Статьи журнала - International Journal of Modern Education and Computer Science
Все статьи: 968
Effective Training Data Improved Ensemble Approaches for Urinalysis Model
Статья научная
Urinalysis remains one of the most commonly performed tests in clinical practice. Laboratory work can be greatly relieved by automated analyzing techniques. However, noisy and imbalanced urine samples make automatically identifying and classifying urine-related diseases become very difficult. This paper proposed hybrid sampling-based ensemble learning strategies by improving training data and classification performance. Having compared the effectiveness of several learning classifiers and data processing techniques, the experiments showed that the suggesting methods provided better classification accuracy than other approaches.
Бесплатно
Effectiveness of MOODLE in Education System in Sri Lankan University
Статья научная
This study examines students' overview of the students' online capabilities of course that we have implemented in the MOODLE platform in a developing country and underlying information technology principles that are critical for an in-depth understanding of e-learning. A structured multiple choice questionnaire was distributed among students' who were enrolled in the certificate of teaching in higher education course at the General Sir John Kotelawela Defence University, Sri Lanka. A total of 31 students participated in this study and completed written and online multiple choice questionnaire on MOODLE. The outcome of this study shows that there is a strong positive response on e-learning on MOODLE platform. Almost 61% of them were able to get extreme good results in the online examination and observed late submission in both printed and online examination. Although the outcome is preliminary in nature, the results provide cause for concern over the status of e-learning education in MOODLE platform in Sri Lanka which is highly satisfactory.
Бесплатно
Effects of Natural Dust on the Performance of PV Panels in Bangladesh
Статья научная
Energy is considered a prime agent in the generation of wealth and a significant factor in economic development. Limited fossil resources and environmental problems associated with them have emphasized the need for new sustainable energy supply options that use renewable energies. Among available technologies for energy production from solar source, photovoltaic system could give a significant contribution to develop a more sustainable energy system. Solar Panel has its wide use starting from a simple 5W diode lamp to a few kW ac drives. A solar panel with a battery and a charge controller and other auxiliary devices like dc to ac converters constitute a Solar Home System (SHS).Solar home system (SHS) is becoming popular day by day and even poor households are now becoming interested to purchase solar home system due to its various advantages. Solar home systems (SHS) have a major problem that is low efficiency. It also decreases output day by day because of improper maintenances, effect of dust and shadow. Accumulation of dust on solar panel of solar photovoltaic (PV) system is a natural process. It was found from the study that the accumulated dust on the surface of photovoltaic solar panel can reduce the system’s efficiency by up to 35% in one month .In this paper we show that the effect of dust accumulation on the solar panel naturally and how it is possible to overcome this problem.
Бесплатно
Статья научная
VANETs is the open model which stimulate in academia and industry oriented researches. However, the model is open and there are many violations in a communication of vehicle to vehicle (V2V) and Vehicle to Infrastructure (V2I). Any anonymous user may extract the useful information. Researchers have proposed many research proposal and solved issues related to VANET. The security is the major concern and to avoid mishappening in driving the vehicle. We proposed the authentication system that provides safety of the driver during travel on the roads. The proposed results deliver the following features: 1) Reliability of VANET model 2) Road Safety 3) Privacy of the vehicles 4) Authentication of message delivery to adjacent nodes. Finally, we provide a view point of how to detect the attacks and withdraw malicious node more efficiently.
Бесплатно
Efficient feature extraction in sentiment classification for contrastive sentences
Статья научная
Sentiment Classification is a special task of Sentiments Analysis in which a text document is assigned into some category like positive, negative, and neutral on the basis of some subjective information contained in documents. This subjective information called as sentiment features are highly responsible for efficient sentiment classification. Thus, Feature extraction is essentially an important task for sentiment classification at any level. This study explores most relevant and crucial features for sentiment classification and groups them into seven categories, named as, Basic features, Seed word features, TF-IDF, Punctuation based features, Sentence based features, N-grams, and POS lexicons. This paper proposes two new sentence based features which are helpful in assigning the overall sentiment of contrastive sentences and on the basis of proposed features; two algorithms are developed to find the sentiment of contrastive sentences. The dataset of TripAdvisor is used to evaluate our proposed features. Obtained results are compared with several state-of-the-art studies using various features on the same dataset and achieve superior performance.
Бесплатно
Element-Based Computational Model
Статья научная
A variation on the data-flow model is proposed to use for developing parallel architectures. While the model is a data driven model it has significant differences to the data- flow model. The proposed model has an evaluation cycle of processing elements (encapsulated data) that is similar to the instruction cycle of the von Neumann model. The elements contain the information required to process them. The model is inherently parallel. An emulation of the model has been implemented. The objective of this paper is to motivate support for taking the research further. Using matrix multiplication as a case study, the element/data-flow based model is compared with the instruction-based model. This is done using complexity analysis followed by empirical testing to verify this analysis. The positive results are given as motivation for the research to be taken to the next stage - that is, implementing the model using FPGAs.
