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

27,762 Article Results

Improving Sentiment Analysis of Short Informal Indonesian Product Reviews using Synonym Based Feature Expansion

10.12928/telkomnika.v16i3.7751
M. Ali; Universitas Brawijaya Fauzi , Ro'i Fahreza; Universitas Brawijaya Nur Firmansyah , Tri; Universitas Brawijaya Afirianto
Sentiment analysis in short informal texts like product reviews is more challenging. Short texts are sparse, noisy, and lack of context information. Traditional text classification methods may not be suitable for analyzing sentiment of short texts given all those difficulties. A common approach to overcome these problems is to enrich the original texts with additional semantics to make it appear like a large document of text. Then, traditional classification methods can be applied to it. In this study, we developed an automatic sentiment analysis system of short informal Indonesian texts using Naïve Bayes and Synonym Based Feature Expansion. The system consists of three main stages, preprocessing and normalization, features expansion and classification. After preprocessing and normalization, we utilize Kateglo to find some synonyms of every words in original texts and append them. Finally, the text is classified using Naïve Bayes. The experiment shows that the proposed method can improve the performance of sentiment analysis of short informal Indonesian product reviews. The best sentiment classification performance using proposed feature expansion is obtained by accuracy of 98%.The experiment also show that feature expansion will give higher improvement in small number of training data than in the large number of them.
Volume: 16
Issue: 3
Page: 1345-1350
Publish at: 2018-06-01

A Smart Monitoring of a Water Quality Detector System

10.11591/ijeecs.v10.i3.pp951-958
S. I. Samsudin , S. I. M. Salim , K. Osman , S. F. Sulaiman , M. I. A. Sabri
The importance to monitor the water quality level is undeniable due to significant impact to human health and ecosystem. The project aims to develop a wireless water quality monitoring system that aids in continuous measurements of water conditions based on pH and turbidity measurements. These two sensors are connected to microprocessor and transmitted to the database by using a Wi-Fi module as a bridge. The developed system was successfully detect both the pH and turbidity values hence updating in IoT platform. Based on the results obtained, the test water sample can be classified to class IIB which is suitable for water recreational used body contact. Overall, the developed system offers fast and easy monitoring of pH and turbidity levels with IoT application for continuous maintenance of clean water. The work is just concern on the physical water parameters hence further extend to chemical parameter for verifying a better result in measuring the WQI value.
Volume: 10
Issue: 3
Page: 951-958
Publish at: 2018-06-01

Stereo Vision Human Motion Detection and Tracking in Uncontrolled Environment

10.12928/telkomnika.v16i3.9033
Bunseng; University Malaysia Chan , King Hann; University Malaysia Lim , Lenin; University Malaysia Gopal , Alpha Agape; University Malaysia Gopalai , Darwin; University Malaysia Gouwanda
Stereo vision in detecting human motion is an emerging research for automation, robotics, and sports science field due to the advancement of imaging sensors and information technology. The difficulty of human motion detection and tracking is relatively complex when it is applied to uncontrolled environment. In this paper, a hybrid filter approach is proposed to detect human motion in the stereo vision. The hybrid filter approach integrates Gaussian filter and median filter to reduce the coverage of shadow and sudden change of illumination. In addition, sequential thinning and thickening morphological method is used to construct the skeleton model. The proposed hybrid approach is compared with the normalized filter. As a result, the proposed approach produces better skeleton model with less influential effect on shadow and illumination. The output results of the proposed approach can show up to 86% of average accuracy matched with skeleton model. In addition, obtains approximately 94% of sensitivity measurement in the stereo vision. The proposed approach using hybrid filter and sequential morphology could improve the performance of the detection in the uncontrolled environment.
Volume: 16
Issue: 3
Page: 955-964
Publish at: 2018-06-01

Generating Travel Itinerary Using Ant Collony Optimization

10.12928/telkomnika.v16i3.7268
ZK. Abdurahman; Telkom University Baizal , Aniq A; Telkom University Rahmawati , Kemas M; Telkom University Lhaksmana , Moh Z; Telkom University Mubarok , M.; Telkom University Qadrian
Travelling is one of the activities needed by everyone to overcome weariness. The number of information about the tourism destination on the internet sometimes does not provide easiness for oncoming tourists. This paper proposes a system capable of making travel itinerary, for tourists who want to visit an area within a few days. For generating itinerary, the system considers several criterias (Multi-criteria-based), which include the popularity level of tourist attractions to visit, tourist visits that minimize budgets or tourist visits with as many destinations as possible. To handle multi criteria-based itinerary, we use the concept of multi attribute utility theory (MAUT). The running time of multi criteria-based itinerary is not significantly different from time-based itinerary. In addition, the number of tourist attractions in the itinerary is more than time-based itinerary, because the combination of solutions from each ant becomes more diverse.
Volume: 16
Issue: 3
Page: 1208-1216
Publish at: 2018-06-01

