International Journal of Electrical and Computer Engineering Systems https://ijeces.ferit.hr/index.php/ijeces <p>The International Journal of Electrical and Computer Engineering Systems publishes original research in the form of original scientific papers, review papers, case studies and preliminary communications. It covers theory and application of electrical and computer engineering, synergy of computer systems and computational methods with electrical and electronic systems, as well as interdisciplinary research.</p> <p><strong>Published by Faculty of Electrical Engineering, Computer Science and Information Technology, Josip Juraj Strossmayer University of Osijek, Croatia.</strong></p> Faculty of Electrical Engineering, Computer Science and Information Technology, Josip Juraj Strossmayer University of Osijek, Croatia. en-US International Journal of Electrical and Computer Engineering Systems 1847-6996 Seven-Level Symmetrical Series/Parallel Multilevel Inverter with PWM Technique Using Digital Logic https://ijeces.ferit.hr/index.php/ijeces/article/view/92 <p>This paper attempts to come up with a proposed configuration of Multilevel inverters with a lesser number of switches that are smaller in size, lesser in cost and with a higher efficiency. Designing an inverter topology with a lesser number of switches and proper control technique is the major challenge. cascaded H-Bridge (CHB) topology are more popular among the existing configurations of multilevel inverters (MLI). Even though it can produce more levels, it needs to accommodate a huge number of switches for higher levels. The focus of this paper is to reduce the number of components for the same voltage level of cascaded H- Bridge configuration. In addition to that, generating the gating pulses for the switches is difficult when there is an asymmetry in the switches. A new symmetrical series/parallel configuration is proposed with reduced switch count and the pulse width modulation (PWM) technique is implemented with digital logic to generate the required gating pulses for the switches. The total harmonic distortion (THDI) of the output current is reduced with this PWM technique. The simulation has been carried out in MATLAB/Simulink software for both R (resistive) and R-L (resistive -inductive) loads.</p> Nagaraju Motaparthi Kiran kumar Malligunta Copyright (c) 2021 International Journal of Electrical and Computer Engineering Systems 2021-08-27 2021-08-27 12 3 123 130 10.32985/ijeces.12.3.1 High Efficiency, Good phase linearity 0.18 µm CMOS Power Amplifier for MBAN-UWB Applications https://ijeces.ferit.hr/index.php/ijeces/article/view/190 <p>This paper presents the design of 3.1-10.6 GHz class AB power amplifier (PA) suitable for medical body area network (MBAN) Ultra-Wide Band (UWB) applications in TSMC 0.18 µm technology. An optimization technique to simultaneously maximize power added efficiency(PAE) and minimize group delay variation is employed. Source and Load-pull contours are used to design inter and output stage matching circuits. The post-layout simulation results indicated that the designed PA has a maximum PAE of 32 % and an output 1-dB compression of 11 dBm at 4 GHz. In addition, a small group delay variation of ± 50 ps was realized over the whole required frequency band . Moreover, the proposed PA has small signal power gain (S21) of 12.5 dB with ripple less than 1.5 dB over the frequency range between 3.1 GHz to 10.6 GHz, while consuming 36 mW.</p> Hamed Mosalam Ahmed Gaddallah Copyright (c) 2021 International Journal of Electrical and Computer Engineering Systems 2021-08-27 2021-08-27 12 3 131 138 10.32985/ijeces.12.3.2 Performance evaluation and implementations of MFCC, SVM and MLP algorithms in the FPGA board https://ijeces.ferit.hr/index.php/ijeces/article/view/107 <p>One of the most difficult speech recognition tasks is accurate recognition of human-to-human communication. Advances in deep learning over the last few years have produced major speech improvements in recognition on the representative Switch-board conversational corpus. Word error rates that just a few years ago were 14% have dropped to 8.0%, then 6.6% and most recently 5.8%, and are now believed to be within striking range of human performance. This raises two issues - what is human performance, and how far down can we still drive speech recognition error rates? The main objective of this article is the development of a comparative study of the performance of Automatic Speech Recognition (ASR) algorithms using a database made up of a set of signals created by female and male speakers of different ages. We will also develop techniques for the Software and Hardware implementation of these algorithms and test them in an embedded electronic card based on a reconfigurable circuit (Field Programmable Gate Array FPGA). We will present an analysis of the results of classifications for the best Support Vector Machine architectures (SVM) and Artificial Neural Networks of Multi-Layer Perceptron (MLP). Following our analysis, we created NIOSII processors and we tested their operations as well as their characteristics. The characteristics of each processor are specified in this article (cost, size, speed, power consumption and complexity). At the end of this work, we physically implemented the architecture of the Mel Frequency Cepstral Coefficients (MFCC) extraction algorithm as well as the classification algorithm that provided the best results.