Power Engineering and Intelligent Systems

In modern years, most patients have diabetic, mean blood pressure and glucose associated health conditions, which can be treated by infusion of an antidote, although the dosage amount depends on the severity of the individual. The monitoring and regulation of the degree of dose is therefore critical in improving the health status of patients. This paper suggests that the dose of the medication infusion be regulated and managed on the basis of its amount. This is done by developing an integrated monitoring device that increases safety in less time and reduces healthcare costs. A statistical model of patient reaction to drugs is obtained in this article. The model comprises five dimensions that range from patient to patient based on their drug response. The key purpose of the documentation is to enhance the efficiency and robustness of medication distribution activities. This Internal model control (IMC) based Proportional integral derivative (PI/PID) controller is introduced as a control system for patient distribution of drugs that will provide enhanced robustness and efficiency. The IMC driven PI/PID system has just one calibration parameter ( $$\lambda$$ ), which is calibrated depending on the highest sensitivity $$\left({M}_{S}\right)$$ . This method does not involve complex mathematical equations.

In this paper, we propose a method for detecting obfuscated malware on Android using graph neural networks (GNNs). Obfuscation is a well-known technique used by malware creators to hide themselves from being detected by anti-virus softwares. Our approach uses GNNs to represent the code of an Android app as a graph and applies graph convolutional networks to classify the app as benign or malicious. We evaluated our method on a real-world dataset of Android apps and compared it to other state-of-the-art algorithms. Our results show that our method outperformed the other algorithms in many different metrics. The proposed method has potential for application in real-world scenarios, as it can detect obfuscated malware with high accuracy.

Vector control and self-control are the most widely used control techniques of the PM synchronous motor. Self-control technique is comparatively simple and cost-effective compared to vector control. However, this technique is unable to provide satisfactory performance for sinusoidal back E.M.F. machines. Self-control is suitable for trapezoidal back EMF motors. The vector control technique is the best high-performance control technique of sinusoidal back E.M.F. machines. In this paper, a semi-vector control scheme is discussed for sinusoidal back E.M.F. machines. The major advantage of this scheme over vector control is that reference frame transformations of motor variables and close current control are not required which makes the drive simple and less costly than vector control drive. The performance of the semi-vector control drive is in between vector control and self-control drives. The developed drive can be used for many industrial and domestic applications in place of a self-control drive. Performance of the drive is being validated by experimental study and satisfactory results are found.

Economic growth for good quality food contributed to packaging advancements. The topic of discussion in this research paper is intelligent packaging technologies, their applications in food packaging, as well as research and breakthroughs in the packaging industry. Food products with more intelligent and active packaging are both healthier and of higher quality. Active packaging makes use of additives to maintain or extend the quality and freshness of the food inside. During the entire process of storage and transportation, intelligent systems check packed foods for correct information. These advances satisfy the demand for foods that are healthier and can be stored for longer. It is anticipated that the market would expand as a result of the incorporation of active and intelligent packaging technologies.

Hackers are inventing novel strategies to breach the encrypted information of practically all existing cryptographic algorithms, and therefore network security has always been an emerging study in communication technology. “Elliptic Curve Cryptography” (ECC) is a new cryptographic approach that has been demonstrated to work in public-key cryptosystems. ECC’s benefits ensure secure data transmission across an insecure medium. The standard ECC key pact procedure is based on El-Gamal encryption. ECC is the handiest procedure for network security because it offers good security with smaller key sizes, quicker computations, lower computing power, and less storage space. By merging ECC and Runge–Kutta (RK) methods, the performance of the ECC cryptanalysis technique is enhanced in relation to speed and security in this paper. The key advantages of RK techniques are that they are simple to use and have a low error rate. The Runge–Kutta-ECC procedure is designed to improve the avalanche effect, speed, throughput, and power consumption of the method. The enhanced performance of the RKECC method is discussed, in addition to the experimental results. There is also a detailed mathematical justification for the RKECC algorithm.

