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

Sentiment analysis by deep learning approaches

10.12928/telkomnika.v18i2.13912
Sreevidya; Amrita Viswa Vidyapeetham P. , O.; Amrita Viswa Vidyapeetham V. Ramana Murthy , S.; Amrita Viswa Vidyapeetham Veni
We propose a model for carrying out deep learning based multimodal sentiment analysis. The MOUD dataset is taken for experimentation purposes. We developed two parallel text based and audio basedmodels and further, fused these heterogeneous feature maps taken from intermediate layers to complete thearchitecture. Performance measures–Accuracy, precision, recall and F1-score–are observed to outperformthe existing models.
Volume: 18
Issue: 2
Page: 752-760
Publish at: 2020-04-01

Enhance manet usability for encrypted data retrieval from cloud computing

10.11591/ijeecs.v18.i1.pp64-74
Fairouz Sher Ali , Hadeel Noori Saad , Falah Hassan Sarhan , Bushra Naaeem
Cloud computing has become a revolutionary computing model which provides an economical and flexible strategy for resource sharing and data management. Due to privacy concerns, sensitive data has to be encrypted before being uploaded to the cloud servers. Over the last few years, several keyword searchable encryption works have been described in the literature. However, existing works mostly focus on secure searching using keyword and only retrieve Boolean results that are not yet adequate. On the other hand, poor-resources of mobile networks play an important role on all applications area nowadays. Mobile nodes mostly act as information retrieval end which make it important to address this problem. In this paper, we present a secure keyword search scheme based on the Bloom filter(SKS-BF), which enhances the system’s usability by allowing ranking based on the relevance score of the search results and retrieves the top most relevant files instead of retrieving all the files. Further, the Bloom filter (BFs) can accelerate a search process involving a large number of keywords. Extensive experiments and network simulation confirm the efficiency of our proposed schemes.
Volume: 18
Issue: 1
Page: 64-74
Publish at: 2020-04-01

Session based cooperation in cognitive radio networks: network level approach

10.11591/ijict.v9i1.pp40-45
Sunil Ghildiyal , Himanshu Goel , Anupam Semwal
The cognitive radio prototype performance is to alleviate the scarcity of spectral resources for wireless communication through intelligent sensing and quick resource allocation techniques. Secondary users (SU’s) actively obtain the spectrum access opportunity by supporting primary users (PU’s) in cognitive radio networks (CRNs). In present generation, spectrum access is endowed through cooperative communication based link-level frame-based cooperative (LLC) principle. In this SUs independently act as conveyors for PUs to achieve spectrum access opportunities. Unfortunately, this LLC approach cannot fully exploit spectrum access opportunities to enhance the throughput of CRNs and fails to motivate PUs to join the spectrum sharing processes. Therefore to overcome this con, network level cooperative (NLC) principle was used, where SUs are integrated mutually to collaborate with PUs session by session, instead of frame based cooperation for spectrum access opportunities. NLC approach has justified the challenges facing in LLC approach. In this paper we make a survey of some models that have been proposed to tackle the problem of LLC. We show the relevant aspects of each model, in order to characterize the parameters that we should take in account to achieve a spectrum access opportunity.
Volume: 9
Issue: 1
Page: 40-45
Publish at: 2020-04-01

Developed third iterative dichotomizer based on feature decisive values for educational data mining

10.11591/ijeecs.v18.i1.pp209-217
Saja Taha Ahmed , Rafah Al-Hamdani , Muayad Sadik Croock
Recently, the decision trees have been adopted among the preeminent utilized classification models. They acquire their fame from their efficiency in predictive analytics, easy to interpret and implicitly perform feature selection. This latter perspective is one of essential significance in Educational Data Mining (EDM), in which selecting the most relevant features has a major impact on classification accuracy enhancement. The main contribution is to build a new multi-objective decision tree, which can be used for feature selection and classification. The proposed Decisive Decision Tree (DDT) is introduced and constructed based on a decisive feature value as a feature weight related to the target class label. The traditional Iterative Dichotomizer 3 (ID3) algorithm and the proposed DDT are compared using three datasets in terms of some ID3 issues, including logarithmic calculation complexity and multi-values featuresselection. The results indicated that the proposed DDT outperforms the ID3 in the developing time. The accuracy of the classification is improved on the basis of 10-fold cross-validation for all datasets with the highest accuracy achieved by the proposed method is 92% for the student.por dataset and holdout validation for two datasets, i.e. Iraqi and Student-Math. The experiment also shows that the proposed DDT tends to select attributes that are important rather than multi-value. 
Volume: 18
Issue: 1
Page: 209-217
Publish at: 2020-04-01

