Recent Advances in Electrical & Electronic Engineering - Volume 18, Issue 7, 2025

Detecting heart disease in a timely manner is vital for preventing its progression, as it is the primary cause of death across the globe. Machine learning has the potential to enhance diagnostic accuracy and enable better clinical decision-making. A machine learning-powered hybrid system for diagnosing heart disease may provide a better optimal solution for heart disease prediction.

The overarching objectives include accuracy improvement, enhanced classification reliability, and the development of high-performance prediction models for heart disease. These objectives indicate a commitment to advancing methodologies and models in the field of machine learning and data science, particularly within the domain of healthcare and disease prediction.

The proposed system was developed using the Cleveland dataset that was preprocessed and analyzed using Recursive Feature Elimination with Cross-Validation (RFECV) and Least Absolute Shrinkage and Selection Operator (LASSO) feature extraction techniques. Further, a hybrid feature selection approach using RFECV and K-Best has been proposed for feature selection. Eight machine learning classifiers such as Multilayer Perceptron (MLP), Random Forest (RF), Extreme Gradient Boosting (XGB), K-Nearest Neighbours (KNN), Extra Tree (ET), Support Vector Machine (SVC), Adaboost, Decision Tree (DT) were utilized, and the performance of the system was measured in terms of various metrics.

The results showed that the proposed HSLE algorithm with hybrid feature selection led to the highest overall accuracy of 98.76%.

As mentioned, the main cause of adult death worldwide is chronic disease. Early detection can stop the condition from getting worse. Our research presents an innovative hybrid machine-learning approach designed to forecast heart disease.

Diabetes mellitus, stemming from insulin deficiency or resistance, poses acute and chronic health issues driven by factors like age, obesity, genetics, and lifestyle. It significantly impacts health, leading to conditions like heart disease, vision problems, and kidney dysfunction, with a notable mortality rate reported by the WHO in 2019. The modern diet has escalated diabetes risk. Machine learning techniques play a pivotal role in disease prediction, aiding timely interventions.

The primary aim of this research work is to explore and contrast the effectiveness of various existing machine-learning models for diabetes disease classification. The goal is to identify the optimal solution that yields the highest accuracy.

In the initial phase, we implemented data pre-processing, followed by the application of a diverse range of machine learning methods to classify diabetes mellitus. Subsequently, a comprehensive analysis was conducted on machine learning algorithms, considering both the complete dataset features and those selected through Particle Swarm Optimization (PSO). The assessment covered various metrics such as accuracy score, precision, F1 score, and log loss for Support Vector Classifier (SVC), K-Nearest Neighbours (KNN), Random Forest (RF), ADA Boost, XG Boost, Extra Tree, and Decision Tree. Ultimately, the introduction of hyperparameter tuning was aimed at enhancing performance and attaining the highest level of accuracy.

The proposed model HSVC combines the Particle Swarm Optimization (PSO) feature selection strategy with optimized hyperparameters, showcasing outstanding performance and achieving an accuracy of 98.66%.

The models developed in this study can potentially be applied or recommended for the classification of other health conditions in different domains, such as Parkinson’s disease, heart disease, and many more.

In recent years, the integration of renewable energy sources, particularly Photovoltaic (PV) systems, into the grid has garnered considerable attention. However, the distributed nature of these grid-integrated PV systems has introduced challenges concerning grid faults and maintenance.

This paper aims to present a pioneering approach to augment the monitoring of grid-integrated PV systems by integrating intelligent methods, specifically machine learning and feature extraction techniques. The primary focus of this approach is on islanding detection, which involves promptly identifying grid faults or maintenance challenges and initiating the grid's transition to an isolated mode of operation. To accomplish this, an intelligent signaling method is employed, capitalizing on the capabilities of Distributed Generation (DG) networks. By recording critical signals such as voltage, current, and frequency at common coupling points, fault conditions can be accurately detected. Signals obtained from the grid are subjected to wavelet transformation to extract pertinent information that characterizes fault conditions. These extracted features are then utilized as inputs to machine learning methods, facilitating the proposal of intelligent islanding scenarios. To assess the efficacy of the proposed approach, simulations are conducted on a grid-connected PV system. The recorded signals are meticulously analyzed, and the extracted features are employed to train machine learning models. The performance of these models is evaluated based on their ability to detect fault conditions and initiate appropriate islanding scenarios accurately.

