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

29,734 Article Results

Speech Emotion Recognition Using Deep Feedforward Neural Network

10.11591/ijeecs.v10.i2.pp554-561
Muhammad Fahreza Alghifari , Teddy Surya Gunawan , Mira Kartiwi
Speech emotion recognition (SER) is currently a research hotspot due to its challenging nature but bountiful future prospects. The objective of this research is to utilize Deep Neural Networks (DNNs) to recognize human speech emotion. First, the chosen speech feature Mel-frequency cepstral coefficient (MFCC) were extracted from raw audio data. Second, the speech features extracted were fed into the DNN to train the network. The trained network was then tested onto a set of labelled emotion speech audio and the recognition rate was evaluated. Based on the accuracy rate the MFCC, number of neurons and layers are adjusted for optimization. Moreover, a custom-made database is introduced and validated using the network optimized. The optimum configuration for SER is 13 MFCC, 12 neurons and 2 layers for 3 emotions and 25 MFCC, 21 neurons and 4 layers for 4 emotions, achieving a total recognition rate of 96.3% for 3 emotions and 97.1% for 4 emotions.Speech emotion recognition (SER) is currently a research hotspot due to its challenging nature but bountiful future prospects. The objective of this research is to utilize Deep Neural Networks (DNNs) to recognize human speech emotion. First, the chosen speech feature Mel-frequency cepstral coefficient (MFCC) were extracted from raw audio data. Second, the speech features extracted were fed into the DNN to train the network. The trained network was then tested onto a set of labelled emotion speech audio and the recognition rate was evaluated. Based on the accuracy rate the MFCC, number of neurons and layers are adjusted for optimization. Moreover, a custom-made database is introduced and validated using the network optimized.The optimum configuration for SER is 13 MFCC, 12 neurons and 2 layers for 3 emotions and 25 MFCC, 21 neurons and 4 layers for 4 emotions, achieving a total recognition rate of 96.3% for 3 emotions and 97.1% for 4 emotions.
Volume: 10
Issue: 2
Page: 554-561
Publish at: 2018-05-01

An Hour Ahead Electricity Price Forecasting with Least Square Support Vector Machine and Bacterial Foraging Optimization Algorithm

10.11591/ijeecs.v10.i2.pp748-755
Intan Azmira Wan Abdul Razak , Izham Zainal Abidin , Yap Keem Siah , Aidil Azwin Zainul Abidin , Titik Khawa Abdul Rahman , Nurliyana Baharin , Mohd. Hafiz Bin Jali
Predicting electricity price has now become an important task in power system operation and planning. An hour-ahead forecast provides market participants with the pre-dispatch prices for the next hour. It is beneficial for an active bidding strategy where amount of bids can be reviewed or modified before delivery hours. However, only a few studies have been conducted in the field of hour-ahead forecasting. This is due to most power markets apply two-settlement market structure (day-ahead and real time) or standard market design rather than single-settlement system (real time). Therefore, a hybrid multi-optimization of Least Square Support Vector Machine (LSSVM) and Bacterial Foraging Optimization Algorithm (BFOA) was designed in this study to produce accurate electricity price forecasts with optimized LSSVM parameters and input features. So far, no works has been established on multistage feature and parameter optimization using LSSVM-BFOA for hour-ahead price forecast. The model was examined on the Ontario power market. A huge number of features were selected by five stages of optimization to avoid from missing any important features. The developed LSSVM-BFOA shows higher forecast accuracy with lower complexity than most of the existing models.
Volume: 10
Issue: 2
Page: 748-755
Publish at: 2018-05-01

Design of a New Cryptographic Hash Function – Titanium

10.11591/ijeecs.v10.i2.pp827-832
Mohammad A. AlAhmad
This paper introduces a new cryptographic hash function that follows sponge construction. Paper begins with outlining the structure of the construction. Next part describes the functionality of Titanium and cipher used. A competition between block cipher and stream cipher is presented and showed the reason of using block cipher rather than stream cipher. Speed performance is calculated and analyzed using state-of-art CPUs.
Volume: 10
Issue: 2
Page: 827-832
Publish at: 2018-05-01

