Search

Now and in the future, a face mask is a very important strategy to protect people when a new contagious life threatens disease spread through the air appears. Currently, there is a serious health emergency because of the coronavirus disease 2019 (COVID-19) epidemic. The negative consequences of this pandemic need to be protected in public areas. Numerous methods are advised by the World Health Organization (WHO) to reduce infection rates and prevent depleting the available medical resources in the absence of efficient antivirals. Wearing masks is a non-pharmaceutical strategy to lessen the susceptibility to COVID-19 infection. This research aims to create a face mask identification system that is efficient and uses deep learning, which has proven to be beneficial in many real-world applications. This system has also used a transfer learning method with the MobileNetV2 model to classify people who wear face masks properly, wear face masks improperly, and are without masks. The results demonstrate that the proposed system has an accuracy of 99.4% which is higher than current systems.

This research presents a comparative analysis of two broken rotor bar (BRB) fault identification techniques for closed-loop induction motors (IMs). Both motor current signal analysis and Hilbert transform (HT) rely on spectrum analysis by means of fast fourier transform (FFT). Both approaches have shown their ability to identify BRBs under varying loads. In contrast, the HT is deemed more efficient than the motor current signature analysis (MCSA) approach when the motor is working without load. To maintain a high-performance speed control and to compensate for BRBs effect on the mechanical speed, the approach of control used is direct torque control (DTC). Utilizing a real-time implementation in MATLAB/Simulink with the real-time interface (RTI) based on the dSPACE 1104 board, the efficacy of the two techniques was evaluated.

This paper designs, simulates, and analyzes the S-band microstrip patch antenna (MPA) for wireless applications. FR-4 (lossy) and Rogger RT/duroid, whose dielectric permittivity is 4.3 and 2.2, respectively, have been used as substrate materials. Simulation is done by computer simulation technology (CST) suite studio 2019 software. Simulations with FR-4 material showed that the return loss was -20.405 dB, the gain was 2.592 dB, the directivity was 7.47 dBi, the voltage standing wave ratio (VSWR) was 1.221, the bandwidth (BW) was 0.0746 GHz, and the efficiency was 34.69%. Also, Rogers RT/duroid material gives results of a return loss of -12.542 dB, a bandwidth (BW) of 0.0349 GHz, a gain of 8.092 dB, a directivity of 8.587 dBi, and an efficiency of 94.24%. The main goal of this antenna is to have a low return loss while getting as close as possible to a VSWR of 1. This will improve the antenna's gain, directivity, and efficiency compared to other antennas. Copper was used to make the patch and the ground, which were 0.35 mm and 0.0077 mm thick, respectively. The results obtained from the proposed antenna were better than those previously published in various in modern scientific journal and conference papers.

XGBoost is a highly effective and widely used machine learning model and its hyperparameters take an important role on the performance of the model. This paper presents a new grid search (GS) algorithm for obtaining optimal hyperparameters of the XGBoost model based on the median values of their error loss. A benchmark method used to evaluate the proposed and original GS algorithms is introduced. Datasets with measured daily electricity demand load values of Ho Chi Minh City, Vietnam and Tasmania state, Australia are analyzed for the performance of both algorithms. The error metrics, mean squared errors (MSEs), of the proposed algorithm are found to be 2,282 MW and 501 MW that are smaller than those of original algorithms, which are 2,424 MW and 537 MW in case of Ho Chi Minh City and Tasmania state, respectively. These results then verify the accuracy of the proposed algorithm.

According to the American cancer society, breast cancer is one of the leading causes of women's mortality worldwide. Early identification and treatment are the most effective approaches to halt the spread of this cancer. The objective of this article is to give a comparison of eight machine learning algorithms, including logistic regression (LR), random forest (RF), K-nearest neighbors (KNN), decision tree (DT), ada boost (AB), support vector machine (SVM), gradient boosting (GB), and Gaussian Naive Bayes (GNB) for breast cancer detection. The breast cancer Wisconsin (diagnostic) dataset is being utilized to validate the findings of this study. The comparison was made using the following performance metrics: accuracy, sensitivity, false omission rate, specificity, false discovery rate and area under curve. The LR method achieved a maximum accuracy of 99.12% among all eight algorithms and was compared to other comparable studies in the literature. The five features chosen are used to calculate the model's fidelity-to-interpretability ratio (FIR), which indicates how much interpretability was sacrificed for performance. The uniqueness of this work is the explainability approach taken in the model's performance, which aims to make the model's outputs more understandable and interpretable to healthcare experts.

