Search

This study examines the latest utilization of the combination of machine learning (ML) and artificial intelligence (AI) in the monitoring and upgrading of water quality, which has become a crucial component of environmental management. In this paper, a thorough examination of modern methods and recent advancements in the fields of artificial intelligence (AI) and machine learning (ML) algorithms, which have considerably enhanced the precision and effectiveness of water quality tracking systems. The study analyzes the integration of these innovations into water treatment methods, focusing their ability to more efficiently identify and reduce contaminants compared to traditional techniques. This paper examines a collection of case studies in which artificial intelligence (AI)-powered devices have been used, showcasing significant developments in the evaluation of water quality and improved levels of treatment efficiency. The present study additionally analyzes the various problems and potential future developments of Artificial Intelligence (AI) and Machine Learning (ML) within this particular domain. These challenges cover issues of scalability, data security, as well as the importance for interdisciplinary collaboration. This paper gives a comprehensive analysis of the impact of AI and ML technologies on water quality management, demonstrating their potential to transform current practices towards greater sustainability and efficiency.

This research paper explores the opportunities and challenges associated with the use of machine learning and artificial intelligence in advanced materials processing. With the exponential growth of data, advanced analytical techniques and powerful computational tools, machine learning and artificial intelligence can be leveraged to develop novel materials with tailored properties, enhance process optimization, and improve manufacturing efficiencies. However, the integration of these technologies into materials processing systems is not without challenges, including data acquisition and pre-processing, algorithm selection and optimization, and the interpretation of results. This paper provides an overview of the state-of-the-art in machine learning and artificial intelligence for advanced materials processing, highlighting case studies and examples of successful applications, and identifying potential future research directions. The goal of this research is to provide insights and recommendations to accelerate the adoption of these technologies and their impact on the development of advanced materials.

Machine learning algorithms have quickly risen to the top of several fields' decision-making processes in recent years. However, it is simple for these algorithms to confirm already present prejudices in data, leading to biassed and unfair choices. In this work, we examine bias in machine learning in great detail and offer strategies for promoting fair and moral algorithm design. The paper then emphasises the value of fairnessaware machine learning algorithms, which aim to lessen bias by including fairness constraints into the training and evaluation procedures. Reweighting, adversarial training, and resampling are a few strategies that could be used to overcome prejudice. Machine learning systems that better serve society and respect ethical ideals can be developed by promoting justice, transparency, and inclusivity. This paper lays the groundwork for researchers, practitioners, and policymakers to forward the cause of ethical and fair machine learning through concerted effort.

The increasing demand for energy utilization in smart homes has led to the exploration of machine learning techniques as a means to optimize energy consumption. This review paper explores the merits and demerits of using machine learning techniques for energy optimization in smart homes. Smart homes are becoming increasingly popular due to the potential benefits they offer, including increased energy efficiency, improved comfort, and enhanced security. However, to achieve these benefits, it is essential to optimize the energy utilization in smart homes. This paper presents machine learning techniques that have been used to optimize energy utilization in smart homes. In this paper proposed the using Stochastic Gradient Descent (SGD) algorithm for optimizing energy utilization in smart homes. However, challenges such as data privacy, accuracy of data collection, and cost may hinder the full adoption of these techniques.

The paper “Design and Implementation of a Smart Home Energy Management System Using IoT and Machine Learning” proposes a system that aims to optimize energy consumption in a smart home environment. The system uses Internet of Things (IoT) devices to collect real-time data on energy usage and machine learning algorithms to predict future consumption patterns. This paper proposes the use of deep neural networks (DNNs) for the design and implementation of a smart home energy management system using IoT and machine learning techniques. The authors demonstrate the effectiveness of the system through experimental results, showing significant energy savings compared to traditional methods. The DNN is built using Keras or Tensor Flow and is trained on extracted features from energy consumption data collected using IoT sensors. The system is implemented with a real-time monitoring system and a user interface for remote access. The proposed system has the potential to save energy and reduce energy costs for households while providing real-time feedback to the user.