Бесплатно
Статья научная
The increasing use of e-mail in the world because of its simplicity and low cost, has led many Internet users are interested in developing their work in the context of the Internet. In the meantime, many of the natural or legal persons, to sending e-mails unrelated to mass. Hence, classification and identification of spam emails is very important. In this paper, the combined Particle Swarm Optimization algorithms and Artificial Neural Network for feature selection and Support Vector Machine to classify and separate spam used have and finally, we compared the proposed method with other methods such as data classification Self Organizing Map and K-Means based on criteria Area Under Curve. The results indicate that the Area Under Curve in the proposed method is better than other methods.
Бесплатно
Emotional Design in Multimedia Learning: How Emotional Intelligence Moderates Learning Outcomes
Статья научная
This study is designed as a preliminary study to explore the effects of emotional intelligence (EI) on achievement, perceived intrinsic motivation and perceived satisfaction when expose to an emotional designed Multimedia Learning Environment (MLE) that was designed to induce either positive, neutral or negative emotions. All three designs had similar content and narration but differed in visual element such as colour, font size, font style and images. Based on the findings, it was reported that students performed better in the design used to induce negative emotion (NegD design) followed by the positive (PosD) and Neutral (NeuD). There is no significant difference in levels of emotional intelligence towards these learning outcomes; however, students with Low EI performed better overall. EI only qualified perceived satisfaction when using a MLE designed to induce emotions and it was found that students with Low EI preferred the design that induces positive emotions. In addition, High EI students favored designs with emotionality (positive or negative) compared to neutral design.
Бесплатно
Empirical Analysis of Bagged SVM Classifier for Data Mining Applications
Статья научная
Data mining is the use of algorithms to extract the information and patterns derived by the knowledge discovery in databases process. Classification maps data into predefined groups or classes. It is often referred to as supervised learning because the classes are determined before examining the data. The feasibility and the benefits of the proposed approaches are demonstrated by the means of data mining applications like intrusion detection, direct marketing, and signature verification. A variety of techniques have been employed for analysis ranging from traditional statistical methods to data mining approaches. Bagging and boosting are two relatively new but popular methods for producing ensembles. In this work, bagging is evaluated on real and benchmark data sets of intrusion detection, direct marketing, and signature verification in conjunction with as the base learner. The proposed is superior to individual approach for data mining applications in terms of classification accuracy.
Бесплатно
Empirical Analysis of HPC Using Different Programming Models
Статья научная
During the last decade, Heterogeneous systems are emerging for high performance computing [1]. In order to achieve high performance computing (HPC), existing technologies and programming models aims to see rapid growth toward intra-node parallelism [2]. The current high computational system and applications demand for a massive level of computation power. In last few years, Graphical processing unit (GPU) has been introduced an alternative of conventional CPU for highly parallel computing applications both for general purpose and graphic processing. Rather than using the traditional way of coding algorithms in serial by single CPU, many multithreading programming models has been introduced such as CUDA, OpenMP, and MPI to make parallel processing by using multicores. These parallel programming models are supportive to data driven multithreading (DDM) principle [3]. In this paper, we have presented performance based preliminary evaluation of these programming models and compared with the conventional single CPU serial processing system. We have implemented a massive computational operation for performance evaluation such as complex matrix multiplication operation. We used data driven multithreaded HPC system for performance evaluation and presented the results with a comprehensive analysis of these parallel programming models for HPC parallelism.
Бесплатно
Статья научная
The main aim of this paper is to avoid hot-spot problem in wireless sensor network with uniform energy dissipation among cluster heads in the network. It proposes an energy efficient unequal clustering mechanism to form limited and equivalent number of clusters across different levels of wireless sensor network to enable invariable energy consumption among them. Concentrated cluster formation near base station ensures minimum relay burden on cluster heads to avoid hot-spot problem in multi-hop data forwarding model. Equivalent number of clusters at each level ensures in-common network load on each cluster head among different data forwarding routes. In addition, a simple disjoint multi-hop routing technique is proposed for smooth data forwarding process. Simulation results evidence that the proposed unequal clustering algorithm overcomes hot-spot problem with invariable energy dissipation among cluster heads across the network and elevates sensor network lifetime.
Бесплатно
Energy saving VM placement in cloud
Статья научная
The tremendous gain owing to the ubiquitous acceptance of the cloud services across the globe results in more complexity for the cloud providers by way of resource maintenance. This has a direct effect on the cost economy for them if the resources are not efficiently utilized. Most of the allocation strategies follow mechanisms involving direct allotment of VMs onto the servers based on their capabilities. This paper presents a VM allocation strategy that looks at VM placement by allowing server capacity to be partitioned into different classes. The classes are mainly based on the RAM and processing abilities which would be matched with VMs need. When the match is found the servers from this category are provisioned for the task executions. Based on the experimentation for various datacenter scenarios, it has been found that the proposed mechanism results in significant energy savings with reduced response time compared to the traditional VM allocation policies.