Confidence of AOI-HEP Mining Pattern

10.12928/telkomnika.v16i3.5303
Harco Leslie Hendric; Bina Nusantara University Spits Warnars , Agung; Bina Nusantara university Trisetyarso , Richard; Ecole Centrale de Nantes Randriatoamanana
Attribute Oriented Induction High level Emerging Pattern (AOI-HEP) has been proven can mine frequent and similar patterns and the finding AOI-HEP patterns will be underlined with confidence mining pattern for each AOI-HEP pattern either frequent or similar pattern, and each dataset as confidence AOI-HEP pattern between frequent and similar patterns. Confidence per AOI-HEP pattern will show how interested each of AOI-HEP pattern, whilst confidende per dataset will show how interested each dataset between frequent and similar patterns. The experiments for finding confidence of each AOI-HEP pattern showed that AOI-HEP pattern with growthrate under and above 1 will be recognized as uninterested and interested AOI-HEP mining pattern since having confidence AOI-HEP mining pattern under and above 50% respectively. Furthermore, the uniterested AOI-HEP mining pattern which usually found in AOI-HEP similar pattern, can be switched to interested AOI-HEP mining pattern by switching their support positive and negative value scores.
Volume: 16
Issue: 3
Page: 1217-1225
Publish at: 2018-06-01

Algorithm for the Representation of Parameter Values of Electrocardiogram

10.12928/telkomnika.v16i3.6934
Sabar; Widyagama University of Malang Setiawidayat , Rudy; Widyagama Husada College of Health Joegijantoro
Important parameters that need to be known from the results of cardiac examination using Electrocardiograph is the parameter value of PQRST amplitude peak on each lead. Peak P is associated with Atrium depolarization, QRS waves associated with ventricle depolarization and peak T associated with ventricle repolarization. The PQRST peak values on each lead to date are still manually calculated using small boxes on the ECG paper. Manual calculations lead to less accurate results and calculated waiting times. Less accuracy can lead to misdiagnosis while waiting times can result in increased disease stage. In this article we have been able to represent the values of PQRST amplitude peak and cardiogram in each cycle on each lead of the electrocardiogram. Continuous signal Electrocardiogram (ECG) examination results, in sampling at certain frequencies to obtain discrete data which is the amplitude as a function of integer numbers (N). The maximum amplitude value of each cycle is peak R. The peak time duration R to peak R (dR) is used as the time period of each cycle. A 1.5dR reversal of RN + 1 reverses the starting point of the cycle (sc) while the 0.5dR duration reversal of RN + 1 will be obtained by the end point of the cycle (ec). The maximum and minimum amplitude values between sc and peak R are peak P and peak Q respectively, while the minimum and maximum values between peak R to ec are peak Q and peak T respectively. Discrete data from Physionet MIT-BIH and bmeuwg are used as data to obtain PQRST peak electrocardiogram parameter values in each cycle.
Volume: 16
Issue: 3
Page: 1295-1302
Publish at: 2018-06-01

A Development of Android-based Mobile Application for Getting Ideal Weight

10.12928/telkomnika.v16i3.8342
Alvina; Bina Nusantara University Aulia , Fidelson; Bina Nusantara University Tanzil , Irma Kartika; Bina Nusantara University Wairooy , Leonardus Kristian; Bina Nusantara University Gunawan , Alvin; Bina Nusantara University Cunwinata , Albert; Bina Nusantara University Albert
The development of this application has a goal to give people who don’t have any idea of how to keep an ideal body weight and to maintain it by having controlled food intakes and exercises. This application is designed by using a Waterfall Model, a 5-phase model that is Communication, Planning, Modeling, Construction, and Deployment starting from as the aforementioned steps. Based on the responds we get from distributing questionnaire, many people didn’t know how to exercise properly and didn’t bother to check the calories of their food. Their weight is also a problem because most of them still have an Overweight or Underweight status. From those responds, we can conclude that our application will indeed help people to get and maintain their ideal body weight.
Volume: 16
Issue: 3
Page: 1289-1294
Publish at: 2018-06-01

Three Dimensional Animation of How to Breed Rabbit

10.12928/telkomnika.v16i3.7576
Tri; Universitas Muria Kudus Listyorini , Syaifur; Universitas Muria Kudus Rochman , Rizkysari; Universitas Muria Kudus Meimaharani
Rabbit is one of the animal groups that is included in herbivore livestock that has been known by people beside of goat, cow, buffalo etc. Most countries in this world have rabbit livestock because of the rabbit has a high body adaptation energy that can make them live in most of the world. Some of the advantages of rabbit breeding are from the side of economic profits. Because of that, this research presents an animation of the way to breed rabbit well and correctly, because rabbit breeding is one of the benificial activities or hobbies. Through media information which uses animation, the process of information delivery will be easier to understand rather than using oral or written from. Therefore, how to breed rabbit animation will make people know the way to breed rabbit well and correctly, that will serve as a three-dimensional form.
Volume: 16
Issue: 3
Page: 1309-1316
Publish at: 2018-06-01