The paper presents a near investigation of different AI procedures for solar power forecasting. The objective of the research is to identify the most accurate and efficient machine learning algorithms for solar power forecasting. The paper also considers different parameters such as weather conditions, solar radiation, and time of day in the forecasting model. This paper proposes a hybrid machine learning model for solar power forecasting that consolidates the strengths of multiple algorithms, including support vector regression, random forest regression, and artificial neural network. However, the study also highlights the importance of incorporating domain knowledge and feature engineering in machine learning models for better forecasting accuracy.

In this paper, we introduce a prediction algorithm that will determine the likelihood that a client will purchase from a website or not. This system is part of a global e-commerce solution that will help the clients to get the best possible experience. The paper presents an overview of the e-commerce system’s various components and their various steps and also an activity diagram of the system, which shows the various steps that the platform can perform. It also provides a general idea of the system’s workflow.

After the emergence of many new technologies, it is possible to search on the development of new devices that can be predicting what is happening in human thought based on EEG signals, such as the method used this paper contains a novel classification of the EEG signals acquired for multiple motor cortex-imagery tasks, where this method was based on the use of the Extra Tree algorithm to well select the best channels that were used for the acquisition of EEG signals, then the use of support vector machine (SVM) algorithm for data classification, moreover this work uses grey wolf optimizer (GWO) algorithm to improve all SVM parameters quickly and to converge the accuracy of the system towards the highest possible values. As a result, this work shows that the accuracy of prediction of motor cortex-imagery based EEG signals can be increased more than 99%. Also, this paper contains a comparison with other methods of the literature.

This paper presents a novel use of machine learning techniques for identifying faults in renewable microgrids within the field of decentralized energy systems. The study investigates the effectiveness of machine learning models in identifying abnormalities in dynamic and variable microgrid environments. It utilizes a comprehensive dataset that includes parameters such as solar, wind, and hydro power generation, energy storage status, and fault indicators. The investigation demonstrates a notable 94% precision in identifying faults, highlighting the superiority of machine learning compared to conventional rule-based approaches, which attained an accuracy rate of 80%. The precision and recall measures emphasize the well-balanced performance of the machine learning models, reducing both false positives and false negatives, and guaranteeing precise problem detection. The effect of faults on microgrid efficiency is significantly reduced, with an only 2% decrease recorded under fault situations, demonstrating the models’ ability to maintain an efficient energy supply. A comparative study reveals a 14% improvement in accuracy when compared to conventional techniques, emphasizing the benefits of adaptive and data-driven approaches in identifying intricate fault patterns. The sensitivity study validates the resilience of the machine learning models, demonstrating their capacity to adjust to different settings. The practical application of the models is validated by real-world testing in a simulated microgrid environment, which leads to their repeated improvement and improved performance. Ethical concerns play a crucial role in assuring ethical data use during research, particularly in the implementation of machine learning, by upholding privacy and security requirements. The study results indicate significant implications for identifying faults in renewable microgrids, providing a potential opportunity for the progress of robust and sustainable decentralized energy networks. The effectiveness of machine learning models stimulates further study in expanding their deployment for varied microgrid situations, including more machine learning approaches, and resolving obstacles associated with real-time application in operational settings.

Greenhouse cultivation plays a pivotal role in modern agriculture by providing a controlled environment for plant growth. The significance of greenhouse insulation lies in its ability to create optimal conditions for plant development, ensuring increased crop productivity and quality. This paper emphasizes the criticality of greenhouse insulation and the necessity for effective predictive models to anticipate plant growth and yield accurately. This research proposes the utilization of Machine Learning (ML)and Deep Learning (DL) techniques to forecast plant growth and yield within controlled greenhouse settings. To achieve this, a novel deep recurrent neural network (RNN) architecture employing the Long Short-Term Memory (LSTM) neuron model is deployed in the prediction process.The study offers a comparative analysis involving various ML methodologies such as support vector regression and random forest regression. The performance evaluation of these diverse methods is conducted using the mean square error criterion to assess their effectivenessin predicting plant growth and yield. The model's sophisticated architecture enables it to produce accurate and timely predictions regarding specific growth parameters by leveraging an advanced neural network. This holistic approach introduces a novel perspective in greenhouse tomato cultivation, providing growers with valuable insights to facilitate informed decision-making, streamline resource distribution, and promote heightened agricultural sustainability.

