Managing personal documents remains a hassle: files accumulate across cloud drives, email, and local devices in formats that mix scanned images with digital text, and conventional retrieval based on filenames and folder hierarchies handles neither ambiguous queries nor cross-format access well. This paper presents Intelli-Docs, a personal document assistant that combines retrieval- augmented generation (RAG) with multimodal retrieval so that users can locate and question their documents through natural language queries. The system ingests documents through three coordinated pipelines. A text pipeline extracts and chunks document text, embeds the chunks, and stores them in a vector index. A query pipeline classifies each request as text retrieval, image retrieval, or general conversation and routes it accordingly. An image pipeline processes scanned and photographic documents with three parallel models: a Tesseract engine for optical character recognition, a BLIP model for caption generation, and a CLIP ViT-B/16 encoder for semantic image embeddings, whose outputs are fused into a single textual representation. Retrieved evidence is passed to a large language model that generates the final grounded answer. On image- text retrieval benchmarks, the retrieval component reached Recall@5 of 92% and mean average precision of 0.89, with a mean query latency of 2.7 s. We describe the architecture, the evaluation protocol, and the observed trade-offs between accuracy and on-device cost, and we discuss the limitations that constrain mobile deployment.
Prashant Bhattarai, S. Baral, Kritika Thapa et al.· Journal of Engineering Issue...· 0 citations
Transportation infrastructure and systems in the United States (US) are increasingly challenged by climate change, aging infrastructure, and rapid urbanization, necessitating planning approaches that integrate both long-term sustainability and short-term resilience. However, most existing frameworks have evaluated these concepts independently, limiting their effectiveness for holistic decision-making. This study proposed a quality prioritization index (QPI) framework that unified sustainability and resilience into a single quantifiable index using the fuzzy analytic hierarchy process (FAHP). Through an extensive literature review, 49 resilience factors were identified and systematically categorized into four dimensions: absorptive capacity, adaptive capacity, restorative capacity, and equitable access. A structured FAHP-based survey was administered to transportation professionals across diverse geographic regions, and their opinions were analyzed using FAHP to obtain factor weights and to prioritize them. These weights were used to develop the resilience prioritization index (RPI). The RPI was subsequently integrated with an existing sustainability prioritization index (SPI) to construct the unified QPI framework. The proposed framework was demonstrated through a case study of five US Gulf of Mexico–adjacent states—Texas, Louisiana, Mississippi, Alabama, and Florida—and its robustness was evaluated using sensitivity analysis. The results revealed that financial preparedness, interagency coordination, strategic resource allocation, and multichannel communication were the most influential factors for transportation system resilience. The case study demonstrated notable regional variations, with Florida exhibiting the highest QPI value, indicating comparatively lower overall transportation system quality, while Alabama and Louisiana showed higher overall quality. Sensitivity analysis further revealed that QPI outcomes were highly responsive to varying sustainability and resilience weights. The QPI framework provides transportation planners and policy makers with a practical decision–support tool for identifying high-impact intervention areas and strategically allocating resources to simultaneously enhance long-term sustainability and short-term resilience.
S. Baral, Behzad Rouhanizadeh, Elnaz Safapour· Journal of Transportation En...· 0 citations