Background: Agriculture is one of the most crucial assets of any country, as it brings prosperity by alleviating poverty, food shortages, unemployment, and economic instability. The entire process of agriculture comprises many sectors, such as crop cultivation, water irrigation, the supply chain, and many more. During the cultivation process, the plant is exposed to many challenges, among which pesticide attacks and disease in the plant are the main threats. Diseases affect yield production, which affects the country’s economy. Over the past decade, there have been significant advancements in agriculture; nevertheless, a substantial portion of crop yields continues to be compromised by diseases and pests. Early detection and prevention are crucial for successful crop management. Methods: To address this, we propose a framework that utilizes state-of-the-art computer vision (CV) and artificial intelligence (AI) techniques, specifically deep learning (DL), for detecting healthy and unhealthy cotton plants. Our approach combines DL with feature extraction methods such as continuous wavelet transform (CWT) and fast Fourier transform (FFT). The detection process involved employing pre-trained models such as AlexNet, GoogLeNet, InceptionV3, and VGG-19. Implemented models performance was analysed based on metrics such as accuracy, precision, recall, F1-Score, and Confusion matrices. Moreover, the proposed framework employed ensemble learning framework which uses averaging method to fuse the classification score of individual DL model, thereby improving the overall classification accuracy. Results: During the training process, the framework achieved better performance when features extracted from CWT were used as inputs to the DL model compared to features extracted from FFT. Among the learning models, GoogleNet obtained a remarkable accuracy of 93.4% and a notable F1-score of 0.953 when trained on features extracted by CWT in comparison to FFT-extracted features. It was closely followed by AlexNet and InceptionV3 with an accuracy of 93.4% and 91.8% respectively. To further improve the classification accuracy, ensemble learning framework achieved 98.4% on the features extracted from CWT as compared to feature extracted from FFT. Conclusion: The results show that the features extracted as scalograms more accurately detect each plant condition using DL models, facilitating the early detection of diseases in cotton plants. This early detection leads to better yield and profit which positively affects the economy.

Fintech is an industry that uses technology to enhance and automate financial services. Fintech firms use software, mobile apps, and digital technologies to provide financial services that are faster, more efficient, and more accessible than those provided by traditional banks and financial institutions. Fintech companies take care of processes such as lending, payment processing, personal finance, and insurance, among other financial services. A data breach refers to a security liability when unapproved individuals gain access to or pilfer susceptible data. Data breaches pose a significant financial, reputational, and legal liability for companies. In 2017, Equifax suffered a data breach that revealed the personal information of over 143 million customers. Combining federated learning (FL) and blockchain can provide financial institutions with additional insurance and safeguards. Blockchain technology can provide a transparent and secure platform for FL, allowing financial institutions to collaborate on machine learning (ML) models while maintaining the confidentiality and integrity of their data. Utilizing blockchain technology, FL can provide an immutable and auditable record of all transactions and data exchanges. This can ensure that all parties adhere to the protocols and standards agreed upon for data sharing and collaboration. We propose the implementation of an FL framework that uses multiple ML models to protect consumers against fraudulent transactions through blockchain. The framework is intended to preserve customer privacy because it does not mandate the exchange of private customer data between participating institutions. Each bank trains its local models using data from its consumers, which are then combined on a centralised federated server to produce a unified global model. Data is neither stored nor exchanged between institutions, while models are trained on each institution’s data.

This dataset used the Digital Competency Scale (DCS) to describe Indonesian pre-service teachers' perceptions. The DCS instrument consisted of five constructs/dimensions, which are: 1) data and information literacy, 2) communication and collaboration, 3) digital content creation, 4) safety, and 5) problem-solving, with a total of 36 items using five-point agreement Likert scale. The data was gathered from 23 education and teacher training faculties at Muhammadiyah Universities in 14 provinces across Indonesia in the academic year 2021/2022. A total of 1400 students (18 to 23 years old) in their first to fifth years of study were recruited using the convenience sampling technique, where they participated in filling in the survey electronically using Google Form. The dataset was analysed with the Rasch model measurement approach using WINSTEPS version 5.2.3 software for data cleaning and validation, and reliability and validity testing of the instrument. This dataset analysis can help teacher-training institutions, or higher education policymakers design effective programmes to improve pre-service teachers' digital competencies. Furthermore, researchers can compare this dataset with more rigorous data from other countries.

