International Journal of Modern Education and Computer Science @ijmecs
Journal articles - International Journal of Modern Education and Computer Science
All articles: 1173
Development of an English to Yorùbá Machine Translator
Scientific article
The study formulated a computational model for English to Yorùbá text translation process. The modelled translation process was designed, implemented and evaluated. This was with a view to addressing the challenge of English to Yorùbá text machine translator. This machine translator can translate modify and non-modify simple sentences (subject verb object (SVO)). Digital resources in English and its equivalence in Yorùbá were collected using the home domain terminologies and lexical corpus construction techniques. The English to Yorùbá translation process was modelled using phrase structure grammar and re-write rules. The re-write rules were designed and tested using Natural Language Tool Kits (NLTKs). Parse tree and Automata theory based techniques were used to analyse the formulated model. Unified Modeling Language (UML) was used for the software design. The Python programming language and PyQt4 tools were used to implement the model. The developed machine translator was tested with simple sentences. The results for the Basic Subject-Verb-Object (BSVO) and Modified SVO (MSVO) sentences translation show that the total Experimental Subject Respondents (ESRs), machine translator and human expert average scores for word syllable, word orthography, and sentence syntax accuracies were 66.7 percent, 82.3 percent, and 100 percent, respectively. The system translation accuracies were close to a human expert.
Free
Development of “Explores the Tenggarong City” Using Autonomous Response of Adaptive NPC
Scientific article
The game is one of the big industries today and can be an alternative entertainment to spend holidays and free time and become a very fun activity for children and adults. The game can also be used as an interactive and attractive promotional media with the theme of traveling. One of the development methods that can support the game platform is Finite State Machine. This method is used to regulate the behavior of Non-Player Character (NPC) in order to guide players to complete the game. The results of the study showed that "Explores The Tenggarong City" game is based on Android, has an interesting gameplay and makes the process of knowledge about destination very enjoyable so that players are expected to know information about the destination in Tenggarong City. This research contributes to the development of NPC and FSM in promotional games.
Free
Scientific article
Diabetes is a chronic disease related to the rise of levels of blood glucose. The disease that leads to serious damage to the heart, blood vessels, eyes, kidneys, and nerves is one of the reasons of death among the people in the world. There are two main types of diabetes: Type 1 and Type 2. The former is a chronic condition in which the pancreas produces little or no insulin by itself. The latter usually in adults, occurs when insulin level is insufficient. Classification of diabetes mellitus data which is one of the reasons of death among the people in the world is important. This study which successfully distinguishes diabetes or normal persons contains two major steps. In the first step, the feature selection or weighting methods are analyzed to find the most effective attributes for this disease. In the further step, the performances of AdaBoost, Gradient Boosted Trees and Random Forest ensemble learning algorithms are evaluated. According to experimental results, the prediction accuracy of the combination of Stability Selection method and AdaBoost learning algorithm is a little better than other algorithms with the classification accuracy by 73.88%.
Free
Different Platforms for Remote Laboratories in Mobile Devices
Scientific article
Remote laboratory is an innovative approach to create and provide laboratory experience to geographically dispersed students from anywhere at any time. One of the most important aspects of remote laboratories is to provide the user maximum mobility and freedom to perform experiments. Apart from the PC-based remotely triggered laboratories to enhance technical education, mobile devices can play a major role in wider implementation of the laboratory for hardware-based remote experimentation. In this paper, different techniques, such as, Adobe Flash Lite, HTML5 and SMS for developing platforms for mobile devices are studied and compared.
Free
Differential antagonistic games with lexicographic vector-payoffs
Scientific article
In this paper the existence problem of the equilibrium situation in differential antagonistic games with perfect information and lexicographic payoffs or in a -dimensional vector-payoffs' game where criteria are strictly ranged with preference relation is studied. The players' dinamic is defined by vector differential x=f( t,x ,u ),y=g( t,y ,v ) equations, respectively control functions u( .), v(. ) and ∈〔0.T〕time interval. This is a game ΓL(x0, y0)=(Γ1,...Γm ) where x0, y0 are starting positions in t=0 moment respectively the first and second players'. x(t)and y(t) are trajectories, the players final aim is finding their optimal variants. A lexicographic ε -equilibrium situation is defined in the game and the conditions of its existence are investiga-terd. These conditions are mainly about f and g functi-ons. The main definitions are introduced and some results are formulated from theory of differential games with scalar payoff functions and independent move-ments, they are the main for getting results for analogic differential games in the case of lexicographic payoffs. Some auxiliary statements correctness are also establi-shed, on its basic it is proved that in ΓL(x0, y0) game for any ε>0 there exists a lexicographic ε-equilibrium situation in pure strategies.
