3,723 research outputs found
Using Support Vector Machine for Prediction Dynamic Voltage Collapse in an Actual Power System
No full textAbstract—This paper presents dynamic voltage collapse
prediction on an actual power system using support vector machines.
Dynamic voltage collapse prediction is first determined based on the
PTSI calculated from information in dynamic simulation output.
Simulations were carried out on a practical 87 bus test system by
considering load increase as the contingency. The data collected from
the time domain simulation is then used as input to the SVM in which
support vector regression is used as a predictor to determine the
dynamic voltage collapse indices of the power system. To reduce
training time and improve accuracy of the SVM, the Kernel function
type and Kernel parameter are considered. To verify the
effectiveness of the proposed SVM method, its performance is
compared with the multi layer perceptron neural network (MLPNN).
Studies show that the SVM gives faster and more accurate results for
dynamic voltage collapse prediction compared with the MLPNN.
Keywor ds —Dynamic voltage collapse, prediction, artificial
neural network, support vector machines
Applications of complex wavelets to locate source of transient in power system / Noralizah Hamzah and Azah Mohamed
No full textThis paper provides solutions in locating the source of the transient based on complex wavelet energy. By using the complex wavelet transform, the transient power at the monitoring point is first calculated and the complex wavelet energy is obtained by integrating the transient power. Initially, there is no wavelet
energy during steady-state condition, but during a transient condition, a wavelet energy is produced by the transient disturbance in power distribution systems. By examining the change in the wavelet energy between the steady state condition and during transient event, it is possible to locate the source of a transient
disturbance. From the wavelet energy plot against time, a change in wavelet energy from an approximately zero to a negative value indicates that the transient source is from downstream or in front of the monitoring point. On the other hand, a change in wavelet energy from an approximately zero to a positive value indicates that the transient source is from upstream or behind the monitoring point. To verify the proposed complex wavelet method, simulations using the PSCAD/EMTDC software have been performed. Simulation results prove that complex wavelet energy is capable of locating accurately the source of transients in a power distribution system
Performance Comparison of Artificial Intelligence Techniques for Non-intrusive Electrical Load Monitoring
No full textThe increased awareness in reducing energy consumption and encouraging response from the use of smart meters have triggered the idea of non-intrusive load monitoring (NILM). The purpose of NILM is to obtain useful information about the usage of electrical appliances usually measured at the main entrance of electricity to obtain aggregate power signal by using a smart meter. The load operating states based on the on/off loads can be detected by analysing the aggregate power signals. This paper presents a comparative study for evaluating the performance of artificial intelligence techniques in classifying the type and operating states of three load types that are usually available in commercial buildings, such as fluorescent light, air-conditioner and personal computer. In this NILM study, experiments were carried out to collect information of the load usage pattern by using a commercial smart meter. From the power parameters captured by the smart meter, effective signal analysis has been done using the time time (TT)-transform to achieve accurate load disaggregation. Load feature selection is also considered by using three power parameters which are real power, reactive power and the TT-transform parameters. These three parameters are used as inputs for training the artificial intelligence techniques in classifying the type and operating states of the loads. The load classification results showed that the proposed extreme learning machine (ELM) technique has successfully achieved high accuracy and Fast learning compared with artificial neural network and support vector machine. Based on validation results, ELM achieved the highest load classification with 100% accuracy for data sampled at 1 minute time interval
Analyzing the quality of artificial intelligence final examination questions according to bloom's taxonomy and syllabus contents / Syazatul Nor Azah Mohamed Mahtar
No full textAs the technology of Artificial Intelligence (AI) expanded widely, AI has been used in many fields. It has become one of the most critical courses in the area of Computer Science and thus being offered in many universities worldwide. To ensure Al knowledge is mastered well by students, their understanding on this course should be measured efficiently. To achieve this, the preparations of the examination questions should follow certain guidelines or requirements for example the syllabus contents and the Bloom's Taxonomy model. The main objective of this project is to develop a system that acts as an analyzer to analyze the quality of the final examination question papers according to the Bloom's Taxonomy and syllabus contents. In UiTM, the process of analyzing the final examination question papers is currently done manually by the Examination Unit staff. Problems can occur because there are many sets of final examination questions at one time and obviously a manual check will not give a 100% accurate results. Therefore, there is a need of a system that can analyze the quality of the final examination questions according to the syllabus contents and Bloom's Taxonomy model. The methods used in this proposed project are the Fuzzy Logic and Keyword Matching Technique. Fuzzy Logic is used to classify the keywords to six different levels in Bloom's Taxonomy model and different topics in the Fundamentals of Artificial Intelligence course (UiTM Computer Science Degree Programme). The Keyword Matching Technique is used to find the matching keyword in the proposed final examination questions. The keyword found in the final examination questions were compared with the keyword of Bloom's Taxonomy and syllabus contents that were stored in the database. After that, the compliance percentage of the final examination questions based on the Bloom's Taxonomy model and syllabus contents were generated. High quality final examination question papers will follow closely the Bloom's Taxonomy and have a fair distribution of questions based on the syllabus contents. In this project, it was observed that Bloom's Taxonomy conformity percentage results for the analyzed examination questions papers did not obtain high percentages. As for the syllabus contents result, not any of the proposed examination papers have a fair distribution of questions based on syllabus contents
