International Journal of Science, Engineering and TechnologyA Rule-Based Decision Support System For Bias In Automated Airport Security Checkpoints
Authors: Mrs. B. Priyanka, Mr. B. Karthik, R. Dheekshitha, N. Uday Kiran, P. Sunil, P. Anand Kumar
Abstract: Airports require efficient systems for managing passenger information, flight bookings, luggage records, and security verification. Traditional procedures often depend on manual documentation and disconnected operations, which may cause delays, data duplication, communication gaps, and difficulties in monitoring passenger activities. This paper presents an Airport Passenger Security and Management System, a Django-based web application that integrates passenger registration, flight booking, luggage management, security verification, and administrative control into a centralized platform. Passengers can register, manage their profiles, view available flights, submit booking requests, and provide luggage details such as the number of bags, total weight, and description. Security officers can review passenger information, validate passport details, verify luggage conditions, select luggage tracking statuses, and approve or reject booking requests. The luggage tracking feature supports status updates such as Submitted, Checked, Dispatched, Loaded, In Transit, Delivered, and Missing. Administrators can manage flights, monitor bookings, and approve or reject security officer registrations through a dedicated dashboard. Email notifications provide updates regarding registration, booking, approval, rejection, and luggage status changes. The system uses Django for application development and SQLite for data storage. By combining passenger management, booking operations, security checking, and luggage tracking, the proposed system improves information organization, reduces manual effort, and supports more transparent airport management. The application also provides a foundation for future integration with biometric authentication, RFID-based luggage tracking, real-time flight information, and intelligent security assessment.
DOI: http://doi.org/10.5281/zenodo.22873837
UQ-TSE-Net: A Lightweight Uncertainty-Aware Network For Reliable Liver Tumor Segmentation In Contrast-Enhanced CT Images
Authors: Sharmila Arun Chopade, Dr. Akash Saxena
Abstract: Liver tumor segmentation of contrast-enhanced CT (computerized tomography) scans is an important step for computer-aided liver cancer diagnosis, treatment, and follow-up. Although deep learning approaches have recently been significantly advancing the task of medical image segmentation, liver tumor segmentation still faces many challenges since liver tumors usually have non-regular shapes, fuzzy boundaries, and heterogeneous enhancement patterns. Besides, class imbalance between lesions and background tissues is also very high. Existing models mostly predict a final liver tumor mask without providing any kind of information on the reliability of this prediction. The absence of uncertainty quantification is one of the most serious problems of medical imaging due to the necessity of reviewing uncertain regions by experts.In this work, we propose UQ-TSE-Net (uncertainty-quantifying total segment enhancement network), a novel uncertainty-aware lightweight architecture for reliable liver tumor segmentation of contrast-enhanced CT scans. The proposed approach combines efficient feature extraction via convolutions, attention-based feature refinement, boundary awareness, and uncertainty estimation using Monte Carlo dropout. The first two blocks form a main segmentation branch, while the latter allows improving the performance of segmentation in ambiguous regions. Finally, the uncertainty of the model predictions is estimated using the Monte Carlo dropout approach that produces a set of different predictions. Based on these predictions, a pixel-level uncertainty map is obtained highlighting low-confidence regions of liver tumors, especially those located at fuzzy tumor margins.For the experiments, we will use the Liver Tumor Segmentation Challenge dataset (LiTS17). The comparison will be made to widely-used segmentation models such as UNet, Attention UNet, UNet++, DeepLabV3+, TransUNet, UNETR, and nnU-Net. The models' performance will be evaluated using classical segmentation metrics like Dice score, Intersection over Union, precision, and recall and additional reliability-oriented metrics, like Expected Calibration Error and Brier score.UQ-TSE-Net will allow getting not only an accurate tumor mask but also uncertainty information that is crucial for further interpreting the results. In the current study, we make another step towards obtaining reliable computer-aided liver tumor analysis with the help of uncertainty-aware lightweight architecture.
DOI: https://zenodo.org/records/22974329
Machine Learning and Deep Learning for Brain Tumor Prediction and Segmentation in MRI: A Systematic Review of Methods, Datasets and Open Challenges
Authors: Research Scholar Namrata Vijayvargiya, Assistant Professor Nirupma Singh
Abstract: Magnetic resonance imaging (MRI) is the reference modality for brain tumor diagnosis, yet manual delineation remains slow, expertise-dependent and subject to inter-observer variability. Over the last four years the literature has shifted decisively from handcrafted feature pipelines to convolutional, encoder-decoder, transformer and hybrid learning architectures. This paper presents a systematic review of forty-one primary studies published between 2023 and 2026, selected from 412 records through a PRISMA-style protocol. The reviewed work is organised into a four-branch taxonomy – classical machine learning, CNN backbones, encoder-decoder segmentation networks and transformer/hybrid ensembles – and is compared on a common footing of accuracy, precision, recall, F1-score, Dice similarity coefficient and intersection over union. Reported classification accuracy ranges from 93.30% to 99.70% and Dice from 0.650 to 0.961, but the spread is shown to be driven as much by dataset choice and evaluation protocol as by architecture. A reference hybrid detection-segmentation pipeline that couples classical preprocessing and region-based localisation with CNN feature learning and a margin-based or meta-learned decision layer is formalised as two algorithms, and priorities for trustworthy, federated and explainable neuro-oncology AI are set out.
BrailleLearn: A Low-Cost IoT-Based Braille Learning System with Dot-Level Error Analysis and Targeted Practice
Authors: Hari Shankar M, Prem Kumar H, Dharmendran V
Abstract: – Learning Braille depends on repeated tactile practice, yet beginners often practise with printed material or with a teacher present to say whether a pattern is right. This paper describes the design of BrailleLearn, a low-cost console in which six push buttons, arranged as a Braille cell, and a confirm button are read by an ESP32 microcontroller. After each attempt the learner’s six-bit pattern is compared with the target pattern, and the difference is resolved to individual dots, separating dots that were left out from dots that were pressed without being required. The accumulated per-dot error counts are intended to drive a targeted practice mode that favours characters involving the dots a learner finds hardest. Feedback is planned through LEDs and a buzzer, with an optional Bluetooth Low Energy link to a smartphone for spoken prompts and progress records. We review related work on refreshable displays, IoT assistive devices, and technology for Braille literacy, state the gap the console addresses, and present the hardware, software, and evaluation design. At the time of writing the physical prototype and firmware have not been completed; no measurements or user-study results are reported, and an evaluation plan is given in their place.