Free
Digital Forensics through Application Behavior Analysis
Scientific article
The field of digital forensic analysis has emerged in the past two decades to counter the digital crimes and investigate the modus operandi of the culprits to secure the computer systems. With the advances in technologies and pervasive nature of the computing devices, the digital forensic analysis is becoming a challenging task. Due to ease of digital equipment and popularity of Internet, criminals have been enticed to carry out digital crimes. Digital forensic is aimed to investigate the criminal activity and bring the culprits to justice. Traditionally the static analysis is used to investigate about an incident but due to a lot of issues related the accuracy and authenticity of the static analysis, the live digital forensic analysis shows an investigator a more complete picture of memory dump. In this paper, we introduce a module for profiling behavior of application programs. Profiling of application is helpful in forensic analysis as one can easily analyze the compromised system. Profiling is also helpful to the investigator in conducting malware analysis as well as debugging a system. The concept of our model is to trace the unique process name, loaded services and called modules of the target system and store it in a database for future forensic and malware analysis. We used VMware workstation version 9.0 on Windows 7 platform so that we can get the detailed and clean image of the current state of the system. The profile of the target application includes the process name, modules and services which are specific to an application program.
Free
Scientific article
This paper discusses teaching-learning experiences for children using today games and digital interactive activities in order to understand the benefits and difficulties for their use. This study also contextualizes the subject under the light of authors from the fields of design and education, resulting in conclusions about the relationship between the advancement of technology, its integration into the school and the effectiveness of new digital materials designed today.
Free
Dimensionality reduction using an improved whale optimization algorithm for data classification
Scientific article
Whale optimization algorithm is a newly proposed bio-inspired optimization technique introduced in 2016 which imitates the hunting demeanor of hump-back whales. In this paper, to enhance solution accuracy, reliability and convergence speed, we have introduced some modifications on the basic WOA structure. First, a new control parameter, inertia weight, is proposed to tune the impact on the present best solution, and an improved whale optimization algorithm (IWOA) is obtained. Second, we assess IWOA with various transfer functions to convert continuous solutions to binary ones. The pro-posed algorithm incorporated with the K-nearest neighbor classifier as a feature selection method for identifying feature subset that enhancing the classification accuracy and limiting the size of selected features. The proposed algorithm was compared with binary versions of the basic whale optimization algorithm, particle swarm optimization, genetic algorithm, antlion optimizer and grey wolf optimizer on 27 common UCI datasets. Optimization results demonstrate that the proposed IWOA not only significantly enhances the basic whale optimization algorithm but also performs much superior to the other algorithms.
Free
Direction to Prepare Item Bank for the Purpose of On-Line Evaluation
Scientific article
Straight forward meaning of On-Line Evaluation is that, few questions are extracted from the question bank and user is asked to "mark" the response. Normally, questions are assumed to be of "objective type". In this paper, this traditional idea is extended and abstract concept of "Item Bank" is introduced. The researchers have developed and tested Item Bank software earlier. The guidelines discussed in the paper are the outcome of this real life experience. The scope of the Item bank would not be confined only the Evaluation of competency of respondents but it covers assessment of the person for fresh recruitments/ Assignments or for the Reward or to Accredit the achievement of the employee performance with the use of client server architecture.
Free
Discovery of Association Rules from University Admission System Data
Scientific article
Association rules discovery is one of the vital data mining techniques. Currently there is an increasing interest in data mining and educational systems, making educational data mining (EDM) as a new growing research community. In this paper, we present a model for association rules discovery from King Abdulaziz University (KAU) admission system data. The main objective is to extract the rules and relations between admission system attributes for better analysis. The model utilizes an apriori algorithm for association rule mining. Detailed analysis and interpretation of the experimental results is presented with respect to admission office perspective.
Free
Discrete Model of Commensalism Between Two Species
Scientific article
This paper deals with an investigation on discrete model of host commensal pair. The model comprises of a commensal (S1), a host (S2) that benefit S1, without getting effected either positively or adversely. The model is characterized by a couple of first order non-linear ordinary differential equations. In all, four equilibrium points of the model would exist and their stability criteria is discussed. The model would be stable if each of the eigen values is numerically less than one. Further the growth rates of the species are numerically estimated using Runge-Kutta fourth order scheme.
