International Journal of Electrical and Computer Engineering (IJECE)

Journal Information
ISSN / EISSN : 20888708 / 20888708
Current Publisher: Institute of Advanced Engineering and Science (10.11591)
Total articles ≅ 2,801
Current Coverage
SCOPUS
Archived in
SHERPA/ROMEO
Filter:

Latest articles in this journal

Malek Alzaqebah, Nashat Alrefai, Eman A. E. Ahmed, Sana Jawarneh, Mutasem K. Alsmadi
International Journal of Electrical and Computer Engineering (IJECE), Volume 10, pp 3672-3684; doi:10.11591/ijece.v10i4.pp3672-3684

Abstract:
Feature selection methods are used to select a subset of features from data, therefore only the useful information can be mined from the samples to get better accuracy and improves the computational efficiency of the learning model. Moth-flam Optimization (MFO) algorithm is a population-based approach, that simulates the behavior of real moth in nature, one drawback of the MFO algorithm is that the solutions move toward the best solution, and it easily can be stuck in local optima as we investigated in this paper, therefore, we proposed a MFO Algorithm combined with a neighborhood search method for feature selection problems, in order to avoid the MFO algorithm getting trapped in a local optima, and helps in avoiding the premature convergence, the neighborhood search method is applied after a predefined number of unimproved iterations (the number of tries fail to improve the current solution). As a result, the proposed algorithm shows good performance when compared with the original MFO algorithm and with state-of-the-art approaches.
Santosh Jankatti, Raghavendra B. K., Raghavendra S., Meenakshi Meenakshi
International Journal of Electrical and Computer Engineering (IJECE), Volume 10, pp 3811-3818; doi:10.11591/ijece.v10i4.pp3811-3818

Abstract:
Big data is the biggest challenges as we need huge processing power system and good algorithms to make an decision. We need Hadoop environment with pig hive, machine learning and hadoopecosystem components. The data comes from industries. Many devices around us and sensor, and from social media sites. According to McKinsey There will be a shortage of 15000000 big data professionals by the end of 2020. There are lots of technologies to solve the problem of big data Storage and processing. Such technologies are Apache Hadoop, Apache Spark, Apache Kafka, and many more. Here we analyse the processing speed for the 4GB data on cloudx lab with Hadoop mapreduce with varing mappers and reducers and with pig script and Hive querries and spark environment along with machine learning technology and from the results we can say that machine learning with Hadoop will enhance the processing performance along with with spark, and also we can say that spark is better than Hadoop mapreduce pig and hive, spark with hive and machine learning will be the best performance enhanced compared with pig and hive, Hadoop mapreduce jar.
Sanae Achsas, El Habib Nfaoui
International Journal of Electrical and Computer Engineering (IJECE), Volume 10, pp 3869-3882; doi:10.11591/ijece.v10i4.pp3869-3882

Abstract:
Vertical selection is the task of selecting the most relevant verticals to a given query in order to improve the diversity and quality of web search results. This task requires not only predicting relevant verticals but also these verticals must be those the user expects to be relevant for his particular information need. Most existing works focused on using traditional machine learning techniques to combine multiple types of features for selecting several relevant verticals. Although these techniques are very efficient, handling vertical selection with high accuracy is still a challenging research task. In this paper, we propose an approach for improving vertical selection in order to satisfy the user vertical intent and reduce user’s browsing time and efforts. First, it generates query embeddings vectors using the doc2vec algorithm that preserves syntactic and semantic information within each query. Secondly, this vector will be used as input to a convolutional neural network model for increasing the representation of the query with multiple levels of abstraction including rich semantic information and then creating a global summarization of the query features. We demonstrate the effectiveness of our approach through comprehensive experimentation using various datasets. Our experimental findings show that our system achieves significant accuracy. Further, it realizes accurate predictions on new unseen data.
Preeti Hemnani, A. K. Rajarajan, Gopal Joshi, S. V. G. Ravindranath
International Journal of Electrical and Computer Engineering (IJECE), Volume 10, pp 3468-3475; doi:10.11591/ijece.v10i4.pp3468-3475

Abstract:
Nuclear Magnetic Resonance (NMR) is a RF technique that is able to detect any compound by sensing the excited resonance signals from atomic nuclei having non-zero spin. NQR is similar to NMR but the only difference is NMR needs a DC magnetic field and due to this its application in the field is limited. A FPGA based NQR spectrometer is designed using a single FPGA chip to perform the digital tasks required for NQR spectrometer. Design of Probe for NMR/NQR spectrometer is researched. Parallel tuned and series tuned Probes are discussed and simulated.14N NQR from NaNO2 is observed from spectrometer designed with parallel tuned probe.
Kummari Rajesh, N. Visali
International Journal of Electrical and Computer Engineering (IJECE), Volume 10, pp 3358-3366; doi:10.11591/ijece.v10i4.pp3358-3366

