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

31,456 Article Results

Sentiments analysis of customer satisfaction in public services using K-nearest neighbors algorithm and natural language processing approach

10.12928/telkomnika.v19i1.17417
Elik Hari; Universitas AMIKOM Yogyakarta Muktafin , Pramono; Universitas AMIKOM Yogyakarta Pramono , Kusrini; Universitas AMIKOM Yogyakarta Kusrini
Customer satisfaction is very important for public service providers, customer satisfaction can be delivered with a survey application or writing criticism that can be used to evaluate and improve service. Unfortunately, there are only a few customers who are willing to give an assessment. The survey application cannot represent the overall feeling of the customer, so it is necessary to analyze the content of the conversation between the customer and the service personnel to determine the level of customer satisfaction. In small amounts, it can be done manually, but in large quantities it is more effective to use the system. A solution is needed in the form of a system that converts voice conversations into text and analyzes customer satisfaction to obtain information for evaluation and improvement of services. This research uses K-nearest neighbors (KNN) and term frequency-inverse document frequency (TF-IDF) algorithm with natural language processing (NLP) approach to classify conversations into 2 classes, "satisfied" and " dissatisfied ". The results of this study received 74.00% accuracy, 76.00% precision and 73.08% recall. In conversations with the label "satisfied" shows customers satisfied with the service and fulfillment of customer desires, while in conversations with the label "not satisfied" customers are less satisfied with the waiting time.
Volume: 19
Issue: 1
Page: 146-154
Publish at: 2021-02-01

Optimizing RPL performance based on the selection of best route between child and root node using E-MHOF method

10.11591/ijece.v11i1.pp224-231
Ahmed R. Zarzoor
IETF has proposed the routing protocol for low power and lossy networks (RPL) for IOT as view as light weight routing protocol. In RPL, the objective function (OF) is used to select the best route between child and root node. Several researches have been conducted in order to, enhance OF according to number parameters such as number of hops, remaining energy and expected number of transmissions (ETX), without a consideration to other challenges such as congestion node problem and latency. So, to overcome these challenges a new technique called “Enhance-Minimum Rank with Hysteresis Objective Function (MHOF)” is proposed in this paper, to select the ideal path between the child and root node. The technique is consisted of three layers: parent selection layer in which parent is selected based on three parameters (ETX, RSSI and nodes’ residual energy), path selection layer in which the best route is chosen according to the minimum of (average ETX value) and maximum of (average remaining energy value) of all nodes in the selected route. The last layer is child node minimization, which utilized to solve the congestion node energy problem by using two parameters (RSSI reference and threshold value). The proposed method has been implemented and evaluated by using Cooja simulator software. The simulation results have shown that selected path with E-MHOF is increased the network lifetime and reduced latency in comparison with MHOF.
Volume: 11
Issue: 1
Page: 224-231
Publish at: 2021-02-01

Duobinary modulation/predistortion techniques effects on high bit rate radio over fiber systems

10.11591/ijeecs.v21.i2.pp978-986
Mahmoud M. A. Eid , Ashraf S. Seliem , Ahmed Nabih Zaki Rashed , Abd El-Naser A. Mohammed , Mohamed Yassin Ali , Shaimaa S. Abaza
The work has presented duobinary modulation and predistortion techniques for the radio over fiber system enhancement for achieving security level. Duobinary modulation technique has more compact modulated spectral linewidth with standard non return to zero modulation code. Different NRZ/RZ rectangle shape employed that are namely exponential rectangle shape (ERS), and Gaussian rectangle shape (GRS) for different transmission bit rates. Switching bias voltage, and switching RF voltage based LiNbO3 modulator are changed to measure the performance parameters of the radio over fiber (RoF) system. Predistortion technique improves the linearity of transmitter amplifiers and it is considered as a power efficiency technique. The optimum values of the Q-factor, data error rate (BER), electrical power, signal gain, noise figure, and light signal/noise ratio are achieved with 8 Volt for both switching biases/switching RF signal at 100 GHz. Signal quality/BER and electrical power after the receiver enhancement ratio by using this technique at different RF signal frequencies. 
Volume: 21
Issue: 2
Page: 978-986
Publish at: 2021-02-01

