Ahmed Sami Jaddoa

We present an integrated system, which is a mix of summarization as well as Question Answering (QA) to boost the performance regarding information retrieval (IR) for long and domain-intensive documents. This work creates a synergistic relationship between both tasks to enhance retrieval efficiency and quality of answers, unlike previous studies focusing separately on either summarization or QA. The framework proposed is comprised of three stages. First, it involves summarization that is used for condensing documents, maintaining their key semantic content. Second, it employs a retrieval-augmented generation (RAG) architecture, where the all-MiniLM-L6-v2 model is used for the retrieval stage, while T5 and BART-Large-CNN models are utilized for the generation stage. Lastly, answers generated are put into comparison with a baseline system which works with complete document processing without summarization. Results at the NIPS dataset reveal that integrating summarization with QA significantly improves each summary informativeness and answer accuracy. To investigate the impact of summarization inside the retrieval pipeline, two complementary eventualities are explored. First, Proactive Summarization as an Indexing Tool (Summarization-First) plays summarization earlier than the indexing and retrieval stages to reduce record size and improve retrieval performance while keeping semantic relevance. Second, Query-Guided Contextual Summarization (Retrieval-First Summarization) applies summarization after the retrieval level, wherein only the retrieved relevant passages are summarized in step with consumer question for generating more targeted and context-conscious solutions. These two scenarios enable a comparative analysis of the way the position of summarization within RAG pipeline impacts retrieval efficiency as well as solution era quality. Received: 19 June 2026 | Revised: 13 August 2026 | Accepted: 14 September 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in Kaggle at https://www.kaggle.com/datasets/benhamner/nips-papers?select=papers.csv. Author Contribution Statement Ahmed Sami Jaddoa: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & Editing, Visualization, Project administration. Jaber Karimpour: Conceptualization, Methodology, Formal analysis, Investigation, Resources, Data curation, Writing – review & editing, Supervision, Project administration. Pedram Salehpour: Conceptualization, Supervision.

Here, we propose a composite system that uses text summarization (TS) and question answering (QA) to supplement the IR process of long documents. Most previous studies have used separate approaches, i.e., either TS or QA. The aim of this paper is to develop an interaction between TS and QA in three stages to enhance IR performance. First, SBERT is used for summarization. Second, an RAG method is employed to retrieve information and generate answers. In the architecture of RAG, retrieval of the document is fulfilled via all-MiniLM-L6-v2, while answer generation is performed via the T5 and BART-large-cnn models. Third, the retrieved answers are assessed and compared with a baseline system in which the documents are treated without summarization. The proposed system aims to improve the quality of retrieved information and accuracy of answers generated by TSQA in a unified pipeline. Experimental evaluation conducted on the NIPS dataset demonstrates that the proposed approach significantly enhances summary informativeness and answer accuracy compared with traditional single-task approaches. The simulation results show improvements of 20.83% in text similarity and 2.38% in BERT scores for answer generation compared with the standard RAG baseline without summarization.

Federated Learning FL is a rapidly evolving machine learning paradigm that enables collaborative model training across decentralized data sources while preserving data privacy. Since its inception in 2016, FL has emerged as a transformative approach in domains such as healthcare, IoT, and edge computing, where data sensitivity and regulatory constraints limit centralized processing. This systematic review consolidates findings from 50 high-quality studies selected from over 250 papers to present a comprehensive synthesis of FL methodologies, core aggregation techniques, privacy-preserving mechanisms, security threats, domain-specific applications, and emerging trends. We categorize challenges into communication overhead, heterogeneity (device, data, model), fairness, trust, and evaluation inconsistencies. We highlight research gaps, notably in standardized evaluation, incentive mechanisms, and deployment scalability. By reviewing recent advances such as vertical federated learning, federated unlearning, and blockchain-based incentives, this paper offers a roadmap for future research and identifies open questions vital for widespread FL adoption.

Liver disease counts are one of the most prevalent diseases all over the world and they are becoming very common these days and can be dangerous. Liver diseases are increasing all over the world due to different factors such as excess alcohol consumption, drinking contaminated water, eating contaminated food, and exposure to polluted air. The liver is involved in many functions related to the human body and if not functioned properly can affect the other parts too. Predication of the disease at an earlier stage can help reduce the risk of severity. This paper implemented oversampling dataset, feature selecting attributes, and performance analysis for the improvement of the accuracy of classification of liver patients in 3 phases. In the first phase, the z-score normalization algorithm has been implemented to the original liver patient data-sets that has been collected from the UCI repository and then works on oversampling the balanced dataset. In the second phase, feature selection of attributes is more important by using RFE feature selection. In the third phase, classification algorithms are applied to the data-set. Finally, evaluation has been performed based upon the values of accuracy. Thus, outputs shown from proposed classification implementations indicate that ANN algorithm performs better than AdaBoost algorithm with the help of feature selection with a 92.77% accuracy