Abstract:
In this paper hybrid method, Modified Nondominated Sorted Genetic Algorithm (MNSGA-II) and Modified Population Variant Differential Evolution(MPVDE) have been placed in effect in achieving the best optimal solution of Multiobjective economic emission load dispatch optimization problem. In this technique latter, one is used to enforce the assigned percent of the population and the remaining with the former one. To overcome the premature convergence in an optimization problem diversity preserving operator is employed, from the tradeoff curve the best optimal solution is predicted using fuzzy set theory. This methodology validated on IEEE 30 bus test system with six generators, IEEE 118 bus test system with fourteen generators and with a forty generators test system. The solutions are dissimilitude with the existing metaheuristic methods like Strength Pareto Evolutionary Algorithm-II, Multiobjective differential evolution, Multi-objective Particle Swarm optimization, Fuzzy clustering particle swarm optimization, Nondominated sorting genetic algorithm-II.
Nazha Cherkaoui, Abdelaziz Belfqih, Faissal El Mariami, Jamal Boukherouaa, Abdelmajid Berdai
International Journal of Electrical and Computer Engineering (IJECE), Volume 10, pp 3412-3422; doi:10.11591/ijece.v10i4.pp3412-3422

Abstract:
In recent years, many works have been done in order to discuss economic dispatch in which wind farms are installed in electrical grids in addition to conventional power plants. Nevertheless, the emissions caused by fossil fuels have not been considered in most of the studies done before. In fact, thermal power plants produce important quantities of emissions for instance, carbon dioxide (CO2) and sulphur dioxide (SO2) that are harmful to the environment. This paper presents an optimization algorithm with the objective to minimize the emission levels and the production cost. A comparison of the results obtained with different optimization methods leads us to opt for the grey wolf optimizer technique (GWO) to use for solving the proposed objective function. First, the method used to estimate the wind power of a plant is presented. Second, the economic dispatch models for wind and thermal generators are presented followed by the emission dispatch model for the thermal units.Then, the proposed objective function is formulated. Finally, the simulation results obtained by applying the GWO and other known optimization techniques are analysed and compared.
C. Arul Murugan, G. Sureshkumaar, Nithiyananthan Kannan, Sunil Thomas
International Journal of Electrical and Computer Engineering (IJECE), Volume 10, pp 3568-3575; doi:10.11591/ijece.v10i4.pp3568-3575

Abstract:
Life of human being and animals depend on the environment which is surrounded by plants. Like human beings, plants also suffer from lot of diseases. Plant gets affected by completely including leaf, stem, root, fruit and flower; this affects the normal growth of the plant. Manual identification and diagnosis of plant diseases is very difficult. This method is costly as well as time-consuming so it is inefficient to be highly specific. Plant pathology deals with the progress in developing classification of plant diseases and their identification. This work clarifies the identification of plant diseases using leaf images caused by bacteria, viruses and fungus. By this method it can be identified and control the diseases. To identify the plant leaf disease Adaptive Neuro Fuzzy Inference System (ANFIS) was proposed. The proposed method shows more refined results than the existing works.
Quang-Vi Ngo, Chai Yi, Trong-Thang Nguyen
International Journal of Electrical and Computer Engineering (IJECE), Volume 10, pp 3927-3935; doi:10.11591/ijece.v10i4.pp3927-3935

Abstract:
This paper presents the research on small-scale wind turbine systems based on the Maximum Power Point Tracking (MPPT) algorithm. Then propose a new structure of a small-scale wind turbine system to simplify the structure of the system, making the system highly practical. This paper also presented an MPPT-Fuzzy controller design and proposed a control system using the wind speed sensor for small-scale wind turbines. Systems are simulated using Matlab/Simulink software to evaluate the feasibility of the proposed controller. As a result, the system with the MPPT-Fuzzy controller has much better quality than the traditional control system.
Adnan Hussein Ali, Alaa Desher Farhood, Maham Kamil Naji
International Journal of Electrical and Computer Engineering (IJECE), Volume 10, pp 4252-4260; doi:10.11591/ijece.v10i4.pp4252-4260

Abstract:
The greatest advantages of optical fibers are the possibility of extending data rate transmission and propagation distances. Being a multi-carrier technique, the orthogonal frequency division multiplexing (OFDM) can be applicable in hybrid optical-wireless systems design owing to its best spectral efficiency for the interferences of radio frequency (RF) and minor multi-path distortion. An optical OFDM-RoF-based wireless local area network (W-LAN) system has been studied and evaluated in this work. The outline for integrating an optical technology and wireless in a single system was provided with the existence of OFDM-RoF technology and the microstrip patch antenna; these were applied in the Optisystem communication tool. The design of the proposed OFDM-RoF system is aimed at supporting mm-wave services and multi-standard operations. The proposed system can operate on different RF bands using different modulation schemes like 4,16 and 64QAM, that may be associated to OFDM and multidata rates up to 5 Gbps. The results demonstrate the robustness of the integrated optical wireless link in propagating OFDM-RoF-based WLAN signals across optical fibers.
Mohammed Qassim Shatnawi, Mohammad Alrousan, Suzan Amareen
International Journal of Electrical and Computer Engineering (IJECE), Volume 10, pp 4363-4371; doi:10.11591/ijece.v10i4.pp4363-4371

Abstract:
Content based image retrieval (CBIR) has become an important factor in medical imaging research and is obtaining a great success. More applications still need to be developed to get more powerful systems for better image similarity matching, and as a result getting better image retrieval systems. This research focuses on implementing low-level descriptors to maximize the quality of the retrieval of medical images. Such a research is supposed to set a better result in terms of image similarity matching. In this research a system that uses low-level descriptors is introduced. Three descriptors have been developed and applied in an attempt to increase the accuracy of image matching. The final results showed a qualified system in medical images retrieval specially that the low-level image descriptors have not been used yet in the image similarity matching in the medical field.
Back to Top Top