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

29,922 Article Results

Relationship of drain induced barrier lowering and top/bottom gate oxide thickness in asymmetric junctionless double gate MOSFET

10.11591/ijece.v11i1.pp232-239
Hakkee Jung
The relationship of drain induced barrier lowering (DIBL) phenomenon and channel length, silicon thickness, and thicknesses of top and bottom gate oxide films is derived for asymmetric junctionless double gate (JLDG) MOSFETs. The characteristics between the drain current and the gate voltage is derived by using the potential distribution model to propose in this paper. In this case, the threshold voltage is defined as the corresponding gate voltage when the drain current is (W/L) × 10-7 A, and the DIBL representing the change in the threshold voltage with respect to the drain voltage is obtained. As a result, we observe the DIBL is proportional to the negative third power of the channel length and the second power of the silicon thickness and linearly proportional to the geometric mean of the top and bottom gate oxide thicknesses, and derive a relation such as DIBL =25.15ηL_g^(-3) t_si^2 √(t_ox1∙t_ox2 ), where η is a static feedback coefficients between 0 and 1. The η is found to be between 0.5 and 1.0 in this model. The DIBL model of this paper has been observed to be in good agreement with the result of other paper, so it can be used in circuit simulation such as SPICE.
Volume: 11
Issue: 1
Page: 232-239
Publish at: 2021-02-01

A short-term hybrid forecasting model for time series electrical-load data using random forest and bidirectional long short-term memory

10.11591/ijece.v11i1.pp763-771
Zannatul Ferdoush , Booshra Nazifa Mahmud , Amitabha Chakrabarty , Jia Uddin
In the presence of the deregulated electric industry, load forecasting is more demanded than ever to ensure the execution of applications such as energy generation, pricing decisions, resource procurement, and infrastructure development. This paper presents a hybrid machine learning model for short-term load forecasting (STLF) by applying random forest and bidirectional long short-term memory to acquire the benefits of both methods. In the experimental evaluation, we used a Bangladeshi electricity consumption dataset of 36 months. The paper provides a comparative study between the proposed hybrid model and state-of-art models using performance metrics, loss analysis, and prediction plotting. Empirical results demonstrate that the hybrid model shows better performance than the standard long short-term memory and the bidirectional long short-term memory models by exhibiting more accurate forecast results.
Volume: 11
Issue: 1
Page: 763-771
Publish at: 2021-02-01

A hybrid method of genetic algorithm and support vector machine for intrusion detection

10.11591/ijece.v11i1.pp900-908
Mushtaq Talb Tally , Haleh Amintoosi
With the development of web applications nowadays, intrusions represent a crucial aspect in terms of violating the security policies. Intrusions can be defined as a specific change in the normal behavior of the network operations that intended to violate the security policies of a particular network and affect its performance. Recently, several researchers have examined the capabilities of machine learning techniques in terms of detecting intrusions. One of the important issues behind using the machine learning techniques lies on employing proper set of features. Since the literature has shown diversity of feature types, there is a vital demand to apply a feature selection approach in order to identify the most appropriate features for intrusion detection. This study aims to propose a hybrid method of Genetic Algorithm and Support Vector Machine. GA has been as a feature selection in order to select the best features, while SVM has been used as a classification method to categorize the behavior into normal and intrusion based on the selected features from GA. A benchmark dataset of intrusions (NSS-KDD) has been in the experiment. In addition, the proposed method has been compared with the traditional SVM. Results showed that GA has significantly improved the SVM classification by achieving 0.927 of f-measure.
Volume: 11
Issue: 1
Page: 900-908
Publish at: 2021-02-01

Coronal slice segmentation using a watershed method for early identification of people with Alzheimer's

10.12928/telkomnika.v19i1.15142
Retno; Jenderal Soedirman University Supriyanti , Anugerah Kevin; Jenderal Soedirman University Marchel , Yogi; Jenderal Soedirman University Ramadhani , Haris Budi; Jenderal Soedirman University Widodo
One physical sign of a person who has Alzheimer's is the diminution of the area of the hippocampus and ventricles. A good quality magnetic resonance imaging (MRI) will provide a high-quality image so that the doctor will quickly analyze the abnormalities of the hippocampus and ventricle area. However, for low-quality MRI, this is difficult to do. This condition will be a significant problem for some regions in developing countries including Indonesia, where many hospitals have only low-quality MRI, and many hospitals do not have them at all. The primary purpose of this research is to develop simple tools to analyze morphological characteristics in Alzheimer's patients. In this paper, we focus only on coronal slice analysis. We will use watershed method segmentation, because of this method able to segment the boundaries automatically, so that parts of the hippocampus and ventricles can be identified in an MRI image. Analysis of morphological characteristics is also classified by age and gender. Then by referring to the value of the clinical dementia rating (CDR), the process of identifying between images with Alzheimer's disease (AD) and healthy models is done based on the morphological analysis that has been done. The results show this method has a better performance compared to the previously work.
Volume: 19
Issue: 1
Page: 63-72
Publish at: 2021-02-01