The results obtained demonstrate the immense potential of the proposed approach in bolstering the monitoring of grid-integrated PV systems.

By synergizing machine learning techniques with feature extraction and intelligent signaling methods with the KNN-Confusion Matrix, all predicted labels match the true labels, resulting in a 100% accuracy. The detection of grid faults and maintenance challenges can be substantially improved, thereby fostering more efficient and dependable operation of these systems.

Though great progress has been made in deep learning-based fusion methods, there still are some troubling challenges, such as low contrast, weak feature preservation, the loss of global information, and poor color fidelity.

A multimodal medical image fusion method based on the Swin Transformer and self-supervised contrast learning is proposed. The Swin Transformer can well utilize the hierarchical attention mechanisms to model the feature dependencies at different scales, and effectively capture both the global and local information. Due to the four defined loss functions, self-supervised contrastive learning can maximize the similarity between positive samples and minimize the similarity between positive and negative samples to make the fused images closer to the source images.

Compared with the seven state-of-the-art methods, the proposed fusion method can effectively deal with darkness, brightness imbalance, edge artifacts, and pseudo-color distortion. Furthermore, for MRI-CT fusion, the mean SSIM, CC, STD and QCB are increased by 11.29%, 3.09%, 20.4% and 17.3%, respectively; for MRI-PET fusion, it can achieve the highest value of all the six objective indicators, with average increases of EN 10.96%, Q^AB/F 19.30%, SSIM 10.07%, CC 4.40%, STD 15.52% and QCB 15.84% respectively and for MRI-CT fusion, the mean SSIM, CC, STD and QCB are increased by 11.29%, 3.09%, 20.4% and 17.3%, respectively.

All the experimental results show significant advantages in both subjective and objective evaluation. The proposed method can maintain the image brightness, detail sharpness and edge information and effectively integrate the structural and functional information between different modalities. The objective indicators, such as the SSIM, CC, STD, Q^AB/F and QCB, can be significantly improved, especially in MRI-PET fusion, where all indicators reached the highest value. As a whole, it significantly enhances the image detail feature and texture while the contrast and brightness are well preserved.

Heart failure is the leading cause of death globally over the last several decades. This raises the necessity of timely, accurate, and prudent methods for establishing an early diagnosis and implementing timely illness care.

This study aims to develop and validate a classification model for the patients admitted to the Intensive Care Unit (ICU) with heart failure, using various machine learning models applied to the MIMIC (Medical Information Mart for Intensive Care)-III database.

A retrospective cohort study was conducted using data extracted from the MIMIC-III database. Machine learning models: Logistic Regression, K-Nearest Neighbor (KNN), Random Forest, Decision Tree, Naïve Bayes, AdaBoost, and XGBoost were utilized to construct the predictive model. The dataset has been preprocessed in two different manners. The study included 1,177 patients with heart failure, selected according to specific inclusion/exclusion criteria and admitted to the ICU.

At the end of the study, the most effective model for predicting patients who survived was Logistic Regression, with an accuracy of 0.9025, sensitivity of 0.9763, precision of 0.9196, and F1-score of 0.9471.

Classification of the patients into those who survived or could not survive due to heart failure was the primary measure, with various clinical and demographic variables used as predictors.

Accurate diagnosis of respiratory conditions is paramount, and this is particularly the case for pneumonia - a common but potentially life-threatening illness that affects many millions worldwide. This review focuses on the diagnostic dilemma and testing paradigm in all types of pneumonia i-e bacterial, viral especially COVID-19 associated.

This study will use chest X-ray and CT scans, traditional tools for pneumonia detection via pulmonary image analysis. Given the subjectivity of radiological interpretations, which may heavily depend on observer expertise, objective methods are required. For solving this problem, we present sophisticated deep learning algorithms to improve image analysis true positive rate and reduce false alarm. This paper compares these state-of-the-art machine-learning techniques with traditional radiological methods to show how technology can revolutionize the diagnosis of pneumonia.