The world is moving toward viable as well as reliable energy sources. The implementation of smart grids is one such drive that aims to coordinate the generation, distribution, and consumption of energy more efficiently. However, managing the smart grid is not an easy task as it involves dealing with a large amount of data and making real-time decisions. Artificial Intelligence has emerged as a promising solution to address these challenges. Smart grids enable utilities to optimize their current infrastructure while reducing the need to build more power plants since they are autonomous and increase the effectiveness and efficacy of electrical power management. In this paper, we have analyzed the management of smart grids using AI with various algorithms used in Smart Grid and focusing on power generation and distribution systems. The paper also highlights the benefits of using AI such as improved efficiency, reduced costs, and enhanced reliability with applications for fault detections and provides the comparison of traditional and modern technology in smart grids.

This paper presents an efficient modeling strategy for fast and accurate simulation of cascaded power electronic converters. The computational cost of simulations is drastically reduced by using Adaptive Multi-resolution Simulation (AMRS) algorithm. The numerical experiments on a benchmark model validate the efficacy of the proposed strategy.

This research is concentrated on building solar cells with greater efficiency than standard solar cells. The main aim of this work is to extend solar cells in such a way that their efficiency can be increased in comparison to regular solar cells. Our project's model is a one-dimensional silicon p–n junction with carrier generation and Shockley–Read–Hall recombination. This model represents how solar cells behave under forward bias at various voltages. For the front surface doping, a geometric doping model is employed, whereas an analytical doping model is used for the uniform bulk doping (the surface is specified in the Boundary Selection for Doping Profile sub-node). The Shockley–Read–Hall recombination model is implemented in a Trap-Assisted Recombination feature, while the photogeneration is carried out in a User-Defined Generation feature. Two Metal Contact features are used to make the electrical connections to the front and back surfaces. The generation rate is expressed simply as a user-defined spatially dependent variable using an integral equation involving the silicon absorption spectrum and solar irradiation. Additionally, the primary recombination impact is captured using the Shockley–Read–Hall model. Photo-generated carriers are swept to either side of the p–n junction’s depletion zone during normal operation. A moderate forward bias voltage is used to generate the electrical power, which is produced by the photo-current and the applied voltage. After reviewing numerous studies, we have been led to the realization that adjusting the dimensions of the solar cell under ID configuration in the COMSOL Multiphysics software has improved the efficiency. We prefer COMSOL Multiphysics because it is simple to use, gives us a lot of exposure, and provides accurate data for whatever material we utilize.

Post quantum cryptography is the key idea to resist quantum attacks. The Fiat-Shamir were the first who introduce efficient lattice-based signatures. A lattice-based signature ensures the security of blockchain architecture against quantum computers. However, a blockchain is always consisting of multiple communicating nodes, so there is a need to develop a verification method for multiple nodes. We have proposed a blockchain using module lattices. Blockchain security relies upon two assumptions, (1) Module Learning With Errors and (2) Module Short Integer Solution. The system can provide security against quantum attacks.

In recent years, the need to integrate new technologies into the educational process has been increasing. The use of the Internet in education has increased steadily over the last decade as new technologies make it easier for students to learn. Using distance learning tools, students’ learning can be flexible across location and time constraints. Therefore, students can access information anytime, anywhere, whether in the library or in the classroom. Distance education is notoriously expensive, and as schools become major providers of distance education, budgeting becomes even more important. Cost relative to the learning environment is a disadvantage of distance education, and the work of education management can eliminate it. Using comprehensive learning management will help improve learning tools and improve learning quality. A web-based learning management system called the Learning Management System (LMS) assists teachers in meeting objectives, planning lessons, and inspiring students. In the twenty-first century, learning management systems (LMS) have emerged as a crucial instrument for delivering education. This white paper provides an overview of LMSs, including their features, capabilities, and future directions. This article discusses the main features and roles, advantages and limitations of LMS, and current trends in LMS development. The essay also analyses difficulties with LMS adoption and makes suggestions for further study. It also discusses the LMS that has been developed and can be integrated directly into the organization if needed. The comparison of several LMSs is also included in the article.

