Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

29,939 Article Results

Neural network technique with deep structure for improving author homonym and synonym classification in digital libraries

10.12928/telkomnika.v19i4.18878
Firdaus; Universitas Sriwijaya Firdaus , Siti; Universitas Sriwijaya Nurmaini , Varindo Ockta Keneddi; Universitas Sriwijaya Putra , Annisa; Universitas Sriwijaya Darmawahyuni , Reza Firsandaya; Universitas Sriwijaya Malik , Muhammad Naufal; Universitas Sriwijaya Rachmatullah , Andre Herviant; Universitas Sriwijaya Juliano , Tio Artha; Universitas Sriwijaya Nugraha
Author name disambiguation (AND), also recognized as name-identification, has long been seen as a challenging issue in bibliographic data. In other words, the same author may appear under separate names, synonyms, or distinct authors may have similar to those referred to as homonyms. Some previous research has proposed AND problem. To the best of our knowledge, no study discussed specifically synonym and homonym, whereas such cases are the core in AND topic. This paper presents the classification of non-homonym-synonym, homonym-synonym, synonym, and homonym cases by using the DBLP computer science bibliography dataset. Based on the DBLP raw data, the classification process is proposed by using deep neural networks (DNNs). In the classification process, the DBLP raw data divided into five features, including name, author, title, venue, and year. Twelve scenarios are designed with a different structure to validate and select the best model of DNNs. Furthermore, this paper is also compared DNNs with other classifiers, such as support vector machine (SVM) and decision tree. The results show DNNs outperform SVM and decision tree methods in all performance metrics. The DNNs performances with three hidden layers as the best model, achieve accuracy, sensitivity, specificity, precision, and F1-score are 98.85%, 95.95%, 99.26%, 94.80%, and 95.36%, respectively. In the future, DNNs are more performing with the automated feature representation in AND processing.
Volume: 19
Issue: 4
Page: 1208-1217
Publish at: 2021-08-01

Hybrid features for object detection in RGB-D scenes

10.11591/ijeecs.v23.i2.pp1073-1083
Sari Awwad , Bashar Igried , Mohammad Wedyan , Mohammad Alshira'H
Object detection is considered a hot research topic in applications of artificial intel-ligence and computer vision. Historically, object detection was widely used in var-ious fields like surveillance, fine-grained activities and robotics. All studies focus on improving accuracy for object detection using images, whether indoor or outdoor scenes. Therefore, this paper took a shot by improving the doable features extraction and proposing crossed sliding window approach using exiting classifiers for object de-tection. In this paper, the contribution includes two parts: First, improving local depth pattern feature along side SIFT and the second part explains a new technique presented by proposing crossed sliding window approach using two different types of images (colored and depth). Two types of features local depth patterns for detection (LDPD) and scale-invariant feature transform (SIFT) were merged as one feature vector. The RGB-D object dataset has been used and it consists of 300 different objects and in-cludes thousands of scenes. The proposed approach achieved high results comparing to other features or separated features that are used in this paper. All experiments and comparatives were applied on the same dataset for the same objective. Experimental results report a high accuracy in terms of detection rate, recall, precision and F1 scorein RGB-D scenes.
Volume: 23
Issue: 2
Page: 1073-1083
Publish at: 2021-08-01

Improving traffic and emergency vehicle clearence at congested intersections using fuzzy inference engine

10.11591/ijece.v11i4.pp3176-3185
Aditi Agrawal , Rajeev Paulus
Traffic signals play an important role in controlling and coordinating the traffic movement in cities especially in urban areas. As the traffic is exponentially increasing in cities and the pre-timed traffic light control is insufficient in effective timing of the traffic lights, it leads to poor traffic clearance and ultimately to heavy traffic congestion at intersections. Even the Emergency vehicles like Ambulance and Fire brigade are struck at such intersections and experience a prolonged waiting time. An adaptive and intelligent approach in design of traffic light signals is desirable and this paper contributes in applying fuzzy logic to control traffic signal of single four-way intersection giving priority to the Emergency vehicle clearance. The proposed control system is composed of two parallel controllers to select the appropriate lane for green signal and also to decide the appropriate green light time as per the real time traffic condition. Performance of the proposed system is evaluated by using simulations and comparing with pre-timed control system in changing traffic flow condition. Simulation results show significant improvement over the pre-timed control in terms of traffic clearance and lowering of Emergency vehicle wait time at the intersection especially when traffic intensity is high.
Volume: 11
Issue: 4
Page: 3176-3185
Publish at: 2021-08-01

