large scale. The novelty of this research lies on the number and uniqueness of factors found.
Бесплатно
Prioritization of Test Cases in Software Testing Using M2 H2 Optimization
Статья научная
By and large, software testing can be well thought-out as a adept technique of achieving improved software quality as well as reliability. On the other hand, the eminence of the test cases had significant effect on the fault enlightening competence of testing activity. Prioritization of Test case (PTC) remnants one challenging issue, as prioritizing test cases remains not up in the direction of abrasion by means of respect to Faults Detected Average Percentage (FDAP) and time execution results. The PTC is predominantly anticipated to scheme assortment of test cases in accomplishing timely optimization by means of preferred properties. Earlier readings have been presented for place in order the accessible test cases in upsurge speed the fault uncovering rate in testing. In this phase, this learning schemes a Modern modified Harris Hawks Optimization centered PTC (M2H2O-PTC) method for testing. The anticipated M2H2O-PTC method aims to exhaust the possibilities the FDAP and curtail the complete execution time. Besides, the M2H2O algorithm is considered for boosting the examination and taking advantage abilities of the conservative H2O algorithm. For validating the enhanced efficiency of the M2H2O-PTC method, an extensive variety of simulations occur on contradictory standard programs and the outcomes are inspected underneath numerous characteristics. The investigational results emphasized enhanced proficiency of the M2H2O-PTC method in excess of the modern methodologies in standings of dissimilar measures.
Бесплатно
Privacy in the age of Pervasive Internet and Big Data Analytics – Challenges and Opportunities
Статья научная
In the age of pervasive internet where people are communicating, networking, buying, paying bills, managing their health and finances over the internet, where sensors and machines are tracking real-time information and communicating with each other, it is but natural that big data will be generated and analyzed for the purpose of "smart business" and "personalization". Today storage is no longer a bottleneck and the benefit of analysis outweighs the cost of making user profiling omnipresent. However, this brings with it several privacy challenges – risk of privacy disclosure without consent, unsolicited advertising, unwanted exposure of sensitive information and unwarranted attention by malicious interests. We survey privacy risks associated with personalization in Web Search, Social Networking, Healthcare, Mobility, Wearable Technology and Internet of Things. The article reviews current privacy challenges, existing privacy preserving solutions and their limitations. We conclude with a discussion on future work in user controlled privacy preservation and selective personalization, particularly in the domain of search engines.
Бесплатно
Procedure for Processing Biometric Parameters Based on Wavelet Transformations
Статья научная
The problem of the article is related to the improvement of means of covert monitoring of the face and emotions of operators of information and control systems on the basis of biometric parameters that correlate with two-dimensional monochrome and color images. The difficulty in developing such tools has been shown to be largely due to the cleaning of images associated with biometric parameters from typical non-stationary interference caused by uneven lighting and foreign objects that interfere with video recording. The possibility of overcoming these difficulties by using wavelet transform technology, which is used to filter images by combining several identical, but differently noisy monochrome and color images, is substantiated. It is determined that the development of technology for the use of wavelet transforms is primarily associated with the choice of the type of basic wavelet, the parameters of which must be adapted to the conditions of use in a particular system of covert monitoring of personality and emotions. An approach to choosing the type of basic wavelet that is most effective in filtering images from non-stationary interference is proposed. The approach is based on a number of the proposed provisions and efficiency criteria that allow to ensure when choosing the type of basic wavelet taking into account the significant requirements of the task. A filtering procedure has been developed, which, due to the application of the specified video image filtering technology and the proposed approach to the choice of the basic wavelet type, allows to effectively clean the images associated with biometric parameters from typical non-stationary interference. The conducted experimental studies have shown the feasibility of using the developed procedure for filtering images of the face and iris of operators of information and control systems.
Бесплатно