To Improve Feature Extraction and Opinion Classification Issues in Customer Product Reviews Utilizing an Efficient Feature Extraction and Classification (EFEC) Algorithm

10.11591/ijeecs.v10.i2.pp587-595
Palaiyah Solainayagi , Ramalingam Ponnusamy
Currently, customer's product review opinion plays an essential role in deciding the purchasing of the online product. A customer prefers to acquire the opinion of other customers by viewing their opinion during online products' reviews, blogs and social networking sites, etc. The majority of the product reviews including huge words. A few users provide the opinion; it is tough to analysis and understands the meaning of reviews. To improve user fulfillment and shopping experience, it has become a general practice for online sellers to allow their users to review or to communicate opinions of the products that they have sold. The major goal of the paper is to solve feature extraction problem and opinion classification problem from customers utilized product reviews which extract the feature words and opinion words from product reviews. To propose an Efficient Feature Extraction and Classification (EFEC) algorithm is implementing to extracts a feature from opinion words. The reviewer usually marks both positive and negative parts of the reviewed product, despite the fact that their general opinion on the product may be positive or negative. An EFEC algorithm is utilized to predict the number of positive and negative opinion in reviews. Based on Experimental evaluations, proposed algorithm improves accuracy 15.05%, precision 13.7%, recall 15.59% and F-measure 15.07% of the proposed system compared than existing methodologies
Volume: 10
Issue: 2
Page: 587-595
Publish at: 2018-05-01

Development of Smart Chicken Poultry Farm

10.11591/ijeecs.v10.i2.pp498-505
Hasmah Mansor , Ammar Nor Azlin , Teddy Surya Gunawan , Mahanijah Md Kamal , Ahmad Zawawi Hashim
In Malaysia, most agriculture industries are still using conventional method to operate. All routines in monitoring and control of chicken poultry farm, for example, utilise man power where the source and energy are very limited. However, the demand from consumers towards the agricultural output is increasing day by day and requires more advanced farming technology in order to obtain maximum efficiency. This paper is focused on the development of smart chicken poultry farm to provide monitoring and control of the farm condition. The electronics, embedded systems and wireless technology are integrated with farm monitoring. Using Master-Slave concept, sensors are used to measure the ambient temperature, ammonia and humidity of the hall of chicken poultry for each slave. The sensors’ readings are then transmitted wirelessly over radio frequency by serial communication using HC-12 RF module to master for further data processing. The design process of both master and slave involved the interfacing of microprocessor, ATMEL ATMega328 with several analogue sensors, LCD, buzzer, relay output, monetary push button and light indicator. Based on the readings from the sensors, the microcontroller produced the output which is connected to the fan for better air ventilation in the chicken poultry farm. Furthermore, PID controller has been integrated to optimize the output control method, hence optimizing hall condition which results to better output for the farm. The system has been successfully implemented and tested at Myra Farm & Services, located at Kalumpang, Tanjung Malim, Perak, Malaysia.In Malaysia, most agriculture industries are still using conventional method to operate. All routines in monitoring and control of chicken poultry farm, for example, utilise man power where the source and energy are very limited. However, the demand from consumers towards the agricultural output is increasing day by day and requires more advanced farming technology in order to obtain maximum efficiency. This paper is focused on the development of smart chicken poultry farm to provide monitoring and control of the farm condition. The electronics, embedded systems and wireless technology are integrated with farm monitoring. Using Master-Slave concept, sensors are used to measure the ambient temperature, ammonia and humidity of the hall of chicken poultry for each slave. The sensors’ readings are then transmitted wirelessly over radio frequency by serial communication using HC-12 RF module to master for further data processing. The design process of both master and slave involved the interfacing of microprocessor, ATMEL ATMega328 with several analogue sensors, LCD, buzzer, relay output, monetary push button and light indicator. Based on the readings from the sensors, the microcontroller produced the output which is connected to the fan for better air ventilation in the chicken poultry farm. Furthermore, PID controller has been integrated to optimize the output control method, hence optimizing hall condition which results to better output for the farm. The system has been successfully implemented and tested at Myra Farm & Services, located at Kalumpang, Tanjung Malim, Perak, Malaysia.
Volume: 10
Issue: 2
Page: 498-505
Publish at: 2018-05-01