Almost all Bengalis who own smartphones also have social media accounts. People from different regions occasionally employ regional Slang that is unfamiliar to outsiders and confuses the meaning of the sentence. Nearly all languages can now be translated thanks to modern technology, but only in very basic ways, which is a concern. Bengali Slang terms are difficult to translate due to a dearth of rich corpora and frequently occurring new Slang terms developed by people, making it impossible for speakers of other languages to understand the context of a sentence in which Slang is used. We developed a solution to this issue. To create models that can detect Bengali Slang terms from social media, we gather various Slang phrases from various regions and develop a modest corpus. Our suggested method nearly always succeeds in extracting Bengali Slang terms from fresh material. We create a total of 7 supervised models and assess which is the most effective for our study. One of them has a 70% accuracy and 86% recall rate for successful identification. Our models may be linked to the social media platform's backend to restrict the use of Bengali Slang in posts, blogs, comments, and other areas.

Electric vehicles (EVs) are now an important part of the automotive industry for two main reasons: decreased reliance on oil and reduced air pollution, which helps us contribute to the development of an environmentally friendly environment. EV buyers examine overall vehicle mileage, recharge time, vehicle mileage after every charge, batteries charging/discharging security, lifespan, charged rate, capability, and temperature increase. A new improved pulse charging technique is proposed, in which the battery is charged using proportional integral derivative (PID) control action and a neural network. A PID controller is used to develop the charging unit in this design. The feed forward neural network was used to determine the values of the PID control parameters. The battery management system (BMS) ensures that this designed battery charging system takes less time to charge the battery efficiently. The system is built with MATLAB/Simulink.

An abstract is often presented separately from the article, so it must be able to in the following article the use of the mobile application is recommended as a tool that serves public safety because currently crimes of extortion and fraud are committed by making false calls to people's mobile devices. Therefore, the objective of this research is to help families with their welfare and safety and motivate the use of mobile applications. In the present work the situation, task, action, dan result (STAR) methodology was applied to elaborate the present work, this technique will allow improving the difficulties of the people. This methodology is very important because it is used to evaluate the circumstances in which people find themselves, a sequence must be followed to achieve the proposed objectives. The result obtained is an average of 84.5% on the design of the mobile prototype; being approved by the experts. The beneficiaries of the research are citizens through the mobile application.

With time, the device's reliance on wireless communication and its users grows tremendously. The ultrawideband (UWB) technology offers a 7.5 GHz uncontrolled bandwidth. Because it allows for larger data rates over a short distance, UWB technology is the current and future requirement of new generation mobile networks. As a result, a novel octagonal slot circular compact UWB antenna with detailed frequency and time-domain analysis is proposed in this research. Throughout the UWB range, the hexagonal-shaped circular radiator aids in reaching better S11 parameters (S11

The brushless direct current (BLDC) motor is characterized by high torque, which made it widely used in many industrial applications. To improve the working performance of the BLDC motor, the addition of controllers such as proportional integral derivative (PID) is adopted. To obtain high-performance controllers, the design process is adopted to develop a suitable algorithm. The genetic algorithm (GA) was chosen to tune the PID controller and get suitable parameters for each of kp, ki and kd with self-tuning. The design process is based on BLDC motor control using the GA to tune the traditional PID controller. Simulations were carried out for three cases including the absence of controllers secondly, by using the traditional control unit and finally with the GA. The integral time absolute error (ITAE) type error control standard for BLDC motor control system was selected. After conducting the simulation, the results demonstrated the superiority of the GA over the traditional ones in terms of response speed, (stability, rise, and settling) time and percentage overshootas details will be mentioned the model in the subsequent paragraphs of the research, finally the simulation results indicate the development and improvement of BLDC motor operation and performance during real time.