Quantitative estimation of TV white space in Southwest Nigeria

10.12928/telkomnika.v19i1.17881
Ilesanmi Banjo; Ekiti State University Oluwafemi , Ayodeji Peter; Ekiti State University Bamisaye , Matthew Adedeji; Ekiti State University Faluru
The demand for bandwidth has increased in recent years with the advent of new technologies in the wireless systems which have resulted into spectrum crunch. Utilizing the free ultra high frequency (UHF), television (TV) channels also known as TV white space (TVWS) has been proposed as a strategy for increasing spectral efficiency. Deploying TVWS requires the knowledge of the estimate of the available TVWS. In this paper, a quantitative estimation of the available TVWS in South West, Nigeria is computed using the protection view point approach, the pollution viewpoint approach and the Federal Communication Commission (FCC) rule. Results from the estimation shows that the pollution view point approach will guarantee enough protection from the primary users and hence prevent interference from the secondary users. The findings also reveal that there are abundant TVWS in the considered states for the deployment of TVWS devices.
Volume: 19
Issue: 1
Page: 36-43
Publish at: 2021-02-01

A genetic algorithm approach for predicting ribonucleic acid sequencing data classification using KNN and decision tree

10.12928/telkomnika.v19i1.16381
Micheal Olaolu; Landmark University Arowolo , Marion Olubunmi; Landmark University Adebiyi , Ayodele Ariyo; Landmark University Adebiyi
Malaria larvae accept explosive variable lifecycle as they spread across numerous mosquito vector stratosphere. Transcriptomes arise in thousands of diverse parasites. Ribonucleic acid sequencing (RNA-seq) is a prevalent gene expression that has led to enhanced understanding of genetic queries. RNA-seq tests transcript of gene expression, and provides methodological enhancements to machine learning procedures. Researchers have proposed several methods in evaluating and learning biological data. Genetic algorithm (GA) as a feature selection process is used in this study to fetch relevant information from the RNA-Seq Mosquito Anopheles gambiae malaria vector dataset, and evaluates the results using kth nearest neighbor (KNN) and decision tree classification algorithms. The experimental results obtained a classification accuracy of 88.3 and 98.3 percents respectively.
Volume: 19
Issue: 1
Page: 310-316
Publish at: 2021-02-01

Particle swarm optimization-based stator resistance observer for speed sensorless induction motor drive

10.11591/ijece.v11i1.pp815-826
Sang Dang Ho , Petr Palacky , Martin Kuchar , Pavel Brandstetter , Cuong Dinh Tran
This paper presents a different technique for the online stator resistance estimation using a particle swarm optimization (PSO) based algorithm for rotor flux oriented control schemes of induction motor drives without a rotor speed sensor. First, a conventional proportional-integral controller-based stator resistance estimation technique is used for a speed sensorless control scheme with two different model reference adaptive system (MRAS) concepts. Finally, a novel method for the stator resistance estimation based on the PSO algorithm is presented for the two MRAS-type observers. Simulation results in the Matlab/Simulink environment show good adaptability of the proposed estimation model while the stator resistance is varied to 200% of the nominal value. The results also confirm more accurate stator resistance and rotor speed estimation in comparison with the conventional technique.
Volume: 11
Issue: 1
Page: 815-826
Publish at: 2021-02-01

The key management of direct/external modulation semiconductor laser response systems for relative intensity noise control

