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

28,451 Article Results

Multi-Criteria in Discriminant Analysis to Find the Dominant Features

10.12928/telkomnika.v14i3.3472
Arif; University of Trunojoyo Muntasa , Indah Agustien; University of Trunojoyo Siradjuddin , Rima; University of Trunojoyo Tri Wahyuningrum
A crucial problem in biometrics is enormous dimensionality. It will have an impact on the costs involved. Therefore, the feature extraction plays a significant role in biometrics computational. In this research, a novel approach to extract the features is proposed for facial image recognition. Four criteria of the Discriminant Analysis have been modeled to find the dominant features. For each criterion is an objective function, it was derived to obtain the optimum values. The optimum values can be solved by using generalized the Eigenvalue problem associated to the largest Eigenvalue. The modeling results were employed to recognize the facial image by the multi-criteria projection to the original data. The training sets were also processed by using the Eigenface projection to avoid the singularity problem cases. The similarity measurements were performed by using four different methods, i.e. Euclidian Distance, Manhattan, Chebyshev, and Canberra.  Feature extraction and analysis results using multi-criteria have shown better results than the other appearance method, i.e. Eigenface (PCA), Fisherface (Linear Discriminant Analysis or LDA), Laplacianfaces (Locality Preserving Projection or LPP), and Orthogonal Laplacianfaces (Orthogonal Locality Preserving Projection or O-LPP). 
Volume: 14
Issue: 3
Page: 1113-1122
Publish at: 2016-09-01

Application of Nonlinear Dynamical Methods for Arc Welding Quality Monitoring

10.12928/telkomnika.v14i3.3589
Shuguang; Jiangmen Polytechnic Wu , Yiqing; Jiangmen Polytechnic Zhou
Owing to its diverse, the stability of arc signals in high-powered submerged arc welding is not very salient, and weld defects are difficult to detect automatically. Aimed at this problem, this paper proposes a noise robustness algorithm for calibrating the singularity points and denoting the kinetics and stability of arc. Firstly, reconstruct a vector, which is the calculation of the approximate entropy in phase space, denotes the distortion of arc. Then, a algorithm for calculation is given based on reconstruction of chaotic time series in phase space. Finally, we apply the calculation of approximate entropy algorithm in phase space to flaw detection for arc signals, which is efficient proved by experimental results.
Volume: 14
Issue: 3
Page: 948-955
Publish at: 2016-09-01

Image Retrieval Based on Multi Structure Co-occurrence Descriptor

10.12928/telkomnika.v14i3.3292
Agus Eko; Universitas Muhammadiyah Malang Minarno , Arrie; Universitas Islam Indonesia Kurniawardhani , Fitri; Universitas Mataram Indonesia Bimantoro
This study present a new technique for Batik cloth image retrieval using Micro-Structure Co-occurence Descriptor (MSCD). MSCD is a developed method based on Enhanced Micro Structure Descriptor (EMSD). Previously, EMSD has been improved by adding edge orientation feature. In previous study, EMSD cannot achieve an optimal precision. Therefore, MSCD is proposed to overcome the EMSD drawback using global feature approach, namely Gray Level Co-occurrence Matrix (GLCM). There are 300 batik cloth images which contain 50 classes used for dataset. The performance result show that MSCD can retrieve Batik cloth images more effective than EMSD.
Volume: 14
Issue: 3
Page: 1175-1182
Publish at: 2016-09-01

Recognition of Odor Characteristics Based on BP Neural Network

10.12928/telkomnika.v14i3.3712
Wu; College of Information Engineering, Inner Mongolia University of Technology Lei , Fang; College of Information Engineering, Inner Mongolia University of Technology Jiandong , Zhao; Inner Mongolia Agriculture and Animal Husbandry Information Center, Yudong
This paper introduces the basic principle and calculation steps of BP neural network algorithm for classification and prediction of odor characteristic parameters. Using the PEN3 electronic nose collects the volatile components of milk and programming BP neural network algorithm under MATLAB condition. This paper validate the use of BP neural network algorithm on milk quality prediction is effective.
Volume: 14
Issue: 3
Page: 956-962
Publish at: 2016-09-01

Nurses Scheduling by Considering the Qualification using Integer Linear Programming

