		FeedBack \| Contact Us \| Links \| Site Map

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

Journal receives papers in continuous flow and we will consider articles from a wide range of Information Technology disciplines encompassing the most basic research to the most innovative technologies. Please submit your papers electronically to our submission system at http://jatit.org/submit_paper.php in an MSWord, Pdf or compatible format so that they may be evaluated for publication in the upcoming issue. This journal uses a blinded review process; please remember to include all your personal identifiable information in the manuscript before submitting it for review, we will edit the necessary information at our side. Submissions to JATIT should be full research / review papers (properly indicated below main title).

Journal of Theoretical and Applied Information Technology
August 2021 | Vol. 99 No.16

Title:	MOBILE BANKING ADOPTION: A SYSTEMATIC REVIEW AND DIRECTION FOR FURTHER RESEARCH
Author:	CHAMA JARIDE, AHMED TAQI
Abstract:	In an environment marked by the growing popularity of mobile technologies, the importance of electronic channels such as mobile banking for banking establishments is no longer to be demonstrated. However, its adoption by users remains a subject of debate due to the multitude of adoption factors cited in previous works as well as the different models of technology adoption used by researchers. This study is a systematic literature review which aims to examine the main theoretical models and factors of adoption that researchers used to describe the acceptance of M-banking technology and predict consumer intent to use it. The main results show that the literature is marked by the dominance of certain theoretical models. However, it remains divided in regards to mobile banking adoption factors with over 61 factors identified. The present article is an update of current knowledge by identifying in quality literature existing relationships in the field of M-banking but also by formulating recommendations in favor of practitioners as well as underlining new research opportunities in favor of theorists in the area of M-banking.
Keywords:	Mobile Banking, Customers Adoption, Technology Acceptance Model, Systematic Review.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	THE APPLICATION OF FUZZY MULTI-CRITERIA DECISION MAKING TO DETERMINE CRITERIA OF SUBMARINE TRAINING LOCATION
Author:	DIDIT HERDIAWAN, AHMADI
Abstract:	Indonesian Navy as a marine security defense force has an Integrated Navy Weapon System, one of them is the power of Submarine and the amount of it will continue to evolve. The current condition demands to perform development and review of strategic and optimal submarine training areas to support the exercise and preparedness of the submarine's strength to prepare the readiness of combat conditions. The purpose of this study was to determine the best criteria for the location of the submarine training by analyzing and reviewing some of the existing locations of Navy Submarine Exercise practice and doing further development. In the selection of submarine training criteria, the method used was the Fuzzy Multiple Decision-Making Criteria (FMCDM). The result of the criteria weight assessment had been re-verified by the experts with 90% agree, 5% strongly agree and 5% disagree and 10 compatible criteria were needed to be considered in selecting the location of Navy submarine training which includes: obstacle/barrier condition, speed of the current, ship maneuver, water area, salinity, depth of water, availability of logistics, density, tidal and availability of materials.
Keywords:	Fuzzy MCDM, Criteria of Location, Submarine Training
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	IMAGE ENCRYPTION USING LOGISTIC-COSINE-SINE CHAOS MAP AND ELLIPTIC CURVE CRYPTOGRAPHY
Author:	BHAT JASRA, MANASHA SAQIB, AYAZ HASSAN MOON
Abstract:	A number of image encryption schemes based upon chaotic systems proposed in the past, have been found to be vulnerable to known-plaintext attack due to the usage of simple linear mapping functions, predictable trajectories etc. In this paper, we propose a hybrid scheme based upon Logistic-Cosine-Sine chaos system and Elliptic Curve Cryptography. The complex chaos mapping function shall result in uniformly distributed pseudo-random outputs and a wider dynamic range while as the Elliptic Curve based cryptography shall be used to leverage the computationally secure encryption of the image pixels. Simulation of the proposed algorithm has been carried using 512-bit standard Elliptic curve given by ECC Brainpool. Results, security analysis reveal that the proposed encryption technique is both computationally efficient as well as resilient against different types of attacks. Comparative analysis shows that the proposed scheme uses lesser number of point multiplications for encryption, and is faster as compared to similar previous schemes.
