Browsing by Author "Rahman, Mostafijur"

Now showing 1 - 20 of 40

A Comparative Analysis of Four Classification Algorithms for University Students Performance Detection
(Lecture Notes in Electrical Engineering, Springer, 2020-03-24) Das, Dipta; Shakir, Asif Khan; Rabbani, Md. Shah Golam; Rahman, Mostafijur; Shaharum, Syamimi Mardiah; Khatun, Sabira; Fadilah, Norasyikin Binti; Qaiduzzaman, Khandker M.; Islam, Md. Shariful; Arman, Md. Shohel
The student’s performance plays an important role in producing the best quality graduate who will responsible for the country’s economic growth and social development. The labor market also concerns with student’s performance because the fresh graduate students are considered as an employee depends on their academic performance. So, identification of the reason behind student’s performance variation provides valuable information for planning education and policies. Many researchers try to find out the reason with different types of data mining approaches in different countries. However, none of them worked with Bangladeshi students. This paper proposed a model for identifying the key factors of variation Bangladeshi students’ academic performance and predicts their results. This paper proposes a model which able to identify the students who need special attention. Different types of feature selection methods were used such as Co-relation, Chi-Square and Euclidean distance to select valuable features and feature selections result through decision tree, Naive Bayes, K-nearest neighbor and Artificial Neural Network classifiers algorithm were compared. The performance analysis is done by using student SGPA and review on given facilities from a university. From the performance analysis result it is found that, decreasing number of classes in dataset, the Artificial Neural Network (ANN) (93.70%) performs better than Decision Tree (DT) (92.18%), K-Nearest Neighbors (KNN) (77.74%) and Naïve Bayes (NB) (68.33%). However, an increasing number of classes in dataset the DT perform better than ANN, KNN, NB.
A Dynamic K-means clustering for Data Mining
(Scopus, 2020) Hossain, Md. Zakir; Akhtar, Md.Nasim; Ahmad, R.B.; Rahman, Mostafijur
Data mining is the process of finding structure of data from large data sets. With this process, the decision makers can make a particular decision for further development of the real-world problems. Several data clustering techniques are used in data mining for finding a specific pattern of data. The K-means method isone of the familiar clustering techniques for clustering large data sets. The K-means clustering method partitions the data set based on the assumption that the number of clusters are fixed.The main problem of this method is that if the number of clusters is to be chosen small then there is a higher probability of adding dissimilar items into the same group. On the other hand, if the number of clusters is chosen to be high, then there is a higher chance of adding similar items in the different groups. In this paper, we address this issue by proposing a new K-Means clustering algorithm. The proposed method performs data clustering dynamically. The proposed method initially calculates a threshold value as a centroid of K-Means and based on this value the number of clusters are formed. At each iteration of K-Means, if the Euclidian distance between two points is less than or equal to the threshold value, then these two data points will be in the same group. Otherwise, the proposed method will create a new cluster with the dissimilar data point. The results show that the proposed method outperforms the original K-Means method.
A Meta Heuristic Search based T-way Event Driven Input Sequence Test Case Generator
(United Kingdom Simulation Society, 2014) Rahman, Mostafijur; Othman, Rozmie Razif; Ahmad, R Badlishah; Rahman, Md. Mijanur
Exhaustive testing for event driven sequence input interaction is costly and not always practicable for all types of software testing. So, an alternative technique is crucial where optimum/near optimum test case generation is key concern. This paper presents a feasible test suite generation technique using a meta heuristic search called Simulated Annealing (SA) for T-way Event Driven Input Sequence Test Case (EDISTC) Generator and abbreviated as T-way EDISTC-SA generator. The T-way EDISTC-SA technique focuses on a heuristic analysis for generating feasible and near optimum test suite(s), where a cost function carefully initiates acceptable test input sequences and a fine-tuned cooling rate with temperature takes part as an iterative perspective. We corroborate on EDISTC-SA algorithm by doing a number of experiments to achieve optimum and/or near optimum test cases from a number of test input sequences. The experimental results are tested on a real application called Embedded Network Traffic Monitoring System (ENTM). Analysis on EDISTC-SA strategy shows that the optimum test suite is found from some of the iterated solution and there is possibility to have more feasible accepted test suites. Full Text Link: http://doi.org/10.5013/IJSSST.a.15.03.10
A Mutation Triggering Method for Genetic Algorithm to Solve Traveling Salesman Problem
(Springer, 2020-07-09) Qaiduzzaman, Khandker M.; Khatun, Sabira; Afsa, Maliha; Sobhan, Sadman; Hossain, Md. Elias; Shaharum, Syamimi Mardiah; Rahman, Mostafijur
This chapter reveals the effect of combining mutation operators in Genetic Algorithm. Though mutation is a very effective genetic operator to escape the local optima, it has an adverse effect on computation time. It is quite a challenge to say how much probability is appropriate for mutation. The major contribution of this chapter is to design a mutation triggering method by combining three mutation operators (Swap, Insertion and 2-Opt) and applying adaptive probability. To decide which mutation can be activated at a given generation, a decision-making method named Mutation Triggering Method is proposed. To measure the performance of the proposed method, the classical traveling salesman problem was considered. The experimental result shows that the proposed method was able to find a better solution (travel cost) than the other approaches. For computation time, the proposed strategy did as well as other mutation strategies. In conclusion, the combination of several mutation operators can ensure the benefits of diversity as well as the benefits of faster convergence.
