Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Not a member yet
776 research outputs found
Sort by
Malayalam Handwritten Character Recognition using CNN Architecture
Get PDFThe process of encoding an input text image into a machine-readable format is called optical character recognition (OCR). The difference in characteristics of each language makes it difficult to develop a universal method that will have high accuracy for all languages. A method that produces good results for one language may not necessarily produce the same results for another language. OCR for printed characters is easier than handwritten characters because of the uniformity that exists in printed characters. While conventional methods find it hard to improve the existing methods, Convolutional Neural Networks (CNN) has shown drastic improvement in classification and recognition of other languages. However, there is no OCR model using CNN for Malayalam characters. Our proposed system uses a new CNN architecture for feature extraction and softmax layer for classification of characters. This eliminates manual designing of features that is used in the conventional methods. P-ARTS Kayyezhuthu dataset is used for training the CNN and an accuracy of 99.75% is obtained for the testing dataset meanwhile a collection of 40 real time input images yielded an accuracy of 95%
Multimachine Stability Enhancement Using Fuzzy- Logic Based PSS Tuning With Shunt FACTS Device
Get PDFIn Large power system network the dynamic behaviour of system is nonlinear in nature. Due to disturbance the system stability cannot be maintained, which leads to outage of power equipment. In order to restore the system parameter after perturbance, coordination control damping is essential. Coordination control damping can be achieved by using fuzzy based PSS and STATCOM in multimachine system for sever disturbance. Due to perturbance the system loss its synchronism and the system parameter deviate from the nominal value. With the effective damping control technique proposed in this article is to minimize the integral square error of speed deviation. Two area 4-Machine 11-bus test system considered and the simulation of proposed system is developed in Matlab/Simulink R2018a
SentiMLBench: Benchmark Evaluation of Machine Learning Algorithms for Sentiment Analysis
Get PDFSentiment Analysis has been a topic of interest for researchers due to its increasing usage by Industry. To measure end-user sentiment., there is no clear verdict on which algorithms are better in real-time scenarios. A rigorous benchmark evaluation of various algorithms running across multiple datasets and different hardware architectures is required that can guide future researchers on potential advantages and limitations. In this paper, proposed SentiMLBench is a critical evaluation of key ML algorithms as standalone classifiers, a novel cascade feature selection (CFS) based ensemble technique in multiple benchmark environments each using a different twitter dataset and processing hardware. The best trained ensemble model with CFS enhancement surpasses current state-of-the-art models, according to experimental results. In a study, though ensemble model provides good accuracy, it falls short of neural networks accuracy by 2%. ML algorithms accuracy is poor as standalone classifiers across all three studies. The supremacy of neural networks is further stamped in study three where it outperforms other algorithms in accuracy by over 10%. Graphical processing unit provide speed and higher computational power at a fraction of a cost compared to a normal processor thereby providing critical architectural insights into developing a robust expert system for sentiment analysis
An Effective Model Of Autism Spectrum Disorder Using Machine Learning
Get PDFAutism spectrum disorder (ASD) is one of the most common diseases that affect human nerves and cause a decrease in the intelligence and comprehension of the person. This disease is a group of various disorders that are characterized by poor social behavior and communication. It affects all age groups, including adults, adolescents, children, and the elderly, but the symptoms of this disease always appear in their early years. ASD suffer from problems, the most important of which are data loss, low quality, and extreme values. This makes the process of diagnosing the ASD early. Our goals in this research is to solve the ASD problems. The cussent authors proposed a technical model that solves all data problems. We used ensemble techniques that include Bayesian Boosting, Classification by Regression, Polynomial by Binominal Classification. We also used classification techniques that include CHAID, Decision Stump, Decision Tree (Weight-Based), Gradient Boosted Trees, ID3. It is proven that the proposed model solves data problems, and has obtained the highest search accuracy that has reached 100% as well as we have obtained the highest f1 measurement that has reached 100%. This proves that our work is superior to its peers
Testable Design for Positive Control Flipping Faults in Reversible Circuits
Get PDFFast computational power is a major concern in every computing system. The advancement of the fabrication process in the present semiconductor technologies provides to accommodate millions of gates per chip and is also capable of reducing the size of the chips. Concurrently, the complex circuit design always leads to high power dissipation and increases the fault rates. Due to these difficulties, researchers explore the reversible logic circuit as an alternative way to implement the low-power circuit design. It is also widely applied in recent technology trends like quantum computing. Analyzing the correct functional behavior of these circuits is an essential requirement in the testing of the circuit. This paper presents a testable design for the k-CNOT based circuit capable of diagnosing the Positive Control Flipping Faults (PCFFs) in reversible circuits. The proposed work shows that generating a single test vector that applies to the constructed design circuit is sufficient for covering the PCFFs in the reversible circuit. Further, the parity-bit operations are augmented to the constructed testable circuit that produces the parity-test pattern to extract the faulty gate location of PCFFs. Various reversible benchmark circuits are used for evaluating the experimental results to establish the correctness of the proposed fault diagnosis technique. Also a comparative analysis is performed with the existing work
