Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Filter Icon

Filters article

Years

FAQ Arrow
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

31,456 Article Results

Reinforcement learning based multi core scheduling (RLBMCS) for real time systems

10.11591/ijece.v10i2.pp1805-1813
Dhruva R. Rinku , M. AshaRani
Embedded systems with multi core processors are increasingly popular because of the diversity of applications that can be run on it. In this work, a reinforcement learning based scheduling method is proposed to handle the real time tasks in multi core systems with effective CPU usage and lower response time. The priority of the tasks is varied dynamically to ensure fairness with reinforcement learning based priority assignment and Multi Core MultiLevel Feedback queue (MCMLFQ) to manage the task execution in multi core system.
Volume: 10
Issue: 2
Page: 1805-1813
Publish at: 2020-04-01

A novel ensemble modeling for intrusion detection system

10.11591/ijece.v10i2.pp1963-1971
Pullagura Indira Priyadarsini , G. Anuradha
Vast increase in data through internet services has made computer systems more vulnerable and difficult to protect from malicious attacks. Intrusion detection systems (IDSs) must be more potent in monitoring intrusions. Therefore an effectual Intrusion Detection system architecture is built which employs a facile classification model and generates low false alarm rates and high accuracy. Noticeably, IDS endure enormous amounts of data traffic that contain redundant and irrelevant features, which affect the performance of the IDS negatively. Despite good feature selection approaches leads to a reduction of unrelated and redundant features and attain better classification accuracy in IDS. This paper proposes a novel ensemble model for IDS based on two algorithms Fuzzy Ensemble Feature selection (FEFS) and Fusion of Multiple Classifier (FMC). FEFS is a unification of five feature scores. These scores are obtained by using feature-class distance functions. Aggregation is done using fuzzy union operation. On the other hand, the FMC is the fusion of three classifiers. It works based on Ensemble decisive function. Experiments were made on KDD cup 99 data set have shown that our proposed system works superior to well-known methods such as Support Vector Machines (SVMs), K-Nearest Neighbor (KNN) and Artificial Neural Networks (ANNs). Our examinations ensured clearly the prominence of using ensemble methodology for modeling IDSs. And hence our system is robust and efficient.
Volume: 10
Issue: 2
Page: 1963-1971
Publish at: 2020-04-01

A new modification nonlinear conjugate gradient method with strong wolf-powell line search

10.11591/ijeecs.v18.i1.pp525-532
Chergui Ahmed , Bouali Tahar
The conjugate gradient method has played a special role in   solving large-scale unconstrained Optimization problems. In this paper, we propose a new family of CG coefficients that   possess    sufficient descent conditions and global convergence properties this CG method is similar to (Wei et al) [7].  Global convergence   result is established under Strong Wolf-Powell line search. Numerical results to find  the  optimum solution of some test  functions show the   new proposed formula has the best result in CPU time and the number of iterations, and the number of gradient evaluations when it comparing with FR, PRP, DY, and WYL 
Volume: 18
Issue: 1
Page: 525-532
Publish at: 2020-04-01

SIEM-based detection and mitigation of IoT-botnet DDoS attacks

10.11591/ijece.v10i2.pp2182-2191
Basheer Al-Duwairi , Wafaa Al-Kahla , Mhd Ammar AlRefai , Yazid Abedalqader , Abdullah Rawash , Rana Fahmawi
The Internet of Things (IoT) is becoming an integral part of our daily life including health, environment, homes, military, etc. The enormous growth of IoT in recent years has attracted hackers to take advantage of their computation and communication capabilities to perform different types of attacks. The major concern is that IoT devices have several vulnerabilities that can be easily exploited to form IoT botnets consisting of millions of IoT devices and posing significant threats to Internet security. In this context, DDoS attacks originating from IoT botnets is a major problem in today’s Internet that requires immediate attention. In this paper, we propose a Security Information and Event Management-based IoT botnet DDoS attack detection and mitigation system. This system detects and blocks DDoS attack traffic from compromised IoT devices by monitoring specific packet types including TCP SYN, ICMP and DNS packets originating from these devices. We discuss a prototype implementation of the proposed system and we demonstrate that SIEM based solutions can be configured to accurately identify and block malicious traffic originating from compromised IoT devices.
Volume: 10
Issue: 2
Page: 2182-2191
Publish at: 2020-04-01