The emergence of electric vehicles (EVs) as a mainstream mode of transportation presents new challenges in the realm of power electronics, particularly concerning reliability and longevity. Power electronics are the cornerstone of EV performance, dictating efficiency, durability, and overall vehicle health. Traditional maintenance strategies fall short in addressing the dynamic operational demands and complex failure mechanisms inherent in EV power systems. This paper introduces a machine learning (ML)-enhanced predictive maintenance framework designed to revolutionize the upkeep of EV power electronics. By harnessing advanced ML algorithms, the framework predicts potential system failures and degradation patterns, enabling preemptive maintenance actions. A robust data-driven approach is employed, utilizing operational data and failure modes to train the predictive models. The efficacy of the proposed method is demonstrated through extensive simulation and real-world EV power system analyses, showcasing significant improvements in fault identification accuracy and maintenance scheduling optimization. The result is a substantial extension of component lifespan and a reduction in unplanned downtimes, propelling EV power electronics towards higher reliability standards. This work not only contributes a novel predictive maintenance methodology but also paves the way for adaptive maintenance regimes, tailored to the unique demands of EV power electronics systems in the pursuit of sustainable and resilient transportation solutions.

As the world seeks sustainable energy solutions, Internet of Things (IoT) applications demand consistent and efficient power sources. This paper presents an innovative hybrid renewable energy system, seamlessly integrating solar photovoltaic panels, wind turbines, and hydrogen fuel cells, tailored for IoT applications. Through machine learning algorithms, our proposed system not only optimizes energy generation in real-time but also ensures uninterrupted energy supply to IoT devices and consumers, even in fluctuating environmental conditions. This universal approach markedly diminishes the dependence on non-renewable energy sources, promoting a greener and more resilient energy infrastructure. The incorporation of hydrogen fuel cells uniquely positions our system as a reservoir for excess energy, ensuring consistent power even when solar or wind outputs diminish. Moreover, by synchronizing IoT devices with our energy system, we have procured real-time data on energy dynamics, facilitating unparalleled optimization and reduced wastage. The presented system shows the way for a sustainable future through the efficient green energy generation with the ever-evolving landscape of IoT applications and machine learning techniques.

The Internet of Things (IoT) is a rapidly evolving environment that allows users to use and control a wide variety of connected objects. The 20 billion IoT devices that will be employed by 2020 are only the top of the iceberg. According to IDC, the overall amount of connected devices will rise to 41.6 billion over the next five years, producing over 80 Zettabytes of data by 2025 which will impact environment severely. These connected environments increase the attack surface of a system since; the risks are multiplied by the number of connected devices. These devices are responsible for more or less critical tasks, and can therefore be the target of users malicious, in this paper we present a methodology to evaluate the security of IoT systems. We propose a way to represent IoT systems, coupled with attack trees in order to assess the chances of success of an attack on a given system.

With the progress of time series prediction, several recent developments in machine learning have shown that the integration of prediction methods into portfolio selection is a great opportunity to structure investment decisions in the renewable energy industry. In this paper, we propose a novel approach to portfolio formation strategy based on a hybrid machine learning model that combines a convolutional neural network (CNN) and long-term bidirectional memory (BiLSTM) with robust input characteristics obtained from Huber’s location for stock prediction and the mean-variance (MV) Markowitz model for optimal portfolio construction. Specifically, this study first applies a prediction method for stock pre-selection to ensure high-quality stock inflows for portfolio formation. Then, the predicted results are integrated into the MV model. To comprehensively demonstrate the superiority of the proposed model, we used two portfolio models, the MV model and the equal-weighted (1/N) portfolio model, with LSTM, BiLSTM and CNN-BiLSTM, and used them as references. Between January 2016 and December 2021, historical data from the Stock Exchange of Thailand 50 Index (SET50) was collected for the study. Experience shows that integrating stock pre-selection can improve VM performance, and the results of the proposed method show that they outperform comparison models in terms of Sharpe ratio, average return and risk.