Securing Data Communication for Data Driven Applications Using End to End Encryption

10.11591/ijeecs.v10.i2.pp756-762
Subhi Almohtasib , Alaa H Al-Hamami
Many users of smartphones have secret data they want to save it on their devices. The probability of a device damage or stolen prevents them from saving data. Therefore, data driven applications used to save user’s data on a remote server. Protection of the data during its transmission considered as one of the success aspect for these applications. In this paper, an enhanced method for data encryption proposed which guarantees data secrecy during its transmission over network. User’s data encrypted before transmission using Base64 class. Data encryption and decryption implemented to halt reverse encryption process. In this way, data is transmitting in a secure and efficient manner accomplishing the main goal of Cryptography.
Volume: 10
Issue: 2
Page: 756-762
Publish at: 2018-05-01

Performance Comparison of Controllers for Suppressing the Structural Building Vibration

10.11591/ijeecs.v10.i2.pp537-544
Normaisharah Mamat , Fitri Yakub , Sheikh Ahmad Zaki Shaikh Salim , Mohamed Sukri Mat Ali
This paper presents the modelling and simulation of controllers for controlling the position of two degree of freedom (2 DOF) mass spring damper system. Proportional integral (PI), fuzzy logic controller (FLC) and sliding mode controller (SMC) are design to minimize the vibration of the system that represent as building structure towards earthquake. A structural building is simulate based on real earthquake occur in El Centro on May 1940. The algorithm for building structure, actuator and controller is derived. Matlab/Simulink is used to analyze the performance of controllers towards the vibration building structure. At the end of the study the time response for two story building for uncontrolled and controlled system is present. Besides, the result for limitation voltage for each controller is also analyse to determine the maximum voltage consume for the system. The simulation results show the comparison of the controllers’ performance in suppressing the building vibration. From performance analysis, SMC provides better performance compared to PI and FLC based on structural vibration reduction.
Volume: 10
Issue: 2
Page: 537-544
Publish at: 2018-05-01

A MIMO H-shape Dielectric Resonator Antenna for 4G Applications

10.11591/ijeecs.v10.i2.pp648-653
S. Salihah , M. H. Jamaluddin , R. Selvaraju , M. N. Hafiz
In this article, a Multiple-Input-Multiple-Output (MIMO) H-shape Dielectric Resonator Antenna (DRA) is designed and simulated at 2.6 GHz for 4G applications. The proposed structure consists of H-shape DRA ( =10) which is mounted on FR4 substrate ( =4.6), and feed by two different feeding mechanisms. First, microstrip with slot coupling as Port 1. Second, coaxial probe as Port 2. The electrical properties of the proposed MIMO H-shape DRA in term of return loss, bandwidth and gain are completely obtained by using CST Microwave Studio Suite Software. The simulated results demonstrated a return loss more than 20 dB, an impedance bandwidth of 26 % (2.2 – 2.9 GHz), and gain of 6.11 dBi at Port 1. Then, a return loss more than 20 dB, an impedance bandwidth of 13 % (2.2 – 2.7 GHz), and gain of 6.63 dBi at Port 2. Both ports indicated impedance bandwidth more than 10 %, return loss lower than 20 dB, and gain more than 10 dBi at 2.6 GHz. The simulated electrical properties of the proposed design show a good potential for LTE applications.
Volume: 10
Issue: 2
Page: 648-653
Publish at: 2018-05-01

