This study introduces an integrated IoT-based framework for machine learning of agricultural crop yield prediction without rivaling in the accuracy levels. After an intensive survey of 16 machine learning algorithms on multiyear data from the principle agricultural zones of Pakistan, we show that ensemble models are capable of achieving close to perfect prediction accuracy. The Random Forest method had excellent performance with R² = 0.99, RMSE = 538.37 kg/ha and MAPE = 0.2944% which are a new benchmark in the field of agricultural yield prediction. Analysis of 400 agricultural records across seven districts showed evident outperformance of the tree-based ensemble methods against conventional ones. The proposed end-to-end framework integrates IoT sensor networks and cutting-edge ML models to monitor in real-time, and with high accuracy, the yields of major crops viz. wheat, cotton, sugarcane and rice. Here, we present an important leapfrogging in precision agriculture technology development that provides disruptive potential to the agricultural planning, resource allocation and food security improvement of developing countries by fusing IoT and machine learning.

Graph Neural Networks (GNNs) have become a critical tool for learning on structured data, particularly for their ability to capture feature dependencies within multivariate datasets. This study investigates the application of Graph Convolutional Networks (GCNs) to improve classification performance on such data. We constructed a fully connected graph using cosine similarity to compare our GCN approach against standard dimensionality reduction techniques like PCA and t-SNE. In our tests, the GCN model clearly surpassed these baselines in accuracy, precision, recall, and F1-score.But the method has its own trade-offs: dense graphs are computationally costly, there are chances of overfitting on smaller datasets and the resulting embeddings may be uninterpretable. We cannot make such a claim of generality at this point because this review has only limited itself to one multivariate data set. In future endeavour we would wish to compare GCNs to more powerful classifiers, such as Random Forests, Deep Neural Networks, with greater regard to efficiency in training and resistance to noise. To summarize, this paper confirms that GNNs are an ideal option when it comes to multivariate classification, although scalability and interpretability have to be resolved in order to make it applicable in the real-life context.

PDAC is one of the most harmful cancer causes due to late diagnosis, its rapid progression, and an 11% survival rate of 5 years. Current methods for diagnosis are very costly, uncomfortable, and unreliable, However, better and more accurate solutions are needed. This study proposes a diagnostic model using urinary biomarkers and machine learning techniques for early detection. Key urinary biomarkers, including LYVE-1, REG1B, TFF1, and plasma CA19-9 are used with patient data. Particle Swarm Optimization is used here for feature selection and hyperparameter tuning, optimizes the machine learning classifiers like Support Vector Machine, Logistic Regression, and Random Forest. Accuracy, precision, recall, and F1-score are used as evaluation metrics; however, random forest achieves the highest accuracy of 89.83%. This study shows how PDAC detection changes after combining molecular diagnostics with machine learning. Future research could explore the study of hybrid swarm intelligence algorithms and increase the data set to make further enhancements to diagnostic capabilities. This model shows a great step toward a quick and accurate diagnosis of PDAC and improves patient outcomes and survival rates.

In the contemporary digital landscape, Software-Defined Networking (SDN) has emerged as a transformative approach that decouples network control from hardware, enabling greater flexibility and centralized management. However, this innovation has also introduced new vulnerabilities, making SDN networks susceptible to cyber-attacks. To reduce the risk of cyber-attack blockchain can play vital role. In paper we propose a novel framework that leverages blockchain technology to enhance the security and resilience of SDN environments against potential threats. By integrating blockchain’s decentralized and immutable characteristics, our approach facilitates secure data transactions, enhances network visibility, and fosters trust among network participants. We present a comprehensive analysis of the vulnerabilities inherent in traditional SDN architectures and outline method, how blockchain can mitigate these risks through secure authentication, data integrity, and enhanced access controls.Furthermore, we conduct a series of experiments to evaluate the performance impact and security benefits of our proposed solution. The results demonstrate a significant reduction in the likelihood of cyber-attacks, showcasing the viability of blockchain as a potent tool for safeguarding SDN networks. Our findings underscore the importance of interdisciplinary approaches in addressing the evolving challenges of network security, paving the way for more resilient and secure SDN infrastructures in the future.

Even though millions of people struggle to interact with the outside world due to visual impairments, vision is an essential part of our daily lives. Because of its ability to identify and navigate around objects in their surroundings, object detection a crucial component of computer vision has become a potentially helpful solution. This study offers a thorough analysis of object detection techniques utilizing a dual classification system that combines traditional and deep learning methods. In addition, we analyze the most popular evaluation metrics and datasets for these systems' training and evaluation. Unlike previous surveys, our work provides a unique perspective by carefully examining the latest advancements in both innovative deep learning models and traditional approaches. The survey's conclusion highlights current problems and recommends future research directions, highlighting the need for more effective models, diverse datasets, and multi-modal data integration to improve assistive technologies for the visually impaired.