10.11591/ijeecs.v21.i2.pp968-977
Mahmoud M. A. Eid , Ashraf S. Seliem , Ahmed Nabih Zaki Rashed , Abd El-Naser A. Mohammed , Mohamed Yassin Ali , Shaimaa S. Abaza
This study outlines the management of either direct or external modulation semiconductor laser systems for the key solution of bit rate up to 25 Gb/s under relative intensity noise (RIN) control. The bias and modulation peak currents based laser rate equations are optimized to achieve max Q factor and min bit error rate (BER) using first proposed model and optical/electrical signal power, optical/electrical signal to noise ratio are also enhanced using second proposed model. The percentage enhancement ratio in max. Q-factor and min. BER using first proposed model ranges from 53.25 % to 71.63 % in compared to the previous model. In the same way, by using second proposed model, the electrical signal power at optical receiver is enhanced within the range of 48.66 % to 68.88 % in compared to the previous model. Optical signal/noise ratio (OSNR) after optical fiber cable (OFC), signal/noise ratio (SNR) after electrical filter are measured with using different electrical pulse generators and electrical modulators at the optimization stage. The first proposed model reported better max. Q and min. BER values than the previous model. In addition to the second proposed model (direct modulation) has outlined better optical/electrical signal power than the previous model, while max. Q, min. BER values are kept constant. It is found that non return to zero pulse generator has presented better signal power than other pulse generators by using second proposed model. As well as the mixed of raised cosine pulse generator with external modulator reported max. Q, min. BER with other pulse generators by using first proposed model. OSNR at OFC is optimized by using continuous phase frequency shift keying (CPFSK) electrical modulator, While SNR at optical receiver is optimized by using phase shift keying (PSK) electrical modulator.
Volume: 21
Issue: 2
Page: 968-977
Publish at: 2021-02-01

Flat lens design using phase correction technique for horn antenna applications

10.12928/telkomnika.v19i1.16212
Nur Hazimah Syazana; Universiti Malaysia Pahang Abdul Razak , Nur Shahira Mat; Universiti Malaysia Pahang Hussain , Nurul Hazlina; Universiti Malaysia Pahang Noordin , Syamimi Mardiah; Universiti Malaysia Pahang Shaharum , Ahmad Syahiman Mohd; Universiti Malaysia Pahang Shah , Mohamad Shaiful Abdul; Universiti Malaysia Pahang Karim
A design of a flat dielectric lens is presented in this study to enhance directivity of a pyramidal horn antenna. The horn antenna is proposed to cover frequency of medical imaging system, which is between 5 and 6 GHz, and dielectric lens is designed based on phase correction techniques. The spherical waves produced by conventional horn antenna is being transform to planar waves by resorting flat lens in order to achieve a highly directive radiation in the farfield region. This is done by drilling numerous holes with different diameters through the dielectric material to produce different phase delay. The radiation characteristics of the lens are simulated using CST Microwave Studio and then compared with measured results. The results showed a good performance for radiation pattern when the lens is attached. This proposed design shows a significant increment of sidelobe level and 3-dB beamwidth between 5 and 6 GHz.
Volume: 19
Issue: 1
Page: 213-219
Publish at: 2021-02-01

Different valuable tools for Arabic sentiment analysis: a comparative evaluation

10.11591/ijece.v11i1.pp753-762
Youssra Zahidi , Yacine El Younoussi , Yassine Al-Amrani
Arabic Natural language processing (ANLP) is a subfield of artificial intelligence (AI) that tries to build various applications in the Arabic language like Arabic sentiment analysis (ASA) that is the operation of classifying the feelings and emotions expressed for defining the attitude of the writer (neutral, negative or positive). In order to work on ASA, researchers can use various tools in their research projects without explaining the cause behind this use, or they choose a set of libraries according to their knowledge about a specific programming language. Because of their libraries' abundance in the ANLP field, especially in ASA, we are relying on JAVA and Python programming languages in our research work. This paper relies on making an in-depth comparative evaluation of different valuable Python and Java libraries to deduce the most useful ones in Arabic sentiment analysis (ASA). According to a large variety of great and influential works in the domain of ASA, we deduce that the NLTK, Gensim and TextBlob libraries are the most useful for Python ASA task. In connection with Java ASA libraries, we conclude that Weka and CoreNLP tools are the most used, and they have great results in this research domain.
Volume: 11
Issue: 1
Page: 753-762
Publish at: 2021-02-01

Drone image-based parameters for assessing the vegetation condition the reclamation success in post-mining oil exploration

10.12928/telkomnika.v19i1.16663
Tirta; Institut Pertanian Bogor University Negara , I Nengah Surati; Institut Pertanian Bogor University Jaya , Cecep; Institut Pertanian Bogor University Kusmana , Irdika; Institut Pertanian Bogor University Mansur , Nitya Ade; Institut Pertanian Bogor University Santi
This paper examines drone-based parameters for assessing the success of reclamation activities in post-mining oil-exploration area. The applied drone-based images were multispectral images having visible light and infrared wavelength regions with 5 cm spatial resolution. The main objective of the study is to develop a mathematical model to estimate a reclamation success, through development of success indices. The model were developed by analyzing the relationship between the vegetation success and the digital number values of original and/or synthetic images of drone-based images using 70 sample plots. The mathematical models were developed using a regression analysis, where responses are biomass, volume, and basal area, while the independent variables were original digital number value of images and their derivative synthetic images. The study found that there is a close relationship between parameter biomass stock (ton/ha) and basal area (cm) with both, i.e., original digital number and vegetation indices.
Volume: 19
Issue: 1
Page: 105-114
Publish at: 2021-02-01