This article introduces a novel workup of a multilevel inverter which can be used for electric vehicles. This multilevel inverter is implemented with seven number of power switches and two asymmetrical sources. The most common modulation technique used in multilevel inverters is pulse width modulation and sinusoidal pulse width modulation is used in this multilevel inverter to eliminate harmful low-order harmonics. In this multilevel inverter, seven switches are used to get the desired output voltage and current waveforms at seven levels. In conventional multi-level inverters, more number of power components are used to obtain seven-level output waveform, which increases harmonic distortion as well as switching losses and cost. This usage of seven switches in the proposed inverter significantly minimizes switching costs, low-order harmonics, and switching losses, thereby reducing total harmonic distortions.

PCOS is a prevalent hormonal disorder that impacts women in the reproductive age bracket. Timely and accurate diagnosis of PCOS is crucial for the proper treatment. To diagnose the presence of PCOS, ultrasound images of the ovaries are widely used by the physicians. Automated detection of PCOS shall reduce the risk of making errors. This study seeks to propose a machine learning classification technique for PCOS detection and to mark the cysts on the ovary using image segmentation. Convolution Neural Network (CNN) architectures such as Inception V3, VGG16, and ResNet are used for classifying images. The model is trained over 781 ovary ultrasound images to distinguish between PCOS and non-PCOS cases. Among the three models used VGG16 model comes with better accuracy. The results of this study show that this approach is effective in detecting PCOS with high accuracy.

Twitter Data Analysis in Social media plays an essential role in spreading information during disasters and needy situations. May it be for seeking help or sharing and updating the seriousness of the situation or communicating the status or response to the public in need, social media plays a major role in case of emergencies. This research focuses on generating word embedding vectors using DistillBERT and generating a similarity matrix to construct the Graph-based Convolution Network model to classify text sequences and to analyse the performance of the DistillBERT with GCN model in Text classification. To implement this, contextual word embeddings are introduced for generating word vectors. The contextual word embeddings and the concept of graph neural networks has gained importance in capturing contextual relationship among the text to improve the performance of classification. This semi supervised model is used to detect and classify the need and availability of resource tweets with an accuracy of 96% as compared with state-of-the-art approaches.

The device described in this publication is a thyristor-switched capacitor (TSC) device used in a 200 kV/11 kV, 200 MW grid system. In addition to the capacitor bank's transient-free switching, a technique for compensating VAR is described. This study's goal is to offer a topology at the lowest possible price. Flexible AC transmission systems (FACTS) have been developed as an alternative to conventional methods for enhancing the efficiency, reliability, and power quality of electrical energy networks. These systems are currently in use in many countries across the world. FACTS are generally referred to as systems that control voltage, impedance, and phase angle in AC systems. Furthermore, due to advancements in semiconductor technology, static VAR compensation devices have begun to be used on the medium and high-voltage sides. The ability of these systems to make adjustments without relying on VAR from the grid is their key strength. In this study, a static VAR compensator made up of three TSCs and one TCR structure is used to supply the system with the necessary VAR. In the simulation studies, the static compensator is used to supply the VAR instead of a voltage source. This prevented the system from using its capacity inefficiently. The use of static VAR compensators is advised, especially when an unbalanced load and instant VAR are needed.