Бесплатно
English Pronunciation Practice Method with CG Animations Representing Mouth and Tongue Movements
Статья научная
Method for English pronunciation practice utilizing Computer Graphics: CG animation representing tongue movements together with mouse movements is proposed. Pronunciation practice system based on personalized CG animation of mouth movement model is proposed. The system enables a learner to practice pronunciation by looking at personalized CG animations of mouth movement model , and allows him/her to compare them with his/her own mouth movements. In order to evaluate the effectiveness of the system by using personalized CG animation of mouth movement model, Japanese vowel and consonant sounds were read by 8 infants before and after practicing with the proposed system, and their pronunciations were examined. Remarkable improvement on their pronunciations is confirmed through a comparison to their pronunciation without the proposed system based on identification test by subjective basis. In addition to the mouth movement, tongue movement is represented by CG animation. Experimental results show 20 to 40 % improvement is confirmed by adding tongue movements for pronunciations of "s" and "th".
Бесплатно
Статья научная
The Recurrent Neural Network (RNN) is well suited for emotional speech recognition because its uses constantly time shifting property. Even though RNN gives better results GRU, LSTM and BILSTM solves the gradient problem and overfitting problem joins the path to reduces the efficiency. Hence in this paper five deep learning architecture is designed in order to overcome the major issues using data augmentation and spatial feature. Five different architectures like: Enhanced Deep Hierarchal LSTM & GRU (EDHLG), EDHBG, EDHGL, EDHGB & EDHGG are developed with dropout layers. The raw data learned from LSTM will be given as the input to GRU layer for deepest learning. Thus, the gradient problem is reduced, and accuracy of each emotion was increased. Also, to enhance the accuracy level spatial features were concatenated with MFCC. Thus, in all models, the experimental evaluation with the Tamil emotional dataset yielded the best results. EDHLG has a 93.12% accuracy, EDHGL has a 92.56 percent accuracy, EDHBG has a 95.42 percent accuracy, EDHGB has a 96 percent accuracy, and EDHGG has a 94 percent accuracy. Furthermore, the average accuracy rate of a single individual LSTM layer is 74%, while BILSTM is 77%. EDHGB outperforms almost all other systems, by an optimal system of 94.27 percent and then a maximum overall accuracy of 95.99 percent. For the Tamil emotion data, emotional states such as happy, fearful, angry, sad, and neutral have a 100% prediction accuracy, while disgust has a 94 percent efficiency rate and boredom has an 82 percent accuracy rate. Also, the training time and evaluation time utilized by EDHGB is 4.43 mins and 0.42 mins which is less when compared with other models. Hence by changing the LSTM, BILSTM and GRU layers large analysis of experiment on Tamil dataset is done and EDHGB is superior to other models, and when compared with basic models LSTM and BILSTM around 26% more efficiency is gained.
Бесплатно
Enhanced Learning with Abacus and its Analysis Using BCI Technology
Статья научная
Although technology is successfully being used these days as a tool to improve education at all levels, its improper usage is curbing the imagination of the student community, leading to a diminution in their thinking capacity and ability to focus and concentrate. As attention is a vital cognitive feature of any learning process, students these days are not coping well with this process. This study attempts to analyse the focusing capacity of students from two different backgrounds; students who have undergone training in mental arithmetic and usage of the abacus and students without any formal mental arithmetic training. The analysis is done through a simple Electroencephalogram (EEG) based gaming software, which measures the time needed for the players to focus and reach a specific attention level. An EEG device measures brain invoked potentials. Due to the availability of low cost commercial grade EEG devices, usage of these devices today, is not confined only to research and clinical purposes, but is being used beyond these applications. This study is an attempt to apply Brain Computer Interface (BCI) Technology to assess cognition. The performance of the first category was found to be better than the second set of students.
Бесплатно
Статья научная
With the outgrowth of cloud computing, a large amount of private information is stored over cloud servers, which is in encrypted format. But searching over encrypted data is very difficult. Earlier search schemes were based on Boolean search through keywords. But don't consider relevance of files. After that ranked search comes into its role, which uses searchable symmetric encryption (SSE). To achieve more practical and efficient design method was further modified to "Order preserving symmetric encryption" (OPSE), which uses primitives and indexed metadata files used in ranked SSE. In this proposed work further enhancements are done to reduce storage space for encrypted metadata using Porter Stemming method. Improvements in retrieval time are also done by using Boyer Moore's searching algorithm.
