Agriculture, the foundation of human civilization, is undergoing a dramatic transformation driven by the Internet of Things (IoT). IoT devices enable farmers to boost yields, reduce waste, and guarantee a safer and more sustainable food supply chain through everything from accurate crop health monitoring to resource optimization and improved food traceability. However, there are serious risks of illegal access, data manipulation, and privacy violations as data moves through cloud-based platforms. These weaknesses may result in poor decision-making, financial damage, and hazards to the safety of food. Blockchain technology is revolutionary because it offers a decentralized, secure foundation for protecting agricultural data. Together with more sophisticated cryptographic methods like homomorphic encryption and zero-knowledge proofs, it forms a strong framework for guaranteeing data security and privacy. This chapter explores how blockchain and cryptography might be combined to address these pressing problems, providing innovative solutions including safe data storage, decentralized sharing systems, and smart contracts that facilitate effective and transparent transactions. We offer a thorough examination of the most recent developments and enduring difficulties in agricultural data management by classifying blockchain applications and investigating fundamental components including consensus mechanisms and cryptography tools. We show how blockchain technology may transform agriculture, from enhancing the traceability of the food supply chain to resolving the issues of unreliable stakeholders. This chapter also emphasizes the broader potential of these technologies, showcasing their scalability to other domains and their capacity to drive innovation in sustainable resource management and data security.

Vehicular edge computing (VEC) is a research paradigm that aims to increase computing resources for internet of vehicles (IoV) applications. With the growth in augmented reality services, 3D gaming, and autonomous driving, scheduling tasks based on deadlines is a difficult task in vehicular networks. Efficient task scheduling is one of the primary features that optimize resource efficacy and performance at the periphery servers. This study presents an adaptive task scheduling method that uses a dynamic time quantum (DTQ) approach to handle VEC systems with changing workloads. The solution not only reduces the task turnaround time but also eliminates context-switching overheads by generating variable times that align with the execution needs and deadlines of incoming tasks. The proposed DTQ-based round-robin scheduling algorithm outperformed both the conventional round-robin and deadline-aware round-robin algorithms with STQ in terms of total context switches, waiting time, and average turnaround time. Thus, dynamic solutions for task management in VEC will play a vital role in enabling efficient and reliable vehicular communication networks.

The integration of edge-enabled IoT into vehicular networks contributes to the fruitful development of ITS in smart cities, improving safety, responsiveness, and efficiency. Edge computing works closely to support real-time decision-making processes that are crucial for the application scenarios mentioned above, such as autonomous driving, traffic optimization, and accident prevention. This method uses the automatic decision-making abilities of machine learning and augmented deep learning methods like convolutional neural networks (CNN) for workload offloading and scheduling. Vehicle-to-everything (V2X) communication through edge nodes and smart sensors can be enhanced further to achieve an incident-free and smooth interaction between vehicles, infrastructure, and pedestrians for optimizing traffic. It addresses security, data privacy, and scalability issues, and helps build resilient and adaptive vehicular networks. Case studies from worldwide smart city initiatives show how these technologies influence the real world. In terms of latency reduction, the successive authentication method shows a 45% reduction compared to DTTCH and DRL method. When comparing the energy consumption rates, the GA method stands out with 24% relative to methods like ARO, MDP, and ECDSA. This chapter attempts to demonstrate how edge-enabled IoT in-vehicle networks may alter urban transportation and build smarter, more sustainable cities by offering a framework for deploying them.

Heart disease is a significant cause of death worldwide, and early prediction is vital for prevention and treatment. This project uses the Framingham Heart Study dataset for the early prediction of Coronary Heart Disease (CHD) using machine learning methods. The Framingham Heart Study is a highly unbalanced dataset, with only 16 % cases of CHD, which impacts the accuracy of the model. To overcome this, data augmentation techniques such as SMOTE and cGAN are applied to create synthetic cases of CHD. The machine learning algorithms that are compared: Random Forest, XGBoost, SVM, and MLP. XGBoost has achieved the highest AUC-ROC of 0.973 when cGAN-augmented data is used, while cGAN-augmented data improves recall and overall model performance significantly. This study identifies the potential for combining machine learning with data augmentation to improve CHD prediction.