This work focuses on fine-grained sentiment analysis of Arabic text using recent Natural Language Processing methods. Arabic is a language rich in variation, spoken by over 400 million people, yet there is a significant lack of resources for sentiment analysis. To address these challenges, this study employs AraBERT, a model specifically fine-tuned for Arabic text. A corpus of one hundred thousand Arabic reviews across categories such as hotels, books, and movies was scraped and cleaned. These reviews were then categorized into positive, negative, and mixed sentiments. AraBERT was compared with traditional machine learning methods, including Logistic Regression, Decision Tree, Naïve Bayes, and Random Forest. AraBERT achieved superior accuracy of 88\%, along with higher precision, recall, and F1 scores for both positive and negative sentiment classes compared to the other models. This work demonstrates that AraBERT effectively analyzes the syntactic and semantic structure of Arabic, making it a valuable tool for Arabic sentiment analysis across various applications. Future work will extend the model to handle neutral sentiments and include additional dialects to further improve its performance.

The Pakistan power system faces a severe energy deficiency due to population growth. The Pakistan power system structure necessitates a smart load management system to address the mismanagement of load distribution that results in load shedding. A continuous power supply is essential for industrial and domestic sectors to enhance Pakistan's economy. Imported fuel presents a significant economic challenge in Pakistan. This system is designed to control and monitor load management utilizing Internet of Things (IoT)-based technology. The implementation of an IoT-based approach enhances system performance by upgrading conventional load management. This study analyzed effective energy management during peak hours. This system employs a smart energy management system to improve load shedding patterns. The system components include a power monitoring module, current sensor, transformer, Wi-Fi module, and relay module integrated with an Arduino-based microcontroller for monitoring and controlling load management. To model a virtual analysis a simulation based circuit diagram is design using Proteus Software. The implementation of this study improves energy transactions between utilities and consumers. In this study, a prototype was designed and implemented using Arduino, and sensors were employed to control and observe a smart load management system. This system utilizes a hypertext preprocessor for login webpage arrangement for IoT control and monitoring. The results indicate that the cumulative analysis for the implementation of this system automatically deactivates unnecessary loads during peak hours. This system can conserve energy during peak-hour intervals. The load parameters for current, voltage, and power were displayed on the LCD screen. The system automatically deactivates the load during harmonics in the power supply until normal conditions are restored. As compared to existing studies this system detects and switch the system during on and off peak hours without any human interaction.

This paper focuses on the systematic mapping of monolithic applicationsto microservices architecture, a popular alternative in the software development industry.The research examines the advantages of microservices and the challenges organizationsencounter during the transition from monolithic systems. A case study of a financialapplication is presented, along with proposed techniques for identifying microserviceswithin monolithic systems using domain-driven development concepts.The study highlights the difficulties and benefits of migrating from monolithic to microservicesarchitecture, offering valuable insights for software architects and developers. Practicalimplications include a technique for identifying microservices on monolithic systemsusing domain-driven concepts and various communication protocols for service interaction.The findings suggest that this proposed technique can enhance work performanceand establish clear models, particularly for complex systems. However, it may have limitedeffectiveness in less complex systems. The paper contributes to the field of softwaredevelopment by providing practical solutions for companies considering a shift tomicroservices architecture and comparing the two architectural styles.

After the invention of new IoT devices the new connection has been added in the network and bulk of data flow in the system. AI is very famous algorithum and software-defined networking (SDN) is new fast network controlling method both can be integrate for fast and secure network-related scenarios and finding great experience and growing interest in the research community. The present network connected to many number of objects over the Internet and present a complex scenario. To ensure security, privacy, confidentiality, and programmability, the architecture of AI and blockchain for SDN network is proposed in this paper. For network service provider this is ample time to apply artificial intelligence (AI) and blockchain (BC) in a software-defined network controller to ensure a secure network control, traffic management and system optimimum performnce. Also for shortest path to reduce delay in the network, the best routing algorithum must be apply in the network. The AI (artificial intelligence) algorithum can help SDN controller to fastdecision to reduced delay and can provide security in the network. In this paper routing algorithm also will be investigate faster Network.

In this paper we present a new approach for the classification of benign and malignant micro-calcification clusters by transforming data from the image to the text domain. A string representation is extracted from binary micro-calcification segmentation images. We extracted two different features from the strings and combined different machine learning techniques towards benign versus malignant classification. We evaluated our proposed method on the DDSM database and experimental results indicates a Classification Accuracy equal to 92%.