A Noble Approach to Develop Dynamically Scalable Namenode in Hadoop Distributed File System Using Secondary Storage
(Scopus, 2020) Shaha, Tumpa Rani; Akhtar, Md. Nasim; Johora, Fatema Tuj; Hossain, Md. Zakir; Rahman, Mostafijur; Ahmad, R. B.
For scalable data storage, Hadoop is widely used nowadays. It provides a distributed file system that stores data on the compute nodes. Basically, it represents a master/slave architecture that consists of a Name Node and copious Data Nodes. Data Nodes contain application data and metadata of application data resides in the Main Memory of Name Node. In cached approach, they fragment the metadata depending on the last access time and move the least frequently used data to secondary memory. If the requested data is not found in main memory then the secondary data will be loaded again on the RAM. So when the secondary data reloads to the primary memory then the NameNode main memory limitation arises again. The focus of this research is to reduce the namespace problem of main memory and to make the system dynamically scalable. A new Metadata Fragmentation Algorithm is proposed that separates the metadata list of NameNode dynamically. The NameNode creates Secondary Memory File in perspective of the threshold value and allocates secondary memory location based on the requirement. According to the proposed algorithm the maximum third, out of fourth of main memory is used at the secondary file caching time. The free space aids in faster operation by Dynamically Scalable NameNode approach. This proposed algorithm shows that the space utilization is increased to 17% and time utilization is increased to 0.0005% with the comparison of the existing fragmentation algorithm.For scalable data storage, Hadoop is widely used nowadays. It provides a distributed file system that stores data on the compute nodes. Basically, it represents a master/slave architecture that consists of a NameNode and copious Data Nodes. Data Nodes contain application data and metadata of application data resides in the Main Memory of NameNode. In cached approach, they fragment the metadata depending on the last access time and move the least frequently used data to secondary memory. If the requested data is not found in main memory then the secondary data will be loaded again on the RAM. So when the secondary data reloads to the primary memory then the NameNode main memory limitation arises again. The focus of this research is to reduce the namespace problem of main memory and to make the system dynamically scalable. A new Metadata Fragmentation Algorithm is proposed that separates the metadata list of NameNode dynamically. The NameNode creates Secondary Memory File in perspective of the threshold value and allocates secondary memory location based on the requirement. According to the proposed algorithm the maximum third, out of fourth of main memory is used at the secondary file caching time. The free space aids in faster operation by Dynamically Scalable NameNode approach. This proposed algorithm shows that the space utilization is increased to 17% and time utilization is increased to 0.0005% with the comparison of the existing fragmentation algorithm.For scalable data storage, Hadoop is widely used nowadays. It provides a distributed file system that stores data on the compute nodes. Basically, it represents a master/slave architecture that consists of a NameNode and copious Data Nodes. Data Nodes contain application data and metadata of application data resides in the Main Memory of NameNode. In cached approach, they fragment the metadata depending on the last access time and move the least frequently used data to secondary memory. If the requested data is not found in main memory then the secondary data will be loaded again on the RAM. So when the secondary data reloads to the primary memory then the NameNode main memory limitation arises again. The focus of this research is to reduce the namespace problem of main memory and to make the system dynamically scalable. A new Metadata Fragmentation Algorithm is proposed that separates the metadata list of NameNode dynamically. The NameNode creates Secondary Memory File in perspective of the threshold value and allocates secondary memory location based on the requirement. According to the proposed algorithm the maximum third, out of fourth of main memory is used at the secondary file caching time. The free space aids in faster operation by Dynamically Scalable NameNode approach. This proposed algorithm shows that the space utilization is increased to 17% and time utilization is increased to 0.0005% with the comparison of the existing fragmentation algorithm.