Artifact elimination in ECG signal using wavelet transform

10.12928/telkomnika.v18i2.14403
Thanh-Nghia; HCMC University of Technology and Education Nguyen , Thanh-Hai; HCMC University of Technology and Education Nguyen , Van-Thuyen; HCMC University of Technology and Education Ngo
Electrocardiogram signal is the electrical actvity of the heart and doctors can diagnose heart disease based on this electrocardiogram signal. However, the electrocardiogram signals often have noise and artifact components. Therefore, one electrocardiogram signal without the noise and artifact plays an important role in heart disease diagnosis with more accurate results. This paper proposes a wavelet transform with three stages of decomposition, filter, and reconstruction for eliminating the noise and artifact in the electrocardiogram signal. The signal after decomposing produces approximation and detail coefficients, which contains the frequency ranges of the noise and artifact components. Hence, the approximation and detail coefficients with the frequency ranges corresponding to the noise and artifact in the electrocardiogram signal are eliminated by filters before they are reconstructed. For the evaluation of the proposed algorithm, filter evaluation metrics are applied, in which signal-to-noise ratio and mean squared error along with power spectral density are employed. The simulation results show that the proposed wavelet algorithm at level 8 is effective, in which the with the “dmey” wavelet function was selected be the best based power spectrum density.
Volume: 18
Issue: 2
Page: 936-944
Publish at: 2020-04-01

Spatial variations of rain intensity over a short length propagation for 5G links based on a rain gauge network

10.12928/telkomnika.v19i2.16809
M.; Universiti Teknologi Malaysia Rashid , Jafri; Universiti Teknologi Malaysia Din , Omar Abdul; Universiti Teknologi Malaysia Aziz
Millimeter-wave (mm-wave) frequency range is among operating bands designated for terrestrial 5G networks. A critical challenge of link-budgeting in mm-wave 5G networks is the precise estimation of rain attenuation for short-path links. The difficulties are further amplified in tropical and subtropical regions where the rainfall rate has a higher intensity. Different models have been proposed to predict rain attenuation. The distance factor is an important parameter in predicting total attenuation from specific rain attenuation. This study investigates the distance factor based on rain gauge networks and measured rain attenuation at 26 GHz for a 300 m link in Malaysia. Considerable discrepancies between available models were observed especially when applied for shorter path links. Also, significant variability of rain intensity is observed from the rain gauge network. This study recommends further investigation of the distance factor for a shorter link. Hence, a measurement campaign incorporating rain gauge networks was established to examine spatial variations of rain intensity over a less than 1 km link. The motivation is to develop a suitable distance factor model for 5G mm-wave propagation.
Volume: 19
Issue: 2
Page: 372-379
Publish at: 2020-04-01

Modification of speed and current limiting performance of BLDC motor based on harmony search optimization method

10.11591/ijeecs.v18.i1.pp549-557
Mohammed Qasim Abbas , Yaser Atta Yassin
The brushless DC (BLDC) motor is a multi-variable and non-linear system so that it's required more advanced explaining and controlling set. In this work, an algorithm is proposed based on the harmony search algorithm (HAS) method. HSA mimics music improvisation process to find the optimal solution. In BLDC motor, many constraints are required; speed performance and current limiting control are dominated. HAS is proposed to find the optimal PID parameters for the two speed and current-limiting controllers that are proposed in the drive. By Matlab/Simulink results, a good performance is shown compared with the classical method that absence current-limiting controller.
Volume: 18
Issue: 1
Page: 549-557
Publish at: 2020-04-01

Various and multilevel of wavelet transform for classification misalignment on induction motor with quadratic discriminant analysis