In the medical profession, brain tumour is a very crucial illness. A brain tumour is an unwanted mass growing in the brain cells; if it’s not prevented, it will eventually cause death. Therefore, tumour diagnosis is essential. Magnetic resonance imaging (MRI) is used to identify the brain tumour quickly. The approach of detecting a brain tumour from human eyesight is quite difficult. The proposed work automatically diagnoses the brain tumour. This proposed technique has two stages: classification and segmentation. The classification stage is used to classify the T2W-MRI images into a tumour and normal using 8 x 8 blocks with gray-level co-occurrence matrix (GLCM) features using a support vector machine (SVM). The second stage segments the FAIR and T1C type MRI images using colour-based segmentation technique. This proposed method uses the BraTS2013 dataset. Classification and segmentation result is calculated by sensitivity, specificity and accuracy. In the segmentation, it additionally uses the dice similarity coefficient (DSC) to find the accuracy. The outcomes denote the proposed method's accuracy of classification as 96.66% and the DSC of segmentation accuracy as 80%.

The objective of the present study is to assess different aspects of online teaching from faculties’ perspective. We investigate the level of the difficulties faced by faculty members in handling Moodle, the satisfaction level of online teaching, and online evaluation, and the role of previous awareness/training programs in facing difficulties handling Moodle. Finally, we find the grey areas in online teaching. We collected data from 104 faculty members of Graphic Era Hill University (GEHU) for the present study. Analysis of variance approach and t-test are used for different purposes. K-Means Clustering method is used for analyzing the role of training programs in facing difficulties in handling Moodle. We found that different aspects of Moodle handling were considered equally difficult; satisfaction level in content delivery only is considered high. Satisfaction levels in two components of evaluation, multiple choice questions (MCQ) and descriptive questions (DQ) were neither considered the same nor high; however, satisfaction in MCQ is considered a little more than in DQ. Through clustering patterns, we found a significant effect of previous awareness/training in facing difficulty in handling Moodle. These findings may be useful for making strategies for online teaching in the future.

The popularity of using automated models in every sector is increasing day by day. Developing an automated model to recognize various diseases in plants from leaf images is the main focus of this research study. Various diseases can occur in plants during their entire lifetime. Automated identification saves time and eliminates human intervention. This study uses image segmentation to separate affected and unaffected regions from leaf images. The discrete wavelet transform has been used to take out significant patterns from images. Local binary pattern has also been used as a texture feature descriptor. The study shows a significant improvement in accuracy using these feature combinations. To train and test the model, a benchmark data set has been used. The efficiency of our model outperforms state-of-the-art models in comparison. The efficiency of our model is 95.08%.

A computer vision-based bird-eye chilli sorting system has become essential due to the rising demand for quality verification and effective sorting of chilli products. The quality of bird-eye chilli, or ‘kantari mulaku’, directly affects the flavour and is a highly sought-after ingredient in many different cuisines around the globe. Computer vision technology-based automated sorting systems can precisely recognize and categorize chillies based on various quality factors like size, shape, colour, and texture. Additionally, computer vision-based sorting systems are perfect for large-scale production facilities because they can constantly run for prolonged periods with little supervision. This paper describes a method for categorizing bird-eye chilli using a 3 DOF robotic manipulator and the You Only Look Once-V5 object recognition algorithm. Images of bird-eye chillies in various orientations and settings make up the dataset used in this research. This dataset was used to train the algorithm, and the model successfully identified and classified bird-eye chilli. The chillies were then grabbed by a robotic manipulator and sorted according to their degree of maturity. The proposed approach obtained an average precision of 0.90 and a mAP of 0.94. Chillies can be graded with high precision, consistency, and efficiency using a robotic manipulator, which boosts output and lowers human error rates. The developed YOLO V5 framework is deployed in Raspberry Pi 4B graphical processing unit, verifying the efficacy. The outcomes of this work show how successfully classifying bird-eye chilli using YOLO V5 can be applied in the food and agricultural industries.

