In this article, we propose a new tutoring strategy to combat school dropout in Morocco. This strategy is based on a collaborative approach involving educational administration and teachers at the national level to ensure equity and equal opportunities for all Moroccan students, on the one hand, and the quality of the training, on the other. Its implementation will be ensured through a computerized system based on the student’s learning and evaluation portfolios in order to provide individualized assistance, taking into consideration his/her shortcomings and didactic needs. In this work, after defining tutoring and its types, we will present the Moroccan ministerial strategy in terms of tutoring by discussing the relevance of the tutoring systems prevailing in Morocco and the existing platforms accredited by the Ministry of Education. Then, we will study the portfolio concept and its forms, in addition to some criticisms established on this tool in order to identify the components, ensuring the quality of the tutoring to be taken into account in our proposed IT solution. Finally, we will study in detail the design of our system by modeling the evaluation and remediation processes and examining its functional behavior.

Read more…

This paper deals with the analysis of the dynamic linkage, co-movement between COVID-19 out- break situations and German stock market. Firstly, Markov Regime Switching Analysis(MRSA) is proposed and employed to investigate the situations in the pandemic, as to catch the dynamics of how the daily number of the newly-infected changes, and also to assess the impact of the pandemic situations on German Market. Secondly, we compute the log growth rates of the weekly new cases and the log-returns of weekly DAX index, then fit the GARCH models to both of them to acquire their volatilities. We then employ the MRSA model once more to expose the dynamic linkages and co-movement between these two volatilities series. Through our empirical analyses, we find that GARCH models can capture the dynamics of stock returns and the growth rates. On the other hand, the MRSA models work well to identify the dynamics between different regimes with different states in dealing with the volatilities obtained from the estimated GARCH models. Our proposed econometric methods are highly practical, it indicates the possibility of replicating the results obtained in this study to assess the impact of other epidemics and negative factors on economic activities. Knowing what may happen during a pandemic, more effective measures and actions can be taken to protect people while dealing with another pandemic in the future.

Read more…

Limited interactive communication modes between students and teachers in online environments may lead to teachers misinterpreting or overlooking student needs during online teaching. Students learning online may also hesitate to make their needs known even when latent desires in teaching flow, pacing, and review, may be beneficial to the quality of the learning experience. The objective of the study is to construct and test models to infer student needs based on the facial expressions of students while they are learning online. Several Random Forest models were constructed to infer the reported conditions and tested using facial expression data extracted from the videos as action units in Facial Action Coding System (FACS). Exploratory Factor Analysis (EFA) was adopted to extract and combine the highly-related facial action units for building the training and testing data. The testing of the inference model yielded a result of 0.028 on the mean average error (MAE). This result suggests these methods would contribute to the development of improved online learning systems that assist teachers in understanding in real-time how students are responding to a lecture or other classroom experience.

Read more…

In this paper we present a measurement system that is able to evaluate radar algorithms for vital signs sensing applications. For such medical applications, it is crucial to develop robust and reliable algorithms that are tested in a laboratory environment. The presented measurement system generates reproducible vital sign micro movement and dynamic clutter using loudspeakers to replicate realistic scenarios with two moving objects. It is described how realistic vital sign movement patterns are prepared using signal synthesis or recorded measurements, e.g. from a published dataset. The capability of the system to evaluate radar algorithms is demonstrated by investigating the impact of a beamforming algorithm on dynamic clutter. During the measurements presented in this paper, one loudspeaker replicates different vital sign movement patterns and the other loudspeaker creates dynamic clutter. It is shown that a digital beamforming improves the dynamic clutter rejection and leads to a better quality of the radar phase signal.

Read more…

Indoor positioning is a complex issue with many, heterogeneous application cases, each one presenting different requirements and environments. In such a complex ecosystem, an agile taxonomy is needed to be able to select a proper solution for a given scenario, as well as practical recommendations for the most used solutions. Besides providing these tools, we analyze a real-world scenario and its requirements, selecting a practical solution and evaluating it together with its implications and consequences, providing a reference guideline for practical applications of indoor positioning.