The COVID-19 pandemic has presented the complication regarding differentiation of COVID-19-associated pneumonia from than other types due to overlapping symptom and radiological features. We want to characterize these fine differences in our study for even more robust diagnostic accuracy and reliability.

We investigated and built a new diagnostic landscape for pneumonia where the traditional individual methods seem to be flawed while machine learning predictions provide some strengths as well as weaknesses. It demonstrates how enhancing diagnosis can again be of par importance towards developing more viably doable public health measures towards mitigating, not only pneumonia, but also other respiratory diseases.

The medical field can utilize radiological images with deep learning techniques to diagnose disease more accurately, enabling the diagnosis and classification of a variety of illnesses. In the domain of learning and machine vision, identifying COVID-19 from X-ray images is a developing area. Since the onset of COVID-19, significant work has been performed, yet some issues remain in this field.

Firstly, there are limited X-ray scans readily available that are classified as COVID-19 positive, resulting in an unbalanced dataset. Secondly, there is no single set of data, classes, or evaluation protocols for all the work performed. This study proposes a three-class balanced dataset based on two validated publicly available datasets. Deep Convolutional neural networks have the potential to operate with both wide breadth and wide depth, which could raise computing complexity. Additionally, to deal with this issue, an attention-guided ensemble model (AGEM) is proposed to classify normal, pneumonia, and COVID-19 images. First, we propose an Attention Guided-Convolutional Neural Network (AG-CNN) architecture based on transfer learning. We used three pre-trained models i.e., InceptionV3, DenseNet121, and MobileNetV2, as the basis for the proposed AG-CNN, resulting in three attention-guided network architectures i.e., AG-InceptionV3, AG-DenseNet121, and AG-MobileNetV2. Then, we used entropy computation and an uncertainty-based weighting ensemble to classify the images into three classes.

The performance was evaluated and compared with existing works and 7 pre-trained models i.e., ResNet50, InceptionV3, VGG-16, VGG-19, Densenet-201, Xception, MobileNetV2, on our three-class dataset. An accuracy of 97.35%, recall of 97.35%, specificity of 98.67%, precision of 97.35%, and F1-score of 97.35% demonstrate the superiority of our proposed attention-guided ensemble model over pre-trained models and other existing studies.

It is noteworthy that for additional analysis, we utilized Grad-CAM or gradient-weighted Class Activation Mapping.

This paper addresses the ongoing challenge of harmonics reduction in power systems, particularly focusing on Flexible AC Transmission Systems (FACTS) devices. Instead of employing a conventional multilevel converter, an alternative configuration is proposed: a 36-pulse gate turn-off thyristor-based converter (GTO-VSC). This converter comprises three 12-pulse Voltage Source Converters (VSCs) as fundamental units, operating collectively on the frequency mode of GTO switching control within a Distribution Static Synchronous Compensator (D-STATCOM). The D-STATCOM dynamically compensates reactive power in the system. The 36-pulse configuration results in AC output voltage waveforms containing harmonics such as the 35^th, 37^th, 71^st, 73^rd, etc., leading to higher total harmonic distortion (THD) levels.

In response, the paper presents a new model featuring a 3-level, 36-pulse, 25kV, ±3MVAr STATCOM configured with 12-pulse GTO-VSCs. This model incorporates PWM gate switching and employs a PI-control methodology to optimize harmonics in simulation, specifically targeting harmonics at the 35^th, 37^th, 71^st, 73^rd, etc., orders using Sim Power Systems toolbox in Math Works software.

The compensator's operational performance is controlled through switching angle optimization, which minimizes harmonics, regulates voltage, and manages reactive power in the electrical transmission system.

The simulation results demonstrate that the proposed model is acceptable for enhancing the flexibility and performance of the FACTS device in mitigating harmonics in power systems.

Blockchain technology has revolutionized data management and transaction recording, extending its application beyond cryptocurrencies to various sectors, including Central Bank Digital Currencies (CBDCs).