The trading world often appears mysterious, filled with stories of fear, hope, addiction, and occasional profits. However, many fail to recognize that consistent profitability in trading is driven by discipline, a well-defined strategy, and strict adherence to rules. This lack of awareness is a key reason why 75-90% of new traders enter the market with high expectations but end up losing their hard-earned money. In this research we propose a quantitative trading strategy based on exponential moving average (EMA) crossovers, volume analysis, and structured profit booking. The strategy utilises a short-term 9-period EMA and along-term 15-period EMA to identify trend reversals, generating buy signals when the two different EMA's crosses under some conditions and sell signals are generated when the opposite occurs. Meanwhile, a confirmation mechanism is introduced, requiring the price to move at least 0.06% above the crossover price while ensuring the crossover candle remains bullish. Additionally, volume conditions are incorporated to validate momentum, ensuring buy signals are triggered only when the trading volume increases in ascending order. To optimize trade management, a multi-tier profit booking system is implemented, allowing partial exits at predefined levels. which ensures that the traders secure gains while allowing profitable trades to run. The strategy's performance is evaluated through historical back-testing, assessing profitability, accuracy, and risk-reward dynamics. The results demonstrate the effectiveness of integrating EMA crossings with volumes and structured exit points in improving trade success rates. This might become the future of so many people to convert their portfolio from a losing streak to a winning streak.

Detecting diseases in tomato leaves at an early stage is crucial for preventing crop damage and improving food security. Traditional diagnostic methods are often inefficient, requiring significant expertise and time. To address this challenge, we explore AI-driven approaches, integrating DL and ML methods for automated disease detection. This study employs CNNs, specifically leveraging the VGG16 architecture for feature extraction. Additionally, we compare its effectiveness with classical classifiers such as KNN and SVM. Using a publicly available dataset of healthy and diseased tomato leaves, our results indicate that CNN-based models outperform conventional machine learning classifiers in both accuracy and efficiency. Moreover, integrating IoT-based analytics enhances early detection, reducing crop losses and promoting sustainable agricultural practices.

Edge computing has become a game-changing technology in both academics and industry as the need for quicker and more effective data processing increases. Edge computing lowers latency and improves real-time analysis by processing and storing data close to its source. The increasing significance of edge computing in the current Information Technology architecture demands the critical need to secure its distributed nature. The integration of blockchain-based technologies with edge computing will be addressed in this chapter. Blockchain and edge computing integration can improve security. At the network edge, blockchain technology guarantees data integrity, authentication, and confidentiality. Secure access control mechanisms for distributed resources are made possible by this integration. It reduces the possibility of single points of failure or concentrated attacks or malicious attacks. Furthermore, it makes tamper-proof transactions possible by utilizing widespread acceptance technique like smart contracts. This technology is used as a strategic approach to improve edge computing systems' security architecture. Key security concerns including data integrity, privacy, and access management are addressed by blockchain. This is known for its decentralization, cryptographic integrity, and elimination of middlemen. These issues are made worse by the distributed nature of edge computing. This analysis, which is based on a thorough examination of the literature, emphasizes how blockchain technology may be used in edge contexts to enforce data protection, guarantee transparency, and provide trustworthy audit trails.

With the development of deep learning and availability of large datasets, the evaluation of player performance has expanded the scope of sports analytics. Predicting the outcomes of players is still of utmost importance for tactical decisions. While Ridge Regression, Gradient Boosting, and Support Vector Regression (SVR) and other traditional machine learning techniques used in sports analytics, the true potential of the complex temporal dependencies of player statistics is still not achieved. These temporal dependencies in the performance data can inspire the design of advanced techniques, so this paper proposes a hybrid RNN-LSTM architecture suitable for player performance evaluation. The proposed model utilizes the forecasting abilities of RNNs coupled with LSTM cells to synthesize memory and guarantee performance. The simulation involved a dataset containing 1007 player-season records spanning 2008 to 2024 and including various bowling and batting performance metrics. All model training and evaluation were performed in the TensorFlow and Keras libraries. The experimental results show that our proposed RNN-LSTM has an accuracy of 0.9635, R2 score of 0.9910, Mean Square Error (MSE) of 301.4782, and Mean Absolute Error (MAE) of 7.6366 that outperform Ridge Regression, Gradient Boosting and SVR baselines. In the end, a hybrid RNN-LSTM model will be highly accurate and scalable. More importantly, it will set the benchmark for player performance prediction. It can predict better than regular machine learning techniques because it captures temporal dependencies.