An incursion into the computer network or system in issue occurs whenever there is an attempt made to circumvent the defences that are in place. Training and examination are the two basic components that make up the intrusion detection system (IDS) and each one may be analysed separately. During training, a number of distinct models are built, each of which is able to distinguish between normal and abnormal behaviours that are included within the dataset. This article proposes a combination of ant colony optimization (ACO) and the firefly approach for feature selection. The final outcome of giving careful thought to the selection of features will eventually result in greater accuracy of categorisation. When classifying various sorts of features, we make use of a wide variety of machine learning (ML) algorithms, including AdaBoost, gradient boost, and Bayesian network (BN), amongst others. The tests and assessments made use of data obtained from three distinct datasets, namely NSL-KDD, UNSW-NB15, and CICIDS 2017. The degree of performance of an individual may be broken down into its component parts, which include the F1 score, accuracy, precision, and recall. Gradient boost performs far better when it comes to recognising and classifying incursions.

This paper presents a compact graphene-based multi-input multi-output (MIMO) antenna for wireless communications operating in frequency band (0.1-10) THz. This work has been performed with four ports microstrip antennas based on 37×88 μ𝑚2, a silicon dioxide (𝑆𝑖𝑜2) substrate and copper on the ground layer, with high isolation by a series of unit cells of graphene selected between adjacent patches to reduce the transmission coefficient and antenna size. Graphene's chemical potential will change by changing the connected DC voltage, leading to bandwidth and resonant frequency variation. The simulation has a reflection coefficient is less than -10 dB at (4.5-10) THz of the frequency scale, mutual coupling (

Recently, pipelines have replaced more carbon-intensive transportation methods making them more environmentally friendly for transporting energy and water supplies. However, pipelines can pollute the air, water, soil, and climate when they leak, causing economic, and environmental damage. Pipeline online monitoring provides data analysis and suitable controlling strategies to contain the risk. This paper proposes a three-dimensional numerical model simulation taking advantage of the fluids moving through pipelines at specific speeds. The transport speeds depend on many conditions, such as pipe diameter, the pressure through which the fluid is being transported, and other factors, such as terrain's topography and viscosity of the fluid. Under these conditions, the inspection approach uses a self-charging movable ball. The sensors inside the ball capture data as it travels through the pipe. The simulation focuses on spherical flow and pipe noise with and without leakage based on the COMSOL software platform. The paper shows the effect of several parameters, including leak location, sensor placement, ball diameter, sound pressure level propagation along a pipe and around the sphere, velocity, and temperature distribution that give the background for future smart ball design in a promising practical pipeline test project.

Most of the human work has been replaced by computers in recent years. With the rise of mobile technology and Internet access, recent developments in machine learning (ML) have designed many algorithms to solve diverse human problems. However, due to a lack of exposure to image processing, identification technology is still not widely employed in Malaysia. This paper outlines the steps involved in creating a mobile application for coin identification using ML. In the literature review, the history of the coins is studied in more depth and the features of already existing coin identification mobile applications are compared by their advantages and disadvantages. In addition, using the neural network model, the classification accuracy of successfully identified coins is recorded and disclosed. This study includes the limitations of the prototype mobile application and future improvements that could be added.

The economic power dispatch (ED) is considered a critical optimization issue in the power system and microgrid. There are several objectives through the economic load dispatch issues such as reducing the operating cost, total emission, or start-up operations. This paper presents a Chameleon swarm algorithm (CSA) for determining the optimal ED of distributed energy resources (DER) in the microgrid. The proposed technique numerically mimics and executes chameleons' behavioral processes to their quest for food, such as their action for rotating their eyes to identify and grab prey using the speed of their sticky tongues. In this study, the CSA has been applied to obtain the optimal power dispatch from DER using the photovoltaic (PV) plants, combined heat power (CHP) systems, and traditional diesel generators. The obtained results from the simulation are compared with the conventional metaheuristic algorithms which have been used in previous studies, such as particle swarm optimization (PSO), genetic algorithm (GA), and artificial bee colony (ABC). Experimentally, the proposed algorithm for solving the ED problem determined the best value of the power dispatch and high performance compared to other metaheuristics methods.