Free
Discussion on Adolescent Internet Addiction Counseling Strategies through DEMATEL
Scientific article
Internet addiction and other such problems stem from the high frequency of Internet usage of adolescents. The study aims at working out the counseling strategy proposed to prevent internet addiction among the youth. In this study, DEMATEL was the avenue for creating a discussion with families, schools, the society and analyzing regulations & policies so as to find out the cause- and-effect relationship among them and work out the most efficient counseling strategy. The study result shows that the family plays the most crucial role in curing the adolescents’ Internet addiction through action.
Free
Scientific article
Identifying students’ learning styles is an important step in supporting adaptive and personalized learning environments, particularly in higher education contexts. This study investigates the use of a transformer-based language model, DistilBERT, for automated learning style identification based on the Felder–Silverman Learning Style Model (FSLSM). Binary responses from the 44-item Index of Learning Styles (ILS) questionnaire were systematically transformed into descriptive textual representations, preserving the underlying FSLSM decision logic while enabling semantic modeling. Separate DistilBERT classifiers were fine-tuned for the four FSLSM dimensions—Active/Reflective, Sensing/Intuitive, Visual/Verbal, and Sequential/Global. Model training was conducted using three epochs within a stratified five-fold cross-validation framework, with the primary objective of assessing optimization stability and representational consistency rather than predictive superiority. Across all dimensions, training loss decreased monotonically, with the most substantial reductions occurring between the first and second epochs, indicating rapid adaptation of pre-trained representations to the structured learning style descriptions. Differences in convergence behavior across dimensions were observed, reflecting variation in class distributions and response patterns. Near-perfect classification metrics were obtained across multiple folds; however, these results are interpreted as evidence of deterministic consistency between the textual inputs and FSLSM-derived labels rather than independent generalization performance. To examine alignment with human judgment, model predictions were further compared with expert assessments conducted independently using standard FSLSM interpretation guidelines. The resulting Cohen’s Kappa coefficient of 1.0 indicates perfect agreement, confirming that the model faithfully reproduces expert-consistent FSLSM categorizations under controlled conditions. Overall, the findings demonstrate that transformer-based models can reliably encode and recover rule-based learning style constructs from descriptive questionnaire data, supporting their use as computational tools for scalable, consistent learning style analysis, while acknowledging the task's deterministic and framework-dependent nature.
Free
Distributed Denial of Service Attacks: A Review
Scientific article
A wireless sensor network (WSN) is a wireless network consisting of spatially distributed autonomous devices using sensors to monitor physical or environmental conditions.WSN is a fluorishing network that has numerous applications and could be used in diverse scenarios. DDoS (Distributed Denial of Service) is an attack where a number of compromised systems attack a single target, thereby causing denial of service for users of the targeted system. The flood of incoming messages to the target system essentially forces it to shut down, thereby denying service to the system to legitimate users.Not much research work has been done in DDoS in WSN.We are conducting a review on DDoS attack to show its impact on networks and to present various defensive, detection and preventive measures adopted by researchers till now.
Free
Distribution System Planning With Distributed Generations Considering Benefits and Costs
Scientific article
One of the methods used in the design and utilization of distribution systems to improve power quality and reliability of load power supply of consumers, is the application of distributed generation (DG) sources. In this paper, a new method is proposed for the design and utilization of distribution networks with DG resources application by finding the optimal sitting and sizing of generated power of DG with the aim of maximization of its benefits to costs. The benefits for DG are considered as system losses reduction, system reliability improvement and benefits from the sale electricity or from lack of purchase of electricity from the main system. The costs of DG are considered as initial capital, maintenance and operation cost and investment cost. In this paper to solve the optimal sitting and sizing problem a Modified particle swarm optimization (PSO) is applied. Simulations are presented on a 69-bus test distribution system to verify the effectiveness of the proposed method. Results showed that the proposed high-power method to find the optimal points of problem is faster and application of DG resources reduced the losses, costs and improved the system voltage profile.