Keywords:	Image Encryption; Image security, Elliptical Curve Cryptography (ECC), Image Encryption Using ECC, Image Encryption Using Chaos theory;
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	COMBINED TECHNIQUES OF INDOOR POSITIONING SYSTEM USING BLUETOOTH LOW ENERGY
Author:	BUDIUTAMA LAWAS LAWU, GEDE PUTRA KUSUMA
Abstract:	This study tried a combination of several methods for the Indoor Positioning System covering all stages, RSSI Filtering, BLE Selection, and Location Estimation, where the fingerprinting approach used by most other studies is partial. In the RSSI Filtering stage, Kalman Filter and Autoencoder methods are used, BLE Selection stage using Strongest Signal and Fisher Criterion. Position estimation uses the WKNN algorithm and the Kalman Filter. Two static and dynamic datasets (including the movement of an object) are used to measure the accuracy of these combined methods. Overall, the best combination on the static dataset is the Kalman filter and the Strongest Signal Criterion which results in an accuracy of 2.44m, and for the dynamic dataset is the Strongest Signal and WKNN + Kalman Filter with an accuracy of 1.91m.
Keywords:	Fingerprint-Based Algorithm, Indoor Positioning Accuracy, RSSI Filtering, BLE Beacon Selection, Location Estimation
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	SENTIMENT-ANALYSIS TO DETECT EARLY DEPRESSIVE SYMPTOM IN BANGLA LANGUAGE FROM SOCIAL MEDIA: A REVIEW STUDY
Author:	MD. HASIBUL HASSAN, AZRINA KAMARUDDIN, MASRAH AZRIFAH AZMI MURAD
Abstract:	Social media platforms hold a vast volume of raw data that has been posted by people in the forms of texts, images, audio and video. People use this medium to express their thoughts and opinions. As a result, the data can be captured, categorized, and analyzed using Sentiment Analysis approaches to identify users’ behavior, customer’s feedback or gauge public opinions. WHO reported that the numbers on existing mental health disorders are a troubling phenomenon. The identification of mental health can be detected using several data domains such as: sensors, text, structured data, and multi-modal system use. Several researches focus on specific public sentiments for example Malays, English, Arabic, Chinese and Korean. However, very little research was conducted about sentiment analysis approaches implementation in Bangla language. The purpose of this paper is to explain the knowledge gap and the proposed model by using Bangla language sentiment analysis. In this paper we have reviewed 50 articles from which 18 are listed here that have the most similarity with our research. The review shows that the mostly used method in Sentiment-analysis is Machine Learning in the field of Opinion-mining. Furthermore, we have identified another variable that can be included to improve the existing algorithm.
Keywords:	Early Depressive Symptom, Sentiment Analysis, Bangla Language, Social Media
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	ENSEMBLE SELECTION AND COMBINATION BASED ON COST FUNCTION FOR UCI DATASETS
Author:	MOHD KHALID AWANG, MOKHAIRI MAKHTAR, ABD RASID MAMAT
Abstract:	It is well-known that the classification performance of any single classifier is outperformed by a multiple classifier approach or an ensemble process that incorporates results from different base classifiers. However, even though they have the potential to achieve greater classification precision, their vast number of base classifiers has greatly influenced ensemble methods. In the ensemble process, the selection and combination of appropriate and varied classifiers is a daunting task. In the previous work, we, therefore, suggested a new soft ensemble selection and combination approach (SSSC) to identify the best subset of heterogeneous ensemble team of classifiers and demonstrated the potential of our proposed algorithm to minimise a large number of classifiers while at the same time generating the highest predictive precision for consumer churn data sets. This paper extended the earlier work with the goal of evaluating whether the proposed SSSC model works well with the other UCI repository benchmark data sets. The findings of the experiments demonstrated that the developed model resulted in the improvement of the chosen UCI data sets' prediction accuracy. Based on the results of the experiments, it indicates that the prediction accuracy of the proposed SSSC outperformed other single classifiers and ensemble methods for Liver Disorder, Hepatitis and Breast Cancer data sets. This work has shown that the proposed SSSC is able to search for a minimal number of classifiers in the repository of the ensemble while at the same time enhancing the precision of the classification of the chosen UCI data sets.
