The globalization of the food supply chain industry has significantly emerged today. Due to this, farm-to-fork food safety and quality certification have become very important. Increasing threats to food security and contamination have led to the enormous need for a revolutionary traceability system, an important mechanism for quality control that ensures sufficient food supply chain product safety. In this work, we proposed a blockchain-based solution that removes the need for a secure centralized structure, intermediaries, and exchanges of information, optimizes performance, and complies with a strong level of safety and integrity. Our approach completely relies on the use of smart contracts to monitor and manage all communications and transactions within the supply chain network among all of the stakeholders. Our approach verifies all of the transactions, which are recorded and stored in a centralized interplanetary file system database. It allows a secure and cost-effective supply chain system for the stakeholders. Thus, our proposed model gives a transparent, accurate, and traceable supply chain system. The proposed solution shows a throughput of 161 transactions per second with a convergence time of 4.82 s, and was found effective in the traceability of the agricultural products.

Conventional crop insurance systems are complex and often not economically feasible. Farmers are often reluctant to be covered for their crops due to lack of trust in insurance firms and the fear of delayed or non-payment of claims. In this paper, a blockchain based crop insurance solution is suggested. The solution suggested in this paper is an affordable, efficient, low cost crop insurance solution which will ensure many farmers are insured and benefiting from timely crop insurance. Currently the cost of administering insurance is an essential barrier to accessing this facility. With the proper use of blockchain based on ethereum this expense can be reduced dramatically. We have conducted various tests on platforms such as Google Cloud and found that the least throughput is 165 transactions. Upon analysis we have found that the time taken by the block formation is directly proportional to the timing of processing. The end-to-end average latency of the system was achieved as 31.2 s, which was quite effective for the infrastructure what we are using. Upon conducting acceptance testing, we found that the system suggested in the paper is effective and we are planning to release the application on open source platforms for future improvements.

Electricity theft is a primary concern for utility providers, as it leads to substantial financial losses. To address the issue, a novel extreme gradient boosting (XGBoost)‐based model utilizing the consumers’ electricity consumption patterns for analysis is proposed for electricity theft detection (ETD). To remove the imbalance in the real‐world electricity consumption dataset and ensure an even distribution of theft and non‐theft data instances, six different artificially created theft attacks were used. Moreover, the utilization of the XGBoost algorithm for classification, especially to identify malicious instances of electricity theft, yielded commendable accuracy rates and a minimal occurrence of false positives. The proposed model identifies electricity theft specific to the regions, utilizing electricity consumption parameters, and other variables as input features. The authors’ model outperformed existing benchmarks like k‐neural networks, light gradient boost, random forest, support vector machine, decision tree, and AdaBoost. The simulation results using the false attacks for balancing the dataset have improved the proposed model's performance, achieving a precision, recall, and F1‐score of 96%, 95%, and 95%, respectively. The results of the detection rate and the false positive rate (FPR) of the proposed XGBoost‐based detection model have achieved 96% and 3%, respectively.

Early diagnosis of pandemic diseases such as COVID-19 can prove beneficial in dealing with difficult situations and helping radiologists and other experts manage staffing more effectively. The application of deep learning techniques for genetics, microscopy, and drug discovery has created a global impact. It can enhance and speed up the process of medical research and development of vaccines, which is required for pandemics such as COVID-19. However, current drugs such as remdesivir and clinical trials of other chemical compounds have not shown many impressive results. Therefore, it can take more time to provide effective treatment or drugs. In this paper, a deep learning approach based on logistic regression, SVM, Random Forest, and QSAR modeling is suggested. QSAR modeling is done to find the drug targets with protein interaction along with the calculation of binding affinities. Then deep learning models were used for training the molecular descriptor dataset for the robust discovery of drugs and feature extraction for combating COVID-19. Results have shown more significant binding affinities (greater than −18) for many molecules that can be used to block the multiplication of SARS-CoV-2, responsible for COVID-19.