Intelligent Packet Delivery in Router Using Structure Optimized Neural Network

10.11591/ijeecs.v10.i2.pp545-553
R. Deebalakshmi , V. L. Jyothi
The Internet itself is a worldwide network connecting millions of computers and less significant networks. Computers communicated by routers. Crucial the role of a router is to our technique of communicating and computing. Routers are situated at gateways, the spaces where two or more networks connect, and are the decisive device that keeps data flow between networks and keeps the networks connected to the Internet. When data is sent between places on one network or from one network to a second network the data is always seen and intended for to the proper place by the router. The router carries out this by using headers and routing tables to establish the best path for routing the data packets. This trim down the effectiveness of edge router only when the path engaged, it will enhanced by classification method, predictable classification methods like port based ,deep packet inspection and  statistical classification are give less precision. In this system structured optimized neural network is used for more precise organization. Classification output forwarded to router dynamically for intellectual packet delivery. The method will improve router competence by greater than before throughput and decreased latency.The Internet itself is a worldwide network connecting millions of computers and less significant networks. Computers communicated by routers. Crucial the role of a router is to our technique of communicating and computing. Routers are situated at gateways, the spaces where two or more networks connect, and are the decisive device that keeps data flow between networks and keeps the networks connected to the Internet. When data is sent between places on one network or from one network to a second network the data is always seen and intended for to the proper place by the router. The router carries out this by using headers and routing tables to establish the best path for routing the data packets. This trim down the effectiveness of edge router only when the path engaged, it will enhanced by classification method, predictable classification methods like port based ,deep packet inspection and  statistical classification are give less precision. In this system structured optimized neural network is used for more precise organization. Classification output forwarded to router dynamically for intellectual packet delivery. The method will improve router competence by greater than before throughput and decreased latency.
Volume: 10
Issue: 2
Page: 545-553
Publish at: 2018-05-01

Maximally Spatial-Disjoint Lightpaths in Optical Networks

10.11591/ijeecs.v10.i2.pp733-740
M. Waqar Ashraf , Sevia M. Idrus , Farabi Iqbal
Lightpaths enable end-to-end all-optical transmission between network nodes. For survivable routing, traffic is often carried on a primary lightpath, and rerouted to another disjointed backup lightpath in case of the failure of the primary lightpath. Though both lightpaths can be physically disjointed, they can still fail simultaneously if a disaster affects them simultaneously on the physical plane. Hence, we propose a routing algorithm for provisioning a pair of link-disjoint lightpaths between two network nodes such that the minimum spatial distance between them (while disregarding safe regions) is maximized. Through means of simulation, we show that our algorithm can provide higher survivability against spatial-based simultaneous link failures (due to the maximized spatial distance).
Volume: 10
Issue: 2
Page: 733-740
Publish at: 2018-05-01

High Potential of Magnet on the Performance of Dual Piezoelectric Fans in Electronics Cooling System

10.11591/ijeecs.v10.i2.pp469-479
Abdul Razak Fadhilah , Robiah Ahmad , Sarip Shamsul
Recently, piezoelectric fan has gained attention as potential active cooling method for electronics devices. Even though the piezoelectric requires high voltage, there are findings to overcome the shortcomings. Adding on a magnet at the tip of the piezoelectric fan to activate other magnetic passive fans is one of the methods to increase the total amplitude generated by the fans. This paper will discuss on the performance of integrated piezoelectric fan with passive fans (later refer to magnetic fans) to enhance the heat transfer in cooling system. A repulsive force produced by the magnets will cause the magnetic blades to oscillate together with the piezoelectric fan. The paper will focus on the optimization parameters of the magnets for selected dimension of piezoelectric fan. The parameters under investigation are the position of the magnet on the piezoelectric fan, number of magnets on each blades and orientation of blades with respect to adjacent blade. Results show that the magnet at middle location of extensive blade with double magnets generate the largest amplitude, 80% better than fan without magnet and for dual integrated piezoelectric fan with magnetic fan, radial orientation gives better result by 25%. By increasing the total amplitude using magnetic force, power consumption can be reduced while the heat transfer performance can be enhanced. it shows a good agreement for positive heat transfer and thermal resistance improvement compared to natural convection.
Volume: 10
Issue: 2
Page: 469-479
Publish at: 2018-05-01