Keywords:	Ensemble Selection, Customer Churn Prediction, Ensemble Combination, Soft Set, Ensemble Methods.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	PERFORMANCE ANALYSIS OF IoT-ENABLED DDoS BOTNETS IN WEARABLE DEVICES
Author:	SHWETARANI, NAWAB MUHAMMAD FASEEH QURESHI, DONG RYEOL SHIN
Abstract:	Wearable devices (WD) such as smartwatches, fitness trackers, Medical wearables, smart headphones, smart glasses, and smart clothing, etc. are gaining popularity in recent years as the number of users is increasing. With sensing, computing, and communication capability wearable devices are forming a new segment called Wearable Internet-of-Things (WIoT). There is a high chance for these WIoT devices to be new sources of attack for malicious activities such as botnet attacks. The goal of our research is to present a performance analysis of DDoS capable IoT botnets in wearable devices. In the first part, we will show the possibilities of deploying these WIoT devices in DDoS attacks. To demonstrate this, we conducted repeated UDP, TCP, HTTP, and ICMP flooding attacks using BoNeSi DDoS botnet simulator, targeting a wearable device. We also proposed a mitigation technique using Cuckoo Filter (CF) which is designed based on benign source information.
Keywords:	Wearable Device, Botnets, IoT Botnets, DDoS Attacks, BoNeSi DDoS Botnet Simulator, Cuckoo Filter.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	DEEP LEARNING BASED HYBRID APPROACH OF DETECTING FRAUDULENT TRANSACTIONS
Author:	MIN JONG CHEON, DONG HEE LEE, HAN SEON JOO, OOK LEE
Abstract:	As daily transactions made with credit cards have been increasing, fraudulent transactions have also continuously increased. Therefore, the importance of detecting anomalous transactions has kept rising. The given dataset, from Kaggle, consists of imbalanced data, 99.83% of normal data and 0.17% of fraud data. Therefore, in order to solve this imbalance problem, we decided to construct a fraud detecting algorithm. Through constructing a new model with a hybrid approach of deep learning and machine learning, which is composed of a Bi-LSTM-Autoencoder and Isolation Forest, we successfully detected fraudulent transactions in the given dataset. This proposed model yielded an 87% detection rate of fraudulent transactions. Compared to other models (Isolation Forest, Local Outlier, and LSTM-Autoencoder), which show 79%, 3% and 82% detection rates, respectively, our proposed model attained the highest rate. On the contrary, when evaluated by accuracy score, our proposed model did not show a higher score. Even though our model has a similar accuracy score compared to other models and does not implement the Variational Autoencoder for feature selection, this model could potentially be utilized as an effective process to detect fraudulent transactions, especially with the number of global cases increasing along with the need for productivity, quicker detection.
Keywords:	Artificial Intelligence, Machine Learning, Deep Learning, EEG, Olfactory Impairment, Diagnosis
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	MODELLING AN INSIDER THREATS DETECTION METHOD AGAINST EMAIL CONTENT
Author:	AMEERA NATASHA MOHAMMAD, WARUSIA YASSIN, RABIAH AHMAD, SUGANYA DEVI
Abstract:	An insider threats has become one of the most challenging malicious activity in cybersecurity defense compared system recently. Since an insider threats usually expand and spread internally, no one could predict what, when and how exactly malicious insider launched their attacks. This is in a view of fact that an email becomes one of the primary targets of an internal threats as this medium widely used by everyone to communicate, share, and exchange confidential information. Therefore, it is extremely important to understand the nature of insider threats behavior beforehand and construct an accurate detection model. Furthermore, every single keyword used in an email can reflect the behavior of an individual and can be used to determine their intentions i.e., have motive to launch an insider threat or not. Henceforth, an innovative approach is proposed in modelling an insider threats detection in this work. In addition, various statistical analysis i.e., scoring, Friedman, linear regression (R2) and correlation coefficient applied to analyze an insider threat relationship among historical insider threats behavior and relevant extracted keywords from an email content. The Friedman statistical used to determine the minimum differences between each extracted insider threats keywords that represent different insider threats factor (motive, opportunity, capability). Besides, linear regression applied to estimate the relationship of an insider threats from training keywords and testing keyword with allocate anomaly score. Finally, the correlation coefficient approach used to determine how strong a relationship is between extracted insider threats keywords and insider threats behavior in this research. The proposed modelling approach has been evaluated using the benchmark dataset known as CERT that comprises malicious email file. Throughout the experiment, the proposed insider threats detection approach has achieved higher attack detection rate as well as minimized undetectable insider threats behavior as compared to previous researcher works.
Keywords:	Insider threats, Email Content, Insider Threats Keywords, Malicious Behavior, Statistical Based
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	A NOVEL APPROACH TO DETECT IOT MALWARE BY SYSTEM CALLS AND LONG SHORT-TERM MEMORY MODEL
Author:	TOAN NGUYEN NGOC, DUNG LUONG THE, PHU TRAN NGHI
Abstract:	As the Internet of Things (IoT) devices become voguish, malware detection on IoT devices is crucial today. In this paper, a novel approach to detect IoT malware based on dynamic analysis and deep learning is proposed. Our method combines an IoT-sandbox to extract system call sequences that are considered as sentences in natural language, then two Long Short-Term Memory (LSTM) model are used to classify. In our approach, a program is determined whether malware or benign by two representative values which are the results of LSTM models. Experiment results show that our proposed method outperforms other based-line machine learning models using similar system call feature in terms of accuracy, F1-Weight and the length of system call sequence. Our method uses quite short system call sequence of 150, but the highest accuracy 98.37 per cent and F1-Weight achieves 98.38 per cent. Therefore, the method can be used in early IoT malware detection solutions.
Keywords:	IoT malware, malware detection, system calls, LSTM model.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	CONTINUOUS NEIGHBOUR DISCOVERY WITH EFFICIENT ASYNCHRONOUS WAKE-UP SCHEDULES IN WIRELESS SENSOR NETWORKS
Author:	SAGAR MEKALA, Dr K SHAHU CHATRAPATHI
Abstract:	Due to low duty cycles requirement in many real world sensor applications, it is essential to design a protocol for continuous neighbour discovery with efficient asynchronous wake-up schedules. The existing BBID-based approaches have certain limitations. For instance, they lack blocks for certain duty cycles. To overcome this problem, in this paper we proposed a Neighbour Discovery Protocol (NDP) that leverages the efficiency in asynchronous wake-up schedules in Wireless Sensor Networks. A scheme named Flexible, Balanced and Energy Efficient Asynchronous Neighbour Discovery (FBE-ND) is proposed to improve performance of block based NDP. It ensures availability of blocks for all possible duty cycles and see that the sensor application works as desired. Towards this end, the BBDC generates discovery schedules for a wide range of duty cycles. First we introduce a simple version of the protocol that leads to better performance in terms of energy efficiency and latency. Then the protocol is revised further using adjustable occupancy rate of channel for further improvement. Our protocol is evaluated with a simulation study. The results revealed that the protocol outperforms existing NDPs such as Todis, Hedis, SearchLight, U-Connect and Disco. The protocol is useful for many sensor applications where low duty cycles are preferred in asynchronous WSN.
Keywords:	Continuous Neighbour Discovery, Wireless Sensor Network (WSN), Low Duty Cycles, Generation Of Discovery Schedules.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	PREDICTING RAINFALL FROM WEATHER OBSERVATIONS USING SVM APPROACH FOR IDENTIFY THE PARAMETER OF FUEL MOISTURE CODE AS FIRE WEATHER INDEX
Author:	DARWIS ROBINSON MANALU, MUHAMMAD ZARLIS, HERMAN MAWENGKANG, OPIM SALIM SITOMPUL
Abstract:	The Fine Fuel Moisture Code (FFMC) is a numeric rating of the dampness substance of litter and other restored fine fills. This code is a pointer of the general simplicity of start and the combustibility of fine fue. In this study we observed the rainfall time series as a parameter to get the index of FFMC. The main goal of this study to predict the amount of rainfall in a particular division or state well in advance. We predict the amount of rainfall using past data to generate the parameter of FFMC using SVM model in North Sumatera. Based on the result, the various visualizations of data are observed in Aek Godang, North Sumatera which helps in implementing the approaches for rainfall prediction to evaluate the parameter of fuel moisture code as fire weather index. The analysed individual year rainfall patterns for 2017, 2018, 2019, the approximately close means, noticed less standard deviations.