Design and Analysis of a Fish-Friendly Micro Gravitational Water Vortex Power Plant (GWVPP) on Zarqa River, Jordan
Get PDFThe main water source of Zarqa River is the treated wastewater from As-Samra Wastewater Treatment Plant (As-Samra WWTP) which is located in Zarqa Governorate in Al-Hashimiyya on the eastern part of the river; this means year-round flowing water in the eastern part of the river. This hydro energy is wasted continuously without exploiting it to generate electricity, but when trying to implement traditional hydropower projects on the river the main problem faced is low water head and low water flow. Since a Gravitational Water Vortex Power Plant (GWVPP) is an in-stream hydropower technology that can be operated with a low hydraulic head of (0.7-5.0) m and a low flow rate of 0.5 m3/s at least; this study proposed to install an on-grid GWVPP on Zarqa River by one of the manufacturing companies to exploit hydro energy and to serve the local community by providing farmers needs of electricity. The study also determines the appropriate site for establishing the GWVPP by collecting site data in terms of head, flow, and proximity to the grid and roads by Google Earth, site visits, and making site measurements. Then one of the GWVPP manufacturers contacted which is Turbulent Company, and then GWVPP has been designed. Environmental and economic feasibility analyses were performed by using RETScreen Expert software. As a result, the research indicates that installing a GWVPP on the Zarqa River is technically, economically, and ecologically viable
Smart System Side Slip Tester Results Accuracy Improvement Using Exponential Filter
Get PDFAccording to Article 6, Paragraph 1, of Law No. 55 of 2012 Concerning Cars, cars that are not roadworthy are particularly harmful for the safety of passengers and other road users. The front wheel ring, which has a significant impact on the safety of the motorized vehicle, is one of the technical requirements for roadworthiness. The front wheel pins make sure the car can go straight, which is related to the steering system's safety and has an impact on fuel economy. Through routine testing at the motor vehicle testing facility owned by the Transportation Service, the front wheel valve examination is performed using a front wheel blade test tool known as the Side Slip Tester. Previously, a lot of the automobile test equipment used at various test facilities was impractical and inaccurate. The construction of a smart system for evaluating wheel blades on cars is covered in this study, along with the implementation of an exponential filter to improve and lower the noise in sensor readings of ADC signals. By comparing the readings of the manufactured tool with a calibrated dial indicator, tests and calibrations are performed. The graph shows that the response to the input signal is quick and excellent for noise filtering, so based on the results of the exponential filter test, 0.2 is the ideal weight for the ADC reading filter. The 9 mm side slip bench shear test yields a maximum error result of 3% following tool calibration
Performance Investigation of Software Agents in Artificial Intelligence and Document Object Model Domain
Get PDFAssessing the performance impact of Artificial Intelligence on questionnaires of pharmacological unit is necessary from the perspective of medical practitioners as well as patient’s perspectives. The proposed study ascertained that software agents based on Artificial Intelligence and Document Object Model domain can deliver better service in medical units in contrast to its other deployment methodologies. So, the proposed work, a prototype is developed by using dialog control class file which accesses the system resources through the kernel objects. We call the software agent as MBot (prototype bot for medical unit). The prototype is deployed for pharmacological unit where the clinical instruction against the disease can be suggested. The experimental arrangement, deployment architecture of MBot, performance metrics and the statistical analysis for the observed data sample are discussed here. The novelty of the proposed work highlights the performance aspects of MBot against its counterpart. It reveals that better response time and validates that the dialog controller class of MBot can process questionnaires through its intelligence
An Improved ANN Approach for Occupancy Detection of A Smart Building
Get PDFBuilding energy performance can be improved with a reduction in energy consumption. The heating and cooling loads of a building are important factors to consider in the field of energy conservation. It is possible to estimate energy consumption by predicting the presence of occupants in a room based on information provided by the HVAC (Heating, Ventilation, and Air Conditioning) system using standard information. Temperature, humidity, light, and CO2 levels from various sensors are taken as input parameters. In addition, the output of the network is programmed to be "0" when the building is not occupied and "1" when the building is occupied for the purpose of occupant detection. Pattern recognition using an Elman back propagation network is being proposed for occupancy detection. The data sets were used for training and testing (with the office door open and closed) the models during occupancy. The proposed ANN-based method is trained and tested and was found to be more effective, with an accuracy of 98.5% and 97.5% in cases of closed and opened doors, respectively
PI-based ZSVM Control of Quasi-Z-Source Inverter for Photovoltaic Applications in Standalone Mode
Get PDFThe power converters Z-source topology are becoming a promoter solution for the energy conversion. This topology has the ability to boost and convert the voltage in a single-stage, unlike the famous two-stage conventionnel structure. The Quasi-Z-Source Inverter (QZSI) is nowadays the subject of several research works. However, it is the most suitable for PV applications, due to his continuous input current, which allows to harvest the maximum power available from the PV panels. In this regard, this paper investigates the dynamic characteristics of the QZSI through the small signal analysis, as well as the scheme control with the SVPWM technique for QZSI in standalone mode. The simulation results illustrate the practicability and the validity of the control scheme proposed