Improving the Cost Factor of DLBCA Lightweight Block Cipher Algorithm

10.11591/ijeecs.v10.i2.pp786-791
Sufyan Salim Mahmood AlDabbagh , Alyaa Ghanim Sulaiman , Imad Fakhri Taha Al Shaikhli , Khalid Abdulkareem Al-Enezi , Abdulrahman Yousef Alenezi
The needing to secure information in restricted environments is very important so that lightweight block cipher algorithm is suitable for these environments. This paper improved DLBCA algorithm by decreasing the cost factor through using the less number of S-boxes. Also, differential and boomerang attacks have been applied in this paper. Finally, all the results have been presented
Volume: 10
Issue: 2
Page: 786-791
Publish at: 2018-05-01

Edge Dissimilarity Reduced-Reference Quality Metric with Low Overhead Bitrate

10.11591/ijeecs.v10.i2.pp631-640
Farah Diyana Abdul Rahman , Dimitris Agrafiotis , Ahmad Imran Ibrahim
In multimedia transmission, it is important to rely on an objective quality metric which accurately represents the subjective quality of processed images and video sequences. Reduced-reference metrics make use of side-information that is transmitted to the receiver for estimating the quality of the received sequence with low complexity. In this paper, an Edge-based Dissimilarity Reduced-Reference video quality metric with low overhead bitrate is proposed. The metric is evaluated by finding the dissimilarity between the edge information of original and distorted sequences. The edge degradation can be detected in this manner as perceived video quality is highly associated with edge structural. Due to the high overhead using the Soergel distance, it is pertinent to find a way to reduce the overhead while maintaining the edge information that can convey the quality measure of the sequences. The effects of different edge detection operator, video resolution and file compressor are investigated. The aim of this paper is to significantly reduce the bitrate required in order to transmit the side information overhead as the reduced reference video quality metric. From the results obtained, the side information extracted using Sobel edge detector maintained consistency throughout the reduction of spatial and temporal down-sample.
Volume: 10
Issue: 2
Page: 631-640
Publish at: 2018-05-01

A Effective Cross Layer Multi-Hop Routing Protocol for Heterogeneous Wireless Sensor Network

10.11591/ijeecs.v10.i2.pp664-671
Manisha R. Dhage , Srikanth Vemuru
In today’s scenario to solve the real world problem heterogeneous wireless sensor is necessary. It consists of different sensor with different sensing capability and different energy level. Routing is important task in HWSN from energy dissipation point of view. In HWSN many routing protocols were proposed but many protocols are for single hop communication between cluster head and sink. Here we have designed multi-hop routing protocol for HWSN, which will be energy efficient and also solve the problem of hot spot using unequal clustering. To make this protocol more energy efficient cross layer information exchange approach is used. Using cross layer communication this protocol will get residual energy, quality of link and neighboring nodes information and this information is used in cluster head selection. Moreover there is no need to do broadcast of residual energy for every round because of RDA (regular data acquisition) nodes. We can predict the energy consumption of node, which will conserve the energy using Energy Efficient Fuzzy Based Cross Layer Protocol (EEFCLP). This proposed protocol can achieve longer sensor lifetime and more energy efficiency.
Volume: 10
Issue: 2
Page: 664-671
Publish at: 2018-05-01

Multivariable Parametric Modeling of a Greenhouse by Minimizing the Quadratic Error

10.12928/telkomnika.v16i2.8486
Mohamed; University of Sultan Essahafi , Mustapha Ait; University of Sultan Lafkih
This paper concerns the identification of a greenhouse described in a multivariable linear system with two inputs and two outputs (TITO). The method proposed is based on the least squares identification method, without being less efficient, presents an iterative calculation algorithm with a reduced computational cost. Moreover, its recursive character allows it to overcome, with a good initialization, slight variations of parameters, inevitable in a real multivariable process. A comparison with other methods recently proposed in the literature demonstrates the advantage of this method. Simulations obtained will be exposed to showthe effectiveness and application of the method on multivariable systems.
Volume: 16
Issue: 2
Page: 641-647
Publish at: 2018-04-18
1 2 3
...
1982 1983
Show 1444 of 1983

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