Internet of things (IoT) devices are gaining traction around the globe. These devices are sometimes hijacked and turned into zombies or botnets. One risk posed by hijacked devices is a ping flood attack, also known as an internet control message protocol echo request flood. Current literature lacks a ping flood attack dataset generated from an IoT device. This paper contributes by developing an IoT network intrusion detection framework for ping flood attacks. This framework deploys an IoT testbed using embedded devices to emulate two datasets, normal ping traffic and malicious ping flood attack traffic. Features are extracted from the captured traffic using the Zeek tool. Attacks are detected using three machine learning algorithms: logistic regression, K-nearest neighbor, and support vector machine. These models are compared using evaluations such as the confusion matrix, accuracy, precision, recall, F1-score, and misclassification (error rate). The models are validated using split validation and cross-fold validation. The time consumed in training and testing the models across various data levels is also analyzed, along with the time required for feature extraction. The discrepancies between capturing tools are discussed. The use of criteria based on the time difference between requests to detect malicious traffic is considered, as is the impact of machine learning models on memory usage. Our work is compared with similar research. The testbed concluded that the K-nearest neighbor algorithm achieved 99.67% detection accuracy, with an error rate of 0.33% and an F1-score of 99.67%, which is the best amongst the three algorithms.

Large-scale events, such as festivals and public gatherings, pose serious problems in terms of traffic congestion, slow transaction processing, and security risks to transportation planning. This study proposes a blockchain-based solution for enhancing the efficiency and security of intelligent transport systems (ITS) by utilizing state channels and rollups. Throughput is optimized, enabling transaction speeds of 800 to 3500 transactions per second (TPS) and delays of 5 to 1.5 s. Prevent data tampering, strengthen security, and enhance data integrity from 89% to 99.999%, as well as encryption efficacy from 90% to 98%. Furthermore, our system reduces congestion, optimizes vehicle movement, and shares real-time, secure data with stakeholders. Practical applications include fast and safe road toll payments, faster public transit ticketing, improved emergency response coordination, and enhanced urban mobility. The decentralized blockchain helps maintain trust among users, transportation authorities, and event organizers. Our approach extends beyond large-scale events and proposes a path toward ubiquitous, Artificial Intelligence (AI)-driven decision-making in a broader urban transit network, informing future operations in dynamic traffic optimization. This study demonstrates the potential of blockchain to create more intelligent, more secure, and scalable transportation systems, which will help reduce urban mobility inefficiencies and contribute to the development of resilient smart cities.

Smart cities use advanced infrastructure and technology to improve the quality of life for their citizens. Collaborative services in smart cities are making the smart city ecosystem more reliable. These services are required to enhance the operation of interoperable systems, such as smart transportation services that share their data with smart safety services to execute emergency response, surveillance, and criminal prevention measures. However, an important issue in this ecosystem is data security, which involves the protection of sensitive data exchange during the interoperability of heterogeneous smart services. Researchers have addressed these issues through blockchain integration and the implementation of smart contracts, where collaborative applications can enhance both the efficiency and security of the smart city ecosystem. Despite these facts, complexity is an issue in smart contracts since complex coding associated with their deployment might influence the performance and scalability of collaborative applications in interconnected systems. These challenges underscore the need to optimize smart contract code to ensure efficient and scalable solutions in the smart city ecosystem. In this article, we propose a new framework that integrates generative AI with blockchain in order to eliminate the limitations of smart contracts. We make use of models such as GPT-2, GPT-3, and GPT4, which natively can write and optimize code in an efficient manner and support multiple programming languages, including Python 3.12.x and Solidity. To validate our proposed framework, we integrate these models with already existing frameworks for collaborative smart services to optimize smart contract code, reducing resource-intensive processes while maintaining security and efficiency. Our findings demonstrate that GPT-4-based optimized smart contracts outperform other optimized and non-optimized approaches. This integration reduces smart contract execution overhead, enhances security, and improves scalability, paving the way for a more robust and efficient smart contract ecosystem in smart city applications.