Handwritten character recognition is one of the practically important issues in pattern recognition applications. The applications of digit recognition include in postal mail sorting, bank check processing, form data entry, etc. The main problem lies within the ability on developing an efficient algorithm that can recognize hand written digits, which is submitted by users by the way of a scanner, tablet, and other digital devices. This paper presents an approach to off-line handwritten digit recognition based on different machine learning techniques. The main objective of this paper is to ensure the effectiveness and reliability of the approached recognition of handwritten digits. Several machines learning algorithms (i.e. Multilayer Perceptron, Support Vector Machine, Naïve Bayes, Bayes Net, Random Forest, J48, and Random Tree) have been used for the recognition of digits using WEKA. The experimental results showed that the highest accuracy was obtained by Multilayer Perceptron with the value of 90.37%.

As agriculture moves toward Agriculture 4.0, which uses Internet of Things (IoT) devices to collect data in real time and monitor things from a distance, these networks are becoming increasingly vulnerable to cyberattacks. A common method used to protect against these kinds of threats is the use of intrusion detection systems (IDS). However, the agricultural environment is often changing and has limited resources, which makes cybersecurity challenging. Several available IDS tools are not designed to work properly in places with few resources, intermittent access, and unpredictable network conditions. This paper investigates the performance of Zeek, an open-source IDS, in identifying potential threats in agricultural IoT networks. We performed both offline and real-time experiments: offline analysis used pcap files from the Stratosphere Laboratory dataset, and real-time evaluation involved simulated live attack scenarios, focusing on unauthorized access attempts and distributed denial-of-service (DDoS) attacks. Zeek's performance was assessed based on CPU and memory utilization, as well as quality of service (QoS) metrics. From the experimental results, we found that Zeek was quite effective in protecting agricultural IoT networks against typical threats. Memory usage remained stable around 5% during offline analysis and under 20% during active attacks. However, CPU usage was more volatile, peaking at 120% during DDoS events. In terms of QoS, the system maintained a good throughput (1,375 kbits/s) with minimal packet loss (0.000186%). Among the attack types that we tested, brute force attacks, which represent attempts at unauthorized access, had the strongest effect on network performance, increasing delay to 2.159 ms and jitter to 0.793 ms. It seems clear that a heavier traffic load during such attacks can interfere with QoS. On the basis of our observation, we recommend practical deployment strategies for agricultural IoT systems that take these limitations into consideration, aiming to keep networks both secure and efficient under pressure. Received: 2 June 2025 | Revised: 2 September 2025 | Accepted: 13 September 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in the Stratosphere Laboratory at https://www.stratosphereips.org/datasets-overview, in GitHub at https://github.com/zeek/zeek, https://github.com/vanhauser-thc/thc-hydra, and https://github.com/antirez/hping. Author Contribution Statement Samsul Huda: Conceptualization, Formal analysis, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration. Muhammad Bisri Musthafa: Conceptualization, Methodology, Software, Validation, Investigation, Resources, Data curation, Writing – review & editing, Visualization. S. M. Shamim: Conceptualization, Methodology, Software, Validation, Investigation, Resources, Data curation, Writing – review & editing, Visualization. Yasuyuki Nogami: Supervision, Funding acquisition.