Read more…

People with visual impairment face daily struggle of navigating through unfamiliar places. This problem mainly caused by their lack of spatial awareness, i.e., the ability to estimate the distance between themselves and their surroundings. In order for visually impaired people to navigate independently, an effective navigation aid is required. The proposed navigation aid device utilizes depth camera to collect visual information of surrounding objects. Then, it represents the obtained visual data into stereophonic sound to notify the user directly through an audio device. The aid device is designed to be portable, comfortable, and easy to use. It can further be developed and upgraded to suit the needs of visually impaired users. Designed to be wearable, this proposed device was tested and received excellent score in portability, comfortability, and ease of use. The subjects were able to detect the position of obstacles in front of them with 92.47% accuracy, and could also estimate the distance of the object with Mean Absolute Error of 0.8. Examination on their navigation ability indicated that the subjects could stop before collision with an object and maneuvers through the gap between two parallel obstacles.

Read more…

This paper extends the idea of creating a Quantum Machine Learning classifier and applying it to real weather data from the weather station behind the Pa Sak Jonlasit Dam. A systematic study of classical features and optimizers with different iterations of parametrized circuits is presented. The study of the weather behind the dam is based on weather data from 2016 to 2022 as a training dataset. Classification is one problem that can be effectively solved with quantum gates. There are several types of classifiers in the quantum domain, such as Quantum Support Vector Machine (QSVM) with kernel approximation, Quantum Neural Networks (QNN), and Variational Quantum Classification (VQC). According to the experiments conducted using Qiskit, an open-source software development kit developed by IBM, Quantum Support Vector Machine (QSVM), Quantum Neural Network (QNN), and Variable Quantum Classification (VQC) achieved accuracy 85.3%, 52.1%, and 70.1% respectively. Testing their performance on a test dataset would be interesting, even in these small examples.

Read more…

In conjunction with psychological stress, physiological indicators such as heart rate (HR) and heart rate variability (HRV) are frequently employed. This study uses a substitute for heart rate variability (HRV) known as short-term pulse rate variability (PRV) to evaluate emotional changes. We examined sixteen college students using a low-cost photoplethysmograph and obtained a short-term PRV reading from one of their index fingers. Each PRV’s parameters during resting condition were established using a particular Trier Social Stress Test (TSST) and divided into four phases (R1: baseline rest, R2: anticipatory stress, R3: stressful event, and R4: recovery period). The Positive Affect and Negative Affect Schedule (PANAS) questionnaire was used to assess the participants’ moods during the experiment. The psychological assessment based on PANAS shows that negative affect tends to increase along the TSST procedure, especially from the baseline rest (R1) to the stressful event (R3), even though it is not statistically significant (p > 0.05). The physiological assessment using PRV revealed that between R1 and R3, the short-term SDRR, pNN50, RMSSD, LF, HF, total power, SD1, and elliptical area of PRV tended to rise considerably (p < 0.01). The properties of PRV show that the heart rate fluctuation also represents psychological changes. We concluded that applying the TSST procedure to induce stress modulates the features of PRV, particularly the time and frequency domain variability properties. Observed patterns following stressful events (interview sessions) indicated an increase in PRV values, mainly the RMSSD, HF, SD1, and elliptical area (p < 0.001). Caution should be applied while perceiving physiological alterations as an immediate sign of mental threats. Nonetheless, these alterations are likely caused by the association between stress and negative emotions.

Read more…

Many millions of people have adverse effects on their lives, both socially and economically, when a power outage occurs. Along with other electrical events, the lack of Situational Awareness (SA) is one of the root causes of power system outages. In order to promote adequate situational awareness, both power system and microgrid interfaces should communicate the necessary information in a helpful format at the right time. It is particularly difficult to present this information to microgrid operators in an accessible and timely manner. A human-centered design approach is used to develop two human-machine interfaces for the Potsdam, NY microgrid project. A detailed description of the process is provided in this extended paper.

