Object detection is a critical task in computer vision, enabling advancements across domains such as autonomous systems, surveillance, and smart devices. This paper presents a hybrid approach leveraging both MobileNet and YOLOv8 to address the challenges of resource constraints and the demand for high detection accuracy. For deployment on devices with limited resources, MobileNetV2, a lightweight and effective architecture, is used to provide dependable performance with minimal computational overhead. YOLOv8-s is integrated to achieve high accuracy in scenarios where computational resources are less restricted. By combining these models, the proposed approach balances computational efficiency and detection precision, offering scalability for diverse real-world applications. Comprehensive evaluations on benchmark datasets demonstrate that MobileNet excels in real-time performance for edge devices, while YOLOv8 provides superior accuracy for complex detection tasks. The results underline the effectiveness of this hybrid strategy for utilization on resource constraint devices and highlights the potential of integrating lightweight and high-accuracy models to enhance object detection systems, paving the way for innovative and adaptable solutions.
Computational biology faces many challenges like protein secondary structure prediction (PSS), prediction of solvent accessibility, etc. In this work, we addressed PSS prediction. PSS is based on sequence-structure mapping and interaction among amino acid residues. We proposed an encoder–decoder with an attention mechanism model, which considers the mapping of sequence structure and interaction among residues. The attention mechanism is used to select prominent features from amino acid residues. The proposed model is trained on CB513 and CullPDB open datasets using the Nvidia DGX system. We have tested our proposed method for Q3 and Q8 accuracy, segment of overlap, and Mathew correlation coefficient. We achieved 70.63 and 78.93% Q3 and Q8 accuracy, respectively, on the CullPDB dataset whereas 79.8 and 77.13% Q3 and Q8 accuracy on the CB513 dataset. We observed improvement in SOV up to 80.29 and 91.3% on CullPDB and CB513 datasets. We achieved the results using our proposed model in very few epochs, which is better than the state-of-the-art methods.
29 May 2025 in Asian Journal of Water, Environment and Pollution
In cheminformatics, predicting molecular properties is crucial for enhancing material research, toxicity assessment, and drug discovery. This research investigates the use of graph neural networks (GNNs) for predicting molecular properties by examining three different architectures: graph convolutional networks (GCNs), graph isomorphism networks (GINs), and graph attention networks (GATs). Employing molecular graph information, these models are evaluated on the MUTEG dataset and measured against key metrics such as accuracy and area under the receiver operating characteristic curve (AUC). Our experimental findings show that GIN has the highest accuracy at 89.2%, exceeding GCN (87.5%) and GAT (88.3%). GIN also achieves the highest AUC of 0.89, whereas the AUCs of GCN and GAT are 0.84 and 0.86, respectively, indicating GIN’s enhanced ability to effectively model graph isomorphisms. We selected GIN for this study because of its proven theoretical and empirical strength in capturing graph-level representations, particularly in domains such as cheminformatics, where molecular structures are naturally modeled as graphs. These results highlight the efficacy of GNNs in predicting molecular properties and position GIN as a favored framework for tasks that demand accurate graph feature extraction. This study further plays a pivotal role in understanding the environmental fate and transport of chemical compounds. We used GIN to identify partition coefficients such as the octanol-water partition coefficient, air-water partition coefficient, and soil–water partition coefficient from the MoleculeNet dataset.