Бесплатно
Enhanced Ring Signatures Schemes for Privacy Preservation in Wireless Sensor Networks
Статья научная
Advancements in the domains of low-data-rate wireless networking and micro-electro-mechanical systems enabled the inception of a new networking domain, called wireless sensor network. These ad-hoc kind of networks have diversified applications in battlefield surveillance, disaster monitoring, intrusion detection etc. These networks consist plethora of sensor nodes which are severely resource constrained. As the application of the wireless sensor network is increasing, there is an emerging need for the security and privacy scheme which makes the network secure from various attacks and hide the ongoing activities in the network from a non-network entity. Privacy in wireless sensor network is yet a challenging domain to work on. Lot of work has been done to ensure privacy in the network. These relate to provide privacy in terms of the network entity and the privacy of the sensed information. Most of the solutions till date is based upon routing in the network layer, random walk based flooding, dummy data injection and cross layer solutions. Each of the schemes induce some overhead in the network. A light weight scheme is always desired for resource constraint wireless sensor networks. In this work we will propose a scheme which assures the privacy of the nodes in the network along with the privacy of the event generated in the network through a self organizing scheme. Through various simulation results the validity of our scheme among different network scenarios will be shown. We will also prove through graphical results that our proposed scheme enhances network lifetime quite satisfactorily.
Бесплатно
Enhancement of energy aware hierarchical cluster-based routing protocol for WSNs
Статья научная
Wireless sensor networks are present almost everywhere because of their extensive variety of utilization. However, sensor nodes are battery constrained. Therefore, proficient utilization of power turns into testing issues. Aggregated data at the base station, by individual nodes cause a flood of information which results in greater power consumption. To avoid or minimize this issue a new technique of data aggregation has been proposed. In this paper, we proposed enhanced novel energy aware hierarchical cluster-based (ENEAHC) routing protocol with the aim to: minimizing as much as total energy consumption and to enhance the performance of the energy efficient protocol by using inter-cluster based data aggregation. LZW based data aggregation likewise connected to the Cluster head (CH) to improve more results. Performance results show ENEAHC scheme reduce the end-to-end energy consumption and prolong the lifetime of the network compared to well known clustering algorithms i.e. LEACH and NEAHC. We design the actual relay node selecting issue like a non-linear programming issue and make use of property of compress sensing to find the optimal solution. The results are evaluated at the end of this paper through simulation.
Бесплатно
Enhancing Efficient Study Plan for Student with Machine Learning Techniques
Статья научная
This research aims to enhance the achievement of the students on their study plan. The problem of the students in the university is that some students cannot design the efficient study plan, and this can cause the failure of studying. Machine Learning techniques are very powerful technique, and they can be adopted to solve this problem. Therefore, we developed our techniques and analyzed data from 300 samples by obtaining their grades of students from subjects in the curriculum of Computer Science, Faculty of Science and Technology, Sakon Nakhon Rajabhat University. In this research, we deployed CGPA prediction models and K-means models on 3rd-year and 4th-year students. The results of the experiment show high performance of these models. 37 students as representative samples were classified for their clusters and were predicted for CGPA. After sample classification, samples can inspect all vectors in their clusters as feasible study plans for next semesters. Samples can select a study plan and predict to achieve their desired CGPA. The result shows that the samples have significant improvement in CGPA by applying self-adaptive learning according to selected study plan.
Бесплатно
Enhancing Information Systems Students' Soft Skill – a Case Study
Статья научная
Information Systems (IS) curricula should provide students with both technical and non-technical (soft) skills. The technical aspects are covered by various courses. However, soft skills like teamwork, interpersonal communication, presentation delivery, and others are hardly covered. Employers, who consider both technical and soft skills to be equally important, search for professional Information Systems employees possessing both sets of skills. These employers often complain that finding an IS graduate with both types of skills is quite difficult. The IS 2010 Model Curriculum refers to both types of skills, considering them an essential part of the graduate knowledge base. However, in many cases the soft skills are not sufficiently addressed, and even if they are, it is not necessarily in the context of software development projects. The Systems Analysis and Design (SAD) course provides an important foundation for the IS profession. This is especially true due to the emerging role of the programmer-analyst who is responsible not only for programming but also for some analysis work. In order to strengthen the soft skills in the context of system analysis and design, we suggest a workshop structure emphasizing these soft skills while students analyze and design a complete information system. Our SAD workshop includes some face to face lectures and team-based collaborations. The students undertake many online activities, including teamwork, interviews with simulated clients, team-based peer reviews, presentation delivery, and so forth. The workshop employs a grade difference calculation mechanism that revealed, along with the students' reflections, that the workshop structure enhanced the students' ability to cope with the workshop assignments while strengthening their soft skills and preparing them for their future analysis and design challenges.
Бесплатно