This distributed ledger technology offers a transparent, immutable, and secure transaction platform, reducing the risk of data tampering and increasing resistance to attacks. However, challenges such as performance, scalability, and security continue to exist; these challenges are particularly concerning consensus mechanisms like Proof of Work (PoW). Field-Programmable Gate Arrays (FPGAs) present a promising solution to enhance the efficiency and security of blockchain consensus mechanisms.

This study explores the implementation of blockchain in embedded systems using FPGAs and discusses the post-quantum cryptographic algorithms to ensure long-term protection.

The research highlights the potential of FPGA-based implementations to revolutionize blockchain applications, emphasizing the need for continuous adaptation and vigilance to address evolving security threats, particularly those posed by quantum computing.

The current method has low detection accuracy for electric vehicle charging ports in complex environments.

This paper proposes a method for electric vehicle charging port recognition based on wavelet enhancement and an improved canny algorithm.

Firstly, a preprocessing assessment model is proposed to determine whether preprocessing enhancement should be applied. Subsequently, we perform a stretch transformation on the S channel in the HSI color space and apply a discrete wavelet transform to the I channel to restore the brightness and detail features of the target objects in the image. Specifically, in this paper, adaptive median filtering and multi-scale Retinex algorithm are utilized on different frequency components respectively. Finally, the features and parameters of the charging port are detected and extracted through the maximum inter-class variance method, morphological processing, the improved Canny algorithm, and Hough transform fitting.

This paper conducts comparative experiments on preprocessing enhancement of charging port images in different environments and features detection of charging ports. The hole feature parameters detected by this method are consistent with the actual situation.

The experiment proves that the method proposed in this paper can meet the requirements of precise identification of charging ports in complex environments.

Due to experimental equipment limitations, it is usually difficult to measure the quasi-static hysteresis loop at extremely low frequencies, which inevitably introduces errors in the static hysteresis model.

This study aims to propose a method for calculating the static hysteresis loops of grain-oriented silicon steel sheets so as to improve the accuracy of the static and dynamic hysteresis model.

The parameters n0 and V0 in the magnetic field strength expression of the excess loss are determined by the measured losses within the range of 0-100Hz. Subsequently, the dynamic components in the quasi-static hysteresis loops are eliminated. Furthermore, a dynamic hysteresis model is established based on the loss and field separation theory, which incorporates the inverse Preisach model.

The dynamic hysteresis loops of the grain-oriented silicon steel sheets are measured in the range of 8-250Hz and compared with the results of both the improved model and the original model.

Experimental results demonstrate the effectiveness and accuracy of the improved model. The proposed method for calculating static hysteresis loops has universal applicability and is meaningful for accurate simulation and prediction of magnetic properties in soft magnetic materials.

With the growing need for information safety and security rules in every corner of the globe. The biometric innovation has been used widely all over the world in daily life. In this view, the Multimodal-based biometric technique has gained popularity and interest due to its capability to resolve various problems associated with single-model biometric identification systems.

In this research, an advanced multimodal-based biometric recognition system is introduced, which depends on multilayer perceptron (MLP), and it identifies humans using biometric features of Fingerprints and IRIS. To build an efficient model, the popular model called RestNet50 was used, the gradient method was used and the hinge technique was used as a loss function. For the technique of fusion, different techniques are used to show the effect of fusion in our model. The recognition rate of introduced systems was assessed by experimenting with various techniques on SDUMLA-HMT datasets based on the multimodal biometric datasets. The recognition rate showed that merging two biometric features in biometric recognition systems gives the best results compared to a single biometric feature.

The results obtained showed the superiority of our model with other existing techniques by obtaining a recognition rate of 99.79% with a feature-based fusion method.

The introduced system used the MLP deep learning technique. The feature level fusion was applied to recognize the user using IRIS and fingerprints. To the best of our belief, this is the first research to incorporate MLP and multimodal-based biometric systems using IRIS and fingerprints.

Arc fault has become an increasingly prominent problem affecting the safe operation of power distribution networks. Research on arc fault detection can effectively reduce electrical fire accidents caused by arc faults, which is of great significance for ensuring the safe and reliable operation of power distribution networks.

