Search

This paper reviews the work in the areas of machine learning applications for energy management in smart buildings, 5G technology’s role in smart energy management, and the use of machine learning algorithms in microgrid energy management systems. The first area focuses on the adaptability of building-integrated energy systems to unpredictable changes through AI-initiated learning processes and digital twins. The second area explores the impact of 5G technology on smart buildings, particularly in Singapore, emphasizing its role in facilitating high-class services and efficient functionalities. The third area delves into the application of various machine learning algorithms, such as supervised and unsupervised learning, in managing and monitoring microgrids. These broad areas collectively offer a comprehensive understanding of how machine learning can revolutionize energy management systems in smart buildings, making them more efficient, adaptable, and sustainable.

Machine Learning (ML) has become a potent predictive analytics tool in several fields, including the study of social media data. Social media sites have developed into massive repositories of user-generated information, providing insightful data about user trends, interests, and behavior. This abstract emphasizes the use of machine learning methods for predictive analytics in social media data and examines the potential and problems unique to this field. Utilizing the capabilities of machine learning algorithms to identify significant trends and forecast user behavior from social media data is the goal of this study. The study makes use of a sizable dataset made up of user profiles, blog posts, comments, and engagement metrics gathered from well-known social networking sites. Predictive models are created using a variety of machine learning algorithms, such as ensemble methods, neural networks, decision trees, and support vector machines. As a result, this study emphasizes how important machine learning is for doing predictive analytics on social media data. The employment of diverse algorithms and preprocessing methods yields insightful information about user behavior and enables precise prediction of user behaviors. To improve the prediction powers of machine learning in this area, future research should concentrate on tackling the obstacles related to social media data, such as privacy concerns and data quality issues.

In the innovative work secure communication and data protection are being main field, which are emerged by cryptography as a fundamental pillar. Strong cryptographic methods are now essential given the rising reliance on digital technologies and the threats posed by bad actors. This abstract examines the evolution of secure communication protocols and data protection techniques as it relates to the advancements in cryptography. The development of post-quantum cryptography is the most notable development in cryptography discussed in this study. As quantum computers become more powerful, they pose a serious threat to traditional cryptographic algorithms, such as RSA and ECC. Designing algorithms that are immune to attacks from quantum computers is the goal of post-quantum cryptography. Lattice-based, code-based, and multivariate-based cryptography are only a few of the methods that have been investigated in this context.

In network analysis, the study and comprehension of complex systems in numerous fields, such as social networks, transportation networks, and biological networks, are made possible by the crucial role played by graph theory and algorithms. In order to give a comprehensive review of the graph theory and network analysis methods, this abstract will focus on their significance, practical uses, and most recent developments. With items represented as nodes or vertices and links between them as edges, graph theory offers a mathematical framework for modeling and evaluating relationships between objects. Researchers may learn important things about the structure, connectivity, and behavior of complex systems by using graph theory in network analysis. As a result, network analysis is made possible by the graph theory and algorithms, which offer strong tools for studying and comprehending the complicated linkages and structures of complex systems. Graph theory and algorithms have many different applications, including social networks, transportation networks, and biological networks. Large-scale network analysis is now possible thanks to the development of effective algorithms and methodologies, which has significantly advanced the subject. The significance of graph theory and algorithms for network research will only rise as networks continue to expand in size and complexity.

One of the most potential uses of artificial intelligence (AI), which has changed a number of industries, is in healthcare. The application of AI in healthcare is discussed in general in this study, with an emphasis on diagnosis, treatment, and prediction. In the area of diagnostics, AI has proven to be remarkably adept at deciphering X-rays, CT scans, and MRI pictures to spot illnesses and anomalies. A branch of AI known as deep learning algorithms has shown to be particularly good at accurately identifying and categorizing medical disorders. Large volumes of imaging data may be swiftly analyzed by AI systems, enabling medical personnel to diagnose patients more accurately and with fewer mistakes. Additionally, AI may combine patient information, genetic data, and other pertinent data to produce tailored diagnostic suggestions. Consequently, AI has become a game-changing force in healthcare, especially in the disciplines of diagnosis, treatment, and prediction. AI systems can help medical personnel make more precise diagnoses, create individualized treatment plans, and forecast patient outcomes by utilizing machine learning algorithms and advanced data analytics. While there are still difficulties, there are enormous potential advantages for AI in healthcare, and coordinated efforts are required to realize these advantages and assure its ethical and fair incorporation into healthcare systems.