Abnormal gait detection by means of LSTM

10.11591/ijece.v10i2.pp1495-1506
Cesar G. Pachon-Suescun , Javier O. Pinzon-Arenas , Robinson Jimenez-Moreno
This article presents a system focused on the detection of three types of abnormal walk patterns caused by neurological diseases, specifically Parkinsonian gait, Hemiplegic gait, and Spastic Diplegic gait. A Kinect sensor is used to extract the Skeleton from a person during its walk, to then calculate four types of bases that generate different sequences from the 25 points of articulations that the Skeleton gives. For each type of calculated base, a recurrent neural network (RNN) is trained, specifically a Long short-term memory (LSTM). In addition, there is a graphical user interface that allows the acquisition, training, and testing of trained networks. Of the four trained networks, 98.1% accuracy is obtained with the database that was calculated with the distance of each point provided by the Skeleton to the Hip-Center point.
Volume: 10
Issue: 2
Page: 1495-1506
Publish at: 2020-04-01

The support of multipath routing in IPv6-based internet of things

10.11591/ijece.v10i2.pp2208-2220
Ibrahim S. Alsukayti
The development of IPv6-based network architectures for Internet of Things (IoT) systems is a feasible approach to widen the horizon for more effective applications, but remains a challenge. Network routing needs to be effectively addressed in such environments of scarce computational and energy resources. The Internet Engineering Task Force (IETF) specified the IPv6 Routing Protocol for Low Power and Lossy Network (RPL) to provide a basic IPv6-based routing framework for IoT networks. However, the RPL design has the potential of extending its functionality to a further limit and incorporating the support of advanced routing mechanisms. These include multipath routing which has opened the doors for great improvements towards efficient energy balancing, load distribution, and even more. This paper fulfilled a need for an effective review of recent advancements in Internet of Things (IoT) networking. In particular, it presented an effective review and provided a taxonomy of the different multipath routing solutions enhancing the RPL protocol. The aim was to discover its current state and outline the importance of integrating such a mechanism into RPL to revive its potentiality to a wider range of IoT applications. This paper also discussed the latest research findings and provided some insights into plausible follow-up researches.
Volume: 10
Issue: 2
Page: 2208-2220
Publish at: 2020-04-01

Challenges, issues and opportunities for the development of smart grid

10.11591/ijece.v10i2.pp1179-1186
Surender Reddy Salkuti
The development smart grids have made the power systems planning and operation more efficient by the application of renewable energy resources, electric vehicles, two-way communication, self-healing, consumer engagement, distribution intelligence, etc. The objective of this paper is to present a detailed comprehensive review of challenges, issues and opportunities for the development of smart grid. Smart grids are transforming the traditional way of meeting the electricity demand and providing the way towards an environmentally friendly, reliable and resilient power grid. This paper presents various challenges of smart grid development including interoperability, network communications, demand response, energy storage and distribution grid management. This paper also reviews various issues associated with the development of smart grid. Local, regional, national and global opportunities for the development of smart grid are also reported in this paper.
Volume: 10
Issue: 2
Page: 1179-1186
Publish at: 2020-04-01

An approach to designing and developing an LMS framework appropriate for young pupils

10.11591/ijece.v10i2.pp1577-1591
Radoslava Kraleva , Mehrudin Sabani , Velin Kralev , Dafina Kostadinova
The lifestyle of the new people generation, called in the scientific literature Generation Z, is closely related to the Internet, computer and information technology. Therefore, people and children belonging to this group can be viewed in terms of software technology as specific users who have high requirements regarding the functions and interface of the software applications, connectivity to social networks and instant communication via the Internet. This influenced not only on the teaching and learning methods but also on the software applications used in the learning process. In recent years, new theoretical teaching methods have emerged, and the number of electronic learning systems increased. However, students lack motivation for the learning process. This requires developing new conceptual models of training and learning software, tailored to the skills and preferences of the end-users. The young students up to 12 years of age: from kindergartens to preschools and primary schools are special users who have not been studied exhaustively. In order to present the problem related to the development of learning and training software thoroughly, the most commonly used standards and current trends, as well as the advantages and disadvantages of LMS platforms have been reviewed. Attention is drawn to the commonly used software design and development technologies. This is the reason to propose a strategy for developing a web-based e-learning management system according to the possibilities of young pupils as a specific user. Having in mind this strategy we described a software architecture, based on SCORM's specification, and we developed an LMS prototype. Its design was tailored to the skills of young children. The basic methodology used in the design and creation of the system we propose is user-centered design. The document is intended for developers, educators and scientists, studying child-computer interaction.
Volume: 10
Issue: 2
Page: 1577-1591
Publish at: 2020-04-01

