Reem Alnanih

Existing Non-Functional Requirement (NFR) classification approaches typically classify NFR statements independently, overlooking the semantic information provided by their associated Functional Requirements (FRs). Moreover, most existing models rely on general-purpose language representations and sentence-level evaluation protocols that may overestimate model generalization. This paper proposes a context-aware NFR classification framework that integrates FR context with the domain-specialized representations learned by the domain-specialized Stage-3 Re-Distill encoder. The proposed framework is evaluated under a strict project-level protocol designed to assess generalization across previously unseen software projects, together with a supplementary sentence-level 10-fold cross-validation experiment for comparison with existing studies. Experimental results demonstrate that the proposed framework achieves 0.86 Accuracy and 0.80 Macro-F1 under the project-level evaluation protocol while consistently outperforming generic pretrained transformer encoders. The experiments further reveal that the contribution of FR context is category-dependent, substantially improving Security and Usability classification while providing little or even negative benefit for Availability. Under sentence-level cross-validation, the same framework achieves a Macro-F1 score of 0.97, highlighting the strong influence of evaluation protocols on reported performance. These findings demonstrate that domain-specialized representations and FR context provide complementary benefits for NFR classification while highlighting the importance of realistic evaluation protocols for assessing model generalization.

Alzheimer’s disease (AD) is a global health challenge requiring early and accurate diagnosis, yet current clinical methods struggle with early stages. Deep learning approaches for MRI-based diagnosis face persistent challenges related to image quality issues, limited model generalization, and subtle inter-class variations. To address these limitations, this paper proposes a robust, end-to-end brain MRI-based framework for multi-class classification of AD stages. Positioned within the broader research priority of artificial intelligence and intelligent healthcare technologies, the proposed methodology incorporates an attention-based ensemble of deep learning models alongside an enhanced image preprocessing that uses Real-ESRGAN to mitigate common compression and resolution degradations in 2-D MRI slices. The ensemble makes use of the superior capabilities of the Swin Transformer to capture global contextual dependencies and EfficientNet-B3/MobileNetV2 for effective multi-scale feature extraction, with feature fusion performed using a Squeeze-and-Excitation attention mechanism. The experiments were performed on a publicly available Alzheimer’s MRI dataset, resulting in classification accuracy of 94.47% and 92.28% for the two proposed frameworks. The robustness and clinical interpretability of the framework are emphasized through comprehensive metrics and qualitative analysis. This framework demonstrates promising benchmark performance on a standardized public dataset, highlighting the potential of cross-paradigm ensembles combined with super-resolution preprocessing.

Non-functional requirements (NFRs) are critical for ensuring software quality, yet they remain difficult to identify due to their implicit and loosely defined relationship with functional requirements (FRs). Existing research predominantly focuses on NFR classification, leaving the more practical problem of linking FRs with their corresponding NFRs largely underexplored. To bridge this gap, this research introduces Re-Distill, a framework that treats FR–NFR association as a retrieval task. It adopts a curriculum-guided, data-centric distillation strategy to improve semantic representations and capture the interdependencies between FRs and NFRs. The framework combines general semantic adaptation, domain-specific specialization, and teacher-guided hard-negative mining in a contrastive learning setting. During inference, it integrates dense and lexical retrieval with cross-encoder reranking to produce ranked NFR candidates for unseen FR queries. Experiments on an expanded FR–NFR dataset show consistent improvements throughout all training stages. The resulting model achieves a Recall@10 of 70.79%, significantly outperforming the zero-shot baseline (42.36% Recall@10). These results highlight the effectiveness of retrieval-based approaches for functional–non-functional requirement linking, providing a practical and scalable way to undertake software requirement analysis.

Light Detection and Ranging (LiDAR) has became an indispensable technology across diverse domains including agriculture, geology, urban planning, and transportation due to its capacity to generate precise, high resolution three dimensional spatial data. However, the substantial volume of data produced by high-density LiDAR scans imposes significant burdens on storage infrastructure, data transmission bandwidth, and computational resources. As such, effective compression techniques are essential to enable scalable LiDAR data management while maintaining the integrity and fidelity required for analytical applications. This paper introduces a new lossless compression framework tailored for LiDAR data stored in the standard LiDAR Aerial Survey (LAS) format. The proposed approach integrates a neural network–based autoencoder with the Lempel–Ziv–Markov chain (LZMA) compression algorithm to generate a highly compact latent representation of LiDAR data. Experimental results demonstrate a compression factor of 17.21:1 with an average efficiency of 94.16%, significantly outperforming both general purpose compressors (e.g. WinRAR) and specialized tools (e.g. LASzip). By substantially reducing data size without compromising quality, the proposed method offers a robust and scalable solution for the efficient handling of large-scale LiDAR files, making it well suited for both operational and resource-constrained environments.