Entrepreneurial attributes and the mediating role of psychological capital on entrepreneurial intention among hospitality students in Malaysian public higher education institutions (PHEIS) / Nur Azah Farhana Mohamed Fadzil
No full textStrengthening entrepreneurship education by cultivating entrepreneurial values to enhance the marketability of graduates is considered relevant as a strategy to improve the employability of hospitality students in public higher learning. Aligned with the issues, the Malaysian Ministry of Higher Education has endorsed entrepreneurship education in all higher education institutions as an initiative to encourage students to enrol in entrepreneurship courses and activities. Therefore, this study investigates entrepreneurial attributes and the mediating role of psychological capital on entrepreneurial intention among Malaysian hospitality students. A quantitative study was implemented via an online survey in five (5) Malaysia's Public Higher Education Institutions (PHEIs), which then resulted in a final sample of 297 respondents. An established self-completed questionnaire was collected. Partial Least Squares-Structural Equation Modelling (PLS-SEM) software was used to analyse the obtained data structuring through probability sampling, using a simple random sampling technique. This study indicated that the dimensions of entrepreneurial attributes and psychological capital significantly influence students' entrepreneurial intention. Findings also revealed that psychological capital as the positive psychological development of an individual allows education providers to ensure students obtain the necessary attributes to function effectively. This verifies that psychological capital affects individuals in learning entrepreneurship, which can be emphasised by the PHEIs in preparing the students to be more confident for future entrepreneurial careers
Riding pink mobile app: women's e-hailing service / Azah Nursyafini Nazari
No full textRiding Pink is a service by women for women, it's a Malaysia's first female's only transportation platform
Phonation in Somali phonology
No full textThe author presents a phonological study on Somali language, in particular it focuses on the binary feature voiced/unvoiced stating its inadequacy.Qoraagu wuxuu halkan ku muujinayaa daraasaad ku saabsan codaynta Af-soomaaliga, wuxuuna si gaar ah diiradda u saarayaa labada qaab codlle/codlaawe oo aan is lahayn.L'autore presenta uno studio fonologico sulla lingua somala: in particolare definisce il tratto binario sonoro/sordo inadeguato ad un'esauriente descrizione della lingua.Mohamed Mohamed Abdi (a cura di
Hautverdächtig
No full textBook Title: Postcolonial Studies; Racial Profiling
Chapter Title: Hautverdächtig
Author(s): Mohamed Wa Baile, Ellen Höhne
Publisher: transcript Verlag
DOI: 10.14361/9783839441459-004
ISBN(s): 978-3-8376-4145-5, 978-3-8394-4145-9
ISSN(s): 2703-1233, 2703-124
The application of Artificial Neural Networks (ANN) applications in various discipline of studies / Wan Nur Azah Wan Nahar and Rahimah Mohamed Yunos
No full textArtificial Neural Networks (ANN) approaches are becoming useful as an alternate way to classical methods. As a computation and learning paradigm, they are presented as a different modeling approach to solve complicated problems. They have been used to solve complicated practical problems in various areas, such as accounting and business, engineering, medical and healthcare, geological and energy. They have also been applied for modeling, identification, prediction and forecasting. ANN have been extensively employed in numerous fields. They are not programmed in the conventional procedure but they are trained using data exemplifying the behavior of a system. This paper presents various applications of neural networks used in various studies. The applications of neural networks could be grouped in three major categories: (1) designing and modeling; (2) identification and evaluation and (3) prediction and control. Published literature presented in this study indicate the potential of ANN as a useful tool in various discipline for many industries. This paper will be very much useful to the researchers and professionals to find out the relevant references related to ANN and current studies related to it
Modelling, Simulation and Identification
No full textModeling, simulation and identification has been actively researched in solving practical engineering problems. This book presents the wide applications of modeling, simulation and identification in the fields of electrical engineering, mechanical engineering, civil engineering, computer science and information technology. The book consists of 17 chapters arranged in an order reflecting multidimensionality of applications related to power system, wireless communication, image and video processing, control systems, robotics, soil mechanics, road engineering, mechanical structures and workforce capacity planning. New techniques in signal processing, adaptive control, non-linear system identification, multi-agent simulation, eigenvalue analysis, risk assessment, modeling of dynamic systems, finite difference time domain modeling and visual feedback are also presented. We hope that readers will find the book useful and inspiring by examining the recent developments in the applications of modeling, simulation and identification
- …