Duplexing mode, ARB and modulation approaches parameters affection on LTE uplink waveform

10.11591/ijece.v10i2.pp1485-1494
Fatima Faydhe Al-Azzawi , Faeza Abas Abid , Zainab faydhe al-azzawi
The next generation of radio technologies designed to increase the capacity and speed of mobile networks. LTE is the first technology designed explicitly for the Next Generation Network NGN and is set to become the de-facto NGN mobile access network standard. It takes advantage of the NGN's capabilities to provide an always-on mobile data experience comparable to wired networks. In this paper LTE uplink waveforms displayed with various duplexing mode, Allocated Resources Blocks ARB, Modulation types and total information per frame, QPSK and 16 QAM used as modulation techniques and tested under AWGN and Rayleigh channels, similarity and interference of the generated waveforms tested using auto-correlation and cross-correlation respectively.
Volume: 10
Issue: 2
Page: 1485-1494
Publish at: 2020-04-01

Torque estimator using MPPT method for wind turbines

10.11591/ijece.v10i2.pp1208-1219
Youssef Baala , Seddik Bri
In this work, we presents a control scheme of the interface of a grid connected Variable Speed Wind Energy Generation System based on Doubly Fed Induction Generator (DFIG). The vectorial strategy for oriented stator flux GADA has been developed To extract the maximum power MPPT from the wind turbine. It uses a second order sliding mode controller and Kalman observer, using the super twisting algorithm. The simulation describes the effectiveness of the control strategy adopted.For A step and random profiles of the wind speed, reveals better tracking and perfect convergence of electromagnetic torque and concellation of reactive power to the stator. This control limits the mechanical stress on the tansmission shaft, improves the quality of the currents generated on the grid and optimizes the efficiency of the conversion chain.
Volume: 10
Issue: 2
Page: 1208-1219
Publish at: 2020-04-01

Improving accuracy of Part-of-Speech (POS) tagging using hidden markov model and morphological analysis for Myanmar Language

10.11591/ijece.v10i2.pp2023-2030
Dim Lam Cing , Khin Mar Soe
In Natural Language Processing (NLP), Word segmentation and Part-of-Speech (POS) tagging are fundamental tasks. The POS information is also necessary in NLP’s preprocessing work applications such as machine translation (MT), information retrieval (IR), etc. Currently, there are many research efforts in word segmentation and POS tagging developed separately with different methods to get high performance and accuracy. For Myanmar Language, there are also separate word segmentors and POS taggers based on statistical approaches such as Neural Network (NN) and Hidden Markov Models (HMMs). But, as the Myanmar language's complex morphological structure, the OOV problem still exists. To keep away from error and improve segmentation by utilizing POS data, segmentation and labeling should be possible at the same time.The main goal of developing POS tagger for any Language is to improve accuracy of tagging and remove ambiguity in sentences due to language structure. This paper focuses on developing word segmentation and Part-of- Speech (POS) Tagger for Myanmar Language. This paper presented the comparison of separate word segmentation and POS tagging with joint word segmentation and POS tagging.
Volume: 10
Issue: 2
Page: 2023-2030
Publish at: 2020-04-01

Investigations on real time RSSI based outdoor target tracking using kalman filter in wireless sensor networks