In this paper, an arc fault detection method based on current convolution is proposed for single-phase AC series arc faults. Firstly, the phase of the measured phase current is acquired through the phase-locked loop. Then, the measured phase current is convoluted with the standard sinusoidal signal whose phase is the same as the measured phase current, and the DC component is obtained by low-pass filtering.

The occurrence of an arc fault is recognized by detecting the change in the DC component.

Finally, the simulation results verify that the proposed method can detect the arc fault quickly and accurately.

Fire incidents occur in complex scenarios, where the dynamic positions and varying scales of flames and smoke pose challenges for fire detection. To improve the stability, localization accuracy, and detection precision of small targets in fire detection, a fused PBCA method for fire and smoke object detection has been proposed in this paper, called FS-YOLOv8.

The objective of this approach was to improve the detection accuracy of flames and smoke, enhance the robustness of the system, and strengthen the feature representation capability. It aimed to optimize the contribution of feature maps at different scales, allowing the network to capture inter-channel correlations while preserving precise localization information of the targets. Furthermore, it aimed to enhance the learning ability of small-scale flame and smoke objects.

Firstly, DCN (Deformable Convolutional Network) was integrated into the CSPDarknet backbone network to extract features from flame and smoke images. Subsequently, a module called PBCA was designed by combining BiFPN (Bidirectional Feature Pyramid Network) and coordinate attention. Finally, a small object detection layer, YOLO HEAD-4, was constructed.

The experimental results of our proposed FS-YOLOv8 method on a self-made dataset demonstrated improved detection accuracy compared to other conventional methods. Therefore, the FS-YOLOv8 method effectively enhanced the performance of object detection in fire and smoke scenarios.

The FS-YOLOv8 method has been found to effectively improve the performance of object detection in fire and smoke scenarios, enhance the robustness of the system, strengthen the feature representation capability, and amplify the learning ability of small-scale flame and smoke objects.

In this article, an IOT solution for managing and controlling a PV system with applications for the home is presented. A DC-DC SEPIC converter, a bidirectional converter, a PWM generator, and a single-phase voltage source inverter with active clamping are used for power conditioning. An output voltage control loop is implemented, and real-time online communication with an internet server is accomplished using the PIC microcontroller.

The ESP8266MOD WIFI IOT module works with the Blynk mobile app. Experimental findings showing the proper operation of IOT features demonstrate the effectiveness of voltage regulation. In this article, frequency is taken into consideration as solar power is integrated with the grid. A user may easily control the DC-DC converter, load batteries, and monitor battery voltage through our user-friendly GUI interface.

In this paper, an IOT (Internet of Things) application was used to control and track the output of a modest PV power plant. The study shows the efficiency of the digitally controlled system developed to regulate the output voltage of the SEPIC DC-DC converter.

They further argue that the ESP8266 and microcontroller's versatility make them an appropriate instrument for remote and real-time monitoring and control of the proposed model from around the world. The energy that is produced by the sun is added to the grid so that it may be put to effective use and contribute to satisfying the rising demand for energy. Solar energy is the input that SEPIC uses to charge the batteries and for all of its other processes. In the event that solar photovoltaic (PV) panels are not available, the SEPIC DC-DC converter will derive its energy from AC power.

In this article, an IOT (Internet of Things) application was used to control and track the output of a modest PV power plant. The research demonstrates the effectiveness of the digitally controlled system created to manage the output voltage of the SEPIC DC-DC converter. They further argue that the ESP8266 and microcontroller's versatility make them an appropriate instrument for allowing remote and real-time monitoring and control of the proposed model from any part of the world. The energy that is produced by the sun is added to the grid so that it may be put to effective use and contribute to satisfying the rising demand for energy. Solar energy is the input that SEPIC uses to charge the batteries and for all of its other processes. In the event that solar photovoltaic (PV) panels are not available, the SEPIC DC-DC converter will derive its energy from AC power.

As one of the key components of ultra-wideband (UWB) system, UWB filter has important research significance. However, the current UWB filter still has the problem of a narrow stopband and cannot suppress the interference signals in the passband.