Customized sorting and packaging machine

10.12928/telkomnika.v19i4.16786
Ashish; ABES Institute of Technology Bhatnagar , Rachit; ABES Institute of Technology Patel , Manan; ABES Institute of Technology Gupta , Mayank; ABES Institute of Technology Pal , Lakshay; ABES Institute of Technology Kumar
India is a country which has a cornerstone of agriculture. And as it comes to fruit/vegetable sorting and packaging in India, human labor has been a vital part. With manual hand picking, it is a very laborious task to classify the quality of fruits/vegetables and simultaneously pack them. One leading-edge technology for the fulfilment of this purpose is ‘Image Processing’ technology which is extremely fast and cost-efficient. Our whole idea revolves around the fact that each fruit will be inspected, sort and simultaneously packed. For the same, a low cost automated mechatronic system has designed consisting of a solitary mechanical arrangement, which is controlled and synchronized through electronic components. Fruits/vegetables are sorted as high-quality and low-quality on the basis of physical appearance and weight. For this, a suitable algorithm is designed using the Open CV library. And the sorting is done using Arduino Uno and Raspberry pi. Hence the aim is to develop a sorting and packaging facility that can be established at the very root level itself which will be economically compact and accurate and will give more justice to farmers.
Volume: 19
Issue: 4
Page: 1326-1333
Publish at: 2021-08-01

A fully integrated violence detection system using CNN and LSTM

10.11591/ijece.v11i4.pp3374-3380
Sarthak Sharma , B. Sudharsan , Saamaja Naraharisetti , Vimarsh Trehan , Kayalvizhi Jayavel
Recently, the number of violence-related cases in places such as remote roads, pathways, shopping malls, elevators, sports stadiums, and liquor shops, has increased drastically which are unfortunately discovered only after it’s too late. The aim is to create a complete system that can perform real-time video analysis which will help recognize the presence of any violent activities and notify the same to the concerned authority, such as the police department of the corresponding area. Using the deep learning networks CNN and LSTM along with a well-defined system architecture, we have achieved an efficient solution that can be used for real-time analysis of video footage so that the concerned authority can monitor the situation through a mobile application that can notify about an occurrence of a violent event immediately.
Volume: 11
Issue: 4
Page: 3374-3380
Publish at: 2021-08-01

Enhancing text classification performance by preprocessing misspelled words in Indonesian language

10.12928/telkomnika.v19i4.20369
Reza; Universitas Multimedia Nusantara Setiabudi , Ni Made Satvika; Universitas Multimedia Nusantara Iswari , Andre; Universitas Multimedia Nusantara Rusli
Supervised learning using shallow machine learning methods is still a popular method in processing text, despite the rapidly advancing sector of unsupervised methodologies using deep learning. Supervised text classification for application user feedback sentiments in Indonesian Language is one of the applications which is quite popular in both the research community and industry. However, due to the nature of shallow machine learning approaches, various text preprocessing techniques are required to clean the input data. This research aims to implement and evaluate the role of Levenshtein distance algorithm in detecting and preprocessing misspelled words in Indonesian language, before the text data is then used to train a user feedback sentiment classification model using multinomial Naïve Bayes. This research experimented with various evaluation scenarios, and found that preprocessing misspelled words in Indonesian language using the Levenshtein distance algorithm could be useful and showed a promising 8.2% increase on the accuracy of the model’s ability to classify user feedback text according to their sentiments.
Volume: 19
Issue: 4
Page: 1234-1241
Publish at: 2021-08-01

Social welfare maximization based optimal energy and reactive power dispatch using ant lion optimization algorithm

10.12928/telkomnika.v19i4.18351
Surender Reddy; Woosong University Salkuti , P.; Woosong University Sravanthi , Seong-Cheol; Woosong University Kim
In this paper an optimal energy and reactive power dispatch problem is solved by using the ant lion optimization (ALO) algorithm by considering the total cost minimization and social welfare maximization (SWM) objectives. Two different market models are proposed in this work, i.e., conventional/sequential market clearing and the proposed/simultaneous market clearing. In each market model, two objectives, i.e., total cost minimization and SWM are considered. The conventional social welfare (SW) consists the benefit function of consumers and the cost function of active power generation. In this paper, the conventional SW is modified by including the reactive power cost function. The reactive power cost calculation is exactly same as that in the conventional practice. The most important difference is that instead of doing cost calculation in post-facto manner as in conventional practice, simultaneous approach is proposed in this work. The scientificity and suitability of the proposed simultaneous active and reactive power methodology has been examined on standard IEEE 30 bus test system.
Volume: 19
Issue: 4
Page: 1379-1387
Publish at: 2021-08-01

A review of intelligent methods for condition monitoring and fault diagnosis of stator and rotor faults of induction machines