10.12928/telkomnika.v14i3.2913
Maya; Bogor Agricultural University Widyastiti , Amril; Bogor Agricultural University Aman , Toni; Bogor Agricultural University Bakhtiar
One of problems that frequently occurs in hospital management is nurses scheduling problem. A suitable schedule is needed in order to avoid fatigue, both physically and psychologically, which subsequently may deteriorate their performance. Nurse scheduling is commonly designed by the head of nurse manually. In this research, nurse scheduling problem is modeled by considering the qualification of the nurses and the model has the form of integer linear programming. The objective of the model is to maximize the number of nurse’s day-offs. Then optimization problem is implemented to nurses scheduling in the High Care Unit and the Emergency room of Rumah Sehat Terpadu Dompet Dhuafa Parung Bogor.
Volume: 14
Issue: 3
Page: 933-940
Publish at: 2016-09-01

MRI Sagittal Image Segmentation from Patients with Abdominal Aortic Aneurysms

10.12928/telkomnika.v14i3.3520
Desti; Faculty of Computer Science and Information Technology Gunadarma University Jl.Margonda Raya 100, Depok 16424, Indonesia Riminarsih , Cut Maisyarah; Faculty of Computer Science and Information Technology Gunadarma University Jl.Margonda Raya 100, Depok 16424, Indonesia Karyati , Achmad Benny; Faculty of Computer Science and Information Technology Gunadarma University Jl.Margonda Raya 100, Depok 16424, Indonesia Mutiara , Bambang; Faculty of Computer Science and Information Technology Gunadarma University Jl.Margonda Raya 100, Depok 16424, Indonesia Wahyudi , E.; Faculty of Industrial Technology Gunadarma University Jl.Margonda Raya 100, Depok 16424, Indonesia Ernastuti
Early detection in patients with abdominal aortic aneurysm (AAA) is esdential to reduce the risk of rupture of aortic wall that causes bleeding and often lead to death. Information about the condition of AAA is indispendable to complete the diagnosis of doctors in decision making. The position and shape of AAA can be obtained by sagittal image from an MRI examination. Characteristics of MRI sagittal image are having a gray level that is almost teh same between one organ to another. Therefore, to separate between one organ to another is difficult. This research is conducted MRI sagittal iamge segmentation in patients to obtain information on morphology and location of abdominal aortic aneurysm (AAA). To Segmenting the MRI Image we comobine thresholding method and Haralick Method. Under this proposed method, obtained sagittal images of the aorta are used to gain information about the location and shape of the aneurysm in abdominal aorta.
Volume: 14
Issue: 3
Page: 1105-1112
Publish at: 2016-09-01

Design and Fabrication of Compact MEMS Electromagnetic Micro-Actuator with Planar Micro-Coil Based on PCB

10.12928/telkomnika.v14i3.3998
Roer Eka; Universiti Kebangsaan Malaysia Pawinanto , Jumril; Universiti Kebangsaan Malaysia Yunas , Burhanuddin; Universiti Kebangsaan Malaysia Majlis , Azrul; Universiti Kebangsaan Malaysia Hamzah
This paper reports a compact design of electromagnetically driven MEMS micro-actuator utilizing planar electromagnetic coil on PCB (Printed Circuit Board). The micro-actuator device consists of an NdFeB permanent magnet, thin silicon membrane and planar micro-coil which fabricated using simple standard MEMS techniques with additional bonding step. Two planar coils designs including planar parallel and spiral coil structure with various coil geometry are chosen for the study. Analysis of the device involves the investigation of electromagnetic and mechanical properties using finite element analysis (FEA), the measurement of the membrane deflection and functionality test. The measurement results show that the thin silicon membrane is able to deform as much as 12.87 µm using planar spiral micro-coil. Reasonable match between simulation and measurement of about 82.5% has been revealed. The dynamic response test on actuator driven by parallel planar coil shows that silicon membrane effectively deformed in 40 s for an input electrical power of only 150 mW. It is also concluded that planar parallel coil is considered for the simple structure and easy fabrication of the actuator system. This study will provide important parameters for the development of compact and simple electromagnetic micro-actuator system for fluidic injection system in lab-on-chip.
Volume: 14
Issue: 3
Page: 856-866
Publish at: 2016-09-01

Wireless Sensor Network Design based on Hybrid Tree-Like Mesh Topology as a New Platform for Air Pollution Monitoring System