10.12928/telkomnika.v18i2.14827
Pressa; Universitas Muhammadiyah Gresik Perdana Surya Saputra , Misbah; Universitas Muhammadiyah Gresik Misbah , Hendra; Universitas Muhammadiyah Gresik Ariwinarno , F. D.; Electronics Engineering Polytechnic Institute of Surabaya Murdianto
Induction motors have become a major part of the industry because of strong construction, cheap in purchasing and maintenance, high efficiency, and easy to operate. Preventive maintenance must always be carried out on all industrial equipment, including induction motors to last long and prevent further damage. Based on research in the industry, around 42%-50% or almost 50% is bearing damage. One reason is the occurrence of misalignment during the installation of the load on the induction motor. This study tries to identify the condition of the motor and classify the level of misalignment damage that occurs. In the process, the mother wavelet like as Daubechis, Symlet and Coiflet discrete wavelet transform (DWT) are selected as tools in processing motor vibration data. The level of DWT applied is 1st to 3rd level. Then, the three types of signal extraction, namely sum, range, and energy, which are obtained from a high-frequency signal of DWT, are used as input to Quadratic and Linear Discriminant Analysis. Then, discriminant analysis analyzes and classifies them into normal operation and two misalignments conditions. The simulation shows that 1st level of Daubechis DWT combined with quadratic discriminant analysis generates the best classification. It results 0% error of classification with Db3, Db4 and Db5, 4.17% error with Db1 and 8.33% error with Db2.
Volume: 18
Issue: 2
Page: 961-969
Publish at: 2020-04-01

A new multi-level key block cypher based on the Blowfish algorithm

10.12928/telkomnika.v18i2.13556
Suhad Muhajer; University of Basrah Kareem , Abdul; University of Technology Monem S. Rahma
Blowfish is a block cypher algorithm used in many applications to enhance security, but it includes several drawbacks. For example, the mix between the key and data is limited. This paper presents a new modification to the Blowfish algorithm to overcome such problems realised through a multi-state operation instead of an XOR. Our proposed algorithm uses three keys in the encryption and decryption processes instead of one for controlling the variable block bits sizes (1, 2, 4, and 8) bits and for determining the state table numbers. These tables are formed from the addition in a Galois field GF (2n) based on block bit size to increase the complexity of the proposed algorithm. Results are evaluated based on the criteria of complexity, time encryption, throughout, and histogram, and show that the original Blowfish, those modified by other scholars, and our proposed algorithm are similar in time computation. Our algorithm is demonstrated to be the most complex compared with other well-known and modified algorithms. This increased complexity score for our proposed Blowfish makes it more resistant against attempts to break the keys.
Volume: 18
Issue: 2
Page: 685-694
Publish at: 2020-04-01

Fuzzy transform for high-resolution satellite images compression

10.12928/telkomnika.v18i2.14903
Donna; National Institute of Aeronautics and Space Monica , Ayom; National Institute of Aeronautics and Space Widipaminto
Many compression methods have been developed until now, especially for very high-resolution satellites images, which, due to the massive information contained in them, need compression for a more efficient storage and transmission. This paper modifies Perfilieva's Fuzzy transform using pseudo-exponential function to compress very high-resolution satellite images. We found that very high-resolution satellite images can be compressed by F-transform with pseudo-exponential function as the membership function. The compressed images have good quality as shown by the PSNR values ranging around 59-66 dB. However, the process is quite time-consuming with average 187.1954 seconds needed to compress one image. These compressed images qualities are better than the standard compression methods such as CCSDS and Wavelet method, but still inferior regarding time consumption.
Volume: 18
Issue: 2
Page: 1130-1136
Publish at: 2020-04-01

Robust audio watermarking based on transform domain and SVD with compressive sampling framework

10.12928/telkomnika.v18i2.14773
Ledya; Telkom University Novamizanti , Gelar; Telkom University Budiman , Elsa; Telkom University Nur Fitri Astuti
The growth of the internet and digital data has resulted forgery, modification and sharing of digital data without property rights. Audio watermarking is one of a solution to protect the copyright of an audio from copyright infringement. This paper proposes an audio watermarking method which is robust against attacks and high capacity. First, a synchronization bit is added to the audio host. After the audio host is decomposed by Lifting Wavelet Transform (LWT), then choose a subband from the output of LWT to be transformed by discrete cosine transform (DCT). Next, the matrix of the signal from DCT is selected for the singular value decomposition (SVD) process, so that is obtained U, S and V matrix. S matrix is embedded with the watermark. Before the embedding process, the watermark image is compressed by Compressive Sampling. The results show that the proposed watermarking system is highly robust against a kind attack of LPF, resampling, and linear speed change which is proven by its BER is zero.
Volume: 18
Issue: 2
Page: 1079-1088
Publish at: 2020-04-01