10.11591/ijece.v11i4.pp2820-2829
Omar Alshorman , Ahmad Alshorman
Nowadays, induction motor (IM) is extensively used in industry, including mechanical and electrical applications. However, three main types of IM faults have been discussed in the literature, bearing, stator, and rotor. Importantly, stator and rotor faults represent approximately 50%. Traditional condition monitoring (CM) and fault diagnosis (FD) methods require a high processing cost and much experience knowledge. To tackle this challenge, artificial intelligent (AI) based CM and FD techniques are extensively developed. However, there have been many review research papers for intelligent CM and FD machine learning methods of rolling elements bearings of IM in the literature. Whereas there is a lack in the literature, and there are not many review papers for both stator and rotor intelligent CM and FD. Thus, the proposed study's main contribution is in reviewing the CM and FD of IM, especially for the stator and the rotor, based on AI methods. The paper also provides discussions on the main challenges and possible future works.
Volume: 11
Issue: 4
Page: 2820-2829
Publish at: 2021-08-01

Particle swarm optimization tuned unified power flow controller for power oscillation reduction

10.11591/ijeecs.v23.i2.pp633-638
Ananda M. H. , M. R. Shivakumar
One of the best flexible AC transmission system (FACTS) is unified power flow controller (UPFC). As it gets more benefit from both real and reactive power transfer, it is used in power system for controlling the transmitted power. The UPFC controls the power on the transmission side of the power system. When the real as well as reactive power is set the UPFC tries to follow the command by using the proportional and integral (PI) controller. But in some power systems the PI controllers cannot produce the proper power due to the power oscillations. These oscillations are created due to PI controller properties. In this paper the PI controller is replaced with the particle swarm optimization tuned PI controller (PSO-PI). It minimizes the power oscillations by using the objective function. The MATLAB 2017b is used to demonstrate the power transfer curves and the voltages. The IEEE 9 bus system is being used as a reference system.
Volume: 23
Issue: 2
Page: 633-638
Publish at: 2021-08-01

User experience assessment of a COVID-19 tracking mobile application (AMAN) in Jordan

10.11591/ijeecs.v23.i2.pp1120-1127
Ashraf Mousa Saleh , Hayfa Y. Abuaddous , Odai Enaizan , Fahad Ghabban
This study assesses the user experience of a COVID-19 tracking application, as employed as a case study of AMAN mobile application based on user experience. This paper proposed an assessment of user experience (UX) for AMAN application (COVID-19 tracking mobile application in Jordan) by implementing a user experience questionnaire tool. The study aims to get feedback and identify UX based on user interaction and usage with the tracking application. The data are taken from 1208 participants who have experience using the application; an online questionnaire was implemented and distributed through social media groups. The research method that was adopted used the instrument from user experience questionnaire (UEQ) of Arabic and English versions. The results from the UX assessment using UEQ showed that there are four scales which are categorized as excellent; they are Attractiveness (Mean=1.9), Efficiency (Mean=2.4), Dependability (Mean=2.1), Stimulation (Mean=1.8), while the two scales on the benchmark of good are Perspicuity (Mean=2.0) and Novelty (Mean=1.6). From the scores, above < 0.8 show a positive evaluation. All scores are above >0,08 indicating that the evaluation of UX has a positive impression. It can be concluded that the AMAN application is very good–satisfying users to track infected cases of COVID 19. 
Volume: 23
Issue: 2
Page: 1120-1127
Publish at: 2021-08-01

Automated system for monitoring and control of the liquid wax production process

10.11591/ijeecs.v23.i2.pp782-790
Martín Díaz-Choque , Carlos Dávila-Ignacio , Augusto Sanchez-Ayte , Guillermo Morales-Romero , Almintor Torres-Quiroz , Nestor Alvarado-Bravo , Florcita Aldana-Trejo
This article describes the design of an automated system for the automatic monitoring and control of the liquid wax production process, in order to quantify its effect on productivity indicators. For which initially the procedure for obtaining the automation will be described; then the results obtained will be presented, the same ones that will be identified through a comparative analysis. During the investigation it was determined that, through the use of a programmable logic controller, it was possible to improve the precision of the dosage of components in the liquid wax production process; By achieving acorrect dosage, it is achieved that the physical-chemical factors that intervene in the quality of the final product, which are the pH and specific density, are within the limits established by the company, this is reflected in the decrease 38.77% of the amount of monthly loss of raw material, thus achieving the optimization of the productivity of the production of liquid wax by 83.69% per month, compared to the non-automated process. 
Volume: 23
Issue: 2
Page: 782-790
Publish at: 2021-08-01

Small intestine bleeding detection using color threshold and morphological operation in WCE images