The significance of quality and productivity in the manufacturing industry cannot be overstated, as they directly impact profitability. To remain competitive and keep pace with advancements in technology, manufacturing industries must continuously improve their processes to enhance the quality and productivity of their products. One technology that has contributed to such improvements is CNC milling machines, which have been used in this study. For this study, the high-strength, ductile, and wear-resistant steel alloy EN24 was selected for milling. Taguchi L9 orthogonal array proposal of experiment was used to select cutting parameters, and a total of nine milling operations were conducted. Rate of material removal and surface roughness were calculated for all the nine experiments. Signal-to-noise (S/N) ratios and mean values were used to identify the influencing cutting parameter for material removal rate and surface roughness. ANOVA technique was employed to calculate the optimal cutting parameters for achieving better material removal rate and surface roughness. To analyze the parameters that influence MRR and surface roughness, a comparison was made between the S/N ratios and initial readings using ANOVA technique. Overall, this study demonstrated the importance of selecting appropriate cutting parameters for achieving optimal MRR and surface roughness of CNC milling procedures, which can lead to improvements in quality and productivity in the manufacturing industry.

In the modern age of technology where everything is powered via physical wires, once considered a technical marvel has now become a bane. Wireless power transfer is the key to the future of power transfer, in this paper a 1kW WPT system is designed and simulated for an PMBLDC motor driven autonomous vehicle. This paper focuses in detail about the variation in performance of the coils and the overall system when ferrite cores and aluminum shielding is considered along with the coils. It provides a comprehensive analysis on the misalignment of transmitter and receiver coils in different orientations and distances. The results indicate a significant increase in power transfer and efficiency of the system when extra components such as cores and shielding are also implemented. It is oriented towards increasing the efficiency of powering autonomous vehicles used in various sectors such as automobiles, information technology, aerospace, robotics, precision and domestic equipment, etc.

Lung cancer is a leading cause of cancer-related deaths worldwide, with a high mortality rate and a significant economic burden on health care systems. Traditional screening methods, such as X-rays and CT scans, have limitations in terms of accuracy and efficiency, leading to many cases of lung cancer being diagnosed at a later stage, when treatment options are limited. In this paper, we aim to develop a highly accurate and efficient tool for detecting lung cancer using a NN classifier. We first build a large dataset of medical images and patient data for training and evaluating the NN classifier. The dataset includes a variety of imaging modalities, including CT scans, X-rays, and other medical images. We then develop and train a NN classifier for lung cancer detection, using a deep learning technique. The NN classifiers optimized for high accuracy and efficiency, with the goal of achieving earlier and more accurate diagnosis of lung cancer. We evaluate the performance of the NN classifier using a variety of metrics, including sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). The classifier is tested on a separate test dataset to ensure that it generalizes well to new data. We also compare the performance of the NN classifier to other traditional screening methods, such as X-rays and CT scans, to determine the potential impact of the NN classifier on lung cancer screening. Finally, we use explainable machine learning technique called as GLCM to identify specific features and patterns in medical images that are indicative of lung cancer. This analysis provides insights into other underlying mechanisms of lung cancer development and may lead to new discoveries and treatment options.

A number of power electronics converter topologies are implemented as Wireless Power Transfer (WPT) systems applications expand. In these applications, the optimal converter design is essential for handling the high power and frequency operation. In this paper, Simulation & Hardware development of High frequency Inverter with 90KHz frequency with Pulse Width Modulation switching strategy is presented. The inverter topology is simulated in 2021a version MATLAB/Simulink with R and RL loads and its conversion ability is proven through relevant waveforms. Simultaneously designed and developed prototype model of power rating 100watt with Mosfet as switches at output voltage of 230V with R load and analyse the output behaviour of voltage waveforms at various loads. The outcomes show effective enhancements for the proposed design.

Face emotion recognition is a challenging problem in computer vision that has been extensively studied in recent years. The project investigates the performance of Local Binary Pattern (LBP), Histogram of Oriented Gradients (HOG), K- Nearest Neighbour (KNN), and Support Vector Machine (SVM) for face emotion recognition. The aim of this study is to evaluate the performance of different combinations of these techniques and to identify the most effective approach for this task. To achieve this, we first collected a dataset of facial expressions that includes seven basic emotions such as happy, sad, angry, surprise, Neutral, fear, and disgust. We then extract LBP and HOG features from the facial images and then KNN and SVM classifiers to classify the emotions. We experimented with various combinations of LBP, HOG, KNN, and SVM and evaluated the performance of each approach using metrics such as accuracy, precision, recall, and F1 score. This study demonstrates the effectiveness of combining LBP and HOG features with KNN and SVM for face emotion recognition. Our results suggest that SVM is the most effective model for this task, when it is combined with HOG features and can further improve the system39;s performance. The model can be implemented using MATLAB and GUI Interface. These findings have important implications for the development of accurate and reliable face emotion recognition systems for various applications, including human-computer interaction, gaming, and healthcare.