Thakur College of Engineering and Technology

Manufacturing systems fail due to vibration. Therefore, vibration analysis is used for maintenance activities. Nowadays, predictive maintenance (PdM) is implemented across industries to increase the efficiency and effectiveness of manufacturing operations. The objective of this study is to conduct a Bibliometric Literature Review (BLR) and Systematic Literature Review (SLR) for PdM using vibration analysis (VA). This study focuses on conducting a BLR and a SLR of PdM using VA. Therefore, the SCOPUS database was used, and 754 research articles were used for a bibliometric literature review. Additionally, the TAK principle was applied, and 89 research papers were systematically reviewed for this literature review. This study reveals that China has published the most research articles and received the most citations in the domain of PdM using VA. Various organizations use VA for PdM. However, there are no linkages between them. The maximum number of research articles was published based on hardware and real-life implementation. This study is beneficial for industrial professionals who want to understand the application of VA in PdM activities, enabling them to implement it in their own industries and enhance productivity. It is beneficial for academics and researchers to understand the current state of the art in PdM using VA. This is one of the first studies to present a bibliometric review of PdM using VA. Additionally, a systematic literature review is conducted to categorize research articles into three distinct categories.

Introduction:Ensuring smarter and more sustainable farming practices is a critical challenge in modern agriculture. Agentic Artificial Intelligence (AAI), combined with Precision Agriculture (PA) and Federated Learning (FL), has the potential to enhance decision-making, optimize resource utilization, and reduce environmental impact. Methods:This study proposes an AAI based framework for precision agriculture that integrates distributed sensing devices, intelligent agents, and federated learning to enable real time monitoring and decision support at the farm level. A practical deployment architecture is outlined, detailing inter-device communication and localized intelligence. The proposed model is evaluated across two distinct datasets tomato disease classification and weed detection. The model is designed to have DenseNet121, MobileNetV2, EfficientDet-D0, and YOLOv8 as local models within a federated learning environment. Results:The federated global model achieved an accuracy of 96.4%, outperforming individual client models, with DenseNet121 and MobileNetV2 attaining accuracies of 95.0% and 93.9%, respectively. For weed species detection, EfficientDet-D0 demonstrated superior performance, achieving an mAP@0.5 of 0.978, average precision of 0.865, and an F1-score of 0.961, compared to YOLOv8 with an mAP@0.5 of 0.956 and an F1-score of 0.935. Discussion:The results confirm the feasibility and effectiveness of integrating AAI with federated learning for intelligent precision agriculture. A SWOT analysis highlights the strengths of the proposed approach, along with deployment challenges and constraints. Overall, this study establishes a roadmap for future research, emphasizing sustainable intelligent farming systems.

The presence of noise and intensity variations in medical images poses significant challenges to traditional segmentation methods. In this paper, we propose an enhanced UNet-based framework, UNet++-ViT, incorporating an autoencoder for image denoising and a hybrid loss function combining Tversky Loss and Focal Loss to improve segmentation performance. This paper introduces UNet++-ViT, a robust segmentation framework that integrates a Vision Transformer (ViT) for global contextual understanding, an autoencoder for effective denoising, and a hybrid Tversky-Focal loss to address class imbalance and refine boundary delineation. We evaluate the approach on the LiTS17 liver CT dataset and compare against the models using single loss functions. The proposed method demonstrates superior performance, achieving a Dice coefficient of 0.994, Jaccard index of 0.957, surpassing the leading model SwinUNet by 3.3 % & nnUNet by 4.1% in Dice score along with improved recall and specificity, outperforming other baseline approaches. These results confirm the effectiveness of combining denoising and hybrid loss strategies for robust and precise liver segmentation.

The AI-Driven Self-Assessment and Proctoring System is an innovative process aiming to change the face of online assessments using the MERN stack and other sophisticated AI technologies. The platform enables teachers to dynamically create multiple-choice questions (MCQs) with large language models (LLMs), thus guaranteeing that the questions are relevant on one end and diverse on the other based on the specified topics. The students, powered by their unique room code, can seamlessly enter an assessment that goes in parallel lines with all the other purposes of being secure and user-friendly. Further, a self-assessment module is another feature of the system that allows students to assess their knowledge independently. Students may select topics of interest for AI-curated questions explicitly tailored to their learning needs, followed by a deep assessment of performance focusing on areas to be improved. The integrity of the exam is secured with the AI-malpractice detection mechanism that, at every instance, watches the actions of the candidates via the device’s camera while detecting any suspicious activity and stopping cheating in its tracks. In this way, the system promises a secure, trustworthy, and efficient assessment ecosystem for the teachers and students. On top of question generation for proctoring exams and grading, the system would help relieve teachers’ workload while engaging the students in the learning process. This AI concept employs a scalable assessment that is adaptable to the need for educational institutions to change and modernize their assessment practices. This technology-enabled solution guarantees equal opportunities in learning, hence becoming a giant leap toward the future of education.

Explainability methods for sequential recommendation are structurally passive: they describe model behaviour without influencing training. This paper closes that loop by deploying a model-agnostic Shapley-based framework as an active auditing instrument within a three-stage audit-debug-refine pipeline. The audit mechanism is formalised as a cooperative game G = (T, v) over interaction timesteps, where the characteristic function v : 2T → ℝ evaluates model confidence over item coalitions. We prove that exact Shapley computation for this game is #P-complete (Proposition 1) and derive that the Monte Carlo estimator achieves ε-approximation in O(T log(1/δ)/ε2) samples with probability 1−δ (Proposition 2). Applying the pipeline to GRU4Rec on MovieLens 100K identifies 236 explanation-unreliable users (25%). Population-level diagnosis rules out sequence sparsity (mean sequence length: 19.97 vs 19.96 for flagged vs unflagged users) and identifies low model confidence (0.012 vs 0.037, three-fold difference) as the root cause. Three targeted interventions — BPR Max pairwise ranking loss, popularity-weighted hard negative sampling, and entropy-based output regularisation — are applied in direct response to this diagnosis. The combined model reduces flagged users by 53% (95% CI: 48.1%–57.9%, p < 0.001), improves mean faithfulness from −0.056 to +0.133, and raises NDCG@10 from 0.4382 to 0.4543. A central empirical finding emerges: faithfulness and robustness behave as competing objectives when training interventions shift the model's confidence distribution — a tension that existing XAI evaluation benchmarks do not capture — quantified by the normalised faithfulness–robustness ratio FRn.