The quality and uniformity of green coffee beans significantly influence the overall flavor and value of the product. In the coffee industry, automated flaws and bean-type identification offer numerous advantages. This study examines the effectiveness of multiple YOLO (You Only Look Once) models for identifying and classifying green coffee beans. Various YOLO variants, including YOLOv3, YOLOv4, YOLOv5, YOLOv7, YOLOv8, and custom models, are compared with a focus on computational efficiency, accuracy, and speed. Utilizing a dataset of 4,032 training and 506 testing images encompassing diverse bean types, defects, and lighting conditions, we assessed the performance. The bounding boxes generated by our models accurately encompass coffee beans, with the background typically uniform and set to black. Our analysis reveals the superior performance of the custom-YOLOv8n model, which we meticulously customized for green coffee bean detection. This model achieved high precision, recall, f1-score, and mAP, demonstrating its potential for real-world implementation in coffee bean quality control systems. The customization process involved fine-tuning the model to focus on significant features relevant to green coffee bean detection and employing specific labeling strategies. Customization allows you to fine-tune the model to focus on important features relevant to green coffee bean detection. This sensitivity ensures that the model can effectively distinguish between different bean types and detect even subtle defects. This paper clarifies our primary objective of evaluating YOLO models’ performance in identifying and categorizing green coffee beans, with potential implications for enhancing efficiency and consistency in the coffee industry. A succinct key sentence underscores the benefits of our research for readers seeking efficient YOLO model selection and implementation in agricultural systems.

Agriculture plays a vital role in Bangladesh’s economy. It is essential to ensure the proper growth and health of crops for the development of the agricultural sector. In the context of Bangladesh, crop diseases pose a significant threat to agricultural output and, consequently, food security. This necessitates the timely and precise identification of such diseases to ensure the sustainability of food production. This study focuses on building a hybrid deep learning model for the identification of three specific diseases affecting three major crops: late blight in potatoes, brown spot in rice, and common rust in corn. The proposed model leverages EfficientNetB0′s feature extraction capabilities, known for achieving rapid high learning rates, coupled with the classification proficiency of SVMs, a well-established machine learning algorithm. This unified approach streamlines data processing and feature extraction, potentially improving model generalizability across diverse crops and diseases. It also aims to address the challenges of computational efficiency and accuracy that are often encountered in precision agriculture applications. The proposed hybrid model achieved 97.29% accuracy. A comparative analysis with other models, CNN, VGG16, ResNet50, Xception, Mobilenet V2, Autoencoders, Inception v3, and EfficientNetB0 each achieving an accuracy of 86.57%, 83.29%, 68.79%, 94.07%, 90.71%, 87.90%, 94.14%, and 96.14% respectively, demonstrated the superior performance of our proposed model.

In this paper, the focus is on the dispatching strategy of microgrids with minimization in costs and emissions. The novelty of this paper is in proposing a new approach toward combined heat and power generation in a grid with renewable energy resources, such as wind turbines, photovoltaic cells which reduces the overall costs considerably. In this research, for simulating the optimal dispatch of DG units and other power generation resources, GAMS software is applied to the problem, which results in a lower calculation time.

Weapon detection in surveillance imagery is a critical task for ensuring public safety in high‐risk environments. While single‐stage object detectors like YOLOv8 provide exceptional localization speed, their semantic reliability often diminishes when distinguishing between lethal weapons and visually similar non‐threat objects in complex scenes. To address this limitation, this work proposes a hybrid weapon detection framework that decouples object localization from semantic verification. The system utilizes a YOLOv8n detector for real‐time region localization, followed by an attention‐enhanced classification stage incorporating a Squeeze‐and‐Excitation (SE) mechanism. A novel conditional decision logic was implemented to manage the consensus between the two stages, incorporating a confidence‐weighted fail‐safe to maintain high recall for unambiguous threats. We evaluated three backbone architectures—NASNetMobile, DenseNet201, and InceptionV3, under identical constraints. Experimental results on a primary test set show that the hybrid NASNetMobile + SE model achieves 96% accuracy, significantly outperforming the standalone YOLOv8n (94%). More critically, on a challenging ablation dataset, the hybrid framework improved pistol precision from 90% to 95%. Furthermore, the integration of the SE block was found to optimize inference, reducing latency compared to the vanilla backbone. The proposed system represents a “Pareto‐optimal” solution for edge‐deployed security infrastructure, prioritizing high‐precision firearm recognition without compromising operational latency.