10.11591/ijece.v11i4.pp3040-3048
A. Al Mamun , M. S. Hossain , P. P. Em , A. Tahabilder , R. Sultana , M. A. Islam
Wireless capsule endoscopy (WCE) is a significant modern technique for observing the whole gastroenterological tract to diagnose various diseases like bleeding, ulcer, tumor, Crohn's disease, polyps etc in a non-invasive manner. However, it will make a substantial onus for physicians like human oversight errors with time consumption for manual checking of a vast amount of image frames. These problems motivate the researchers to employ a computer-aided system to classify the particular information from the image frames. Therefore, a computer-aided system based on the color threshold and morphological operation has been proposed in this research to recognize specified bleeding images from the WCE. Besides, A unique classifier, quadratic support vector machine (QSVM) has been employed for classifying the bleeding and non-bleeding images with the statistical feature vector in HSV color space. After extensive experiments on clinical data, 95.8% accuracy, 95% sensitivity, 97% specificity, 80% precision, 99% negative predicted value and 85% F1 score has been achieved, which outperforms some of the existing methods in this regard. It is expected that this methodology would bring a significant contribution to the WCE technology. 
Volume: 11
Issue: 4
Page: 3040-3048
Publish at: 2021-08-01

Deep learning with focal loss approach for attacks classification

10.12928/telkomnika.v19i4.18772
Yesi Novaria; Universitas Sriwijaya Kunang , Siti; Universitas Sriwijaya Nurmaini , Deris; Universitas Sriwijaya Stiawan , Bhakti Yudho; Universitas Sriwijaya Suprapto
The rapid development of deep learning improves the detection and classification of attacks on intrusion detection systems. However, the unbalanced data issue increases the complexity of the architecture model. This study proposes a novel deep learning model to overcome the problem of classifying multi-class attacks. The deep learning model consists of two stages. The pre-tuning stage uses automatic feature extraction with a deep autoencoder. The second stage is fine-tuning using deep neural network classifiers with fully connected layers. To reduce imbalanced class data, the feature extraction was implemented using the deep autoencoder and improved focal loss function in the classifier. The model was evaluated using 3 loss functions, including cross-entropy, weighted cross-entropy, and focal losses. The results could correct the class imbalance in deep learning-based classifications. Attack classification was achieved using automatic extraction with the focal loss on the CSE-CIC-IDS2018 dataset is a high-quality classifier with 98.38% precision, 98.27% sensitivity, and 99.82% specificity.
Volume: 19
Issue: 4
Page: 1407-1418
Publish at: 2021-08-01

An electric circuit model for a lithium-ion battery cell based on automotive drive cycles measurements

10.11591/ijece.v11i4.pp2798-2810
Jaouad Khalfi , Najib Boumaaz , Abdallah Soulmani , El Mehdi Laadissi
The on-board energy storage system plays a key role in electric vehicles since it directly affects their performance and autonomy. The lithium-ion battery offers satisfactory characteristics that make electric vehicles competitive with conventional ones. This article focuses on modeling and estimating the parameters of the lithium-ion battery cell when used in different electric vehicle drive cycles and styles. The model consists of an equivalent electrical circuit based on a second-order Thevenin model. To identify the parameters of the model, two algorithms were tested: Trust-Region-Reflective and Levenberg-Marquardt. To account for the dynamic behavior of the battery cell in an electric vehicle, this identification is based on measurement data that represents the actual use of the battery in different conditions and driving styles. Finally, the model is validated by comparing simulation results to measurements using the mean square error (MSE) as model performance criteria for the driving cycles (UDDS, LA-92, US06, neural network (NN), and HWFET). The results demonstrate interesting performance mostly for the driving cycles (UDDS and LA-92). This confirms that the model developed is the best solution to be integrated in a battery management system of an electric vehicle.
Volume: 11
Issue: 4
Page: 2798-2810
Publish at: 2021-08-01

Smart security door system using SMS based energy harvest

10.11591/ijece.v11i4.pp3410-3423
Abdullah Hamas , Amgad Muneer , Suliman Mohamed Fati
Over the last decade, different studies have been conducted to increase security to identify sensor technology and provide alternative energy with other energy harvest techniques such as vibration energy harvester and sun energy harvester. There is no combinational approach to utilize the door to create energy and use it for security measures in the literature, making our system different and unique. This proposed system comprises the security and the energy harvest; the security section utilizes a motion detector sensor to detect intruders. For instance, the magnetic door lock type firmly locks the door, which can only open with a generated password. On the other side, the energy harvest section utilizes the door motion to generate electricity for the system, which solves power shortage and limited battery life issues. Moreover, this study includes a GSM module that allows authorized owners to receive a generated password as a security enhancement. This design mainly focuses on improving or optimizing the conventional security doors' overall performance as sliding door, panel door, or revolving door. The experimental results show the system efficiency in terms of power generation and the time needed to authenticate the property owner. Notably, the power generator can generate electricity more rapidly, while the needed time to receive the mobile device's security code is around 3.6 seconds.
Volume: 11
Issue: 4
Page: 3410-3423
Publish at: 2021-08-01
1 2 3
...
1995 1996
Show 936 of 1996

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration