scispace - formally typeset
Search or ask a question

Showing papers in "Indonesian Journal of Electrical Engineering and Computer Science in 2022"


Journal ArticleDOI
TL;DR: This study clarified an overview of wired and wireless optical communication system block diagram with practical applications by presenting a theoretical circuit as an example and modified it to fit and work in communication purposes.
Abstract: This study clarified an overview of wired and wireless optical communication system block diagram with practical applications. Freespace optical (FSO) communication is a trending field that is rising so fast to replace electromagnetic waves in a communication, so we have presented a theoretical circuit as an example and modified it to fit and work in communication purposes, simulation is used and then practical work is done and printed circuit board (PCB) is designed. Light emitting diode (LED) have been used as transmitter and Photo Transistor as a receiver and variable resistance to change voltage sent to the LED that indicates the change in the transmitted signal.

32 citations


Journal ArticleDOI
TL;DR: In this paper, the first order surface grating fiber coupler under the period chirp and apodization functions variations effects is demonstrated and the fiber coupling delay and dispersion are simulated and demonstrated with grating wavelength with quadratic/cubic root period chircp and Gaussian/uniform apodisation function.
Abstract: The paper has demonstrated the first order surface grating fiber coupler under the period chirp and apodization functions variations effects. The Fiber coupler transmittivity/reflectivity, the fiber coupler grating index change and the fiber coupler mesh transmission cross-section are clarified against the grating length with the quadratic/cubic root period chirp and Gaussian/uniform apodization functions. The fiber coupler delay and dispersion are simulated and demonstrated with grating wavelength with quadratic/cubic root period chirp and Gaussian/uniform apodization function. As well as the fiber coupler output pulse intensity is simulated against the time period with the quadratic/cubic root period chirp and Gaussian/uniform apodization function. The fiber coupler peak intensity variations against the transmission range variations is also demonstrated by OptiGrating simulation software.

32 citations


Journal ArticleDOI
TL;DR: The investigation results confirm that the optimal execution is the support vector machine technique, and it gives high-accuracy prediction results, and the performance of the forward propagation artificial neural networks (ANN) technique is acceptable.
Abstract: The heart, like a pump, is an organ about the size of a fist, mainly composed of muscle and connective tissue that functions to distribute blood to tissues. The heart is located under the rib cage, above the diaphragm between the lungs, slightly closer to the left. Sometimes a small, unexpected problem with the veins or the valves that supply the heart affects a person's life and can lead to death. Early diagnosis is essential to predict diseases that affect the human heart and lead people to live another period of life. In this context, the authors introduce two methods for early diagnosis of heart disease, the support vector machine and artificial neural network. The medical data is taken from the University of California Irvine (UCI) Machine Learning Repository database, and it contains reports of 170 people. The investigation results confirm that the optimal execution is the support vector machine technique. It gives high-accuracy prediction results. As for the performance of the forward propagation artificial neural networks (ANN) technique is acceptable.

20 citations


Journal ArticleDOI
TL;DR: The study proved that dividing of addressed problem into sub-problems will achieve better performance and accuracy and the CAD3 proved its efficiency on the other dataset such as acute lymphoblastic leukemia image database (ALL-IBD1) and blood cell count dataset (BCCD).
Abstract: The developing of deep learning systems that used for chronic diseases diagnosing is challenge. Furthermore, the localization and identification of objects like white blood cells (WBCs) in leukemia without preprocessing or traditional hand segmentation of cells is a challenging matter due to irregular and distorted of nucleus. This paper proposed a system for computer-aided detection depend completely on deep learning with three models computer-aided detection (CAD3) to detect and classify three types of WBC which is fundamentals of leukemia diagnosing. The system used modified you only look once (YOLO v2) algorithm and convolutional neural network (CNN). The proposed system trained and evaluated on dataset created and prepared specially for the addressed problem without any traditional segmentation or preprocessing on microscopic images. The study proved that dividing of addressed problem into sub-problems will achieve better performance and accuracy. Furthermore, the results show that the CAD3 achieved an average precision (AP) up to 96% in the detection of leukocytes and accuracy 94.3% in leukocytes classification. Moreover, the CAD3 gives report contain a complete information of WBC. Finally, the CAD3 proved its efficiency on the other dataset such as acute lymphoblastic leukemia image database (ALL-IBD1) and blood cell count dataset (BCCD).

19 citations


Journal ArticleDOI
TL;DR: This paper used a hybrid approach that combines both lexicon-based and deep learning, with BERT as the DL model, and shows that the hybrid technique outperforms existing approaches in several metrics.
Abstract: Sentiment analysis (SA) is widely used today in many areas such as crime detection (security intelligence) to detect potential security threats in realtime using social media platforms such as Twitter. The most promising techniques in sentiment analysis are those of deep learning (DL), particularly bidirectional encoder representations from transformers (BERT) in the field of natural language processing (NLP). However, employing the BERT algorithm to detect crimes requires a crime dataset labeled by the lexiconbased approach. In this paper, we used a hybrid approach that combines both lexicon-based and deep learning, with BERT as the DL model. We employed the lexicon-based approach to label our Twitter dataset with a set of normal and crime-related lexicons; then, we used the obtained labeled dataset to train our BERT model. The experimental results show that our hybrid technique outperforms existing approaches in several metrics, with 94.91% and 94.92% in accuracy and F1-score respectively.

15 citations


Journal ArticleDOI
TL;DR: The performance of the proposed model by using CNN algorithm shows promising results in the detection of COVID-19, and it has outperformed all its comparatives in terms of detection accuracy.
Abstract: Nowadays, the coronavirus disease (COVID-19) is considered an ongoing pandemic that spread quickly in most countries around the world. The COVID-19 causes severe acute respiratory syndrome. Moreover, the technique of chest computed tomography (CT) is a method used in the detection of COVID-19. However, the CT method consumes more time and higher-cost as compared with chest X-ray images. Therefore, this paper presents convolutional neural network (CNN) algorithm in the detection of COVID-19 by using X-ray images. In this method, we have used a balanced image database for the normal (healthy) and COVID-19 subjects. The total number of image database is 188 samples (94 healthy samples and 94 COVID-19 samples). Furthermore, there are several evaluation measurements are used to evaluate the proposed model such as accuracy, precision, specificity, sensitivity, F-measure, G-mean, and others. According to the experimental results, the proposed model obtains 98.68% accuracy, 100% precision, and 100% specificity. Besides, the proposed model achieves 97.37%, 98.67%, and 98.68% for sensitivity, F-measure, and G-mean, respectively. The performance of the proposed model by using CNN algorithm shows promising results in the detection of COVID-19. Also, it has outperformed all its comparatives in terms of detection accuracy.

13 citations


Journal ArticleDOI
TL;DR: The obtained results show that the learned generative model makes excellent quantitative and visual performances, the model is capable of generating realistic and diverse samples for human faces and create a complete portrait with respect of given text description.
Abstract: The advancements in artificial intelligence research, particularly in computer vision, have led to the development of previously unimaginable applications, such as generating new contents based on text description. In our work we focused on the text-to-image synthesis applications (TIS) field, to transform descriptive sentences into a real image. To tackle this issue, we use unsupervised deep learning networks that can generate high quality images from text descriptions, provided by eyewitnesses to assist law enforcement in their investigations, for the purpose of generating probable human faces. We analyzed a number of existing approaches and chose the best one. Deep fusion generative adversarial networks (DF-GAN) is the network that performs better than its peers, at multiple levels, like the generated image quality or the respect of the giving descriptive text. Our model is trained on the CelebA dataset and text descriptions (generated by our algorithm using existing attributes in the dataset). The obtained results from our implementation show that the learned generative model makes excellent quantitative and visual performances, the model is capable of generating realistic and diverse samples for human faces and create a complete portrait with respect of given text description.

12 citations


Journal ArticleDOI
TL;DR: Experimental results show the effectiveness of the designed method in detecting brain tumors automatically and produce better accuracy in comparison to previous approaches.
Abstract: Due to the advances in information and communication technologies, the usage of the internet of things (IoT) has reached an evolutionary process in the development of the modern health care environment. In the recent human health care analysis system, the amount of brain tumor patients has increased severely and placed in the 10th position of the leading cause of death. Previous state-of-the-art techniques based on magnetic resonance imaging (MRI) faces challenges in brain tumor detection as it requires accurate image segmentation. A wide variety of algorithms were developed earlier to classify MRI images which are computationally very complex and expensive. In this paper, a cost-effective stochastic method for the automatic detection of brain tumors using the IoT is proposed. The proposed system uses the physical activities of the brain to detect brain tumors. To track the daily brain activities, a portable wrist band named Mi Band 2, temperature, and blood pressure monitoring sensors embedded with Arduino-Uno are used and the system achieved an accuracy of 99.3%. Experimental results show the effectiveness of the designed method in detecting brain tumors automatically and produce better accuracy in comparison to previous approaches.

9 citations


Journal ArticleDOI
TL;DR: In this paper , memory optimization and architectural level modifications are introduced for realizing the low power residual number system (RNS) with improved flexibility for electroencephalograph (EEG) signal classification.
Abstract: In this paper, memory optimization and architectural level modifications are introduced for realizing the low power residue number system (RNS) with improved flexibility for electroencephalograph (EEG) signal classification. The proposed RNS framework is intended to maximize the reconfigurability of RNS for high-performance finite impulse response (FIR) filter design. By replacing the existing power-hungry RAM-based reverse conversion model with a highly decomposed lookup table (LUT) model which can produce the results without using any post accumulation process. The reverse conversion block is modified with an appropriate functional unit to accommodate FIR convolution results. The proposed approach is established to develop and execute pre-calculated inverters for various module sets. Therefore, the proposed LUT-decomposition with RNS multiplication-based post-accumulation technology provides a high-performance FIR filter architecture that allows different frequency response configuration elements. Experimental results shows the superior performance of decomposing LUT-based direct reverse conversion over other existing reverse conversion techniques adopted for energy-efficient RNS FIR implementations. When compared with the conventional RNS FIR design with the proposed FSM based decomposed RNS FIR, the logic elements (LEs) were reduced by 4.57%, the frequency component is increased by 31.79%, number of LUTs is reduced by 42.85%, and the power dissipation was reduced by 13.83%.

9 citations


Journal ArticleDOI
TL;DR: A novel unsupervised AD Host-IDS for internet of things (IoT) based on adversarial training architecture using the generative adversarial network (GAN) is proposed, which could be a solution for detecting cyber abnormalities in the IoT.
Abstract: Machine learning (ML) and deep learning (DL) have achieved amazing progress in diverse disciplines. One of the most efficient approaches is unsupervised learning (UL), a sort of algorithms for analyzing and clustering unlabeled data; it allows identifying hidden patterns or performing data clustering over provided data without the need for human involvement. There is no prior knowledge of actual abnormalities when using UL methods in anomaly detection (AD); hence, a DL-intrusion detection system (IDS)- based on AD depends intensely on their assumption about the distribution of anomalies. In this paper, we propose a novel unsupervised AD Host-IDS for internet of things (IoT) based on adversarial training architecture using the generative adversarial network (GAN). Our proposed IDS, called “EdgeIDS”, targets mostly IoT devices because of their limited functionality; IoT devices send and receive only specific data, not like traditional devices, such as servers or computers that exchange a wide range of data. We benchmarked our proposed “EdgeIDS” on the message queuing telemetry transport (MQTTset) dataset with five attack types, and our obtained results are promising, up to 0.99 in the ROC-AUC metric, and to just 0.035 in the ROC-EER metric. Our proposed technique could be a solution for detecting cyber abnormalities in the IoT.

9 citations


Journal ArticleDOI
TL;DR: This study addresses the issue by finding the most efficient CNN model with the least data loss and classification time by employing MobileNetV2, which is observed to give the best and the quickest result in an emergency.
Abstract: COVID-19 illness has a detrimental impact on the respiratory system, and the severity of the infection may be determined utilizing a selected imaging technique. Chest computer tomography (CT) imaging is a reliable diagnostic technique for finding COVID-19 early and slowing its progression. Recent research shows that deep learning algorithms, particularly convolutional neural network (CNN), may accurately diagnose COVID-19 using lung CT scan images. But in an emergency, detection accuracy simply is not enough. Determinants of data loss and classification completion time play a critical element. This study addresses the issue by finding the most efficient CNN model with the least data loss and classification time. Eight deep learning models, including Max Pooling 2D, Average Pooling 2D, VGG19, VGG16, MobileNetV2, InceptionV3, AlexNet, NFNet using a dataset of 16000 CT scans image data of COVID-19 and non-COVID-19 are compared in the study. Using the confusion matrix, the performance of the models is compared and together with the data loss and completion time. It is observed from the research that MobileNetV2 provides the highest accurate result of 99.12% with the least data loss of 0.0504% in the lowest classification completion time of 16.5secs per epoch. Thus, employing MobileNetV2 gives the best and the quickest result in an emergency.

Journal ArticleDOI
TL;DR: In this paper , the authors proposed SecMac-secure router discovery (SecMac-SRD) technique, which requires reduced processing time and may thwart fake RA assaults, is proposed as an improved secure RD mechanism.
Abstract: The design of router discovery (RD) is a trust mechanism to confirm the legitimacy of the host and router. Fake router advertisement (RA) attacks have been made possible by this RD protocol design defect. Studies show that the standard RD protocol is vulnerable to a fake RA attack where the host will be denied a valid gateway. To cope with this problem, several prevention techniques have been proposed in the past to secure the RD process. Nevertheless, these methods have a significant temporal complexity as well as other flaws, including the bootstrapping issue and hash collision attacks. Thus, the SecMac-secure router discovery (SecMac-SRD) technique, which requires reduced processing time and may thwart fake RA assaults, is proposed in this study as an improved secure RD mechanism. SecMac-SRD is built based on a UMAC hashing algorithm with ElGamal public key distribution cryptosystem that hides the RD message exchange in the IPv6 link-local network. Based on the obtained expected results display that the SecMac-SRD mechanism achieved less processing time compared to the existing secure RD mechanism and can resist fake RA attacks. The outcome of the expected results clearly proves that the SecMac-SRD mechanism effectively copes with the fake RA attacks during the RD process.

Journal ArticleDOI
TL;DR: The proposed speech encryption scheme provides a better security system with robust decryption quality and is evaluated using spectrogram analysis, histogram analysis, key space analysis, correlation analysis,Key sensitivity analysis and randomness test analysis.
Abstract: Using a new key management system and Jacobian elliptic map, a new speech encryption scheme has been developed for secure speech communication data. Jacobian elliptic map-based speech encryption has been developed as a novel method to improve the existing speech encryption methods' drawbacks, such as poor quality in decrypted signals, residual intelligibility, high computational complexity, and low-key space. Using the Jacobian elliptic map as a key management solution, a new cryptosystem was created. The proposed scheme's performance is evaluated using spectrogram analysis, histogram analysis, key space analysis, correlation analysis, key sensitivity analysis and randomness test analysis. Using the results, we can conclude that the proposed speech encryption scheme provides a better security system with robust decryption quality.

Journal ArticleDOI
TL;DR: This study succeeded in making a stochastic susceptible infected recovered deceased (SIRD) simulation using Python programming language to determine the effectiveness of prevention methods such as masks policy, social distancing, vaccination, quarantine, and lockdown.
Abstract: A simulation is needed to observe and indicate how much preventive measures influence the pandemic flow, controlling and stopping it. This study succeeded in making a stochastic susceptible infected recovered deceased (SIRD) simulation using Python programming language to determine the effectiveness of prevention methods such as masks policy, social distancing, vaccination, quarantine, and lockdown. Every preventive measure is modeled based on an equivalent actual event and every essential aspect that affects the course of the pandemic. A person is represented as a circle moving freely in two-dimensional space, and disease spreads through person-to-person contact. This simulator then tested using parameters to simulate COVID-19 and found significant results between communities that implement preventive measures and those that do not. We found that within 106 days, 284 people were infected, but when five preventive methods are applied for a total of 33 days, only 31 people were infected. Adequate to simulate epidemic events and their prevention measures, this simulator can also be used as a learning tool with factors in epidemic events such as population density, mobility, infection rate, disease mortality, and every effect of each preventive measure. Users can change and influence the simulation course using interactive and straightforward software tools.

Journal ArticleDOI
TL;DR: The proposed deep convolutional neural network (DCCN) based on a residual network (Resnet-50) that can identify COVID-19 from two other classes (pneumonia and normal) in chest X-ray images and may help health professionals in confirming their first evaluation of CO VID-19 patients.
Abstract: The novel coronavirus, also known as COVID-19, initially appeared in Wuhan, China, in December 2019 and has since spread around the world. The purpose of this paper is to use deep convolutional neural networks (DCCN) to improve the detection of COVID-19 from X-ray images. In this study, we create a DCNN based on a residual network (Resnet-50) that can identify COVID-19 from two other classes (pneumonia and normal) in chest X-ray images. DCNN was evaluated using two classification methods: binary (BC-1: COVID-19 vs. normal, BC-2: COVID-19 vs. pneumonia) and multi-class (pneumonia vs. normal vs. COVID-19). In all experiments, four fold cross-validation was used to train and test the model. This architecture's average accuracy is 99.9% for BC-1, 99.8% for BC-2, and 97.3% for multi-class cases. The experimental findings demonstrated that the suggested system detects COVID-19 with an average precision and sensitivity of 95% and 95.1% for multi-class classification, respectively. According to our findings, the proposed DCNN may help health professionals in confirming their first evaluation of COVID-19 patients.

Journal ArticleDOI
TL;DR: In this paper , the design of a hydroponic planting process monitoring system based on the internet of things has been discussed, which uses an ESP32 microcontroller board as the main controller.
Abstract: This article discusses the design of a hydroponic planting process monitoring system based on the internet of things. This device uses an ESP32 microcontroller board as the main controller. The parameters that were monitored and acquired were the conditions of the hydroponic growing media. Those parameters are; water pH, water temperature, water turbidity level, and ambient air temperature and humidity. The five parameters are measured by analog sensors integrated with the ESP32. These parameters affect the growth process and the quality of crop yields. This article also describes the calibration method for each sensor used for parameter measurement. Then the monitoring of these parameters is carried out by utilizing a real-time database, namely Google Firebase. This platform is very suitable for all IoT-based monitoring and control applications. Measurement result data is uploaded and saved to the real-time database. Then paired by Android-based applications. This application was created to be used by hydroponic farmers who use this device. Thus the results of monitoring can be used to optimize the process of growing hydroponic plants.

Journal ArticleDOI
TL;DR:
Abstract: Many solar plants have been installed globally, and they must be continuously protected and supervised to ensure their safety and reliability. Photovoltaic plants are susceptible to many defects and failures, and fault detection technology is used to protect and isolate them. Despite numerous inter-national standards, invisible photovoltaic defects continue to cause major is-sues. As a result, smart technologies like AI (Artificial Intelligence) and IoT are being developed for remote sensing, problem detection, and diagnosis of photovoltaic systems. Solar plants generate not only green electricity but also a lot of data, such as power output. With AI, a clear picture of electricity yields should be possible. The output of entire solar parks could be monitored and analyzed. The AI could also detect malfunctions within a solar park, according to the research. This would speed up and simplify maintenance work. Deep learning (DL) and IoT applications for photovoltaic plants are discussed. The most advanced techniques, such as DL, are discussed in terms of precision and accuracy. Incorporating DL and IoT approaches for fault detection and diagnosis into simple hardware, such as low-cost chips, maybe cost-effective and technically feasible for photovoltaic facilities located in remote locations.

Journal ArticleDOI
TL;DR: In this paper , the authors proposed a hybrid street lighting system based on the IoT and included the most sophisticated battery charging system to improve the battery's cells' life cycle, which has the potential to make a significant contribution to lowering CO2 emissions and government subsidies for street lighting.
Abstract: Every country is subsidising millions of dollars for street lighting as those are connected to the grid. Besides, the generation of electricity comes from fossil fuels with emissions of carbon dioxide (CO2). Therefore, alternative generation of electricity can be done by using a hybrid system. Solar energy starts as the day begins, and the wind is accessible on the streets with a to-and-fro motion of the car. It does not rely on any factor. This hybrid system generates 12V DC, whereas no AC converters are used, resulting in a reduction the system's cost. The control system was constructed based on IoT and included the most sophisticated battery charging system to improve the battery's cells' life cycle. The hardware system has been simulated using EasyEDA and incorporated with the PCB design. The prototype is constructed alongside collected data to compare with the theoretical basis towards net-zero energy street lighting (nZESL). The prototype was able to lead to nZESL and backup stability of the system is 10 hours per day, along with the validation of theoretical analyses and effectiveness of the system. The system has the potential to make a significant contribution to lowering CO2 emissions and government subsidies for street lighting.

Journal ArticleDOI
TL;DR: The research exploits deep learning to analyze the real data set of CSE-CIC-IDS2018 network traffic, which includes normal behavior and attacks, and evaluates the deep model long short-term memory (LSTM), which achieves accuracy of detection up to 99%.
Abstract: The evolution of the internet of things as a promising and modern technology has facilitated daily life. Its emergence was accompanied by challenges represented by its frequent exposure to attacks and its being a target for intruders who exploit the gaps in this technology in terms of the nature of its heterogeneous data and its large quantity. This made the study of cyber security an urgent necessity to monitor infrastructures It has network flaw detection and intrusion detection that helps protect the network by detecting attacks early and preventing them. As a result of advances in machine learning techniques, especially deep learning and its ability to self-learning and feature extraction with high accuracy, the research exploits deep learning to analyze the real data set of CSE-CIC-IDS2018 network traffic, which includes normal behavior and attacks, and evaluate our deep model long short-term memory (LSTM), That achieves accuracy of detection up to 99%.

Journal ArticleDOI
TL;DR: In this paper , a comparison between four different DC-DC converters for solar power conversion is presented. And it is observed that the non-inverting buck-boost converter is the finest converter for solar energy conversion.
Abstract: This paper covers the comparison between four different DC-DC converters for solar power conversion. The four converters are buck converter, buck-boost converter, boost converter, and noninverting buck-boost converter. An MPPT algorithm is designed to calculate battery voltage, current of PV array, the voltage of PV array, power of PV array, output power. It is observed that the non-inverting buck-boost converter is the finest converter for solar power conversion. The final circuit design has the results of 12.2V battery voltage, 0.31A current of PV array, 34V voltage of PV array, 23mW power of PV panel, and 21.8mW of output power. The efficiency of this system is nearly 95%. All four circuits are simulated in MATLAB/Simulink R2020b.

Journal ArticleDOI
TL;DR: The final conclusion shows that using new wavelets DHWT better peak signal of noise ratio (PSNR)s can be obtained and that the proposed algorithm fills in better the lack of awareness of the watermark and its strength under different attacks.
Abstract: In this work, new discrete wavelets were derived Hermite polynomials for obtained discrete hermite wavelet transformation (DHWT), and their efficiency for use in image processing is demonstrated by proving the realization of important theorems. Moreover, the role of the new and proposed waveforms in their effective effect in placing the watermark with the color image is clarified, and a program was created using MATLAB software by creating a subprogram for constructing the new wavelet and proving its efficiency with an analytic image. The process is repeated using DHWT to analyze the image. The color image has been subjected to various attacks after which the watermark is retrieved from the image after comparing it with the proposed algorithm and it has proven its power faster and better than the previously suggested methods. The final conclusion shows that using new wavelets DHWT better peak signal of noise ratio (PSNR)s can be obtained and that the proposed algorithm fills in better the lack of awareness of the watermark and its strength under different attacks.

Journal ArticleDOI
TL;DR: The autoregressive (AR) model is the most accurate in predicting the price of Bitcoin, Ethereum, Litecoin, and Tether-token, with 97.21%, 96.04%, 95.8%, and 99.91% accuracy, consecutively.
Abstract: Cryptocurrencies are encrypted digital or virtual money used to avoid counterfeiting and double spending. The scope of this study is to evaluate cryptocurrencies and forecast their price in the context of the currency rate trends. A public survey was conducted to determine which cryptocurrency is the most well-known among Bangladeshi people. According to the survey respondents, Bitcoin is the most famous cryptocurrency among the eight digital currencies. After that, we'll explore the four most well-known cryptocurrencies: Bitcoin, Ethereum, Litecoin, and Tether token. The 'YFinance' python package collects our cryptocurrency dataset, and the relative strength index (RSI) is employed to investigate these cryptocurrencies. Autoregressive (AR), moving average (MA), and autoregressive moving average (ARMA) models are applied to our time-series data from 2015-1-1 to 2021-6-1. Using the 'closing' price and a simple moving average (SMA) graph, bitcoin and tether are identified as oversold or overbought cryptocurrencies. We employ the seasonal decomposed technique into the dataset before implementing the model, and the augmented dickey-fuller test (ADF) indicates too much seasonality in the dataset. The autoregressive (AR) model is the most accurate in predicting the price of Bitcoin, Ethereum, Litecoin, and Tether-token, with 97.21%, 96.04%, 95.8%, and 99.91% accuracy, consecutively.

Journal ArticleDOI
TL;DR: This study develops a customer churn prediction approach with the three intelligent models Random Forest, AdaBoost, and Support Vector Machine that achieves the best result when the Synthetic Minority Oversampling Technique (SMOTE) is applied to overcome the unbalanced dataset and the combination of undersampling and oversampling.
Abstract: In this era, machines can understand human activities and their meanings. We can utilize this ability of machines in various fields or applications. One specific field of interest is a prediction of churning customers in any industry. Prediction of churning customers is the state of art approach which predicts which customer is near to leave the services of the specific bank. We can use this approach in any big organization that is very conscious about their customers. However, this study aims to develop a model that offers a meaningful churn prediction for the banking industry. For this purpose, we develop a customer churn prediction approach with the three intelligent models Random Forest (RF), AdaBoost, and Support Vector Machine (SVM). This approach achieves the best result when the Synthetic Minority Oversampling Technique (SMOTE) is applied to overcome the unbalanced dataset and the combination of undersampling and oversampling. The method on SMOTED data has produced excellent results with a 91.90 F1 score and overall accuracy of 88.7% using RF. Furthermore, the experimental results show that RF yielded good results for the full feature-selected datasets.

Journal ArticleDOI
TL;DR: The objective of the article is to demonstrate the feasibility of a proposal to determine the degree of perception of student satisfaction through the use of data science and natural language processing (NLP), supported by the social network twitter, as an element of data collection.
Abstract: Currently, the data generated in the university environment related to the perception of satisfaction is generated through surveys with categorical response questions defined on a Likert scale, with factors already defined to be evaluated, applied once per academic semester, which generates very biased information. This leads us to wonder why this survey is applied only once and why it only asks about some factors. The objective of the article is to demonstrate the feasibility of a proposal to determine the degree of perception of student satisfaction through the use of data science and natural language processing (NLP), supported by the social network twitter, as an element of data collection. As a result of the application of this proposal based on data science, it was possible to determine the level of student satisfaction, being 57.27%, through sentiment analysis using the Python library "NLTK"; Thus, it was also possible to extract texts linked to the relevant factors of teaching performance to achieve student satisfaction, through the term frequency and inverse document frequency (TF-IDF) approach, these being those linked to the use of tools of simulation in the virtual learning process.

Journal ArticleDOI
TL;DR: In this article , the authors demonstrate the practical aspects of process control theory for undergraduate students at the Department of Chemical Engineering at the University of Bahrain, through retrofitting an existing plate-and-frame heat exchanger unit that has been operated using an analog PID temperature controller.
Abstract: This paper aims to demonstrate the practical aspects of process control theory for undergraduate students at the Department of Chemical Engineering at the University of Bahrain. Both, the ubiquitous proportional integral derivative (PID) as well as model predictive control (MPC) and their auxiliaries were designed and implemented in a real-time framework. The latter was realized through retrofitting an existing plate-and-frame heat exchanger unit that has been operated using an analog PID temperature controller. The upgraded control system consists of a personal computer (PC), low-cost interface using X-transposed-region (XTR) converter, national instruments USB 6008 data acquisition card, and LabVIEW software. LabVIEW control design and simulation modules were used to design and implement the PID and MPC controllers. The performance of the designed controllers was evaluated while controlling the outlet temperature of the retrofitted plate-and-frame heat exchanger. The distinguished feature of the MPC controller in handling input and output constraints was perceived in real-time. From a pedagogical point of view, realizing the theory of process control through practical implementation was substantial in enhancing the student’s learning and the instructor’s teaching experience

Journal ArticleDOI
TL;DR: In this paper , a new design of a viscometer based on the s tokes viscosity measurement method is proposed, which is controlled by using a program installed on the user's smartphone, which also carries out the primary data processing.
Abstract: New design of a viscometer based on the s tokes viscosity measurement method is proposed. The principle of operation of this viscosimetr is based on the use of ball periodic alternated movement in a horizontally positioned cuvette that filled with the test liquid. The movement appears under the in fluence of a magnetic field that created by two electromagnets. Registration of the ball movement inside the cuvette is carried out using an optoelectronic pair. A distinctive feature of the proposed design is control by using a program that installed on t he user's smartphone, which also carries out the primary data processing. Data transmission is carried out over the radio channel using a Bluetooth module. Disposable cuvettes are used for measurements. This approach makes it possible to significantly redu ce both the device production costs and operating costs by eliminating most of the operations for the device preparing for working (the vast majority of existing types of viscometers require thorough flushing of all units in contact with the test medium). In addition, the proposed approach excludes the occurrence of measurement errors associated with insufficiently thorough preparation of the device for operation.

Journal ArticleDOI
TL;DR: An automated technique for skin cancer prediction, detection, and diagnosis including trending noninvasive and nonionizing techniques that combines deep learning methods to diagnose melanoma with high accuracy is introduced.
Abstract: Although melanoma is not the most common type of skin cancer, it is supposed to extend to other areas of the body if not early diagnosed. Melanoma is the deadliest form of skin cancer and accounts for about 75% of deaths associated with skin cancer. The present study introduces an automated technique for skin cancer prediction, detection, and diagnosis including trending noninvasive and nonionizing techniques that combines deep learning methods to diagnose melanoma with high accuracy. Computer-aided diagnosis (CAD) using medical images is utilized to distinguish benign and malignant tumors, which can assist physicians in early identification of symptoms, thus lowering the mortality rate. The CAD system consists of four phases; detection of the region of interest (RoI), using data augmentation techniques, processing RoI using convolutional neural network (CNN) to extract the most important features, and finally the extracted CNN features are input to a support vector machine (SVM) classifier to decode the two classes benign (B) and malignant (M). Two datasets, ISIC and CPTAC-CM, were utilized to train the CNNs. GoogleNet, ResNet-50, AlexNet, and VGG19 were investigated and compared. The accuracy of the proposed CAD system has reached 99.8% for ISIC database and 99.9% for CPTAC-CM database.

Journal ArticleDOI
TL;DR: In this article , a detailed study to compare between the performance of the major types of electric motors that are used in EVs is addressed, and the results of this comparative study are tabulated and by careful consideration for all these results, the appropriate electric motor for EVs has been chosen.
Abstract: Now days, it is vital to use electric vehicles (EVs) instead of traditional cars with internal combustion engines (ICEs) in order to reduce the high level of pollution in the environment, and many researchers are investigating the possible improvements on these vehicles. The main component of EVs is the electric motor and the selection of a motor with high efficiency, excellent dynamic response and high starting torque has a strong effect on the performance of EVs. In addition to that a reasonable price for the electric motor is required. This work focuses on the selection of the most suitable electric motor for EVs. Therefore a detailed study to compare between the performance of the major types of electric motors that are used in EVs is addressed in this paper. The results of this comparative study is tabulated and by careful consideration for all these results, the appropriate electric motor for EVs has been chosen. From the other hand, the artificial intelligent (AI) techniques play a crucial role in the EVs technologies, and several kinds of AI techniques used in EVs applications are overviewed in this work.

Journal ArticleDOI
TL;DR: This work proposes a novel CNN based model for brain tumor classification that reaches highest accuracy 99.8%, and optimal error 0.005 using Adam when compared with other six well-known CNN architectures.
Abstract: Detection and classification of brain tumors are of formidable importance in neuroscience. Deep learning (DL), specifically convolution neural networks (CNN), has demonstrated breakthroughs in the field of brain image analysis and brain tumors classification. This work proposes a novel CNN based model for brain tumor classification. Our pipeline starts with prepossessing and data augmentation techniques. Then, a CNN classification step is developed and utilizes ResNet50 architecture as its core. Particularly, our design modified the ResNet50 output with a global average pooling (GAP) layer to avoid over-fitting. The proposed model is trained and tested using different optimization algorithms. The final classification is achieved using a sigmoid layer. We tested the proposed structure on T1 weighted contrast-enhanced magnetic resonance images (T1-w MRI) that are collected from three datasets. A total of 3586 images containing two classes (i.e., bengin, and malignant) were used in our experiments. The proposed model reach highest accuracy 99.8%, and optimal error 0.005 using Adam when compared with other six well-known CNN architectures.

Journal ArticleDOI
TL;DR: A hybrid bidirectional encoder representation from transformers for text semantics using graph convolutional network and word embedding-based deep learning model to identify near duplicates based on the semantic relationship between text documents.
Abstract: Data deduplication techniques removing repeated or redundant data from the storage. In recent days, more data has been generated and stored in the storage environment. More redundant and semantically similar content of the data occupied in the storage environment due to this storage efficiency will be reduced and cost of the storage will be high. To overcome this problem, we proposed a method hybrid bidirectional encoder representation from transformers for text semantics using graph convolutional network hybrid bidirectional encoder representation from transformers (BERT) model for text semantics (HBTSG) word embedding-based deep learning model to identify near duplicates based on the semantic relationship between text documents. In this paper we hybridize the concepts of chunking and semantic analysis. The chunking process is carried out to split the documents into blocks. Next stage we identify the semantic relationship between documents using word embedding techniques. It combines the advantages of the chunking, feature extraction, and semantic relations to provide better results.