Suitable maintenance management plants of solar photovoltaic plants are required for global energy demands. The volume and variety of data acquired by thermographic cameras carried by unmanned aerial vehicles and Supervisory Control and Data Acquisition Systems increase the complexity of fault detection and diagnosis. The maintenance industry is requiring novel fault detection techniques that can be implemented in Internet of Thing platforms to automate the analysis and increase the suitability and reliability of the results. This paper presents a novel platform built with PHP, HTML, CSS and JavaScript for the combined analysis of data from Supervisory Control and Data Acquisition Systems and thermal images. The platform is designed. A real case study with thermal images and time series data from the same photovoltaic plant is presented to test the viability of the platform. The analysis of thermal images showed a 97% of accuracy for panel detection and 87% for hot spot detection. Shapelets algorithm is selected for time series analysis, providing an 84% of accuracy for the pattern selected by user. The platform has proven to be a flexible tool that can be applied for different solar plants through data upload by users.

The goal of this research is to enhance the accuracy of predicting students' performance in online education during the Covid-19 pandemic by comparing the Novel Inception algorithm with the GoogleNet algorithm. Materials and Methods: The current research paper investigates the performance of two distinct algorithms, namely the Novel Inception algorithm and the GoogleNet algorithm, in two separate groups with 20 samples in each group. The statistical significance of the collected data was assessed using SPSS with a G-power value set at 85%. The study also explores the accuracies of these algorithms with varying sample sizes. Result: Inception algorithm provides a higher accuracy of 91.0480% when compared to GoogleNet algorithm with accuracy of 89.8860% in predicting the Performance of Students in online education during covid. With a significance value of p=0.007 (p

Automatic text summarization is increasingly required with the exponential growth of unstructured text through increasing internet and social media usage across the globe. The various approaches are outcomes of extraction-based and abstraction-based. In Extraction-based summarization, the extracted content from the original data, is typically presented in the same or slightly modified form without significant paraphrasing or restructuring. Abstractive methods involve building an internal representation of the original content and then using that representation to generate a summary that may not be present in the original text verbatim. They employ natural language processing techniques, such as language generation models, to paraphrase and rephrase sections of the source document to create a more human-like summary. Abstraction in abstractive summarization is indeed a challenging task because it requires not only linguistic and syntactic understanding but also a deeper semantic understanding of the original content. The evaluation of automatically summarized text through criteria of precision and recall, and various evaluation methods, datasets used for domain based and generic text summarization. This paper proposes the Sentence Length Impact (SLI) algorithm to summarize English text content, which gives 92% accuracy and translating the same in French.

The primary resource of a country is agriculture and crop production. The economic development of the country also resides on the agricultural products which ultimately determines the growth of the citizen. The major crisis in food production is the influence of diseases in plants. This ultimately abolish the economy of the country, as major portion of progress of the nation is dependent on agriculture and its products. The challenges faced by the farmers are the unawareness of the various diseases that affects different parts of the plants. They should be able to identify the early infection caused in plants by different pathogens like bacteria, fungi, virus etc., Main disease-causing agent is found to be the fungus which was the vital factor that produce serious loss in the agriculture. Again, the pesticides and fertilizers used by the agriculturist changes to be hazardous for human beings and wild life species. This problem should be considered as a chief calamity and an alternate measure must be found to support the cultivators. An innovative step adopted by the researchers are prompt detection of the diseases using machine learning and deep learning algorithms. These algorithms use different image processing techniques and computer vision process to classify the disease in plant parts at an earlier stage. This paper provides a detailed review on the fungal infection caused in plant leaves and its identification using deep learning methodology.