Implementation of Augmented Reality as Information and Promotion Media on Dieng Tourism Area

10.12928/telkomnika.v16i4.7759
Banu Nur; Semarang State University Affan , Agus; Semarang State University Suryanto , Arief; Semarang State University Arfriandi
Information and promotion became necessary for tourists to get also improve their knowledge of tourism and their experiences about the tourist destination. Dieng tourist area had manytourist attractions and would be styled to be promoted at the world level tourism by Central Java government in Indonesia, but tourist information and promotional media not yet structured and interactive, as well as the need of media that can provide knowledge, experience for tourists with packaged in an interactive and interesting way. The purpose of this research is to produce Augmented Reality application that could visualize information of Dieng tourism objects, as an interactive, interesting information and tourism promotional media. The user would get information about every tourist attraction in Dieng through the augmented reality application that contains many contents about the sites by scanned Natural Marker that already exist in every Dieng tourist attraction sites with his smartphone.
Volume: 16
Issue: 4
Page: 1818-1825
Publish at: 2018-06-01

Performance Evaluation of DV-HOP and Amorphous Algorithms based on Localization Schemes in Wireless Sensor Networks

10.12928/telkomnika.v16i3.8560
Doan; Telkom University Perdana , Adi; Telkom University Nugroho , Favian; Telkom University Dewanta
In the field of high-risk observation, the nodes in Wireless Sensor Network (WSN) are distributed randomly. The result from sensing becomes meaningless if it is not known from where the originating node is. Therefore, a sensor node positioning scheme, known as the localization scheme, is required. The localization scheme consists of distance estimation and position computing. Thus, this research used connectivity as distance estimation within range free algorithm DV-Hop and Amorphous, and then trilateral algorithm for computing the position. Besides that, distance estimation using the connectivity between nodes is not needed for the additional hardware ranging as required by a range-based localization scheme. In this research compared the localization algorithm based on range free localization, which are DV-Hop algorithm and Amorphous algorithm. The simulation result shows that the amorphous algorithm have achieved 13.60% and 24.538% lower than dv-hop algorithm for each parameter error localization and energy consumption. On node density variations, dv-hop algorithm gained a localization error that is 26.95% lower than amorphous algorithm, but for energy consumption parameter, amorphous gained 14.227% lower than dv-hop algorithm. In the communication range variation scenario, dv-hop algorithm gained a localization error that is50.282% lower than amorphous. However, for energy consumption parameter, amorphous algorithm gained 12.35%. lower than dv-hop algorithm.
Volume: 16
Issue: 3
Page: 1150-1157
Publish at: 2018-06-01

Optimization of PV Systems Using Data Mining and Regression Learner MPPT Techniques

10.11591/ijeecs.v10.i3.pp1080-1089
Adedayo M. Farayola , Ali N Hasan , Ahmed Ali
Supervised machine learning techniques such as artificial neural network (ANN) and ANFIS are powerful tools used to track the maximum power point (MPPT) in photovoltaic systems. However, these offline MPPT techniques still require large and accurate training data sets for successful tracking. This paper presents an innovative use of rational quadratic gaussian process regression (RQGPR) technique to generate the large and very accurate training data required for MPPT task. To confirm the effectiveness of the RQGPR technique, the combination of ANN and RQGPR as ANN-RQGPR technique results were compared with the conventional ANN technique results, and that of combined ANN and linear support vector machine regression as ANN-LSVM technique results under different weather conditions. Results show that ANN-RQGPR technique produced the overall best result and with an improved performance. 
Volume: 10
Issue: 3
Page: 1080-1089
Publish at: 2018-06-01

Efficient Data Security for Mobile Instant Messenger

10.12928/telkomnika.v16i3.4045
Putra; Harbin University of Science and Technology Wanda , Huang; Harbin University of Science and Technology J. Jie
Instant Messenger (IM) becomes one of the most popular applications in mobile technology and communication. A lot of users around the world installed it for daily activities. Current IM found security lacks both in authentication and encryption matters. Various IM growing today still not apply an efficient method in authentication and encryption process, conventional security methods and client-server architecture system have to risk too many users for attacking server such as compromising, cracking password or PINs by Unauthorized people. Common IM services lack native encryption to protect information being transmitted over the public network and still used high computation in the mobile environment, this problem needs efficient security methods. Then, in public IM also found various messages with fake users, it occurs because public IM carry out the separate system in authentication and encryption process, strong authentication need to solve this issue in messenger environment. The tremendous growth of mobile IM user needs efficient and secure communication way. This paper proposes a new efficient method for securing message both in encryption and authentication within the end-to-end model. In this research, security method proposes new algorithms based on Elliptic Curve (EC) works in Peer to Peer (P2P) architecture than a conventional client-server model. The result shows this method produces efficient time in authentication and encryption process while applying in a mobile environment. Besides, it is compatible with the mobile phone which has a limitation of computation capabilities and resources.
Volume: 16
Issue: 3
Page: 1426-1434
Publish at: 2018-06-01