WEIDJ: Development of a new algorithm for semi-structured web data extraction

10.12928/telkomnika.v19i1.16205
Ily Amalina; Universiti Malaysia Terengganu Ahmad Sabri , Mustafa; Universiti Malaysia Terengganu Man
In the era of industrial digitalization, people are increasingly investing in solutions that allow their process for data collection, data analysis and performance improvement. In this paper, advancing web scale knowledge extraction and alignment by integrating few sources by exploring different methods of aggregation and attention is considered in order focusing on image information. The main aim of data extraction with regards to semi-structured data is to retrieve beneficial information from the web. The data from web also known as deep web is retrievable but it requires request through form submission because it cannot be performed by any search engines. As the HTML documents start to grow larger, it has been found that the process of data extraction has been plagued with lengthy processing time. In this research work, we propose an improved model namely wrapper extraction of image using document object model (DOM) and JavaScript object notation data (JSON) (WEIDJ) in response to the promising results of mining in a higher volume of image from a various type of format. To observe the efficiency of WEIDJ, we compare the performance of data extraction by different level of page extraction with VIBS, MDR, DEPTA and VIDE. It has yielded the best results in Precision with 100, Recall with 97.93103 and F-measure with 98.9547.
Volume: 19
Issue: 1
Page: 317-326
Publish at: 2021-02-01

A new SDN-based load balancing algorithm for IoT devices

10.11591/ijeecs.v21.i2.pp1209-1217
Hind Sounni , Najib El kamoun , Fatima Lakrami
Nowadays, the emergence of the Internet of things devices has wholly revolutionized the customer's communication habits. The information can be collected at any time and anywhere. However, the mobility of communication devices in a dense network results inseveral problems, such as unbalanced network load and increased bandwidth demands, which decrease the network performance. To deal with these issues, this paper proposes a new load balancing algorithm based on the software-defined Network to enhance the performance of mobile devices communication over a Wi-Fi network. The use of the software-defined network automatizes the configuration of the network through a centralized controller; it provides programmability and an overall view of the network, along with optimizing resource allocation based on real-time network information, which facilitates the implementation of our algorithm. The proposed algorithm is implemented and evaluated through simulation using mininet-WiFi. The results indicate that our proposed method provides an efficient network load balancing and improves performancdevices' performance.
Volume: 21
Issue: 2
Page: 1209-1217
Publish at: 2021-02-01

Application of model reduction for robust control of self-balancing two-wheeled bicycle

10.12928/telkomnika.v19i1.16298
Vu Ngoc; Thai Nguyen University of Technology Kien , Nguyen Hong; Thai Nguyen University of Technology Quang , Ngo Kien; Thai Nguyen University of Technology Trung
In recent years, balance control of two-wheeled bicycle has received more attention of scientists. One difficulty of this problem is the control object is unstable and constantly impacted by noise. To solve this problem, the authors often use robust control algorithms. However, robust controller of self-balancing two-wheeled bicycle are often complex and higher order so affect to quality during real controlling. The article introduces the stochastic balanced truncation algorithm based on Schur analysis and applies this algorithm to reduce order higher order robust controller in control balancing two-wheeled bicycle problem. The simulation results show that the reduced 4th and 5th order controller arcoording to the stochastic balanced truncation algorithm based on Schur analysis can control the two-wheeled bicycle model. The reduced 3rd order controller cannot control the balance of the two-wheeled bicycle model. The reduced 4th and 5th order controller can replace the original controller while the performance of the control system is ensured. Using reduced 5th, 4th order controller will make the program code simpler, reducing the calculation time of the self-balancing two-wheel control system. The simulation results show the correctness of the model reduction algorithm and the robust control algorithm of two-wheeled self-balancing two-wheeled bicycle.
Volume: 19
Issue: 1
Page: 252-264
Publish at: 2021-02-01

Voltage collapse prediction using artificial neural network

10.11591/ijece.v11i1.pp124-132
Samuel Isaac , Soyemi Adebola , Awelewa Ayokunle , Katende James , Awosope Claudius
Unalleviated voltage instability frequently results in voltage collapse; which is a cause of concern in power system networks across the globe but particularly in developing countries. This study proposed an online voltage collapse prediction model through the application of a machine learning technique and a voltage stability index called the new line stability index (NLSI_1). The approach proposed is based on a multilayer feed-forward neural network whose inputs are the variables of the NLSI_1. The efficacy of the method was validated using the testing on the IEEE 14-bus system and the Nigeria 330-kV, 28-bus National Grid (NNG). The results of the simulations indicate that the proposed approach accurately predicted the voltage stability index with an R-value of 0.9975 with a mean square error (MSE) of 2.182415x10−5 for the IEEE 14-bus system and an R-value of 0.9989 with an MSE of 1.2527x10−7 for the NNG 28 bus system. The results presented in this paper agree with those found in the literature.
Volume: 11
Issue: 1
Page: 124-132
Publish at: 2021-02-01

