Agricultural food production is projected to be 70% higher by 2050 than it is today, with the world population rising to more than 9 billion, 34% higher than it is now. The farmers have been forced to produce more with the same resources. This pressure means that optimizing productivity is one of the main objectives of the producers but also in a sustainable way. Not only does agriculture face a decline in production, but it has also had to face limitations in data collection, storing, securing, and sharing, climate change, increases in input prices, traditional food supply chain systems where there is no direct connection between the farmer and the buyer, and limitations on energy use. Existing IoT‐based agriculture systems have a centralized format and operate in isolation, leaving room for unresolved issues and major concerns, including data security, manipulation, and single failure points. This paper proposes a futuristic IoT with a blockchain model to meet these challenges. Further, this paper also proposes and novel energy‐efficient clustering IoT‐based agriculture protocol for lower energy consumption and network stability and compares its results with its counterpart low‐energy adoptive clustering hierarchy (LEACH) protocol. The simulation results show that the proposed protocol network stability is 23% higher as compared to LEACH as first node of LEACH dies at 168 rounds while IoT‐based agriculture first node dies after 463 rounds. Similarly, IoT‐based agriculture protocol energy consumption is 68% lower than that of LEACH. The proposed protocol also extends the network life to more rounds and demonstrates an increase of 112%.

In Software Quality Assurance (SQA), predicting defect-prone software modules is essential for ensuring software reliability and consistency. This task is commonly achieved through Machine Learning (ML) techniques, but improving model performance typically incurs significant computational costs. These high computational costs and uncertain payoffs make most Software engineering researchers reluctant to optimize ML models. This creates a need for novel techniques that can achieve near optimal performance of hyperparameter settings while maintaining the computational efficiency of default settings. To address this, we employed five ML models, Decision Tree, Ranger, Random Forest, Support Vector Machine, and k-nearest Neighbors and optimized their parameters using the random search technique. Our experiments covered six diverse Software Fault Prediction (SFP) datasets, encompassing a wide range of software features, application domains, and defect patterns, to evaluate the approach’s generalizability and effectiveness.. Moreover, the Permutation Feature Importance (PFI)-based model-agnostic method was employed to identify the top ten features critical for model accuracy and efficiency. These selected features were used to retrain the ML models without hyperparameter (default settings) to determine whether similar performance could be achieved at low computational cost. The results show an average accuracy improvement of 77.39% and a 92.02% reduction in computational cost. The most important case attained a 99.25% accuracy improvement and a 96.77% cost reduction. Such results clearly show that the PFI-based feature selection is capable of high performance at a fraction of computational cost, offering an efficient solution for software engineers to optimize ML models.

The upcoming models of vehicles will be able to communicate with each other and will thus be able to share and/or transfer information. A vehicular ad hoc network (VANET) is an application of this vehicular communication that leads to an intelligent transportation system (ITS). Vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) are the two distinct types of vehicular ad hoc networks (VANET). V2V and V2I technologies are together known as V2X and are recently being tested. Continuous research to enhance routing considers different characteristics and exciting aspects of VANETs. The proposed schemes are classified based on the operational scenario. A survey of proposed routing schemes in the last eight years is presented to determine the design considerations and the approach used in every proposed system, along with their shortcomings. This survey will assist new scholars in this field to analyze existing state-of-the-art systems. The table at the end of each routing scheme shows the proposed routing scheme’s simulation, routing, and scenario parameters. This paper also reviews VANET technology, its role in the intelligent transportation system, recent development in the field, and the timeline for implementation of the system.

In Wireless Body Area Networks (WBANs), every healthcare application that is based on physical sensors is responsible for monitoring the vital signs data of patient. WBANs applications consist of heterogeneous and dynamic traffic loads. Routine patient’s observation is described as low-load traffic while an alarming situation that is unpredictable by nature is referred to as high-load traffic. This paper offers a thematic review of traffic adaptive Medium Access Control (MAC) protocols in WBANs. First, we have categorized them based on their goals, methods, and metrics of evaluation. The Zigbee standard IEEE 802.15.4 and the baseline MAC IEEE 802.15.6 are also reviewed in terms of traffic adaptive approaches. Furthermore, a comparative analysis of the protocols is made and their performances are analyzed in terms of delay, packet delivery ratio (PDR), and energy consumption. The literature shows that no review work has been done on traffic adaptive MAC protocols in WBANs. This review work, therefore, could add enhancement to traffic adaptive MAC protocols and will stimulate a better way of solving the traffic adaptivity problem.