A modified multi-level inverter with a cascaded H-bridge with a grid connected hybrid wind-solar energy system is given. Utilising their individual MPPT (maximum power point tracking) systems. In this paper, both solar and wind energy are used as input sources to the system. The total harmonic (THD) is reduced so that the appliances in the system are least affected or damaged. The dc/dc booster converters are used to step up the voltage and the maximum power is obtained by using maximum power point tracking (MPPT). Due to non-linear loads, the harmonics are produced in the system so in order to reduce the harmonics we use the MLI, as the level increases the harmonic distortion in the system decreases, so that we can reduce the disturbances and increase the appliances efficiency. So, the pulse width modulation (PWM) is used as an inverter in the system to produce the sinusoidal ac output. In this paper, we discuss mostly about, to obtain balanced voltage and current of two sources when connected by a dc-link, reducing the THD and Improve the Power quality. As the frequency is constant but the voltage is variable the voltage and frequency will be matchable as the frequency maintains constant. Hence, the output waveforms of multi-level inverter, and the simulation investigations were verified and completed in MATLAB/Simulink.

One of the psychological disorders known as autism spectrum disorders (ASD) is a very challenging one to analyze and goes undiagnosed in many people. This condition develops from birth and persists throughout life, and has no cure. It is possible to predict ASD using a variety of indicators, including functional magnetic resonance imaging (fMRI) data, kinematic traits, game-based applications, questionnaires given to parents and guardians, social reciprocity, head motion, motor activities, and eye-tracking. A better prognosis for the patient can be achieved with earlier prediction. This research work provides a thorough overview of the various machine learning and artificial intelligence algorithms utilized for ASD diagnosis and prediction in patients of various ages using clinical methods. This article also emphasizes the datasets that were utilized to predict autism in individuals, their results, limitations, and the hindrances of the methods involved.

Data transmission and communication in mobile wireless sensor networks are hindered due to the limited energy of the sensor node. This causes various challenges in the communication between sensor nodes having network loss, latency, and in complete transactions. To concern, a clustering-based network model has been developed where the cluster head election is the major issue. Therefore, we proposed an intelligent cluster-based network model with the objective to provide intelligent energy-efficient cluster head election and data aggregation mechanisms using Artificial Intelligence techniques in the mobile sensor network. Also, to overcome the network overhead, a mechanism has been presented to validate data similarity among the nearby sensor nodes. The performance evaluation of the proposed scheme has been conducted using Python with machine learning and the results obtained reflect better performance in terms of cluster head selection and data aggregation.

Fire alarms are an essential aspect in providing safety for individuals and structures during a fire emergency. However, traditional fire alarms have several limitations, including false alarms and slow response times. In this study, we describe implementation and comparison of various techniques for machine learning like Naive Bayes, Random Forest, KNN, Logistic Regression, SVM Linear Kernel, and Decision trees to improve fire detection and response using various parameters such as Humidity, Temperature, MQ139, TVOC, and eCO2. There are many research papers which use deep learning and artificial intelligence using datasets containing images. However, our model has used a real-time-stamped text dataset and split them into train sets and test sets. Using various machine learning algorithms, different parameters have been calculated such as accuracy, precision, F1score, sensitivity, specificity, kappa, and RMSE values. Our findings suggest that fire alarms play an important role in smart home technology by providing early warning in the event of a fire and helping to protect people and property. Overall, fire alarms are becoming increasingly integrated into smart home technology, providing users with added convenience, safety, and peace of mind.

This paper presents the design and simulation of a solar cell coplanar patch antenna for IoT and Wireless sensor Networks. In this proposed work, a single solar cell is used as the radiating element and can be used as a power harvesting device. Initially, coplanar patch antenna is designed and Solar cell is integrated with the patch with a thickness of 0.5 mm. The radiation characteristics of the solar cell-based patch design are compared with a coplanar based same structured antenna without solar cell integration. The proposed antenna is designed at 2.42 GHz frequency without solar cell and with solar cell. The proposed design provides the conversion of light energy to electric energy. The relative study of the design gives the performance measures like return loss, gain, and radiation patterns.