Diponegoro University's Rectorate building uses electricity from the National Electricity Company with a S2 social subscription type of 105 kVA. The designed solar power plant has a capacity of 25 kW, or 25% of the installed electrical capacity. This research aims to compare the solar panels and inverter configurations that will be used in solar power plants. Moreover, this study aims to find out which configuration will provide the best results and the biggest savings. Technical analysis is carried out with the photovoltaic system (PVSyst) software to calculate the energy produced by solar panels, inverter losses, and other results. On the other hand, economic analysis is carried out with RetScreen software to calculate net present value (NPV), benefit cost ratio (BCR), and payback period (PP). Based on the PVSyst simulation results, the estimated energy production for each variant is 39,684 kWh; 39,633 kWh; 39,507 kWh; and 39,446 kWh. The first variant has the biggest performance ratio value of 84.1%. Based on the Retscreen calculation result, the third variant has an NPV value of $22,698, a BCR value of 2, and a PP of 8.7 years, which has the best result and the highest advantages.

The increasing implementation of autonomous robots in industries and daily life demands the development of a robust control algorithm that enables robots to perform their tasks successfully. Critical tasks such as rescue missions and area exploration require robots to work cooperatively in a formation to accomplish the tasks quickly. Moreover, the existence of obstacles in the environment requires all the robots' to rapidly process environmental changes to maintain the formation pattern. Thus, this paper introduces a distributed robot formation control system using the consensus algorithm that enables a group of robots to establish and maintain formations using only the local information of the robots. Furthermore, an obstacle avoidance algorithm based on the distance and angle between robots and obstacles is introduced to ensure safe navigation for the group of robots. The algorithm's effectiveness is demonstrated by a multi-robot system with randomly generated starting positions and velocities, where it is shown that the robots can agree on the control variables and establish the required formation while also avoiding obstacles in the environment.

The utilization of a microgrid with a photovoltaic (PV) and wind generation system presents a challenge due to their voltage and power output variations. This problem is majorly addressed within the converter section of the microgrid using maximum power point tracking (MPPT) algorithms and voltage regulation strategies. This paper presents an interleaved boost converter (IBC) modeling and voltage control using a hybrid adaptive neuro-fuzzy inference system-proportional plus integral plus derivative (ANFIS-PID) controller for an off-grid microgrid. The modeling used the interleaving technique to obtain the microgrid’s transfer function (TF) and case study simulation models within MATLAB and Simulink environments. The performance of the ANFIS-PID controller, which regulates voltage in the microgrid, was compared to that of the traditional proportional integral (PI) controller. Results indicated that the hybrid ANFIS-PID controller performed better than the PI controller in terms of reduced settling time, overshoot, rise time, and the ability to address the nonlinear dynamics of the microgrid.

Food delivery methods are at the top of the list in today's world. People's attitudes toward food delivery systems are usually influenced by food quality and delivery time. We did a sentiment analysis of consumer comments on the Facebook pages of Food Panda, HungryNaki, Pathao Food, and Shohoz Food, and data was acquired from these four sites’ remarks. In natural language processing (NLP) task, before the model was implemented, we went through a rigorous data pre-processing process that included stages like adding contractions, removing stop words, tokenizing, and more. Four supervised classification techniques are used: extreme gradient boosting (XGB), random forest classifier (RFC), decision tree classifier (DTC), and multi nominal Naive Bayes (MNB). Three deep learning (DL) models are used: convolutional neural network (CNN), long term short memory (LSTM), and recurrent neural network (RNN). The XGB model exceeds all four machine learning (ML) algorithms with an accuracy of 89.64%. LSTM has the highest accuracy rate of the three DL algorithms, with an accuracy of 91.07%. Among ML and DL models, LSTM DL takes the lead to predict the sentiment.

Wireless power transfer (WPT) is a technology used to transmit power using air as it medium of transfer. The function of the WPT is similar to a transformer. The power provided on the primary side will be transferred through air to the secondary side. The performance of the WPT is crucially depends on the air gap length, 𝛿 that separates primary and secondary side. In this paper discusses the performance of WPT using series-to-series topology. The performance of the WPT was estimated using finite element analysis (FEA). During the study, focus was given to effect of turn ratio, a, air gap length, 𝛿 and capacitor value at primary Cp, and secondary, Cs winding to voltage ratio of the WPT. The air gap length, 𝛿 was set to 1 and 2 mm while the capacitors were set depend on the ratio of primary to secondary winding capacitor, Cp/Cs. The WPT performance also being tested under no-load and loaded operation to observed it effect. As a result, the WPT with turn ratio, a at 0.37, air gap length, 𝛿 at 1 mm and ratio of primary to secondary winding capacitor, Cp/Cs at 0.5 produce the best voltage ratio compared to other settings.