Free
Document Summarization Based on Information Retrieval Using Query Search Ranking Method
Scientific article
This work proposes a Query Searching Based Ranking Summarization Data Retrieval (QS-RSDR) method for document summarization based on information retrieval. QS-RSDR ranks query-based retrieval of important information, enabling the creation of a detailed report of information requirements using generated sections of sample documents. Relating Keyword Query Search Summarization (RKQSS) generates the main summary from the most relevant document in the query and then the summary from the other documents. The method resolves similarity terms related to the query using the Word Frequency (WF) method. Sentence ranking weights and sentence frequency improve the accuracy of the retrieved documents. Simulation results show improved accuracy in information retrieval. The proposed method can help address unclear and short queries and understand the nature of the required information behind the query. The paper concludes that QS-RSDR is an effective solution for document summarization based on information retrieval using the query search ranking method.
Free
Scientific article
In recent years there has been a massive growth in textual information in textual information especially in the internet. People now tend to read more e-books than hard copies of the books. While searching for some topic especially some new topic in the internet it will be easier if someone knows the pre-requisites and post- requisites of that topic. It will be easier for someone searching a new topic. Often the topics are found without any proper title and it becomes difficult later on to find which document was for which topic. A text categorization method can provide solution to this problem. In this paper domain based ontology is created so that users can relate to different topics of a domain and an automated text categorization technique is proposed that will categorize the uncategorized documents. The proposed idea is based on Term Frequency – Inverse Document Frequency (tf -idf) method and a dependency graph is also provided in the domain based ontology so that the users can visualize the relations among the terms.
Free
Driver behaviour profiling using dynamic Bayesian network
Scientific article
In the recent past, there has been a rapid increase in the number of vehicles and diversification of road networks worldwide. The biggest challenge now lies on how to monitor and analyse behaviours of vehicle drivers as a catalyst to road safety. Driver behaviour depends on the state and nature of the road, the state of the driver, vehicle conditions, and actions of other road users among other factors. This paper illustrates the ability of Dynamic Bayesian Networks towards determination of driving styles with respect to acceleration, cornering and braking patterns. Bayesian Networks are probabilistic graphical models that map a set of variables and their conditional dependencies. Sample test results showed that the 2-Time-slice Bayesian Network model is suitable for generation of driver profiles using only four GPS data parameters namely speed, altitude, direction and signal strength against time. The model classifies driver profiles into two sets of observations: driver behaviour and nature of operational environment. Adoption of the model could offer a cost effective, easy to implement and use solution that could find many applications in vehicle driver recruiting firms, vehicle insurance companies and transport and road safety authorities among other sectors.
Free
Scientific article
Most programmers and users resort to find individual solution per problem depending on the data and nature of problem, that will lead to solve a specific problem using an algorithm without the ability of this solution to solve a new problem. This variance comes from the difference in algorithm parameters from one problem to another, as these parameters related to data nature, its size, and values it carried that can affect the way algorithm work. Individual solutions lead to increase in time cost and effort spent on solving a new problem, which the new problem requires to work on programming new criteria for algorithm solution. That is prompted us to highlight necessaries to develop main components for algorithms used in practical life, such as data mining algorithms so that a solution designed for one problem can be more easily adapted to new problems with different data structures, within the general scope of decision tree applicability. These algorithm components need control mechanism settings, so when using component to solve problem, there is no need to develop algorithm settings again, regardless data size and data structure. We found that the dynamic solution saves effort and time needed to solve problems with same algorithm. In this paper, we present our methodology for using ID3 decision tree algorithm to mine data dynamically, and the mechanism used to achieve the dynamic solution, that provides a flexible and reusable solution for a wide range of problems that require decision tree support, reducing the need to redesign or reimplement models for each new task The proposed model was tested on three datasets. The proposed model achieved an accuracy of 97%, 97%, and 93% on the breast cancer, heart disease, and diabetes datasets, respectively.
Free
Dynamic Effort Allocation Problem Using Genetic Algorithm Approach
Scientific article
Effort distribution plays a major role in software engineering field. Because the limited price projects are becoming common today, the process of effort estimation becomes crucial, to control the budget agreed upon. In last 10 years, numerous software reliability growth models (SRGM) have been developed but majority of model are under static assumption. The basic goal of this article is to explore an optimal resource allocation plan to minimize the software cost throughout the testing phase and operational phase under dynamic condition using genetic algorithm technique. This article also studies the resource allocation problems optimally for various conditions by investigating the activities of the model parameters and also suggests policies for the optimal release time of the software in market place.
Free