Keywords:	Rainfall, Predicting, FFMC, SVM Model, North Sumatera
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	PRIVACY PRESERVING LOCATION BASED SERVICES QUERY SCHEME BASED ON FULLY HOMOMORPHIC ENCRYPTION
Author:	FIFI FAROUK, YASMIN ALKADY, RAWYA RIZK
Abstract:	Location-Based Services (LBSs) are increasingly popular in today’s society. LBSs are used in a broad variety of applications such as social networks with location sharing. LBSs can help people enjoying a convenient life and has attracted considerable interest recently. However, the privacy issues of LBS are still challenging today. Usually LBS Providers (LBSPs) offer user privacy protection statement to assure users that their private location information would not be given away. However, many LBSs run-on third-party cloud infrastructures. So, the privacy is still in a big problem. While a large number of privacy-preserving solutions for LBS have been proposed, nowadays most of these solutions do not consider the fact that LBS is typically cloud-based. Aiming at the challenges, in this paper, we present a new efficient Privacy Preserving LBS Query scheme based on Fully Homomorphic Encryption (PPQ_FHE). In PPQ_FHE scheme, the LBSP’s data are outsourced to the cloud server in an encrypted manner, and a registered user can get accurate LBS query results without divulging his/her location information to the LBSP and cloud Server Provider (CSP). Specifically, based on improving FHE over Advanced Encryption Standard (AES). We provide a security analysis to show that PPQ_FHE scheme preserves privacy in the presence of different threats. PPQ_FHE analysis and evaluation results demonstrate that proposed PPQ_FHE scheme can preserve the privacy of the LBS users in an efficient and secure way. The results prove the feasibility and efficiency of PPQ_FHE scheme in terms of query's response time, query accuracy, throughput and query overhead.
Keywords:	Advanced Encryption Standard, Fully Homomorphic Encryption, Location-Based Services, Privacy Preserving, and Security.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	USE OF DEEP LEARNING NEURAL NETWORKS FOR THE CLASSIFICATION OF BIRD SPECIES BASED ON THEIR SONG
Author:	HOLMAN MONTIEL A., FREDY MARTÍNEZ, MIGUEL R. PÉREZ P.
Abstract:	An innate quality of living beings is the expression of their emotions in sound form. Birds stand out within living beings that perform sound communication, because they modulate their song to indicate moods or emotions as a protection or survival mechanism. This mechanism and the sound produced changes according to the taxonomic distribution of birds, since each species has its own physiognomy and even within the same species there can be different types of singing. Therefore, the study of the characteristic tonalities of each bird species and its song has become a topic of general interest in certain areas of biology, to determine the possible geographical locations or survival habits of each species. However, the classification of the tones generated in the song of a bird is a subject under study, due to the large number of sounds generated by a single species of bird. Therefore, this article proposes a strategy of classification and identification of the species of a bird by extracting characteristics of the tone of its song with a computational learning algorithm. Our scheme proposes the use of digitized bird sounds, which are processed by digital filters to extract the acoustic characteristics of interest. This filtering is performed in a two-stage scheme, which allows us to narrow down the region of interest of each digital file, which in the end constitutes the dataset of the learning system. To learn the typical characteristics of the sounds, different deep neural network structures are evaluated to identify the topology capable of replicating the characteristics of the samples. The results show a high performance of the identifier, which is linked to the characteristics of the network architecture.