10.12928/telkomnika.v14i3.2279
Muhammad; AMIK Teknokrat Iqbal , Muhammad; Bogor Agricultural University Fuad , Heru; Bogor Agricultural University Sukoco , Husin; Bogor Agricultural University Alatas
In this paper, we propose a new platform for air pollution monitoring system based on wireless sensor network (WSN) with Tree-like Mesh topology. We used ZigBee device and General Packet Radio Service (GPRS) for data transfer protocol. The results of a conducted test showed a good performance in delivering data in real time mode. We found that the fewer hop produced higher throughput but lower delay and packet loss ratio. The system performance demonstrated that the reduction of one hop increased 32.06% of throughput, decreased 23.28% of delay and 0.01% of packet loss ratio.In this paper, we propose a new platform for air pollution monitoring system based on wireless sensor network (WSN) with Tree-like Mesh topology. We used ZigBee device and General Packet Radio Service (GPRS) for data transfer protocol. The results of a conducted test showed a good performance in delivering data in real time mode. We found that the fewer hop produced higher throughput but lower delay and packet loss ratio. The system performance demonstrated that the reduction of one hop increased 32.06% of throughput, decreased 23.28% of delay and 0.01% of packet loss ratio
Volume: 14
Issue: 3
Page: 1166-1174
Publish at: 2016-09-01

Big Data Analysis with MongoDB for Decision Support System

10.12928/telkomnika.v14i3.3115
Sulistyo; Bina Nusantara University Heripracoyo , Roni; Bina Nusantara University Kurniawan
The big data is currently a growing topic in the world of information technology. Based on the literature mentioned that manage of big data can create significant value for the world economy, improving productivity and competitiveness of enterprises and the public sector as well as creating a large economic surplus for consumers. However, based on the information obtained, the big data is still not widely applied in the company or organization. This study aimed to explore more information about the big data and proceed with making an application prototype big data management. This experiment established with the big data storage that is database, this research use NoSQL database technology that can map the needs of both structured and unstructured. And this research will be carried out migration of Relational Database (RDBMS) into the database MongoDB.   Prototype will be create with the object of study is structured and unstructured data. The expected result of this research is a model or prototype of big data management that can help organizations and companies (especially education) to make decisions based on various types of data.
Volume: 14
Issue: 3
Page: 1083-1089
Publish at: 2016-09-01

Adaptive Resource Allocation Algorithm in Wireless Access Network

10.12928/telkomnika.v14i3.3615
Zhanjun; Chongqing University of Posts and Telecommunications Liu , Yue; Chongqing University of Posts and Telecommunications Shen , Zhonghua; Chongqing University of Posts and Telecommunications Yu , Fengxie; Chongqing University of Posts and Telecommunications Qin , Qianbin; Chongqing University of Posts and Telecommunications Chen
Wireless network state varies with the surrounding environment, however, the existing resource allocation algorithm cannot adapt to the varying network state, which results to the underutilization of frequency and power resource. Therefore, in this paper, we propose an adaptive resource allocation algorithm which can efficiently adapt to the varying network state by building an optimal mathematical model and then changing the weighted value of the objective function. Furthermore, the optimal allocation of subcarrier and power is derived by using the Lagrange dual decomposition and the subgradient method. Simulation results show that the proposed algorithm can adaptively allocate the resource to the users according to the varying user density which represents the network state.
Volume: 14
Issue: 3
Page: 887-893
Publish at: 2016-09-01

Scalable Nodes Deployment Algorithm for the Monitoring of Underwater Pipeline

10.12928/telkomnika.v14i3.3464
Muhammad Zahid; Universiti Teknologi Malaysia Abbas , Kamalrulnizam; Universiti Teknologi Malaysia Abu Bakar , Muhammad; University of Tabuk Ayaz Arshad , Muhammad; Universiti Teknologi Malaysia Tayyab , Mohammad Hafiz; Universiti Teknologi Malaysia Mohamed
Underwater Wireless Linear Sensor Networks (UW-LSNs) possess unique features as compared to the terrestrial sensor networks for pipeline monitoring. Other than long propagation delays for long range underwater pipelines and high error probability, homogeneous node deployment also makes it harder to detect and locate the pipeline leakage efficiently. Determining the exact leakage position with minimum delay stays a major issue where pipelines length is extremely long and expensive to deploy many underwater sensors. In order to tackle the problem of large scale pipeline monitoring and unreliable underwater link quality, many algorithms have been proposed and even some of them provided good solutions for these issues but the scalable nodes deployments still need focus and prime attention. In order to handle the problem of nodes deployment, we therefore propose a dynamic nodes deployment algorithm where every node in the network is assigned location in a quick and efficient way without needing any localization scheme. It provides an option to handle the heterogeneous types of nodes, distribute topology and mechanism in which new nodes are easily added to the network without affecting the existing network performance. The proposed distributed topology algorithm divides the pipeline length into segments and sub-segments in order to manage the higher delay issue. Normally nodes are randomly deployed for the long range underwater pipeline inspection yet it requires some proper dynamic nodes deployment algorithm assigning unique position to each node
Volume: 14
Issue: 3
Page: 1183-1191
Publish at: 2016-09-01

