Articles
9,199 Documents
Voiced and unvoiced separation in malay speech using zero crossing rate and energy
Rafizah Mohd Hanifa;
Khalid Isa;
Shamsul Mohamad;
Shaharil Mohd Shah;
Shelena Soosay Nathan;
Rosni Ramle;
Mazniha Berahim
Indonesian Journal of Electrical Engineering and Computer Science Vol 16, No 2: November 2019
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v16.i2.pp775-780
This paper contributes to the literature on voice-recognition in the context of non-English language. Specifically, it aims to validate the techniques used to present the basic characteristics of speech, viz. voiced and unvoiced, that need to be evaluated when analysing speech signals. Zero Crossing Rate (ZCR) and Short Time Energy (STE) are used in this paper to perform signal pre-processing of continuous Malay speech to separate the voiced and unvoiced parts. The study is based on non-real time data which was developed from a collection of audio speeches. The signal is assessed using ZCR and STE for comparison purposes. The results revealed that ZCR are low for voiced part and high for unvoiced part whereas the STE is high for voiced part and low for unvoiced part. Thus, these two techniques can be used effectively for separating voiced and unvoiced for continuous Malay speech.
Boost Action Recognition through Computed Volume
Li Wang;
Ting Yun;
Haifeng Lin
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 4: April 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
We detect interest points in temporal-spacial space and use the local feature plus their positions to recognize action in a video. Although some previous methods take advantage of the position of each interest point besides the local feature of them, and achieve good performance, it consumes much time to position these points due to the complexity of an action. We propose two simple methods to position each interest point, and design a new feature for action recognition. Evaluation of the approach on two sets of videos suggests its effectiveness. DOI: http://dx.doi.org/10.11591/telkomnika.v11i4.2344
Tele-Robotic Assisted Dental Implant Surgery with Virtual Force Feedback
Amjad Ali Syed;
Amir Mahmood Soomro;
Arbab Nighat Khizar;
Xing-guang Duan;
Huang Qiang;
Farhan Manzoor
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 1: January 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
The dental implant surgical applications full of risk because of the complex anatomical architecture of craio-maxillofacial area. Therefore, the surgeons move towards computer-aided planning for surgeries and then implementation using robotic assisted tele-operated techniques. This study divided into four main parts. The first part is developed by computer-aided surgical planning by image modalities .The second part is based on Virtual Surgical Environment through virtual force feedback haptic device. The third part is implemented the experimental surgery by integrating the prototype surgical manipulator with the haptic device poses using inverse kinematics method. The fourth part based on monitoring the robotic manipulator pose by using image guided navigation system to calculate the position error of the surgical manipulator. Thus, this tele-robotic system is able to comprehend the sense of complete practice, improve skills and gain experience of the surgeon during the surgery. Finally, the experimental outcomes show in satisfactory boundaries. DOI : http://dx.doi.org/10.11591/telkomnika.v12i1.3124
Tag count based priority scheduling algorithm for mitigating the RFID collisions
Hema C;
Sharmila Sankar;
Sandhya M
Indonesian Journal of Electrical Engineering and Computer Science Vol 18, No 1: April 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v18.i1.pp434-442
RFID (Radio Frequency IDentification) is a developing technology that employs electromagnetic signals to send the data among reader and tags to identify categorize and track the moveable items. The objective of this paper is to mitigate the reader collision problem by scheduling the readers in RFID system. Mobile readers in the RFID network send the same frequency signal to the air to read the data from the tags. While these two signals interfere each other and Tags are unable to backscatter signal to the reader. This causes a reader collision problem. The Reader collision problem reduces the lifetime of the RFID network and generates redundant data in the RFID Network. Tag Count based Priority Scheduling algorithm is proposed, that enhances the throughput of the readers and mitigates the reader collision problem. In the cluster based RFID network, The Dragonfly algorithm performed the Cluster Head reader election and cluster construction process and then allotting the mobile readers in the cluster. This algorithm improves the energy efficiency and diminishes the reader collision problem, thereby alleviating the tag information loss and expanding the mobile RFID network life time, while compared with Priority Clustering Protocol and the Graph Coloring based TDMA algorithm.
Edge Detection Based on Biomimetic Pattern Recognition
Ning Chen;
Xiao-ping Song;
Yi Liu
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 9: September 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v12.i9.pp6965-6968
This paper introduced a technique for edge detection by Biomimetic pattern recognition (BPR). The images were scanned into a computer. Due to the nature of the acquiring technique, the acquired images have lots of artifacts, resulting in complicated edge detection. According to this, we used Biomimetic pattern recognition, which is based on “matter cognition” instead of “matter classification” and rather closer to the function of the human being. Finally, the experiments showed that the technique is feasible and has some flexibility.
