Effective software projects hinge on robust requirements, yet flawed requirements often lead to costly delays and revisions. While tools have been developed to identify defects in Software Requirements Specifications (SRS), the advent of Large Language Models (LLMs) like GPT-4 presents new opportunities for enhancing requirements quality. However, the potential of LLMs in this realm remains largely unexplored, particularly in the context of large-scale industrial documents. To bridge this gap, we investigate the efficacy of zero-shot GPT-4 in various requirements analysis tasks using an industrial software specification document. Our study evaluates LLM performance in detecting defects, such as ambiguities, inconsistencies, and incompleteness, while also analyzing GPT-4’s ability to identify issues across version iterations and support technical experts in requirements analysis. Qualitatively, we identify key limitations of LLMs in defect detection, notably their inability to cross-reference throughout the document and their constrained understanding of specialized contexts. Quantitatively, we find that while LLMs excel in identifying incomplete requirements (precision 0.61), their performance is less impressive in detecting inconsistencies (precision 0.43) and ambiguities (precision 0.39). Although GPT-4 demonstrates promise in automating early defect detection across versions and providing accurate technical answers, our results underscore that they cannot entirely replace human analysts due to their lack of nuanced domain knowledge in a zero-shot setting. Nevertheless, avenues like few-shot learning and complex prompt design offer the potential to enhance LLM precision in defect detection.

Early-stage cancer diagnosis potentially improves the chances of survival for many cancer patients worldwide. Manual examination of Whole Slide Images (WSIs) is a time-consuming task for analyzing tumor-microenvironment. To overcome this limitation, the conjunction of deep learning with computational pathology has been proposed to assist pathologists in efficiently prognosing the cancerous spread. Nevertheless, the existing deep learning methods are ill-equipped to handle fine-grained histopathology datasets. This is because these models are constrained via conventional softmax loss function, which cannot expose them to learn distinct representational embeddings of the similarly textured WSIs containing an imbalanced data distribution. To address this problem, we propose a novel center-focused affinity loss (CFAL) function that exhibits 1) constructing uniformly distributed class prototypes in the feature space, 2) penalizing difficult samples, 3) minimizing intra-class variations, and 4) placing greater emphasis on learning minority class features. We evaluated the performance of the proposed CFAL loss function on two publicly available breast and colon cancer datasets having varying levels of imbalanced classes. The proposed CFAL function shows better discrimination abilities as compared to the popular loss functions such as ArcFace, CosFace, and Focal loss. Moreover, it outperforms several SOTA methods for histology image classification across both datasets. The paper code is publicly available at https://github.com/Taslim-M/CFAL-max-margin-keras .

Bats play a pivotal role in maintaining ecological balance, and studying their behaviors offers vital insights into environmental health and aids in conservation efforts. Determining the presence of various bat species in an environment is essential for many bat studies. Specialized audio sensors can be used to record bat echolocation calls that can then be used to identify bat species. However, the complexity of bat calls presents a significant challenge, necessitating expert analysis and extensive time for accurate interpretation. Recent advances in neural networks can help identify bat species automatically from their echolocation calls. Such neural networks can be integrated into a complete end-to-end system that leverages recent internet of things (IoT) technologies with long-range, low-powered communication protocols to implement automated acoustical monitoring. This paper presents the design and implementation of such a system that uses a tiny neural network for interpreting sensor data derived from bat echolocation signals. A highly compact convolutional neural network (CNN) model was developed that demonstrated excellent performance in bat species identification, achieving an F1-score of 0.9578 and an accuracy rate of 97.5%. The neural network was deployed, and its performance was evaluated on various alternative edge devices, including the NVIDIA Jetson Nano and Google Coral.