Read more…

Blockchain technology has been successfully applied in many fields for immutable and secure data storage. However, for applications with on-chain big data, blockchain scalability remains to be a main concern. In this paper, we propose a novel scalable storage scheme, called HistoChain, for a consortium blockchain network to manage blockchain data. We use a current blockchain and historical blockchains to store on-chain big data, where the current blockchain and the historical blockchains store data from recent years and earlier years, respectively. Both the current blockchain and the historical blockchains are maintained by super peers in the network; while regular peers manage only the current blockchain and can retrieve historical data by making queries to the super peers. We present procedures for generating historical blockchains, dynamically balancing the data retrieval workload of super peers, and concurrently retrieving historical blockchain data in response to queries. We further provide a case study of healthcare data storage using a consortium blockchain, and the simulation results show that our scalable HistoChain storage scheme supports efficient access and sharing of big data on the blockchain.

Read more…

The detection and classification of fish is a prevalent and fascinating area of study. Numerous researchers develop skills in fish recognition in both aquatic and non-aquatic environments, which is beneficial for population control and the aquaculture industry, respectively. Rarely is research conducted to optimize the recognition of fish with diverse backgrounds. This paper proposes a method for fish recognition that uses the landmarking technique to optimize YOLO version 4 to detect and classify fish with varying background conditions, making it applicable for both underwater and terrestrial fish recognition. The proposed procedure was evaluated on the Bringham Young University (BYU) dataset containing four different fish species. The final test results indicate that the detection accuracy had reached 96.60% with an average confidence score of 99.67% at the 60% threshold. The outcome is 4,94% better than the most common traditional labeling method.

Read more…

Currently, the quality and quantity of product must be inspected before transporting. Currently the popular unsealing box product inspecting is performed by weighing the box where the errors occur according to the tolerance of the weighting machine and tolerance weight of the product. On the other hand, the quantity of product can be inspected automatically using the image processing and recognition where the sealed box needs to be unpacked which is difficult to be implemented in practice. Then, the error in product transportation causes a loss profit of for the vendor and losing the reliability from customers. In this paper, we proposed a new volume estimation technique to estimate the product quantity in the sealed box using RSSI with machine learning for improving the monitoring accuracy. The proposed system includes one transmitter on the top and five receivers at bottom of the package. Based on practical environment, we align the product’s pattern inside the boxed package into two cases including horizontal/vertical aligned pattern and random pattern. In the experiment, we compare the volume estimation accuracy of five machine learning techniques including linear regression, logistic regression, Naïve Bayes, KNN, and NN. From the results, the NN method provide the highest volume estimation accuracy among others and consumes the shortest estimation time. NN presents accuracy as 99.4% and consumes 6.51 milliseconds of estimation time. Moreover, for protecting the products from the delivery process, shockproof material must be put to cover the product in the box. Three shockproof types are considered in our experiment such as bubble wrap, paper, and airbag and our proposed system is considered all kinds of shockproof situations. The suggested method can estimate the volume of products without necessitating their opening or destruction. The suggested approach is also resistant to the impacts of packaging cushioning material.