A Novel Approach of Fair Scheduling to Enhance Performance of Hadoop Distributed File System
(Scopus, 2020) Hussain, R.; Rahman, Mostafijur; Tarin, Tanjila Akter
Nowadays, big data is one of the most challenging issues for managing big amounts of data more effectively and efficiently. It widely used in E-commerce, social media, online business and such types of applications. Hadoop Distributed File System (HDFS) is one of the widely used frameworks which can easily handle and store large amounts of data set frequently. For HDFS job scheduling is more challenging because it plays an important role in time optimization in big data. For resolving this issue in this paper, we introduce a job scheduling algorithm which is more time efficient and accurate than existing fair job scheduling algorithm. We optimize the time cycle of fair scheduling by minimizing iteration. We have accelerated with the different number of jobs in the existing algorithm and proposed an algorithm for experimentally proving the time complexity and time measurement. It is observed that the proposed method is computationally efficient than the existing one and our algorithm has reduced the number of iterations and improved the time efficiency on average 26.719%.
A Novel Hybrid Evolutionary Mating Algorithm for Covid19 Confirmed Cases Prediction based on Vaccination
(IEEE, 2023-05-01) Ahmed, Marzia; Mohamad, Ahmad Johari; Rahman, Mostafijur; Sulaiman, Mohd Herwan; Kashem, Mohammod Abul
Microorganisms may cause illness when they enter the body, multiply, and spread to other parts. The rapid spread of COVID-19 to neighboring countries is examined in this research. Anticipating a positive COVID-19 occurrence helps in determining risks and creating countermeasures. As a result, developing robust mathematical models with small error margins for predictions is crucial. Based on these findings, a combined method of evaluating confirmed cases of COVID-19 with universal immunization is recommended. First, the best hyperparameter values of the RBF kernel-based LSSVM (least square support vector machine) were determined using the most recent Evolutionary Mating Algorithm (EMA). After that, LSSVM will complete the task of prediction. This hybrid method has been utilized for time series forecasting in Malaysia since the country's immunization program against COVID-19 got underway. We evaluate our results next to those of well-known methodologies in nature-inspired metaheuristics.
A portable class Lecture Recording system for E-learning purpose
(IEEE Xplore, 2014-02-10) Iszaidy, I.; Ahmad, R.B; Kahar, N.F; Rahman, Mostafijur; Yaakob, Shahrul Nizam
In a new educational concept, the Lecture Recording system is one of the devices that are widely used to provide educational material to students. Even so, the existing Lecture Recording systems are able to record only one video in real time. If the system is able to record multiple video, the video editing is done after recording time. In this paper, a new design for lecture recording system is introduced. It offers a simple equipment set up for lecture recording that will minimize lecturer's burden. Furthermore, the system will edit the video in real time depend on user setting. This system is also small in size and portable. This lecture recording system allows students to re-experience the lecture session at anytime and anywhere by downloading it or viewing it through the portal. This lecture recording system is user friendly where it can be installed without any additional software. Therefore, it can be a great system for lecturers who are using laptops for their class presentation. Full Text Link: http://doi.org/10.1109/ICOS.2013.6735047
A portable network traffic analyzer
(IEEE Xplore, 2009-02-20) Rahman, Mostafijur; Khalib, Zahereel Ishwar Abdul; Ahmad, R.B
Embedded system is known for its limitation in terms of processing power, memory, and power consumption. Incorporating solution into an embedded system, which requires optimum usage of these limitation, is thus a challenge. The aim of this study is to see how Embedded Linux could cope with those limitations in producing reliable embedded web-based traffic monitoring system. The approach to the study is to adopt a low-end embedded Linux platform and develop a network traffic monitoring system which runs on the platform. Among the functionalities incorporated include capturing and storing network packet information into files, analyzing data statistically and displaying minimal statistical data as well as sending data files through TCP/IP connection to the web based monitoring system. This paper will describe the architectural design and implementation of the network monitoring system. Interesting enough the system proved to be competent, where it manages to provide useful reliable information within its limitation. Full Text Link: http://doi.org/10.1109/ICED.2008.4786787
An adaptive replication model for heterogeneous systems
(IEEE Xplore, 2015-01-22) Nader-Uz-Zaman, M.; Kashem, Mohammod Abul; Ahmad, R. Badlishah; Rahman, Mostafijur