Improved myoelectric pattern recognition of finger movement using rejection-based extreme learning machine

10.12928/telkomnika.v19i1.16566
Khairul; University of Jember Anam , Adel; University of Technology Sydney Al-Jumaily
Myoelectric control system (MCS) had been applied to hand exoskeleton to improve the human-machine interaction. The current MCS enables the exoskeleton to move all fingers concurrently for opening and closing hand and does not consider robustness issue caused by the condition not considered in the training stage. This study addressed a new MCS employing novel myoelectric pattern recognition (M-PR) to handle more movements. Furthermore, a rejection-based radial-basis function extreme learning machine (RBF-ELM) was proposed to tackle the movements that are not included in the training stage. The results of the offline experiments showed the RBF-ELM with rejection mechanism (RBF-ELM-R) outperformed RBF-ELM without rejection mechanism and other well-known classifiers. In the online experiments, using 10-trained classes, the M-PR achieved an accuracy of 89.73% and 89.22% using RBF-ELM-R and RBF-ELM, respectively. In the experiment with 5-trained classes and 5-untrained classes, the M-PR accuracy was 80.22% and 59.64% using RBF-ELM-R and RBF-ELM, respectively
Volume: 19
Issue: 1
Page: 134-145
Publish at: 2021-02-01

A hybrid feature selection on AIRS method for identifying breast cancer diseases

10.11591/ijece.v11i1.pp728-735
Achmad Ridok , Nashi Widodo , Wayan Firdaus Mahmudy , Muhaimin Rifa’i
Breast cancer may cause a death due to the late diagnosis. A cheap and accurate tool for early detection of this disease is essential to prevent fatal incidence. In general, the cheap and less invasive method to diagnose the disease could be done by biopsy using fine needle aspirates from breast tissue. However, rapid and accurate identification of the cancer cell pattern from the cell biopsy is still challenging task. This diagnostic tool can be developed using machine learning as a classification problem. The performance of the classifier depends on the interrelationship between sample sizes, some features, and classifier complexity. Thus, the removal of some irrelevant features may increase classification accuracy. In this study, a new hybrid feature selection fast correlation based feature (FCBF) and information gain (IG) was used to select features on identifying breast cancer using AIRS algorithm. The results of 10 times the crossing (CF) of our validation on various AIRS seeds indicate that the proposed method can achieve the best performance with accuracy =0.9797 and AUC=0.9777 at k=6 and seed=50.
Volume: 11
Issue: 1
Page: 728-735
Publish at: 2021-02-01

An intelligent indian stock market forecasting system using LSTM deep learning

10.11591/ijeecs.v21.i2.pp1082-1089
K Kumar , Dattatray P. Gandhmal
Stock market data is considered to be one of the chaotic data in nature. Analyzing the stock market and predicting the stock market has been the area of interest among the researchers for a long time. In this paper, we have stepped forward and used a deep learning algorithm with classification to predict the behavior of the stock market. LSTM deep learning algorithm is used with an optimization algorithm to formulate the hyperparameters. To further improve the accuracy of prediction the stock data is first given to a classification algorithm to reduce the number of input parameters. In this research Technical indicators are subjected to classification and deep LSTM algorithm which are both integrated to improve the accuracy of prediction. Deep LSTM hyperparameters are trained using the optimization algorithm. In this paper infosys and zensar stocks data is collected from the Indian stock market data i.e. both national stock exchange (NSE) and bombay stock exchange (BSE). The proposed approach is applied on infosys and zensar share values, the prediction accuracy obtained by employing this integrated approach of classification and LSTM has given a prominent value of MSE and RMSE as 1.034 and 1.002 respectively. 
Volume: 21
Issue: 2
Page: 1082-1089
Publish at: 2021-02-01

Vibration attenuation control of ocean marine risers with axial-transverse couplings

10.12928/telkomnika.v19i1.15778
Tung Lam; Hanoi University of Science and Technology Nguyen , Anh Duc; Thai Nguyen University Nguyen
The target of this paper is designing a boundary controller for vibration suppression of marine risers with coupling mechanisms under environmental loads. Based on energy approach and the equations of axial and transverse motions of the risers are derived. The Lyapunov direct method is employed to formulated the control placed at the riser top-end. Proof of existence and uniqueness of the solutions of the closed-loop system is provided. Stability analysis of the closed-loop system is also included.
Volume: 19
Issue: 1
Page: 235-243
Publish at: 2021-02-01

Performance of multi-hop cognitive MIMO relaying networks with joint constraint of intercept probability and limited interference