Read more…

The main contradiction identified in the study is that the existing scientific and methodological solves of economy development management processes does not create prerequisites for improving the efficiency of their work, the introduction of progressive technologies for material and moral stimulation of the work of performers and administrative and managerial personnel, advanced social mechanisms for country’s economy development and social security employees. Economic and mathematical modeling of the complex system of social financing of enterprises and the economy of the country, scientifically sound personnel policy and the system of motivation of performers and administrative and management personnel is an important and urgent problem. The purpose of the study is to develop and implement an economic and mathematical model of a comprehensive system of social financing of enterprises and the economy of the country, optimizing the wages of the workforce, consistent with revenue growth, deductions for the development of the enterprise (relevant for the employer and the entire workforce), taxation and social contributions (important for the state). The results of the studies conducted and presented in this article allow us to conclude that the proposed social financial technologies for the development of enterprises and the economy of Russia, make it possible, at quite achievable rates of growth of gross domestic product (revenue of enterprises) by 3% per year, to ensure an increase in the wages of working citizens for 5 years by 34 %, which will make it possible to practically end poverty, and to increase contributions to the development fund over 5 years by 16%. Starting from 2026, increase receipts from income tax, tax on profit rate and value added tax and bring this growth to 30% by 2041, which will allow the state to solve many social problems.

Read more…

This paper describes the design of a phase shifter with electrically adjustable parameters employing only one voltage differencing gain amplifier (VDGA) and one floating capacitor. This circuit requires no external resistors, resulting in a resistorless design and a low component count. The proposed circuit implements a first-order all-pass filter response with electronic control of its passband gain, pole frequency, and phase difference via bias current modification. Non-ideal effects of the VDGA on the phase shifter circuit are also examined. PSPICE simulation results using TSMC 0.25-m real process parameters and practical test results using readily available LM13700s are incorporated to validate the theoretical conclusions. The results indicate that the simulations and experiments yielded phase shift deviations of 2.22% and 3.11%, respectively. The pole-frequency errors for simulations and experiments were 0.31% and 0.63%, respectively. The applicability of the suggested phase shifter is illustrated by the design of the voltage-mode quadrature oscillator.

Read more…

In this research paper, a technical and economic-environmental study was developed to investigate the possibility of establishing various hybrid power systems with different operation modes. Grid-connected and standalone hybrid systems (solar-wind with storage batteries and diesel generators) have been realized in order to carry out a comparative analysis study of two configurations. These systems have been investigated through the Hybrid Multi-Energy Resource Optimization software (HOMER), which calculates pollutant gas emissions, simulates and optimizes energy consumption based on energy demand and resources. As part of the economic analysis, the internal rate of return, the net present value and the payback period were estimated. Both configurations have been developed to meet the power consumption of an audiovisual system. The results obtained show that the first system is the most cost-effective to establish, considering in particular the energy production potential and gas emissions. It can be stated that the proffered grid-connected hybrid system is the most suitable and cost-effective system as it offers several advantage. The total net present cost is $5.425million and the total energy cost is approximately $0.0686 per unit.

Read more…

In the field of micro-LED displays, there is strong demand for red phosphors with high photoluminescence intensity, high color purity, and small particle size. Here, we focus on Eu(III) complexes because they produce sharp photoluminescence spectra with high color purity and can be dissolved in polymer, enabling a reduction in particle size to the molecular level. We have previously established novel molecular design concepts for Eu(III) complexes by coordinating two different phosphine oxide structures to one Eu(III) ion in order to enhance photoluminescence intensity and increase solubility in polymers and solvents. Many Eu(III) complexes have been developed based on these concepts and their photoluminescence properties investigated. Eu(III) complexes with two different phosphine oxide structures are important candidates for red phosphors in micro-LEDs.

Read more…

Medical adherence is a major concern globally and is increasing with improved access to medication. Unfortunately, patients taking multiple medications often struggle with confusion about when and how to take each medication. To address this issue, an inexpensive domestic device has been proposed to improve medication adherence. This device uses Wi-Fi and cellular Internet of Things (IoT) integration to dispense medication at the prescribed times, making it suitable for use in both home and long-term care settings. The device also includes a web interface that allows users to control the device and make changes to dosage and other related information. Additionally, the device features an intricate system for sorting pills to ensure accurate and efficient medication delivery. Automating medication taking through this device can improve patient adherence and overall health outcomes, which could significantly impact public health and quality of life for patients struggling with medication adherence.