In this paper, a novel UWB bandpass filter is proposed, which has wide stopband characteristics and good out-of-band rejection performance and implements a notch function for the WLAN band and the X satellite communication band in the passband to improve the anti-interference performance.

The filter adopts a novel composite right/left handed transmission line (CRLH-TL) structure to realize the passband characteristics with low insertion loss (< 0.8dB). The anticoupled line structures generate two transmission zeros (TZs) in the upper stopband, which improves the upper stopband performance of the filter. The short circuit step impedance resonators (SIRs) and the asymmetric coupling structure generate a notched band in the passband respectively.

The simulated and measured results show that the 3dB passband range is 3.4-11.0 GHz, the out-of-band rejection is more than 20 dB in the stopband range of 12.8-28 GHz, and the dual-notched bands are located at 5.86 GHz and 8.0 GHz respectively. The measured results are basically consistent with the simulated results.

Compared with the existing filters, the proposed filter has outstanding advantages and has a wide range of application prospects in the field of indoor UWB positioning system.

Higher power consumption raises chip temperature because it draws more current from the power source, which directly affects how long the batteries survive in portable devices. High temperature affects the dependability and functionality of a circuit, requiring more complex packaging and cooling strategies. One of the most significant challenges in VLSI design is power consumption. The power consumption of the circuit rises with both transistor density and chip complexity. In addition, one of the essential building blocks of hardware in the majority of VLSI applications and digital signal processing systems is the multiplier.

This study aimed to design and compare array multiplier, Vedic multiplier, and Wallace tree multiplier using variable bit lengths.

In this paper, authors designed array multiplier, Vedic multiplier, and Wallace tree multiplier using variable bit lengths. For comparison, the VIVADO tool was used to simulate and synthesize multiplier outputs.

Wallace tree multipliers resulted in 31.153mW, 13.220mW, 4.099mW, and 0.988 mW of power dissipation for 16-bit, 8-bit, 4-bit, and 2-bit, respectively. The best multiplier was designed using different logic like AOI, OAI, NAND-NAND, and NOR-NOR and was compared based on power dissipation. It was observed that 2.256mW power dissipation was observed for NOR-NOR logic, which was minimal among other logics.

The 4-bit Wallace multiplier using NOR-NOR logic was used for FPGA implementation, which can be used in digital signal processing applications.

With the advancement in technology nodes and scaling trends, the majority of the device performance depends upon the interconnections made between two or more devices. With these scaling trends, frequency plays a vital role. As the technology decreases, frequency tends to rise to giga-hertz. This increase in frequency gives rise to inductance parameters in the interconnect circuits. For long wires, the inductive impedance can become comparable to the resistive component due to which performance degradation can be observed along with overshoot and crosstalk issues that can no longer be ignored.

This article aims to examine the delay model and reconstruct an interconnect circuit that serves as a transmission line, ranging in length from 1 mm to 10 mm.

By keeping the frequency high, low voltage and rise/ fall time, performance parameters such as delay, power consumption, and overshoot are observed.

The interconnect structure is compared with another state-of-the-art technique.

Diabetes has been rising in recent years and prior research has demonstrated Machine Learning Techniques (MLTs) to be useful tools for predicting diabetes. This research has examined the accuracy of six different MLTs for predicting diabetes using lifestyle data gathered from UCI (University of California). To improve medical outcomes and prevent its onset, the prediction of diabetes is necessary. This research has proposed a new framework based on the early detection of diabetes using lifestyle factors. Various MLTs, such as Logistic Regression (LR), Decision Tree Classification (DTC), Random Forest Classification (RFC), Support Vector Classification (SVC), and K-Nearest Classification (KNC) have been used for tenfold cross-validation and the results obtained from different techniques have been verified. Among all classification techniques, LR has achieved the highest accuracy of 93%, the precision of 92%, the recall score of 94%, the F1 score of 93%, and the weighted average of 90%, respectively. The proposed framework is utilized by the healthcare sector to predict diabetes early. It can also be used with datasets from various sectors that share diabetes-related data.