10.11591/ijece.v10i2.pp1943-1951
K. Vadivukkarasi , R. Kumar
Target tracking is essential for localization and many other applications in Wireless Sensor Networks (WSNs). Kalman filter is used to reduce measurement noise in target tracking. In this research TelosB motes are used to measure Received Signal Strength Indication (RSSI). RSSI measurement doesn’t require any external hardware compare to other distance estimation methods such as Time of Arrival (TOA), Time Difference of Arrival (TDoA) and Angle of Arrival (AoA). Distances between beacon and non-anchor nodes are estimated using the measured RSSI values. Position of the non-anchor node is estimated after finding the distance between beacon and non-anchor nodes. A new algorithm is proposed with Kalman filter for location estimation and target tracking in order to improve localization accuracy called as MoteTrack InOut system. This system is implemented in real time for indoor and outdoor tracking. Localization error reduction obtained in an outdoor environment is 75%.
Volume: 10
Issue: 2
Page: 1943-1951
Publish at: 2020-04-01

Asymmetric quasi impedance source buck-boost converter

10.11591/ijece.v10i2.pp2128-2138
Muhammad Ado , Awang Jusoh , Tole Sutikno
An impedance source buck-boost converter (BBC) prototype for renewable energy (RE) application in the transportation industry is proposed. Its functions include stabilizing the variable output voltage of the RE sources such as fuel cells and photovoltaic cells. The converter utilized a topology of DC-DC quasi-impedance source converters (q-ZSCs) to achieve the gain curve of the BBC. With BBC gain curve, the converter earned advantages over the two other classes of non-isolated DC-DC q-ZSCs. These advantages include ecient buck-boost capability at the ecient duty ratio range of 0:35-0:65 and continuous and non-zero gain at the ecient duty ratio range. The converter's q-ZSC topology implies using two capacitors and two inductors. These two capacitors and inductors formed two separate LC filters that provides second order filtering compared to the first order filtering in BBC. Its other advantages over the traditional BBC include elim-ination of dead and overlap-time, simple contol and permitting higher switching frequency operation. The converter is capable of utilizing high switching frequency and asymmetric components to achieve BBC gain by using smaller components to reduce cost, weight and size. Its simulation response and that of a correspond-ing BBC for some given specifications were compared, presented and analyzed. An experimental scaled-down prototype was also developed to confirm its operation. Analysis of the converters responses comfirmed the prototype's second order filtering as against the first order filtering in traditional BBC.
Volume: 10
Issue: 2
Page: 2128-2138
Publish at: 2020-04-01

Augmentation of a SCADA based firewall against foreign hacking devices

10.11591/ijece.v10i2.pp1359-1366
Abhishek Mungekar , Yashraj Solanki , R. Swarnalatha
An Industrial firewall is a system used to supervise and regulate traffic to and from a network for the purpose of securing appliances on a network. It analyzes the data passing through it to an already defined surveillance criteria or protocols, discarding data that does not meet the protocol’s requirements. In effect, it is a filter preventing undesirable network traffic and selectively limiting the type of transmission that occurs between a secured transmission line. In this research paper a SCADA based Firewall is implemented for protection of the data transmission to a PLC, against external hacking devices. This firewall is virtually exposed to several external hackers and the degree of vulnerability is carefully studied, in order to develop an ideal Firewall.
Volume: 10
Issue: 2
Page: 1359-1366
Publish at: 2020-04-01

Miniaturized UWB elliptical patch antenna for skin cancer diagnosis imaging

10.11591/ijece.v10i2.pp1422-1429
Sameer Alani , Zahriladha Zakaria , A. Ahmad
The biomedical imaging shows promising results in many applications such as protein characterization and cancer detection using non-ionizing radiation. Skin cancer is one of the most common types of cancer because it is exposed by sun rays during the day. Many techniques have been offered to detect the tumor in the early stage such as ultrasonic and MW imaging. However, most of these studies showed a large printing area with lower BW so as the low resolution. To overcome these drawbacks, a new low profile UWB elliptical patch antenna with high performance is designed on PTFE as a substrate. Then a layer of Indium Tin Oxide (ITO) applies to improve the antenna radiation characteristics. The proposed antenna has a broad BW from 3.9 GHz to 30 GHz along with a resonance at 2.4 GHz. Furthermore, the antenna presents a maximum gain of 7.3 dB, maximum directivity of 7.78 dBi, the maximum radiation efficiency of 92 %, and consistent, stable radiation pattern throughout the frequency band. Besides, the time-domain characteristics show that the antenna can be a suitable candidate for microwave imaging of skin cancer.
Volume: 10
Issue: 2
Page: 1422-1429
Publish at: 2020-04-01
Show 1254 of 2098

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