Read more…

The COVID-19 pandemic has caused a substantial death toll throughout the world. The pandemic has created a threat to public health, the economy, food systems, and the workplace. An increased reprioritization of health expenditure towards COVID-19 vaccines will impact on allocations to other medical facilities. In developing countries, hospitals shortage the infrastructure to facilitate patients. Therefore, traditional checkups and clinics are not practical. According to research done in this article, 95 percent would prefer telemedicine and telehealth rather than conventional inspections. Even though smart healthcare technology has been implemented, it does not show adequate effectiveness when commercialized. Therefore, in this paper, a microcontroller-based, low-cost, automated, real-time system has been proposed to give a convenient solution for measuring the vital signs of the body. In this project, Multiple sensors with a microcontroller were intended to measure heartbeats per minute, Oxygen Saturation, body temperature and electrocardiogram of a patient at home without going to a hospital. The developed system indicated very less percentage error in temperature measurement and was able to maintain high accuracy on Beats per Minute, Oxygen Saturation and Electrocardiogram. This approach provides a feasible solution for both patients and medical professionals.

Read more…

As the significance of new and renewable energy is highlighted, land-based solar power generation has seen remarkable progress. This study utilizes the Strength Reduction Method in DIANA, a numerical analysis software, to assess the stability concerning various variables, such as slope angle, water level, water depth, and changes in material properties, with a focus on the factor of safety (FOS). This research aims to address the safety concerns of land-based solar power generation facilities installed on varying terrains. The standardized slope permit criteria for solar panels in mountainous areas were revised to a steeper 15 degrees, however, this shift necessitates further investigation as it is not grounded on ample research. Findings from this study revealed a decreasing trend in the factor of safety (FOS) with the increasing slope angle and an inverse proportionality between the factor of safety (FOS) and groundwater level. Moreover, we analyzed the factor of safety (FOS) concerning water level and soil strength. Future studies will incorporate additional factors for a more comprehensive safety factor (FOS) assessment.

Read more…

Over the past decade, Bitcoin’s unprecedented performance has underscored its po-sition as the premier asset class. Starting from an insignificant value and reaching an astounding high of around 65,000 U.S dollars in 2021 – all without a central con-trolling authority – Bitcoin’s trajectory is undoubtedly a historical feat. Its intangible nature, initially a subject of skepticism, has turned into an attractive quality, leading many investors to allocate a significant portion of their portfolios to Bitcoin. The traditional banking and investment sectors have also turned their attention to Bitcoin’s exponential growth. Concurrently, research on macro-economic variables and investor sentiment explaining Bitcoin’s price fluctuations has seen considerable development. However, there is a notable absence of studies leveraging On-Chain Data, information derived from transaction data in Bitcoin’s blockchain network. This paper fills this gap by using LSTM (Long Short-Term Memory), a technique widely utilized for time-series data prediction, in conjunction with On-Chain Data, to predict Bitcoin prices.

Read more…

Among the development of technology, a large number of medical devices have been implemented in various forms for therapy and treatment. Remote controllability, real-time response, small size, and non-toxicity of the devices are the critically requirement to be operated in the blind, unstructured and fluidic environments of biomedical regions. Untethered soft swimming milli-robots have been developed to fulfill the remote operation in such that region under magnetic navigation. A motor-less mechanism of the soft robots utilizes a high degree of freedom provided by magnetic compliance of the deformable structure with a minimal control of the oscillating magnetic field. Theoretically, magnetic property of the soft robots is defined by magnetic moments consisting of orientation and strength. Orientation of magnetic moments can be defined by magnetizing technique, and strength of magnetic moments is obtained by their quantity in the magnetic structure. Herein, this work investigates how magnetic moments through the details of magnetic orientation and quantity affects swimming behavior and performance. The soft robots are fabricated with elastomer embedded with NdFeB microparticles to obtain three types of distinguish magnetic property in the deformable structure; the I robot has non-uniform magnetic orientation and uniform magnetic strength, the II robot has uniform magnetic orientation and non-uniform magnetic strength, and the III robot has non-uniform magnetic orientation and non-uniform magnetic strength. The results interestingly report that each type of robot’s property functions mechanism and benefits swimming performance differently under the same magnetically control parameters. The I robot does not have any exceptional potential, but the II robot can be operated at the higher control frequency even reaching the step-out point. The III robot shows the greatest performance in swimming and maneuverability. These results would be useful to design a swimming soft-robot capable of applying for various purposes, especially when the demand concerns non-harm, small-scale size, soft interface and remote controllability.

