http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Automatically Extracting Embedded Schemas from Regular Applications
Jinan Fiaidhi,Yvette E. Gelogo 인문사회과학기술융합학회 2012 예술인문사회융합멀티미디어논문지 Vol.2 No.1
A RDBMS is usually accessed using blocking drivers like JDBC/ODBC which require clients to block and wait for the result of each query they issue. An asynchronous database access mechanism would eliminate the need for such blocking and greatly improve client performance. Thread-Per-Connection and Thread Pooling are two methods currently being used to provide this asynchrony. This is inefficient since a lot of memory and computing power is spent in creating, scheduling and switching multiple threads. By these methods we cannot show how asynchronous database access can be achieved with a single thread using the Fork-Join mechanism which employs Future objects in Java. So, in this paper we propose an approach for automatically extracting embedded schemas from regular applications, e.g., written in java and automatically computing how schemas change as applications evolve. To showcase our approach, we perform a long-term schema evolution study. Our platform can be used for performing long-term, large-scale embedded schema evolution studies that are potentially beneficial to dynamic updating and schema evolution researchers.
Niki Shakeri,Jinan Fiaidhi,Sabah Mohammed,Tia-hoon Kim 보안공학연구지원센터 2014 International Journal of u- and e- Service, Scienc Vol.7 No.5
Recommender systems are now popular both commercially and in the research community, where many approaches have been suggested for providing recommendations. However, evaluating the affectivity of recommender systems is a challenging problem and most of the approaches used for evaluation are based on using some sort of a dataset. This paper describes a method for measuring the accuracy of a collaborative filtering based recommender systems called “User-Advertisement Simulation” that utilizes a simulation approach that creates artificial users and advertisements of a virtual market, then measures accuracy of the products’ ranking based on the user’s profile.
Mohannad Al-Mousa,Jinan Fiaidhi 보안공학연구지원센터 2014 International Journal of Multimedia and Ubiquitous Vol.9 No.11
Massive Open Online Courses (MOOC) platforms provide a rich environment for knowledge creation through its massiveness and inherited collaborative tools. However, it also restricts spontaneous knowledge sharing by the existing LMS barriers between the main multimedia content and the collaborative tools. None the less, the collaboration still massive due to the number of participants. The separation of the multimedia content and the discussion tools is the first focus point of this paper. Moreover, this article is presenting a new added value to the MOOC architecture so to link the learner’s discussions and its summary with the multimedia contents. The added-value component involves a summarization algorithm that summarizes the shared collaborative textual discussion collected from the various learners viewing relevant MOOC multimedia/video contents. The affectivity of the summarization component was tested using the popular ROUGE software package from University of Southern California. The new MOOC architecture represents an enhanced learning environment that enables learners to share the multimedia information along with its annotated collaborative information with the power of summarizing the final outcome of the presented annotations relevant to a specific shared multimedia content.
Implementing Innovative Routing Using Software Defined Networking (SDN)
Adnan Shahid,Jinan Fiaidhi,Sabah Mohammed 보안공학연구지원센터 2016 International Journal of Multimedia and Ubiquitous Vol.11 No.2
Software Defined Networking (SDN) is an open source networking framework recently introduced. It allows developers to program and reprogram the network so that intelligence and new features can be integrated to optimize and enhance the performance of the network. This paper is focused on optimizing the routing implementation of SDN (i.e. SDN Controller). We have used the Floodlight Open Source SDN Controller1 in our experimentation. The Floodlight controller provide source Java libraries and APIs.. It uses Dijkstra’s algorithm to calculate the shortest path between any source and any destination within the network. However, the default routing implementation of Floodlight Controller is such that, while calculating any path, it ignores the actual bandwidth of the link as it takes a unit value for each link. The resultant calculated path becomes a least hop path. This least hop path may be an optimal path where all the links in the network have equal bandwidth and may not be optimal where the networks have unequal link bandwidth. However, today’s networks are mostly consisting of unequal link bandwidth. The goal of this paper is to re-structure the Floodlight Controller so that it can collect the actual bandwidth of all the links in the network and use this information to calculate
Identifying EEG Binary Limb Motor Imagery Movements using Thick Data Analytics
Vikas Trikha,Jinan Fiaidhi,Sabah Mohammed 사단법인 미래융합기술연구학회 2020 아시아태평양융합연구교류논문지 Vol.6 No.9
Electroencephalography (EEG) is non-invasive technology that is widely used to record brain signals in brain computer interfacing (BCI) systems to control, motor imagery, in which movements signals occurring in limbs can control some services. Researchers have proposed numerous classification schemes of these motor imagery to incorporate it with various neurorehabilitation, neuroprosthetics and gaming applications. However, the existing classification schemes face the performance degradation caused by motor-imagery EEG signals with low signal to noise ratio. The paper’s main objective is to use possible thick data analytics techniques to classify effectively the motor imagery EEG signals. Our attempt start with notable classifiers including Decision Trees, Extra Trees, Naive Bayes, Random Forest and SVM and move later to enhance classifications using variety of ensemble learning techniques including Bagging, Adaboost and Stacking. More techniques has been applied on the results of the ensemble learring to eliminate classification noise and supply more relevant features such as substituting outliers with mean value and exercising band-pass filter and Common Spatial Pattern (CSP). The thick data methods has been validated on a public dataset rendered by BCI competition II dataset III and was found to produce better classification performance metric which included performance metric parameters like accuracy, specificity, sensitivity, precision and recall when confronted with the existing work, thus projecting the usefulness of motor imagery BCI. The analytics is inclusive of Area Under the Curve (AUC) score and Mathews Correlation Coefficient (MCC) score to display an impactful analysis.
Tejas Wadiwala,Jinan Fiaidhi,Sabah Mohammed 사단법인 미래융합기술연구학회 2020 아시아태평양융합연구교류논문지 Vol.6 No.10
Thick data analytics are being pursued to break the barriers of using the big data predictive analytics for small datasets. The main objective of this paper is to improve the performance of the EEG for biometric authentication using eye blinking brain signals through the use of ensembles techniques. Biometric identification differs largly from the other EEG eye movement analytics applications such as detecting epileptic seizure, identification of stress feature or detecting driving drowsiness as it requires high model rubstness and accuracy. A perfect biometric should be unique, universal and permanent over time. Previous analytical approaches on eye movement failed to show the reliability of the the brain signals to distinguish individuals based on the properties of eye-movements seen as time-signals and for this reason the eye movement have not been considered as a possible solution for a biometric system. This paper's primary focus is on the use of ensemble methods to secure the robustness of the person identification from the EEG eye movement waves. Our approach is a multitier one and it start with training notable binary classification models for biometic identification using eye movement. The training tier is followed by ensemble learning (boosting, bagging, and stacking algorithms) to narrow the differences of accuracy gap among classifiers. The classifier's robustness has been measured with the help of variety of accuracy measures including the Matthews correlation coefficient (MCC). The third tier is guage the person prediction model stability using the AUROC (Area Under the Receiver Operating Characteristics) metric. The results obtained in this study proves that it is possible to use an eye tracking based biometric for detection of person identity with reasonably high sensitivity and specificity.