Data replication is an increasingly important topic as databases are more and more deployed over distributed systems, grid community and clustering systems. The performance, reliability and portability of entire database may possible by using replication technique. Replication may be considered as a data backup policy. Replication in homogeneous system is common practice in real life, but replication in heterogeneous system is quite challenging, because of the dissimilar computing environment. Since the computer environment porn to be heterogeneous, hence it's a promising field for researchers to consider replication in heterogeneous environment. In our research a persistence layer has been proposed for replication in heterogeneous systems. This persistence layer work on asynchronous model, hence it may call as asynchronous replication model. The model works implements multi threading technique for creating parallel connection with peer servers. The main server and replicated server are connected with a common interface. The interface is a replication engine, which intelligently holds data and makes decision depending on different factors for sending data to smoothen the replication process. The whole structure follows the rules of SOA (Service oriented architecture) thus, modification of replication servers do not affect the main server. Finally the architecture of this concept builds on different configurable files. These files help us in system up-gradation without shutting down the system. At the end, some experiments have been carried out and the results have been analyzed. Full Text Link: doi.org/10.1109/ICED.2014.7015771
An Approach to Building Energy Clusters Using Particle Swarm Optimization Algorithm for Allocating the Tasks in Computational Grid
(Scopus, 2019) Rahman, Mostafijur
The proper mapping in case of allocation of available tasks among particles is a challenging job to accomplish. It requires proper procedural approach and effectual algorithm or strategy. The deterministic polynomial time for task allocation problem is relative. The existence of proper and exact approach for allocation problem is void. However, for the survival of the grid and executing the assigned tasks, the reserved tasks need to be allocated equally among the particles of the grid space. At the same time, the applied model for task allocation must not consume unnecessary time and memory. We applied Particle Swarm Optimization (PSO) for allocating the task. Additionally, the particles will be divided into three clusters based on their energy level. Each cluster will have its own cluster header. Cluster headers will be used to search the task into space. In a single cluster, particles member will be of same energy level status such as full energy, half energy, and no energy level. As a result, the system will use the limited time for searching task for the remaining tasks in it if a particular task requires allocating half task to a particle.
An Efficient Multi-sensing and GSM Equipped Fire Monitoring System
(MATEC, 2017-12-11) Fahad Bin Zamal, Md.; Sayed, Shehrin; Bhuiyan, Touhid; Rahman, Mostafijur
The principal goal of fire monitoring system is to react promptly to a fire and not to misleading particulate signatures produced by nuisance sources. In this paper we proposed a system that not only able to detect and prevent fire at early stages but also capable of interact with surround environment. Recent researches lead us to detect fire by light and heat sensor, image processing, smoke detection mechanism but failed to integrate those in one The advancement on fire detection technologies has been significant over the last few decade due to rapid progress in communication technologies, advances in sensing devices and greater understanding of fire physics. But lack of intelligence among fire monitoring system often failed to make an impact on fire incidents. Our proposed fire monitoring system is incorporated in such a way that can communicate with environment by itself through the help of GSM Modem. Here we introduce an intelligent and advance fire monitoring system that can communicate by itself with fire station and can detect fire at its early stage and extinguish it in the shortest time subject to a few effective factors. Full Text Link: http://doi.org/10.1051/matecconf/201714001003
An Embedded Network Traffic Monitoring System for Portable Applications
(UniMAP Library, 2013) Rahman, Mostafijur; Ahmad, R. Badlishah; Khalib, Zahereel Ishwar Abdul; Yahya, Abid; Rahman, Md. Mijanur; Ahmed, Manjur; Alee, Naufal
This study presents an enhanced Embedded Network Traffic Monitoring (ENTM) system capable of capturing and analyzing network traffic information on data networks. The system incorporates an enhanced packet probing subsystem for low end interfacing to data network. The packet analysis engine included a sophisticated memory managing scheme to tolerate considerable bursts in network traffic. Comparative experimental results showed that the ENTM system had performance comparable with well known third party tools. In order to demonstrate that resource constraints do not significantly degrade system performances, researchers implemented the packet probing subsystem on a desktop where memory and processing power were much larger. It was found that the ENTM system had only little degradation (0.5%) in performances compared to the desktop version. Requirements of low processing power and memory make the system suitable for low end and portable applications.