Read more…

Continuously Variable Series Reactor (CVSR) is a device that can vary the reactance in an ac circuit by controlling the magnetization of a ferromagnetic core, shared by ac and dc windings. The bias dc current can change the equivalent ac reactance(inductance) in order to, for example, control load flow, damp oscillations, or fault current limitation. Gyrator-Capacitor (G-C) approach in modeling electromagnetic devices provides a strong and practical way in simulating an integrated system composed of magnetic and electric/electronic circuits. The G-C model provides key advantages in analysis of electromagnetic devices, including CVSR. Understanding the performance and the operational characteristics of the CVSR is essential for its proper utilization in the power grid. This paper presents a detailed G-C approach that includes the ferromagnetic core nonlinearities, namely, hysteresis and saturation. The approach has been applied in modeling the electromagnetic coupling between the ac and dc circuits of a three-phase CVSR. Analysis of the effect of different control dc circuit types on the equivalent ac inductance is presented, during operating conditions at different ferromagnetic states. In addition, induced voltages across the windings and the power exchange with the control circuit are presented.

Read more…

The quality of the electric power system must be maintained properly, one of which is voltage. Under certain operating conditions, the bus voltage may drop below its minimum level, called bad voltage. A large reactive load can cause a voltage drop across the bus or the location of the bus is far from the generator stations, so that the line impedance has a large value. One technique to increase the voltage is through compensation technique. This paper presents the determination of the minimum statistical VAR compensation for increasing the voltage to the minimum safety limit. The methodology creates a compensating model for bad bus voltages. Electrical quantities (voltage, power and system losses) are calculated through the power flow technique. The compensating capacity is increased until the voltage rise reaches its minimum security limit. The simulation results on the IEEE 9 bus system show that the voltage increases on all buses with minimal compensation on buses 5 and 8, and can save up to 1.37 MW of power

Read more…

Like many STEM research projects, the members of the National Science Foundation-funded STEM SEALS project dramatically shifted from in-person delivery of a summer institute to distance-learning with minimal time for preparation. However, the daunting challenge also offered the unique opportunity to apply Design-based Research within an exploratory study to inform and document the progression and supply counsel to other STEM providers contemplating a shift to a virtual platform. The goals of this exploratory study include (1) to make apparent the barriers to transitioning to virtual STEM enrichment programming in rural spaces during the COVID-19 pandemic, (2) detail important decisions made in the move online, along with the reasoning behind those decisions, and (3) share best practices that arose during the inaugural effort. Methods included the review of multiple data sources, including project meeting minutes, educator reviews of materials, and pre/post institute student and teacher surveys. to inform rapid-paced learning cycles. As a result, the team adopted a mindset that focused on high-quality STEM experiences. Strategies supported by the research include effective substitutes for in-person demonstrations, leveraging existing platforms, employing mechanisms for troubleshooting, and framing failure in ways that encouraged the development of a positive STEM identity

Read more…

This article explains the fundamental principles of the economic policy that are integrated into the decentralized public platform Waterfall. The platform has a DAG (Directed Acyclic Graph) based system architecture and is designed to develop decentralized applications and financial services. The main goal of this work is to create a favorable environment that incentivizes positive behavior from each network participant and from the system as a whole. Economic leverages ensure general equilibrium to provide an optimal data replication ratio, attack protection, and affordable transaction fees. Although this model of tokenomic is designed explicitly for the current version of the Waterfall platform named Salto Collazo, the presented approaches possess the potential to be applied across a broad spectrum of decentralized public platforms, owing to their inherent transparency and a set of tuned parameters.