The Combined Forecasting Model of Discrete Verhulst-BP Neural Network Based on Linear Time-Varying
Shang Hongchao;
Long Xia;
He Tingjie
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 4: April 2014
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Firstly, this paper, aiming at the problem of errors produced by the transformation of differential equation directly into difference equation from traditional gray Verhulst model,through generating reciprocal for the original data sequence, constructs the discrete Vrhulst model based on linear time-varying(LTDVM model);And then we, taking the LTDVM predicted value as an input value and the original data as a mentor training value, put forward the combined forecasting model of discrete Verhulst-BP neural network based on linear time-varying. Meanwhile, in order to improve the training speed and agility and effectively avoid the saturation region of S-type function, this article normalized in advance the input data and mentor training values to better ensure the usefulness, self-learning ability and fault tolerance of the model. At last, we will study the cases to demonstrate that the model has high modeling and forecasting accuracy. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4938
Ground Fault Line Selection with Improved Residual Flow Incremental Method
Wenhong Li;
Tingqiang Guan;
Xueguang Qi;
Gonghua Wang
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 8: August 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
According to the shortcoming of single-phase ground fault line selection method in the resonant grounded system such as the uncertainty of its device by fast compensation with the automatic compensation equipment, an arc suppression and residual flow incremental method is proposed to effectively choose the earth fault line. Firstly, when the single-phase ground fault occurs, the arc suppression coil parameters are adjusted to realize compensation and arc suppression. Then the arc suppression coil inductance values are modulated to make the zero-sequence current of fault line changed, at the same time, the zero-sequence current value is detected and its change will be captured to select the fault line. The simulation experiments prove that the arc grounding over voltage damage can be effectively reduced by arc suppression coil full compensation and fault line can be effectively selected by arc suppression and residual flow increment method. DOI: http://dx.doi.org/10.11591/telkomnika.v11i8.3106
Design of compact ultra wideband antenna for microwave medical imaging application
Adib Othman;
Nur Ishmah Sabirah Shaari;
Abdullah M. Zobilah;
Noor Azwan Shairi;
Zahriladha Zakaria
Indonesian Journal of Electrical Engineering and Computer Science Vol 15, No 3: September 2019
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v15.i3.pp1197-1202
A compact ultra wideband (UWB) antenna for operation at 6 GHz intended for microwave medical imaging (MMI) application is proposed. The microstrip patch antenna (MPA) was design in hexagon shape which is contain H-slot at the centre top of the patch and a slot at the ground. Those slots method is utilised to enhance the operating bandwidth as well as minimising the antenna’s impedance mismatch caused by its proximity to material. Results shows that, the implementation of slot on the patch has profoundly enhance the bandwidth (BW) of the antenna to 503.54 MHz. Measurement of fabricated antenna produce significant result in term of producing wide bandwidth of 520 MHz, with slightly shifting on operating frequency. Therefore, it has been proved that the required performance of UWB antenna has been achieved successfully.
Comprehensive learning particle swarm optimization for sizing and placement of distributed generation for network loss reduction
Eshan Karunarathne;
Jagadeesh Pasupuleti;
Janaka Ekanayake;
Dilini Almeida
Indonesian Journal of Electrical Engineering and Computer Science Vol 20, No 1: October 2020
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v20.i1.pp16-23
With the technological advancements, distributed generation (DG) has become a common method of overwhelming the issues like power losses and voltage drops which accompanies with the leaf of the feeders of radial distribution networks. Many researchers have used several optimization techniques and tools which could be used to locate and size the DG units in the system. particle swarm optimization (PSO) is one of the famous optimization techniques. However, the premature convergence is identified as a fundamental adverse effect of this optimization technique. Therefore, the optimization problem can direct the objective function to a local minimum. This paper presents a variant of PSO techniques, “comprehensive learning particle swarm optimization (CLPSO)” to determine the optimal placement and sizing of the DGs, which uses a novel learning strategy whereby all other particles’ historical best information and learning probability value are used to update a particle’s velocity. The CLPSO particles learn from one exampler for few iterations, instead of learing from global and personal best values in every iteration in PSO and this technique retains the swarm's variability to avoid premature convergence. A detailed analysis was conducted for the IEEE 33 bus system. The comparison results have revealed a higher convergence and an accuracy than the PSO.
A New Method for Intrusion Detection using Manifold Learning Algorithm
Guoping Hou;
Xuan Ma;
Yuelei Zhang
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 12: December 2013
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Computer and network security has received and will still receive much attention. Any unexpected intrusion will damage the network. It is therefore imperative to detect the network intrusion to ensure the normal operation of the internet. There are many studies in the intrusion detection and intrusion patter recognition. The artificial neural network (ANN) has proven to be powerful for the intrusion detection. However, very little work has discussed the optimization of the input intrusion features for the ANN. Generally, the intrusion features contain a certain number of useless features, which is useless for the intrusion detection. Large dimensions of the feature data will also affect the intrusion detection performance of the ANN. In order to improve the ANN performance, a new approach for network intrusion detection based on nonlinear feature dimension reduction and ANN is proposed in this work. The manifold learning algorithm was used to reduce the intrusion feature vector. Then an ANN classifier was employed to identify the intrusion. The efficiency of the proposed method was evaluated with the real intrusion data. The test result shows that the proposed approach has good intrusion detection performance. DOI: http://dx.doi.org/10.11591/telkomnika.v11i12.3638