In this paper, we have used the proposed framework to predict diabetes mellitus in the healthcare system, diagnose various ailments, and assess if MLA performs well. The proposed system has been developed based on the MLT for the classification of DM. An intelligent framework for Diabetes Mellitus (DM) that has been developed using MLT illustrates the full workflow from data input to output. The five algorithms, Logistic Regression (LR), Decision Tree Classification (DTC), Random Forest Classification (RFC), Support Vector Classification (SVC), and K-Nearest Classification (KNC), have been compared in terms of accuracy, precision, recall, and F1 score.

Results from the experimental setting using MLTs for DM prediction based on lifestyle predictors have been obtained. Descriptive statistics of lifestyle characteristics have been displayed along with their corresponding metrics, such as mean, standard deviation, minimum, maximum, etc. For instance, the age parameters’ mean, standard, and minimum at 25%, 50%, 75%, and maximum values were as follows: 520.0, 48.02, 12.151, 16.0, 39.0, 47.5, 57.0, and 90.0 respectively. Feature engineering is crucial to the process of constructing MLT. Insignificant or incorrect characteristics may have a negative impact on the way a model runs. The training time is drastically reduced and accuracy is increased with careful feature selection. In machine learning frameworks, some feature selection strategies include embedding, filter, wrapper, embedded, and hybrid techniques. An alarming number of people around the world suffer from the chronic and dangerous disease of diabetes. Using MLT, early DM prediction-based biological variables have been obtained in this research work. Data on patients’ lifestyles have been thoroughly examined in order to create a framework. The Canonical-correlation Analysis (CCA) has been used to select the ideal combination of lifestyle features. Finally, 10-fold cross-validations have been used to apply five alternative machine learning techniques for the prediction of disease.

To our knowledge, it is the first time a framework has been proposed that has yielded prediction results so much better than those from earlier research. The results obtained in this suggested work have been found accurate and reliable by metrics evaluation.

Parallel prefix adders are widely used in high-speed arithmetic circuits due to their ability to perform additions in logarithmic time. However, the high area and delay of exact parallel prefix adders prompted the development of approximate parallel prefix adders. These adders are a promising solution for high-speed arithmetic circuits because they sacrifice accuracy for reduced area and delay.

This paper presents a performance analysis of five approximate parallel prefix adders realized with field programmable gate array technology. The five approximate parallel prefix adders are the Kogge-Stone adder, the Sklansky adder, the Brent-Kung adder, the Han-Carlson adder, and the Ladner-Fisher. Each adder is implemented in a Xilinx Artix-7 FPGA. The area and delay of five approximate parallel prefix adders are evaluated. The Kogge-Stone approximate parallel prefix adder, out of five approximate parallel prefix adders, consumes the least delay, irrespective of the number of bits.

The Sklansky approximate parallel prefix adder out of five approximate parallel prefix adders consumes the least area irrespective of the number of bits in addition. Overall, our research sheds light on the trade-offs between area, power delay, and power delay products of five approximate parallel prefix adders implemented with FPGA technology.

This analysis can help choose the best approximate parallel prefix adder for specific high-speed arithmetic applications. In the case of 16- and 32-bit five approximate parallel prefix adders, Ladner-fisher shows the best power delay product, whereas 64- and 128-bit five approximate parallel prefix adders, Sklansky adder shows the best power delay product.

With the continuous development of permanent magnet synchronous motors (PMSM) and the increasing demand for the application of flywheel battery, the requirements for PMSMs are also increasing.

A multi-objective genetic algorithm is used to solve the optimal design solution.

Multi-objective genetic algorithm is fast and accurate in calculation results, and it is easy to obtain the optimal solution. The results show that the cogging torque is reduced by 23.6%, the torque ripple is reduced by 25%, and the average torque is increased by 1.2%.

A multi-objective optimization design was conducted on a surface-mounted PMSM. Firstly, the sensitivity of different optimization variables was calculated. The high-sensitivity parameters were selected as the final optimization variables. The response surface between the optimization variables and the optimization objectives was calculated. The genetic algorithm was used to solve the optimal design solution. The effectiveness of the optimization results was verified by the combination of finite element simulation and experimental tests.