Read more…

The article presents a simulation of obstacle detection based on noise-free optical flow images for motion control of mobile robots. The detection of hazardous areas in optical flow images is accomplished by dividing multiple layers of optical flow vectors into equal parts. Based on the results of calculating the average magnitude of the vectors in the divided parts and using a solution of comparing these average magnitudes with each other, the robot can figure out obstacle position to avoid and guide the robot to a safe direction.The experiments are simulated on Matlab program to test the performance of the system. The simulated office environment with many obstacles randomly arranged along the corridors is used to test the ability to recognize obstacles to avoid. Simulation results related to different obstacle density scenarios are analyzed to demonstrate the stability of obstacle detection from the noise-free optical flow images.

Read more…

This article presented an overview of the evolution of China’s internet financial industry, emphasizing the critical importance of fintech, a novel economic sector improving the efficiency of financial services through innovative technology applications. The systems referred to encompass those technologies, applications, and tools that enhance the efficiency and accessibility of financial services. The historical trajectory of fintech, recent developments, and potential risks were thoroughly examined. A case study was conducted focusing on the significant factors influencing electronic payment in China. The study identified and analyzed key elements shaping China’s electronic payment landscape using the VAR model. The results offered insights into the future development of the electronic payment system in China.

Read more…

The exponential growth in the number of automobiles over the past few decades has created a pressing need for a robust license plate identification system that can perform effectively under various conditions. In Morocco, as in other regions, local authorities, public organizations, and private companies require a reliable License Plate Recognition (LPR) system that takes into account all plates specifications (HWP, VWP, DP, YP, and WWP) and multiple fonts used. This research paper introduces an intelligent LPR system implemented using the Yolov5 and Detectron2 frameworks, which have been trained on a customized dataset comprising multiple fonts (such as CRE, HSRP, FE-S, etc.) and accounting for different circumstances such as illumination, climate, and lighting conditions. The proposed model incorporates an intelligent region segmentation approach that adapts to the plate’s type, thereby enhancing recognition accuracy and overcoming conventional issues related to plate separators. With the use of image preprocessing and temporal redundancy optimization, the model achieves a precision of 97,181% when handling problematic plates, including those with specific illumination patterns, separators, degradations, and other challenges, with little advantage to Yolov5 over Detecton2.

Read more…

In this study, we conducted an experimental study and efficiency optimization of the outer rotor (hub) BLDC (brushless direct current) motor and axial BLDC motor for light electric vehicles. Both motors were investigated in the simulation environment and experimentally. The axial flux BLDC motor had a rated power of 10 KW, and a rated speed of 4550 rpm, while the outer rotor (hub) BLDC motor had a rated power of 1 KW and a rated speed of 300 rpm. The speed, efficiency, torque, and weight values of both motors were examined comparatively. The torque/volume values of the hub motor and axial flux motor were used as references for analysis. The hub motor and axial flux motors, with equal volume values, were simulated using ANSYS Electronics Desktop software. The simulation data were also compared with experimental studies. To optimize these motors using a genetic algorithm (GA), lower and upper limit values were determined for various parameters such as the outer and inner diameter of the stator, the outer diameter of the rotor, air gap length, slot height, axial length, air gap flux density, magnet thickness, and tooth width in the hub motor. Similarly, in the axial flux motor, parameters such as the outer and inner diameter of the stator, air gap length, slot height, air gap flux density, magnet thickness, tooth width, stator length, and rotor length were optimized using the GA method. The application of GA optimization has led to a 1.91% increase in the hub motor efficiency and a 3.45% increase in the axial motor efficiency.

Read more…