Presently, fast proliferation of information enforces novel challenges on content management. Further, computerized audio classification along-with content description is considered as valuable method to manage audio contents. In general, classification involves two steps. First, is the processing of accessible data in economical ways to deliver explanatory features. Second is how accurate features of undetermined tests is evaluated to choose classifier. In this paper, k-neighbor algorithm with machine learning is proposed for feature extraction as well as content classification/description. This algorithm enhances Quality of Service parameters of classifiers. Here, development of training as well as testing data set is developed to increase the classifier accuracy. A test engine set-up bed using simulation tool MATLAB is designed to estimate the implementation performance of the algorithm. A range of features are studied to evaluate effectiveness in terms of accuracy, zero crossing rate (ZCR) and spectral roll frequency. From the experimentation results, it is observed that the proposed algorithm can achieve accuracy of 95.8% for 2 sec window length as compare with k-neighbor algorithm. A total enhancement of 11% is achieved with cross validation error of 29.6. A superior assortment of training fabric to extract few additional useful features can enhance accuracy further.

Due to the increased attacks on different applications, data security has become crucial. Many modes can be used to operate the advanced encryption standard (AES), some of which provide integrity, and some outperform other modes in security and simplicity. In this paper, the chain block cipher (CBC) mode has been modified to provide more security to the encrypted data by making it robust against the bit-flipping attack and adding an integrity approach using the keyedhash function. In addition, using the keyd-hash function increases the number of keys needed in CBC-AES to two keys, and this can make the proposed model more secure against bruteforce attacks and Grover’s quantum search algorithm.

Software defined network (SDN) is a new approach concept for planning, developing, and operating computer networks. Routing is the process of selecting paths on a network system to send or forward packets to the destination network. This study aims to obtain the results of the calculation analysis using the k-nearest neighbor (k-NN) method as the implementation of the recommendations. The results of the analysis use a mesh topology design approach with predicted values of throughput, jitter, delay, and packet loss. This value is used as a recommendation to the network manager to determine the best path. The best path selection from the analysis results is i) path-1 (very good) which includes switch 1, switch 2, and switch 4; ii) path-2 (good) to switch 1, switch 3 and switch 4 switch 4; iii) channel-3 (moderate) through switch 1, switch 2, switch 3 and switch 4; and iv) channel-4 (bad) through switch 1, switch 3, switch 2, and switch 4. While the calculation using the confusion matrix is accuracy=72.31%, precision=96.08% and recall=87.84%.

In the realm of power line communication (PLC), impulsive noise is often regarded as the most difficult challenge to face in PLC. The impulsive noise effects are reduced by employing a combined adaptive least mean square (LMS) filtering and Reed Solomon (RS) coding. As a result, the bit error rate (BER) and throughput performance over this channel are enhanced. The results of a MATLAB computer simulation indicated that a significant improvement is achieved by utilizing the LMS adaptive filter in conjunction with the RS code. This is in contrast to a system that utilizes RS code alone or a system that utilizes the conventional time domain clipping approach.

This paper explains a simple and efficient methodology for calculating monthly energy losses (EL) using the load loss factor technique and a representative composite load profile. One of the important benefits of the proposed work is a simpler, more efficient and less rigorous method to estimate the system-wide energy loss of an extensive distribution network with reasonable accuracy. The sum of all EL provided by each feeder section is used to calculate the total feeder EL. A base case feeder with a typical cable type and power factor is used to generate regression equations, a peak power loss function to estimate the EL. A case study is then used to show the models and techniques that have been established. The result indicates a high level of agreement with the time-series load flow simulations (smaller than 10% deviations). With this model, an approach to estimate the EL of all radial feeders of various configurations and characteristics could be extended and implemented. The spreadsheet approach is ideal for completing a quick energy audit of existing distribution feeder EL and determining the sensitivity of distribution network efficiency to changes in feeder sections and load characteristics.