An Improved Optimization Algorithm-Based Prediction Approach for the Weekly Trend of COVID-19 Considering the Total Vaccination in Malaysia
(Springer, 2023-05-28) Ahmed, Marzia; Sulaiman, Mohd Herwan; Mohamad, Ahmad Johari; Rahman, Mostafijur
SARS-CoV-2 is a multi-organ disease characterized by a wide range of symptoms, which also causes the severe acute respiratory syndrome. When it initially began, it rapidly spread from its origin to adjacent nations, infecting millions of people around the globe. In order to take appropriate preventative and precautionary actions, it is necessary to anticipate positive COVID-19 instances in order to better comprehend future risks. Therefore, it is vital to building mathematical models that are resilient and have as few prediction mistakes as feasible. This research recommends an optimization-based Least Square Support Vector Machines (LSSVM) for forecasting COVID-19 confirmed cases along with the daily total vaccination frequency. In this work, a novel hybrid Barnacle Mating Optimizer (BMO) via Gauss Distribution is combined with the Least Squares Support Vector Machines algorithm for time series forecasting. The data source consists of the daily occurrences of cases and frequency of total vaccination from February 24, 2021, to July 27, 2022, in Malaysia. LSSVM will thereafter conduct the prediction job with the optimized hyper-parameter values using BMO via Gauss distribution. This study concludes, based on its experimental findings, that hybrid IBMOLSSVM outperforms cross validations, original BMO, ANN, and a few other hybrid approaches with optimally optimized parameters.
Analyzing the Quality of Water and Predicting the Suitability for Fish Farming Based on IOT in the Context of Bangladesh
(2019 International Conference on Sustainable Technologies for Industry 4.0 (STI), IEEE, 2019-12) Ahmed, Marzia; Rahaman, Md. Obaidur; Rahman, Mostafijur; Kashem, Mohammod Abul
Nearly 5.3% of the national income of Bangladesh comes from fish. Fishes are the significant natural essentials that help to grow national income, nutrition, reduce the unemployment problem of a country and also earn foreign currency. Furthermore, it's a great source of low cost, high protein and other health beneficiary nutrients comparative to red meat. Nonetheless, to fulfill the expected demand for fish, the existing system and conventional fish farming has been failed to raise the amount of fish needed for the growing population. This paper analyzed the water quality parameters standards for the suitability of fish farming and the causes of fish diseases affected by the parameters through collected ponds data from the different areas of Bangladesh. Several machine learning algorithms have been compared for accuracy for the significance water level and error rate. Logistic regression has been fitted better to train and test part. The prediction has been done to find out whether the new pond's water quality is suitable for fish farming with respect to the value of quality parameters. An empirical IOT based system design has been given to comparing the prediction in the future. Moreover, this research also analyzed the feasible environment parameter and standards for fish growth, the reason, and risk for fish death as well as the growth rate of fish by monitoring the quality parameters of water for fish.
AttNet: An Attention-Based BiGRU Network for Remaining Useful Life Prediction
(Scopus, 2024) Shakil, Ahsanul Haque; Orin, Mst. Afsana; Rahman, Mostafijur; Kabir, Md Alamgir
Remaining Useful Life (RUL) prediction is crucial for prognostics and health management (PHM) in industrial applications, as it helps to reduce unexpected maintenance and downtime costs. This study introduces AttNet, an Attention-Based Bidirectional Gated Recurrent Unit (BiGRU) Network designed for RUL prediction that can effectively capture and prioritize key temporal features in the data, leading to more accurate RUL predictions. Our model builds upon previous works, specifically improving upon the approaches utilized deep learning models for RUL prediction on the NASA C-MAPSS turbofan engine dataset. Experimental results show that AttNet outperforms state-of-the-art achieving maximum RMSE 17.27% improvement on FD001 and 9.06% improvement on FD003. It shows the effectiveness of our AttNet in accurately predicting RUL.