Wind energy is an essential source of renewable energy that has gained popularity in recent years. Accurately forecasting wind energy production is crucial for efficient energy management and distribution. This paper proposes a machine learning-based approach using Support Vector Regression (SVR) and Random Forest Regression (RFR) to forecast wind energy production. The proposed methodology involves data collection, preprocessing, feature selection, model training, optimization, and evaluation. The performance of the models is assessed using mean squared error (MSE), root mean squared error (RMSE), and coefficient of determination (R-squared) metrics. The results indicate that the proposed SVR-RFR model outperforms individual models, achieving a higher accuracy in forecasting wind energy production.

The growing demand for sustainable and eco-friendly transportation has led to the widespread adoption of electric vehicles (EVs). However, the limited driving range of EVs and the need for frequent recharging remain significant challenges. To address these challenges, researchers have proposed various energy optimization techniques, including machine learning-based approaches. In this paper, proposed method of Smart EV energy optimization systems for EVs. The system uses machine learning algorithms to analyze and learn from historical driving data, such as the driving patterns, road conditions, weather, and traffic. Based on this analysis, the system predicts the energy consumption of the EV and optimizes the energy usage to minimize energy waste and extend the driving range.

Water scarcity is a major challenge in the agriculture industry, and traditional irrigation methods are often wasteful and inefficient. To address this challenge, a smart solar irrigation system that uses loT and Artificial Neural Network (ANN) algorithms can optimize water usage for agriculture. The system can provide automated irrigation, improve crop yields, and reduce water consumption. This paper proposes a design and implementation methodology of a smart solar irrigation system using loT and ANN algorithms. The system includes solar panels, a water pump, a water storage tank, sensors, loT devices, and ANN algorithms. The system is designed to automate the irrigation process by controlling the water pump based on the data collected from the sensors.

The Machine Learning-Based Wind Turbine Control System (MLBWTCS) is a new technology that uses machine learning algorithms to optimize the performance of wind turbines. The system collects data from sensors installed on the wind turbine to monitor various variables such as wind speed, blade pitch angle, generator torque, and power output. The data collected is preprocessed and fed into a machine learning model, which predicts the optimal settings for the turbine operations. The predictions are then used to control the operations of the wind turbine in real-time. The MLBWTCS has been shown to improve the efficiency and reliability of wind turbines, resulting in increased power generation and reduced maintenance costs. This paper presents a detailed description of the design and implementation of the MLBWTCS, including data collection, preprocessing, feature selection and machine learning model selection.

Investment in human capital, along with natural resource management, is an important indicator of sustainable development. One of the areas of such investments is the creation of artificial intelligence systems that allow for the classification of texts. This paper analyzes the use of artificial intelligence systems for stylometric text analysis. On the basis of the algorithm of the convolutional artificial immune system, a system for stylometric analysis of texts was developed and implemented in software. In order to determine the possibility of using this system to determine the authorship of literary works, it was trained and tested. For this, the works of two authors were chosen: Leo Tolstoy and Fyodor Kryukov. This system demonstrated a high quality of text classification and a good speed of work and learning. So, to test the performance of the system, 11 works by Leo Tolstoy and 12 works by Fedor Kryukov were taken that were not used to train the system. All works of these authors were classified correctly. It should be noted that the artificial immune system algorithm can also be successfully used in other tasks requiring text classification.

The large increase in the on-road vehicle population in China has raised sustainability concerns regarding air pollution prevention, energy conservation, and climate change mitigation. Vehicle emission inventory is an irreplaceable tool to characterize the temporal and spatial distribution of the air pollutant and provide guidance to the policy makers with effective vehicle emission controls. This review paper reviewed two kinds of typical vehicle emission inventories. The top-down vehicle emission inventories is calculated based on the static datasets (e.g., vehicle population, vehicle kilometer traveled, and fuel consumption). These inventories could track historical emissions abatement progress and examine potential benefits from future regulations. The technological evolution in intelligent transportation systems have facilitated emission inventories to satisfy the increasing sophisticated management demand. The bottom-up link-level vehicle emission inventories are development based on the availability of the real-world traffic profiles. To simulate the temporal and spatial patterns with high-resolution, traffic demand model and machine learning methods are employed to elucidate traffic emissions.