</p> Salaheddine Khamlich Fathallah Khamlich Issam Atouf Mohamed Benrabh Copyright (c) 2021 International Journal of Electrical and Computer Engineering Systems 2021-08-27 2021-08-27 12 3 139 153 10.32985/ijeces.12.3.3 Expiry Prediction and Reducing Food Wastage using IoT and ML https://ijeces.ferit.hr/index.php/ijeces/article/view/225 <p>This paper details development of a low-cost, small-size, and portable electronic nose (E-nose) for the prediction of the expiry date of food products. The Sensor array is composed of commercially available metal oxide semiconductors sensors like MQ2 sensor, temperature sensor, and humidity sensor, which were interfaced with the help of ESP8266 and Arduino Uno for data acquisition, storage, and analysis of the dataset consisting of the odor from the fruit at different ripening stages. The developed system is used to analyze gas sensor values from various fruits like bananas and tomatoes. Responding signals of the e-nose were extracted and analyzed. Based on the obtained data we applied a few machine learning algorithms to predict if a banana is stale or not. Logistic regression, Decision Tree Classifier, Support Vector Classifier (SVC) &amp; K-Nearest Neighbours (KNN) classifiers were the binary classification algorithms used to determine whether the fruit became stale or not. We achieved an accuracy of 97.05%. These results prove that e-nose has the potential of assessing fruits and vegetable freshness and predict their expiry date, thus reducing food wastage.</p> Kartik Nair Bhavya Sekhani Krina Shah Sunil Karamchandani Copyright (c) 2021 International Journal of Electrical and Computer Engineering Systems 2021-08-27 2021-08-27 12 3 155 162 10.32985/ijeces.12.3.4 Legacy Digital Transformation: TCO and ROI Analysis https://ijeces.ferit.hr/index.php/ijeces/article/view/329 <p>Legacy Digital Transformation is modernizing or migrating systems from non-digital or older digital technology to newer digital technologies. Digitalization is essential for information reading, processing, transforming, and storing. Social media, Cloud, and analytics are the major technologies in today's digital world. Digitalization (business process) and Digital Transformation (the effect) are the core elements of newer global policies and processes. Recent COVID pandemic situation, Organizations are willing to digitalize their environment without losing business. Digital technologies help to improve their capabilities to transform processes that intern promote new business models. Applications cannot remain static and should modernize to meet the evolving business and technology needs. Business needs time to market, Agility, and reduce technical debt. Technology needs consist of APIs, better Security, Portability, Scalability, Cloud support, Deployment, Automation, and Integration. This paper elaborates different transformation/modernization approaches for Legacy systems written in very long or End of Life (EOL) systems to newer digital technologies to serve the business needs. EOL impacts application production, supportability, compliance, and security. Organizations spend money and resources on Digital Transformation for considering Investment versus Return on Investment, Agility of the System, and improved business processes. Migration and Modernization are critical for any Legacy Digital Transformation. Management takes decisions to proceed with Digital Transformation for considering Total Cost Ownership (TCO) and Return on Investment (ROI) of the program. The paper also includes a TCO-ROI calculator for Transformation from Legacy / Monolithic to new architectures like Microservices.</p> Ravi Kiran Mallidi Manmohan Sharma Jagjit Singh Copyright (c) 2021 International Journal of Electrical and Computer Engineering Systems 2021-08-27 2021-08-27 12 3 163 170 10.32985/ijeces.12.3.5 Appointment scheduling system in multi doctor/multi services environment https://ijeces.ferit.hr/index.php/ijeces/article/view/417 <p>Appointment scheduling systems are used by health care providers to manage access to their services. In this paper an algorithm and a web application for automatic appointment scheduling is presented. Both are implemented using the concept of booking appointments for patients for a specific service offered by each doctor. The purpose of the application is to make signing up for a specific service easier for patients and to improve health tourism in Croatia by maximizing doctor’s efficiency and minimize patient waiting time. Medical providers are added to the system, they add the services which they provide, and each service offered has its own duration time. Users register, search for services matching their parameters, and schedule an appointment for the requested service. Available appointments are generated using the presented algorithm, which is the main part of this paper. The algorithm searches the database and returns possible appointments. If patient has more than one appointment, possible appointments time can be before the existing appointment, between two appointments, or at the end of the last appointment. Thus, web application enables the patient to reserve desirable appointment time.</p> Ivica Lukić Mirko Köhler Erik Kiralj Copyright (c) 2021 International Journal of Electrical and Computer Engineering Systems 2021-08-27 2021-08-27 12 3 171 176 10.32985/ijeces.12.3.6