MapReduce Integrated Multi-algorithm for HPC Running State Analysis

10.12928/telkomnika.v14i3.3771
ShuRen; Northwest Branch of PetroChina Research Institute of Petroleum Exploration and Development Liu , ChaoMin; Northwest Branch of PetroChina Research Institute of Petroleum Exploration and Development Feng , HongWu; Northwest Branch of PetroChina Research Institute of Petroleum Exploration and Development Luo , Ling; Northwest Branch of PetroChina Research Institute of Petroleum Exploration and Development Wen
High-performance computer clusters are major seismic processing platforms in the oil industry and have a frequent occurrence of failures. In this study, K-means and the Naive Bayes algorithm were programmed into MapReduce and run on Hadoop. The accumulated high-performance computer cluster running status data were first clustered by K-means, and then the results were used for Naive Bayes training. Finally, the test data were discriminated for the knowledge base and equipment failure. Experiments indicate that K-means returned good results, the Naive Bayes algorithm had a high rate of discrimination, and the multi-algorithm used in MapReduce achieved an intelligent prediction mechanism.
Volume: 14
Issue: 3
Page: 1123-1127
Publish at: 2016-09-01

Fuzzy C-Means Clustering Based on Improved Marked Watershed Transformation

10.12928/telkomnika.v14i3.2757
Cuijie; Hebei University of Technology Zhao , Hongdong; Hebei University of Technology Zhao , Wei; Tianjin University of Science and Technology Yao
Currently, the fuzzy c-means algorithm plays a certain role in remote sensing image classification. However, it is easy to fall into local optimal solution, which leads to poor classification. In order to improve the accuracy of classification, this paper, based on the improved marked watershed segmentation, puts forward a fuzzy c-means clustering optimization algorithm. Because the watershed segmentation and fuzzy c-means clustering are sensitive to the noise of the image, this paper uses the adaptive median filtering algorithm to eliminate the noise information. During this process, the classification numbers and initial cluster centers of fuzzy c-means are determined by the result of the fuzzy similar relation clustering. Through a series of comparative simulation experiments, the results show that the method proposed in this paper is more accurate than the ISODATA method, and it is a feasible training method.
Volume: 14
Issue: 3
Page: 981-986
Publish at: 2016-09-01

Distributed Target Localization in Wireless Sensor Networks using Diffusion Adaptation

10.11591/ijeecs.v3.i3.pp512-518
Amirhosein Hajihoseini , Seyed Ali Ghorashi
Localization is an important issue for wireless sensor networks. Target localization has attracted many researchers who work on location based services such as navigation, public transportation and so on. Localization algorithms may be performed in a centralized or distributed manner. In this paper we apply diffusion strategy to the Gauss Newton method and introduce a new distributed diffusion based target localization algorithm for wireless sensor networks. In our proposed method, each node knows its own location and estimates the location of target using received signal strength. Then, all nodes cooperate with their neighbors and share their measurements to improve the accuracy of their decisions. In our proposed diffusion based algorithm, each node can localize target individually using its own and neighbor’s measurements, therefore, the power consumption decreases. Simulation results confirm that our proposed method improves the accuracy of target localization compared with alternative distributed consensus based target localization algorithms.  Our proposed algorithm is also shown that is robust against network topology and is insensitive to uncertainty of sensor nodes’ location.
Volume: 3
Issue: 3
Page: 512-518
Publish at: 2016-09-01

Action Recognition of Human’s Lower Limbs Based on a Human Joint

10.12928/telkomnika.v14i3.3556
Feng Liang , Zhili Zhang , Xiangyang Li , Yong Long , Zhao Tong
In order to recognize the actions of human’s lower limbs, a novel action recognition method based on a human joint was proposed. Firstly, hip joint was chosen as the recognition object, its y coordinates were as recognition parameter, and human action characteristics were achieved based on filtering and wavelet transform. Secondly, an improved self-organizing competitive neural network was proposed, which could classify the action characteristics automatically according to the classification number. The classification results of motion capture data proved the validity of the neural network. Finally,an action recognition method based on hidden Markov model (HMM) was introduced to realize the recognition of classification results of human action characteristicswith the change direction of y coordinates. The proposed action recognition method needs less action information and has a fast calculation speed. Experiments proved the method hada high recognition rate and a good application prospect.
Volume: 14
Issue: 3
Page: 1192-1202
Publish at: 2016-09-01
1 2 3
...
1896 1897
Show 1533 of 1897

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