The capitalization table, commonly known as a cap table, is a comprehensive record of ownership and equity distribution within a company. It serves as a document, typically in the form of a spreadsheet or database table, that outlines all the securities or shares in a company and presents the equity capitalization of the company. However, cap tables maintained on centralized databases are susceptible to significant attacks. Corda has emerged as a blockchain platform specifically designed for business applications, prioritizing privacy and scalability. Corda operates as a private blockchain, enabling communication exclusively between involved parties in a transaction. Its primary objective is to facilitate secure and efficient value-added transactions and data sharing among businesses. As a solution, a Corda-based platform is proposed to bring together companies and investors for private equity funding. The proposed platform leverages a secure version of the cap table, referred to as a mirror table, to deliver cap table functionalities. By utilizing the blockchain technology provided by Corda, transactions become secure and tamper-proof, significantly reducing the risk of fraudulent activities and enhancing investor confidence. This innovative approach has the potential to revolutionize the crowdfunding industry by establishing a secure and transparent means for businesses to raise capital and for investors to participate in investments.

Innovations in AI have altered various industries, changed how we think of plausible solutions for any problem, and allowed us to create products, thoughts, and concepts that were previously unimaginable. As a result, more patent applications for inventions created by AI have been filed, raising several questions about the legal standing of AI as an inventor. In addition to offering a critical study of the worldwide legal system regulating the patenting of AI-generated work, this non-empirical research article explores the consequences and difficulties of acknowledging AI as an inventor. By reviewing the existing legal framework, examining inventorship criteria, analyzing challenges tied to legal inventorship for AI-generated inventions, reviewing relevant case law, and proposing potential solutions, this study sheds light on the complex legal, ethical, and social considerations involved. Furthermore, it suggests future research directions, including the exploration of dedicated patent laws and regulations for AI-generated inventions, as well as investigations into the ethical and social implications and potential consequences of acknowledging AI as a legal inventor.

Cybersecurity is a major concern due to the increasing reliance on technology and interconnected systems. Malware detectors help mitigate cyber attacks by comparing malware signatures. Machine learning can improve these detectors by automating feature extraction, identifying patterns, and enhancing dynamic analysis. In this paper, the performance of six multiclass classification models is compared on the Malimg dataset, Blended dataset, and Malevis dataset to gain insights into the effect of class imbalance on model performance and convergence. It is observed that the more the class imbalance less the number of epochs required for convergence and a high variance across the performance of different models. Moreover, it is also observed that for malware detectors ResNet50, EfficientNetB0, and DenseNet169 can handle imbalanced and balanced data well. A maximum precision of 97% is obtained for the imbalanced dataset, a maximum precision of 95% is obtained on the intermediate imbalance dataset, and a maximum precision of 95% is obtained for the perfectly balanced dataset.

The prediction of a business plays a major role in market analysis. In order to look for the business potential in the market, we have conducted a study to explore how the combination of artificial intelligence (AI) and business intelligence (BI) techniques can be used for regional market analysis to get the best potential in an area and predict the business. Our research focused on analyzing and interpreting data from various sources, such as demographics, economic indicators, consumer behavior, and social media. Decisions are made in terms of two parameters: insight and forecast. We aimed to generate insights and forecasts that would assist businesses in making informed decisions. To achieve the insight and forecast, we used the OSEMN framework. OSEMN stands for Obtain, Scrub, Explore, Manipulate, and Interpret. This framework is useful in gathering relevant data, cleaning and preparing it for analysis, exploring patterns and trends, manipulating the data as needed, and interpreting the findings. We conducted a regional market analysis case study, by employing machine learning algorithms and data mining techniques within this framework. Our project resulted in providing a piece of valuable information on market trends, customer preferences, and potential investment opportunities. These results demonstrated the potential of AI and BI in enhancing business intelligence and decision-making processes, particularly in the context of regional market analysis. We highlighted the benefits of utilizing AI and BI technologies while acknowledging the boundaries and challenges they may present. We also discussed the implications and limitations of this approach. We have suggested some potential areas for further study in this field, recognizing the need for ongoing research to refine and expand upon these techniques.