Sustainability in software engineering encompasses environmental, human, social, and economic dimensions, each essential for ensuring software’s positive and lasting impact. This paper presents an innovative Internet of Things (IoT)-based Smart Waste Management (SWM) system. The proposed system addresses key limitations in existing solutions, including lack of real-time responsiveness, inefficient routing, inadequate emergency detection, and limited user-centric design. While prior studies have investigated IoT applications in SWM, challenges remain in achieving dynamic, integrated, and scalable systems for sustainable urban development. The proposed solution introduces a holistic architecture that enables real-time monitoring of waste bin levels and fire incidents through Waste Bin Level Monitoring Units (BLMUs) equipped with ultrasonic and flame sensors. Data is transmitted via Wi-Fi to a centralized City Command and Control Center (4C), allowing for automated alerts and dynamic route optimization. A dual-platform software suite supports both administrative and operational workflows: a desktop web application and a role-based Android mobile app developed in Flutter, and integrated with Google Cloud Firestore, enabling centralized data management and efficient resource allocation. We validated the system through a working prototype, demonstrating notable contributions including enhanced emergency responsiveness, optimized waste collection routes, and improved stakeholder engagement. This research contributes to the advancement of sustainable urban infrastructure by offering a scalable, data-driven SWM framework grounded in software engineering principles and aligned with smart city objectives. This paper presents an innovative IoT-based Smart Waste Management (SWM) system that addresses key limitations in existing solutions, including insufficient real-time responsiveness, inefficient routing, inadequate emergency detection, and limited user-centric design.

In today’s competitive digital landscape, application usability plays a critical role in user satisfaction and retention. Negative user reviews offer valuable insights into real-world usability issues, yet traditional analysis methods often fall short in scalability and contextual understanding. This paper proposes an intelligent framework that utilizes large language models (LLMs), including GPT-4, Gemini, and BLOOM, to automate the extraction of actionable usability recommendations from negative app reviews. By applying prompting and fine-tuning techniques, the framework transforms unstructured feedback into meaningful suggestions aligned with three core usability dimensions: correctness, completeness, and satisfaction. A manually annotated dataset of Instagram negative reviews was used to evaluate model performance. Results show that GPT-4 consistently outperformed other models, achieving BLEU scores up to 0.64, ROUGE scores up to 0.80, and METEOR scores up to 0.90—demonstrating high semantic accuracy and contextual relevance in generated recommendations. Gemini and BLOOM, while improved through fine-tuning, showed significantly lower performance. This study also introduces a practical, web-based tool that enables real-time review analysis and recommendation generation, supporting data-driven, user-centered software development. These findings illustrate the potential of LLM-based frameworks to enhance software usability analysis and accelerate feedback-driven design processes.

Self-driving cars are expected to become a convenient source of transportation in near future. However, achieving a self-driving car at Level 5 still poses challenges. The challenges could be attributed to maintaining desirable functionality under uncertainty while accomplishing a task. This paper proposes a hybrid N-redundancy-based resilient framework for the perception module that integrates abstract sensor fusion and a probabilistic deep learning model to ensure resilient performance. Experimental results using the CARLA simulator demonstrate that our model consistently outperforms existing approaches in runtime efficiency while maintaining functional integrity under attack. Time-based performance evaluations reveal that our hybrid model achieves faster and more reliable outputs, validating its effectiveness in resilient autonomous perception.

Road object segmentation is crucial for autonomous driving, as it enables vehicles to perceive their surroundings. While deep learning models show promise, their generalization across diverse road conditions, weather variations, and lighting changes remains challenging. Different approaches have been proposed to address this limitation. However, these models often struggle with the varying appearance of road objects under diverse environmental conditions. Foundation models such as the Segment Anything Model (SAM) offer a potential avenue for improved generalization in complex visual tasks. Thus, this study presents a pioneering comprehensive evaluation of the SAM for zero-shot road object segmentation, without explicit prompts. This study aimed to determine the inherent capabilities and limitations of the SAM in accurately segmenting a variety of road objects under the diverse and challenging environmental conditions encountered in real-world autonomous driving scenarios. We assessed the SAM’s performance on the KITTI, BDD100K, and Mapillary Vistas datasets, encompassing a wide range of environmental conditions. Using a variety of established evaluation metrics, our analysis revealed the SAM’s capabilities and limitations in accurately segmenting various road objects, particularly highlighting challenges posed by dynamic environments, illumination changes, and occlusions. These findings provide valuable insights for researchers and developers seeking to enhance the robustness of foundation models such as the SAM in complex road environments, guiding future efforts to improve perception systems for autonomous driving.

The increasing adoption of Artificial Intelligence (AI) in several industries has created a demand for user-centered explanations that align with how users think and understand concepts. This paper presents EXACT (EXplainable AI with Cognitive Theories), a novel framework that combines cognitive theories that explain how people think and understand with cognitive functions, focusing on perception, memory and language abilities, to improve users’ comprehension of and engagement with artificial intelligence technologies. By aligning cognitive functions with the design principles of Human-Computer Interaction (HCI), which promote user-centered intuitive systems. the framework addresses challenges related to making AI understandable to users with various levels of cognitive abilities. As a proof-of-concept, a self-diagnosis tool was created to demonstrate the framework’s effectiveness. Then, 60 participants were divided into a control group and an experimental group. Participants completed six tasks designed to evaluate their perception, memory, and language-related cognitive functions. The experimental group outperformed the control group across all tasks, demonstrating significantly improved performance. Subjective metrics also supported these findings: the experimental group reported higher levels of understanding (4.60 vs. 2.87), confidence (4.67 vs. 3.07), and clarity (4.87 vs. 2.80) compared to the control group. These findings suggest that EXACT framework significantly enhances user’s functions when using AI systems. However, further research is needed to explore its broader applicability in other contexts and utilize other cognitive functions.