Hybrid algorithm for two-terminal reliability evaluation in communication networks

10.11591/ijeecs.v21.i2.pp1185-1192
Musaria Karim Mahmood , Osman Ucan , Zahraa Zaidan , Sulaiman M. Karim
Network reliability is valuable in establishing a survivable communication network. Reliability evaluation algorithms are used in the design stage and during the network deployment. This work presents a new multistage hybrid technique for two-terminal reliability evaluation problem. It is based on a combination of graph reduction techniques and tie-set method. A new approach has been introduced for deducing tie-sets in a network containing both unidirectional and bi-directional edges. The proposed algorithm can be applied for both simple and complex networks without restrictions. The results confirm that new algorithm evaluates network's reliability with decreasing computing time compared to classical algorithms. The results for a case study of a 20-node network have demonstrated that the required time for reliability evaluation is decreased from (t>1 hour) in the case of using a classical algorithm, to (t<1 second) for the new algorithm.
Volume: 21
Issue: 2
Page: 1185-1192
Publish at: 2021-02-01

Performance of downlink NOMA with multiple antenna base station, full-duplex and D2D transmission

10.12928/telkomnika.v19i1.15861
Minh-Sang; Industrial University of Ho Chi Minh City Van Nguyen , Dinh-Thuan; Ton Duc Thang University Do
The implementation of non-orthogonal multiple access (NOMA) and transmit antenna selection (TAS) technique has considered in this paper since TAS-aware base station (BS) provides the low cost, low complexity, and high diversity gains. In this paper, we investigate performance of two users by deriving outage probability. The system performance benefits from design of TAS and full-duplex (FD) scheme applied at NOMA users, and bandwidth efficiency will be enhanced although self-interference exists due to FD. The main contribution lies in the exact expressions of outage probability which are derived to exhibit system performance. Different from the simulated parameters, the analytical results show that increasing number of transmit antennas at the BS is way to improve system performance.
Volume: 19
Issue: 1
Page: 19-26
Publish at: 2021-02-01

Straggler handling approaches in mapreduce framework: a comparative study

10.11591/ijece.v11i1.pp375-382
Anwar H. Katrawi , Rosni Abdullah , Mohammed Anbar , Ibrahim AlShourbaji , Ammar Kamal Abasi
The proliferation of information technology produces a huge amount of data called big data that cannot be processed by traditional database systems. These Various types of data come from different sources. However, stragglers are a major bottleneck in big data processing, and hence the early detection and accurate identification of stragglers can have important impacts on the performance of big data processing. This work aims to assess five stragglers identification methods: Hadoop native scheduler, LATE Scheduler, Mantri, MonTool, and Dolly. The performance of these techniques was evaluated based on three benchmarked methods: Sort, Grep and WordCount. The results show that the LATE Scheduler performs the best and it would be efficient to obtain better results for stragglers identification.
Volume: 11
Issue: 1
Page: 375-382
Publish at: 2021-02-01

A hybrid naïve Bayes based on similarity measure to optimize the mixed-data classification

10.12928/telkomnika.v19i1.18024
Fatima El; University Chouaib Doukkali Barakaz , Omar; University Chouaib Doukkali Boutkhoum , Abdelmajid El; University Chouaib Doukkali Moutaouakkil
In this paper, a hybrid method has been introduced to improve the classification performance of naïve Bayes (NB) for the mixed dataset and multi-class problems. This proposed method relies on a similarity measure which is applied to portions that are not correctly classified by NB. Since the data contains a multi-valued short text with rare words that limit the NB performance, we have employed an adapted selective classifier based on similarities (CSBS) classifier to exceed the NB limitations and included the rare words in the computation. This action has been achieved by transforming the formula from the product of the probabilities of the categorical variable to its sum weighted by numerical variable. The proposed algorithm has been experimented on card payment transaction data that contains the label of transactions: the multi-valued short text and the transaction amount. Based on K-fold cross validation, the evaluation results confirm that the proposed method achieved better results in terms of precision, recall, and F-score compared to NB and CSBS classifiers separately. Besides, the fact of converting a product form to a sum gives more chance to rare words to optimize the text classification, which is another advantage of the proposed method.
Volume: 19
Issue: 1
Page: 155-162
Publish at: 2021-02-01
1 2 3
...
1994 1995
Show 1018 of 1995

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