Shared-hidden-layer Deep Neural Network for Under-resourced Language the Content

10.12928/telkomnika.v16i3.7984
Devin; Institut Teknologi Bandung Hoesen , Dessi Puji; Institut Teknologi Bandung Lestari , Dwi Hendratmo; Institut Teknologi Bandung Widyantoro
Training speech recognizer with under-resourced language data still proves difficult. Indonesian language is considered under-resourced because the lack of a standard speech corpus, text corpus, and dictionary. In this research, the efficacy of augmenting limited Indonesian speech training data with highly-resourced-language training data, such as English, to train Indonesian speech recognizer was analyzed. The training was performed in form of shared-hidden-layer deep-neural-network (SHL-DNN) training. An SHL-DNN has language-independent hidden layers and can be pre-trained and trained using multilingual training data without any difference with a monolingual deep neural network. The SHL-DNN using Indonesian and English speech training data proved effective for decreasing word error rate (WER) in decoding Indonesian dictated-speech by achieving 3.82% absolute decrease compared to a monolingual Indonesian hidden Markov model using Gaussian mixture model emission (GMM-HMM). The case was confirmed when the SHL-DNN was also employed to decode Indonesian spontaneous-speech by achieving 4.19% absolute WER decrease.
Volume: 16
Issue: 3
Page: 1226-1238
Publish at: 2018-06-01

Design of Dual Band Stacked RDRA for 5G Applications

10.12928/telkomnika.v16i3.9037
A. I.; Universiti Teknologi Malaysia (UTM) Bugaje , M. H.; Universiti Teknologi Malaysia (UTM) Jamaluddin , R.; Universiti Teknologi Malaysia (UTM) Selvaraju , M. N.; Universiti Teknologi Malaysia (UTM) Hafiz , AdulKadir Bello; University of Science and Technology Allero Shallah
This paper focuses on the investigation and discussion of three different designs of stacked Rectangular Dielectric Resonator Antenna (RDRA) at dual bands of 25 GHz and 32 GHz for 5G applications. First, basic stacked RDRA. Second, basic stacked RDRA with a single notch. Third, basic stacked RDRA with double notches. All the proposed structure consists of two stacked DRA of dielectric permittivity of 10 which mounted on a Duriod dielectric substrate of dielectric permittivity of 2.2 and feed by Microstrip aperture slot feeding technique (MSA) for 50 Ω characteristic impedance. Authentication of all the proposed designs comparison is completed using 3D simulation tool by observing the performance of reflection coefficient, bandwidth, and gain. All the proposed RDRA are demonstrated simulated reflection coefficient lower than 20 dB for both bands and simulated gain more than 6 dBi. Meanwhile, for simulated bandwidth, only the proposed basic stacked RDRA with single and double notches are demonstrated simulated bandwidth more than 1 GHz, which fulfill the requirement for 5G applications.
Volume: 16
Issue: 3
Page: 1120-1125
Publish at: 2018-06-01

Planning of Energy Saving with Cogeneration System

10.12928/telkomnika.v16i3.5651
Imam Abdul; Universitas Muria Kudus Rozaq , NYD; Universitas Muria Kudus Setyaningsih , Budi; Universitas Muria Kudus Gunawan
PT Dua Kelinci is one of the largest food industries in Pati Regency one of whose products is egg peanut which needs huge electric and heat energy so that energy saving needs to be done. One of the efforts of energy saving is by conducting cogeneration (merging between electric and heat). This research started from a data collection, i.e. finding out the need of electricity and heat in the process of egg-peanut manufacture by a cogeneration technology at PT Dua Kelinci. The research method includes technical analysis and economic analysis. From the technical analysis, it is found that the electric energy saving by using cogeneration 103.680 kW and the heat energy saving is 4,075 TJ/year. From the economic analysis it is seen that before using cogeneration the cost that should be expended is USD 75.209,61 while after using cogeneration the cost is USD 60.6014,04 therefore from the economic aspect there is energy saving as much as USD 15.19,57/year.
Volume: 16
Issue: 3
Page: 989-996
Publish at: 2018-06-01
1 2 3
...
1850 1851
Show 1305 of 1851

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