User stories collection via interactive chatbot to support requirements gathering

10.12928/telkomnika.v18i2.14866
Ferliana; Universitas Multimedia Nusantara Dwitama , Andre; Universitas Multimedia Nusantara Rusli
Nowadays, software products have become an essential part of human life. To build software, developers must have a good understanding of the requirements of the software. However, software developers tend to jumpstart system construction without having a clear and detailed understanding of the requirements. The user story concept is one of the practices of the requirements elicitation. This paper aims to present the work conducted to develop an Android chatbot application to support the requirements elicitation activity in software engineering, making the work less time-consuming and structured even for users not accustomed to requirements engineering. The chatbot uses Nazief & Adriani stemming algorithm to pre-process the natural language it receives from the users and artificial mark-up language (AIML) as the knowledge base to process the bot’s responses. A preliminary acceptance test based on the technology acceptance model results in an 83.03% score for users’ behavioral intention to use.
Volume: 18
Issue: 2
Page: 890-898
Publish at: 2020-04-01

A robust method for VR-based hand gesture recognition using density-based CNN

10.12928/telkomnika.v18i2.14747
Liliana; Informatics Department Petra Christian University Liliana , Ji-Hun; Keimyung University Chae , Joon-Jae; Keimyung University Lee , Byung-Gook; Dongseo University Lee
Many VR-based medical purposes applications have been developed to help patients with mobility decrease caused by accidents, diseases, or other injuries to do physical treatment efficiently. VR-based applications were considered more effective helper for individual physical treatment because of their low-cost equipment and flexibility in time and space, less assistance of a physical therapist. A challenge in developing a VR-based physical treatment was understanding the body part movement accurately and quickly. We proposed a robust pipeline to understanding hand motion accurately. We retrieved our data from movement sensors such as HTC vive and leap motion. Given a sequence position of palm, we represent our data as binary 2D images of gesture shape. Our dataset consisted of 14 kinds of hand gestures recommended by a physiotherapist. Given 33 3D points that were mapped into binary images as input, we trained our proposed density-based CNN. Our CNN model concerned with our input characteristics, having many 'blank block pixels', 'single-pixel thickness' shape and generated as a binary image. Pyramid kernel size applied on the feature extraction part and classification layer using softmax as loss function, have given 97.7% accuracy.
Volume: 18
Issue: 2
Page: 761-769
Publish at: 2020-04-01

Optimal tuning linear quadratic regulator for gas turbine by genetic algorithm using integral time absolute error

10.11591/ijece.v10i2.pp1367-1375
Jamal M. Ahmed
For multiple input-multiple output (MIMO) systems, the most common control strategy is the linear quadratic regulator (LQR) which relies on state vector feedback. Despite this strategy gives very good result, it still has trial and error procedure to select the values of its weight matrices which plays a important role in reaching to the desiered system performance. In order to overcome this problem, the Genetic algorithm is used. The design of genetic algorithm based linear quadratic regulator (GA-LQR) utilized Integral time absolute error (ITAE) as a cost function for optimization. The propsed procedure is implemented on a linear model of gas turbine to control the generator spool’s speed and the output power.
Volume: 10
Issue: 2
Page: 1367-1375
Publish at: 2020-04-01

Benchmarking level interactivity of Indonesia government university websites

10.12928/telkomnika.v18i2.14888
Nurdin; Institut Agama Islam Negeri (IAIN) Palu Nurdin , Zana Chobita; STMIK Bina Mulia Palu Aratusa
Website interactivity is increasingly essential for higher education institutions in maintaining their relationship with stakeholders. However, limited is known what the level interactivity of a university website is without comparing with other similar educational institutions. Through the use of website content analysis and benchmarking strategy, we evaluate 41 government university website for benchmarking purposes. Base on thirteen interactive criteria, we successfully benchmarked the government university websites and built a-five levels of websites interactivity with different features. Our study highlights that higher level interactivity of website contains more feature that support a two-way communication between university and consumers, while lower level of websites interactivity merely have basic features for communication. The findings suggest the highest level of websites interactivity, the more features they should have. More importantly, the findings suggest web developer to design more interactive features in developing a higher level of website interactivity.
Volume: 18
Issue: 2
Page: 853-859
Publish at: 2020-04-01
1 2 3
...
2097 2098
Show 1262 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