The use of smart grid technologies, in the energy sector has brought about upgrade, such as high efficiency, lower operating costs and better energy management. However, it has also established security aspects. Safeguarding the smart grid is of importance due to its role as essential infrastructure. The innovative potential of blockchain holds promise in enhancing the security of the grid. This paper aims to explore how blockchain technology can be utilized for protecting the grid. It delves into the security issues associated with grids and investigates how blockchain can address them. Additionally, it provides an analysis of studies on blockchain and its application, in grid protection while considering the pros and cons of utilizing blockchain based solutions.

Recently, several significant growth in the perception of Renewable Energy Sources (RES) in power systems, has led to a drop in the complete system inertia. The tie-line power movement and frequency stability control are two important aspects of power system operation. In this paper, a virtual inertia controller is proposed for a hybrid interconnected power system to enhance the frequency stability and control the tie-line power flow. The VIC follows the inertia of synchronous generators using power electronics converters. The controller calculates the power imbalance concerning the generation and consumption in the power system and provides a proportional response to maintain the system frequency within the desired range. The Grey Wolf Optimization (GWO) algorithm can be used to enhance the controller parameters, such as the gain and time constant, to minimize the frequency deviation in the power system. The proposed controller is designed to regulate the power output of renewable energy sources and provide a frequency response during a disturbance. The model result demonstrates that the suggested controller enhances the frequency stability and reduces the power fluctuations caused by the RES.

This study concentrates on different types of prognosis algorithms for forecasting lithium-ion battery parameters. Various SoC estimation techniques are examined and compared based on their SoC estimation performance indexes. SoC estimation methods are broadly classified as Kalman filter, particle filter, data-driven and hybrid methods. These types of filters are compared based on the complexity of the implementation on hardware as well as their performance parameters such as statistics (errors), driving test schedules, laboratory testing data, type of battery model used and different types of prognosis methods used in the SoC estimation. It helps in the proper selection of the hardware and methods for battery model parameter forecasting which is critical for electrical vehicle (EVs) battery management system coordination and control. This study also focuses on the challenges faced by the different SoC prognosis methods and their modern trends to improve the forecasting of important parameters of the batteries.

Agricultural products decide the economy of a country like India. The agricultural business has the involvement of a large population. The quality and quantity of agricultural products highly depend on environmental conditions and facilities provided to farmers. Timely and efficient detection of diseases in plants and crops is one of the most critical issues that affect crop production. Therefore, it is highly desirable to develop some cheap and easy-to-handle automated plant disease detection systems for the timely treatment of plants. Leaves are considered a primary source of information about the health of plants. In the case of plants, the disease may be easily visualized and identified by observing its effect on leaves. Therefore, this paper introduces a bag-of-features in sigmoidal spider monkey optimization to identify a diseased leaf, separating the diseased leaf from a healthy leaf. The investigational outcomes show the superiority of the anticipated technique in contrast to other meta-heuristic-based systems.

Smart grid is a reliable and efficient system for electrical power distribution in recent years. One of the drawbacks of this grid is its susceptibility to cyber-attacks. State estimation of the power grid under such an attack is of utmost importance for preventing serious damage to the grid. This paper focuses on the detection of False Data Injection (FDI) attacks that manipulates the Phasor Measurement Unit (PMU) data. An algorithm is presented that can detect the attack zone by analyzing the anomalies in the measurement after the attack. The algorithm is tested on the standard IEEE 118-bus system and the estimation error is used to evaluate the performance of this algorithm. It can successfully detect the attacked buses and estimate the parameters after the attack using graph theoretical methods. The algorithm also differentiates between attacks, load disturbances and single-line faults in the grid.