This study explores the integration of the JADE (Java Agent Development Framework) platform with deep reinforcement learning (DRL) to enhance governmental interoperability and optimize administrative workflows in municipal settings. The proposed approach combines the JADE’s robust multi-agent system (MAS) capabilities with the adaptive decision-making power of DRL to address prevalent challenges faced by government agencies, such as fragmented operations, incompatible data formats, and rigid communication protocols. By enabling seamless communication between agents across departments such as the Treasury, the Event Management department, and the Public Safety department, the hybrid system fosters real-time collaboration and supports efficient, data-driven decision making. Agents leverage historical and real-time data to adapt to environmental changes and make optimized decisions that align with overarching governmental objectives, such as resource allocation and emergency response. The result is a system capable of managing intricate administrative duties using structured agent communication and the integration of DRL-driven learning models, improving governmental interoperability. Key performance indicators highlight the system’s effectiveness, achieving a task completion rate of 95%, decision accuracy of 96%, and a communication latency of just 120 ms. Additionally, the framework’s flexibility ensures seamless scalability, accommodating complex and large-scale tasks across multiple governmental units. This research presents a scalable, automated, and resilient framework for optimizing governmental processes, offering a pathway to more efficient, transparent, and adaptive public sector operations.

Agriculture is the backbone of the Ethiopian economy. It plays a significant role in the growth of the national economy. Among these, mung bean production takes the highest level of income for most smallholder farmers in all regions of Ethiopia who cultivate mung bean crops. Therefore, this study aims to predict mung bean production using a machine learning algorithm. For this study, the datasets were collected from the Central Statistical Agency of Ethiopia database. A total of 10273 instances were used for the experiment. Python machine learning tool was used to conduct the experiment and build an optimal model. To achieve the objective of this study, different experiments were conducted using Random Forest, Gradient Boosting, and Xgboosting algorithms. In addition, the predictive performances of the classifiers are evaluated and compared using accuracy, precision, recall, F1-score, and confusion matrix. Experimental result shows that the Xgboosting classifiers algorithm achieves the best performance with 98.65 % test accuracy and 99.8 % train accuracy. As a result, the Xgboosting classifier was selected for implementing the model to predict mung bean production. The findings of this study show that the main determinant factors for mung bean production include Meher season, use of extension program, fertilizer used, and fertilizer type. Therefore, the outcome of this research is essential to support the decision-making process of experts and it will enable them take corrective measures on the factors affecting mung bean production.

Highlights A CNN and HOG model performs better than predefined CNN architectures, such as the Inception and ResNet-50. The usage of ADF image filtering algorithms was the most suitable filtering algorithm for medical images. The QSVM classifier enhances the classification process's performance and is more effective than traditional SVMs.

Monitoring sesame plant health and detecting disease early are essential to reducing disease spread and facilitate effective management practices. In this research, we developed an image classification model to detect bacterial blight-infected, phyllody-infected, and healthy sesame crops. Since images were necessary to carry out this study, we collected 2300 images at the Gondar and Humera Agriculture Research Centers and directly from the field in Metema. Since the collected images were limited, to increase the number of images in the dataset, we used image augmentation with different variations. In the image preprocessing step, we used a median filter for noise filtering, and contrast stretching techniques were used for image contrast and brightness enhancement. SegNet semantic segmentation, which is deep convolution neural network-based architecture, was used to segment the leaf part of the image from the background. In the feature extraction and classification steps, a deep convolutional neural network was used. Finally, we evaluated the proposed model and compared it with two recent deep convolution neural network models, namely, Xception and InceptionV3. The proposed model for the classification of sesame diseases achieved better accuracy, with 96.67% testing accuracy, 97.78% validation accuracy, and 98% training accuracy.

This study provides a novel approach to the field of prognostics and health management (PHM) in nanotechnology: multi-agent systems integrated with ontology-based knowledge representation and Deep Reinforcement Learning (DRL). This framework has agents acting in a network-like manner, where every agent investigates a particular subject of nanotechnology design and lifecycle management for an interdependent and multifaceted problem-solving approach. Ontologies give the framework a semantic dimension, which allows for the precise and context-dependent interpretation of data. These permit observations attuned towards understanding the behaviors of nanomaterials, performance limitations, and failure mechanisms. On the other hand, having a DRL-integrated module permits agents to provide dynamic adaptation to changing operational contexts, datasets, and user scenarios while continuously calibrating their decisions for better accuracy and efficiency. Preliminary evaluations based on expert-reviewed test cases demonstrated a 95% task success rate and a decision-making accuracy of 96%, indicating the system’s strong potential in handling complex nanotechnology scenarios. These results show good robustness and adaptability to certain PHM problems, such as predictive maintenance of nanodevices, lifespan optimization of nanomaterials, and risk assessment in complex environments. This study introduces a novel integration of Multi-Agent Systems (MAS), ontology-driven reasoning, and DRL, enabling dynamic cross-ontology collaboration and online learning capabilities. These features allow the system to adapt to evolving user needs and heterogeneous knowledge domains in nanotechnology.