In this paper we present a high performance Deep Learning architecture based on Convolutional Neural Network (CNN). The proposed architecture is effective as it is capable of recognizing and analyzing with high accuracy different Sign language datasets. The sign language recognition is one of the most important tasks that will change the lives of deaf people by facilitating their daily life and their integration into society. Our approach was trained and tested on an American Sign Language (ASL) dataset, Irish Sign Alphabets (ISL) dataset and Arabic Sign Language Alphabet (ArASL) dataset and outperforms the state-of-the-art methods by providing a recognition rate of 99% for ASL and ISL, and 98% for ArASL.

Today, Machine Learning is being rolled out in a variety of areas. It is a promising field that can offer several assets and can revolutionize several aspects of technology. Nevertheless, despite the advantages of machine learning technologies, learning algorithms can be exploited by attackers to carry out illicit activities. Therefore, the field of security of machine learning is deriving attention in these times so as to meet this challenge and develop secure learning models. In this paper, we overview a taxonomy that will help us understand and analyze the security of machine learning models. In the next sections, we conduct a comparative study of most widespread adversarial attacks then, we analyze common methods that were advanced to protect systems built on Machine learning models from adversaries. Finally, we discuss a proposition of a pattern designed to ensure a security assessment of machine learning models.

Phishing is a common attack on credulous people by making them disclose their unique information. It is a type of cyber-crime where false sites allure exploited people to give delicate data. This paper deals with methods for detecting phishing websites by analyzing various features of URLs by Machine learning techniques. This experimentation discusses the methods used for detection of phishing websites based on lexical features, host properties and page importance properties. We consider various data mining algorithms for evaluation of the features in order to get a better understanding of the structure of URLs that spread phishing. To protect end users from visiting these sites, we can try to identify the phishing URLs by analyzing their lexical and host-based features.A particular challenge in this domain is that criminals are constantly making new strategies to counter our defense measures. To succeed in this contest, we need Machine Learning algorithms that continually adapt to new examples and features of phishing URLs.

In this paper, we discuss the prediction of future solar cell photo-current generated by the machine learning algorithm. For the selection of prediction methods, we compared and explored different prediction methods. Precision, MSE and MAE were used as models due to its adaptable and probabilistic methodology on model selection. This study uses machine learning algorithms as a research method that develops models for predicting solar cell photo-current. We create an electric current prediction model. In view of the models of machine learning algorithms for example, linear regression, Lasso regression, K Nearest Neighbors, decision tree and random forest, watch their order precision execution. In this point, we recommend a solar cell photocurrent prediction model for better information based on resistance assessment. These reviews show that the linear regression algorithm, given the precision, reliably outperforms alternative models in performing the solar cell photo-current prediction Iph

The prediction lifetime of a Lithium-ion battery is able to be utilized as an early warning system to prevent the battery’s failure that makes it very significant for assuring safety and reliability. This paper represents a benchmark study that compares its RUL prediction results of single and hybrid methods with similar articles. We suggest a hybrid method, named the CNN-LSTM, which is a combination of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM), for predicting and improving the accuracy of the remaining useful life (RUL) of Lithium-ion battery. We selected three statistical indicators (MAE, R², and RMSE) to assess the results of performance prediction. Experimental validation is performed using the lithium-ion battery dataset from the NASA and results reveal that the effectiveness of the suggested hybrid method in reducing the prediction error and in achieving better RUL prediction performance compared to the other algorithms.

Sentiment analysis is a very substantial area of research in our environment. Many studies have focused on the topic in recent years. It has rapidly gained interest due to the unusual volume of opinion-bearing data on the Internet (Big Social Data). In this paper, we focus on sentiment environment analysis from Amazon customer reviews shared by a machine learning based approach. This process starts with the collection of reviews and their annotation followed by a text pre-processing phase in order to extract words that are reduced to their root. These words will be used for the construction of input variables using several combinations of extraction and weighting schemes. Classification is then performed by a supervised Machine Learning classifier. The results obtained from the experiments are very promising.