10.12928/telkomnika.v19i1.18006
Phu Tran; Industrial University of Ho Chi Minh City Tin , Duy-Hung; Ton Duc Thang University Ha , Pham Minh; Posts and Telecommunications Institute of Technology Quang , Nguyen Thanh; Posts and Telecommunications Institute of Technology Binh , Nguyen Luong; Posts and Telecommunications Institute of Technology Nhat
In this paper, we propose a multi-hop multiple input multiple output (MIMO) decode-and-forward relaying protocol in cognitive radio networks. In this protocol, a multi-antenna secondary source attempts to send its data to a multi-antenna secondary destination with assistance of multiple intermediate multi-antenna nodes, in presence of a multi-antenna secondary eavesdropper. A primary network includes a primary transmitter and a primary receiver which are equipped with multiple antennas, and use transmit antenna selection (TAS) and selection combining (SC) to communicate with each other. Operating on the underlay spectrum sharing method, the secondary source and relay nodes have to adjust their transmit power so that the outage performance of the primary network is not harmful and satisfy the quality of service (QoS). Moreover, these secondary nodes also reduce their transmit power so that the intercept probability (IP) at the eavesdropper at each hop is below a desired value. To improve the outage performance of the secondary network under the joint constraint of IP and limited interference, the TAS/SC method is employed to relay the source data hop-by-hop to the destination. We derived exact closed-form expressions of the end-to-end (e2e) outage probability (OP) and IP of the proposed protocol over Rayleigh fading channels. Monte Carlo simulations are then performed to verify the theoretical derivations.
Volume: 19
Issue: 1
Page: 44-50
Publish at: 2021-02-01

Multi-user media streaming service for e-learning based web real-time communication technology

10.11591/ijece.v11i1.pp567-574
Naktal Edan , Sanabil A. Mahmood
Web real-time communication (WebRTC) standards do not define precisely how two browsers establish and control their communication. Therefore, a signalling mechanism/protocol has not specified in WebRTC. The essential goal of this research is to create and apply a WebRTC bi-directional video conferencing based on mesh topology (many-to-many) using Google Chrome, Firefox, Opera, and Explorer. This experiment involved through Ethernet and Wireless of the Internet and 4G networks in e-learning. The signalling mechanism of this experiment has been created and implemented using JavaScript language along with MultiConnection libraries. In addition, an evaluation of quality of experience (QoE), resources, such as bandwidth consumption, and CPU performance was done. In this paper, a novel implementation was accomplished over e-learning using different networks, different browsers, many peers, opening one or many rooms concurrently, defining room initiator, sharing the information of the new user with participants, using user identification (user-id), and so on. Moreover, the paper also highlights the advantages and disadvantages of using WebRTC video conferencing.
Volume: 11
Issue: 1
Page: 567-574
Publish at: 2021-02-01

Differential evolution detection models for SMS spam

10.11591/ijece.v11i1.pp596-601
Sarab M. Hameed
With the growth of mobile phones, short message service (SMS) became an essential text communication service. However, the low cost and ease use of SMS led to an increase in SMS Spam. In this paper, the characteristics of SMS spam has studied and a set of features has introduced to get rid of SMS spam. In addition, the problem of SMS spam detection was addressed as a clustering analysis that requires a metaheuristic algorithm to find the clustering structures. Three differential evolution variants viz DE/rand/1, jDE/rand/1, jDE/best/1, are adopted for solving the SMS spam problem. Experimental results illustrate that the jDE/best/1 produces best results over other variants in terms of accuracy, false-positive rate and false-negative rate. Moreover, it surpasses the baseline methods.
Volume: 11
Issue: 1
Page: 596-601
Publish at: 2021-02-01

Enabling full-duplex in multiple access technique for 5G wireless networks over Rician fading channels

10.12928/telkomnika.v19i1.16245
Chi-Bao; Industrial University of Ho Chi Minh City Le , Dinh-Thuan; Industrial University of Ho Chi Minh City Do
Nowadays, unmanned aerial vehicle (UAV) relays’assisted Internet of Things (IoT) systems provide facility in order to overcome the large scale fading between source and sink. The full-duplex scheme enables wireless network to provide higher spectrum efficient technology. This paper analyses performance of two users which are served by new emerging non-orthogonal multiple access (NOMA) technique. Exact outage probability of such two users are derived and checked via Monte-Carlo simulation. These analytical results provide guideline to design UAV in real application. This paper provides a comprehensive study to examine impact of interference, fixed power allocation factors to system performance.
Volume: 19
Issue: 1
Page: 192-198
Publish at: 2021-02-01
1 2 3
...
2097 2098
Show 1121 of 2098

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