Design of an embedded data acquisition system for remote application
(IEEE Xplore, 2015-09-07) Mashkoor, Alaa Abdulhussain; Ahmad, R.B; Rahman, Mostafijur; Kadhim, Zahraa Ali
In recent times, various Data Acquisition Systems (DAS) are available in the market. The basic operation of all DAS's are same, only the differences found in terms of hardware architectures, sampling rate, channel supports, costs, user friendly features, etc. This paper proposed an Embedded Data Acquisition System which appealing features are: variable channel supports (2/4/8/32/64), notification sends to admin using Short Message Service (SMS), and web monitoring system which trend to use our system in remote area and named as Embedded Remote Data Acquisition System (ERDAS). In this research, the development phase consists, a Single Board Computer (SBC, TS-7800) as a processing unit, GNU/Linux based Embedded Debian 7 Operating System (OS) as an application development platform and customized kernel module to support 3G modem for notification send/receive to/from the remote area. Results show the developed GUI and accuracy based on CPU and memory usage. We found that the variation of CPU load is 2% to 3% and the memory usage is around 2MB, which conclude that the technically compact designed ERDAS modules are fitting to execute on the low-end embedded hardware and OS. Full Text Link: http://doi.org/10.1109/ISTT.2014.7238243
Development of a framework to reduce overhead on database engine through data distribution
(IEEE Xplore, 2015-01-22) Rahman, Md. Hafizur; Akter, Md. Nasim; Ahmad, R. Badlishah; Nader-uz-zaman, M.; Rahman, Mostafijur
Software driven solutions are limited to the amount of memory size and storage capacity, but the sizes of databases are increasing every day. Hence, now a day, handling data and accessing it in an acceptable time is one of the biggest challenges especially in a large database system. In a database, the records can be categorized according to the access frequencies; some records are very frequently accessed (hot data), some records are hardly accessed (cold data) and other records accessed occasionally (warm data). In a conventional database we keep all hot, warm and cold records in a single database. In case of record access (query, update etc.) a query might takes longer time even if a good data accessing algorithm (clustering/mining) incorporate with the database. Thus categorizing of the data set, i. e. clustering in terms of access frequency may improve data accessibility. In this paper, we are proposing a data clustering mechanism based on data access frequency. Finally, the expected result shows how and why data accessibility time should outperform other available data clustering techniques. Full Text Link: http://doi.org/10.1109/ICED.2014.7015773
Efficient Anti-kidnapping and Anti-harassment (Avoidance-detection-notification) Mobile Application for Unwanted Incidents
(2019 IEEE Student Conference on Research and Development, 2019) Hossain, Md. Elias; Rahman, Mostafijur; Hassan, Md. Maruf
Kidnapping and harassment is not only a global issue but also a historic issue in Bangladesh. In between the years of 2010 and 2018, the total number of kidnapping events were found, 6708 (Avg. 745.33 events per year) in Bangladesh. The government is trying to capture and punish the kidnappers. But there are a few ways by which the victim can also notify the responsible persons about the unwanted incidents in real-time. This research proposes to design and develop an anti-kidnapping and anti-harassment mobile application that is consists of two modules, the Avoidance and the Detection modules. The Avoidance module notifies the user about some unsafe locations. The Detection module is further divided into four sub modules, the Notification module, Sound module, Sensor module, and Spy module. The Notification module is activated by pressing the SOS key and the Sound module is activated by voice command. Both of these modules can send the current location of the user by sending SMS to some selected contact numbers. In the Voice module, the audio voice can be recorded for 15 seconds and saved in phone storage or cloud. The Sensor module uses accelerometer sensor and compass sensor. During unwanted circumstances, the accelerometer sensor is activated by shaking the phone three times and the compass sensor is activated by the movement of the user. The Notification module is tested by sending notifications in different areas in Bangladesh. It is found that the average response time of the notification module is 0.74 milliseconds. The complete application is tested by following the System Usability Scale (SUS) method. It is found that the SUS score of the system is 75.56 %, which indicates that the system is good enough to use.
Embedded system for portable Lecture Recording System: Design and development
(IEEE Xplore, 2013-12-19) Iszaidy, I.; Ahmad, R.B; Kahar, N. F.; Rahman, Mostafijur; Jais, M. I.; Fuad, F. A. A.
E-learning is a new educational concept by using the Internet technology. It delivers the digital content and provides a learner-oriented environment for the teachers and students. The Lecture Recording system is one of the devices that are widely used for E-Learning. However, the existing Lecture Recording system needs to be installed on a PC or Notebook. In this paper, a new design for lecture recording system is presented. It offers a simple equipment set up for lecture recording that will minimize lecturer's burden. Furthermore, the recorded lectures will automatically create recorded file in a format that is supported by HTML5. This system is also small in size and portable. This portable lecture recording system allow students to re-experience the lecture session at anytime and anywhere by downloading it or viewing it through the portal. This lecture recording system is user friendly where it can be installed without any additional software. Therefore, it can be a great system for lecturer's who are using laptop/net-book for their class presentation. Full Text Link: http://doi.org/10.1109/ISWTA.2013.6688789