Keywords:	Deep learning neural networks; Computer learning; Taxonomy; Classification; Signal processing
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	BLOCKING CONTROL AND DYNAMIC EXCHANGE BUFFER SWITCHING NEW APPROACH FOR MOBILE WIRELESS SENSOR NETWORKS
Author:	YASSINE SABRI , AOUAD SIHAM , ABERRAHIM MAIZATE
Abstract:	Mobile sensor nodes are usually positioned in low battery power unattended surroundings. Wireless hypermedia sensor-based networks have a huge capacity and a continual flow of data from source to sink. The congestion emerges when the input amount exceeds the number of resources available. The effect of congestion is packet loss, buffer overflow, and waste of power, as well as increasing delays from end to end. The suggested dynamic alternating buffer technique for switching and management of the congestion, using the residual buffer, residual energy and sensor-mobile node confidence level, is applied to effectively control the congestion. The system is based on a cost-effectiveness analysis which calculates main and replacement buffers on time. The dynamic buffer shift is possible by this approach and the congest impact is optimized. The BETCC performance is compared to that of other current protocols such as TCEER and TFCC with respect to energy usage and data loss ratios.
Keywords:	Mobile network, Wireless Sensor Networks, Blocking control, congestion control.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	SUPPLY CHAIN OPTIMIZATION USING GENETIC ALGORITHM IN INDUSTRY MANUFACTURE: A SYSTEMATIC LITERATURE REVIEW
Author:	MASMUR TARIGAN, FORD LUMBAN GAOL
Abstract:	One of the supply chain and exchange of material information from suppliers to final consumers is the supply chain idea. Customer needs fluctuate or go unnoticed as a result of the increase, decrease, and cancellation of consumer interest, and supply chains play a role in market competition. The thorough literature review aims to find a more accurate and efficient application of genetic algorithms in the manufacturing industry for supply chain optimization. from the journal search results, 171 journals were found for the period 2016-2021, after review, 118 journals that were relevant to the research were selected, from these relevant journals there were 23 selected journals. Of these 23 journals, there are still gaps in the criteria for research questions, based on search strings, process criteria, so that further research on supply chain optimization using genetic algorithms can still be done.
Keywords:	Genetics, Algorithms, Supply Chain, Optimization, Effective, Efficiency, Accurate
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	A REAL-TIME ADAPTIVE BITCOIN TRADING SYSTEM USING GENETIC PROGRAMMING
Author:	MONIRA ALOUD
Abstract:	The author presents a simple data-driven intraday technical indicator trading approach based on Genetic Programming (GP) for return forecasting in the Bitcoin market. We use five trend-following technical indicators as input to GP for developing trading rules. Using data on daily Bitcoin historical prices from January 2017 to February 2020, our principal results show that the combination of technical analysis indicators and Artificial Intelligence (AI) techniques, primarily GP, is a potential forecasting tool for Bitcoin prices, even outperforming the buy-and-hold strategy. Sensitivity analysis is employed to adjust the number and values of variables, activation functions, and fitness functions of the GP-based system to verify our approach's robustness.
Keywords:	Bitcoin market; Artificial Intelligence; Genetic Programming; Technical analysis; Trading rule
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text

Title:	NUMERICAL SIMULATION OF WAVE PROPAGATION IN MIXED POROUS MEDIA USING FINITE ELEMENT METHOD
Author:	MARAT NURTAS, ZHARASBEK BAISHEMIROV, SULTAN ALPAR, FATIMA TOKMUKHAMEDOVA
Abstract:	In this paper we research the problem of acoustics in porous media in three separated subdomains. In each region assumes different physical properties: geometry of the pore, viscosity of fluid places in the middle of the two elastic domains. In this task, we first consider the solution of differential equations. A mathematical model of these physical phenomena described by the initial boundary-value problems for complex systems of differential equations in partial derivatives. Then these equations were solved using two numerical methods: finite element method (FEM) and the traditional finite difference method (FDM). Solutions allows to analyse wave propagation phenomena in porous media. The polynomial functions were used as the interpolation basis-test functions in order to get weak solution for the finite element method. The numerical results of our simulation illustrate the method is obviously effective, especially if we want research physical problems with complex domains in 2D and 3D spaces.
Keywords:	Numerical Simulation, Wave Propagation , Pours Media, Finite Method
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2021 -- Vol. 99. No. 16 -- 2021
Full Text