Transformer-Based Object Detection Architectures for Autonomous Driving Perception: A Comprehensive Review
Autonomous vehicle perception is one of the most important components in intelligent transportation systems, and the reliable trade-off between high fidelity of detection precision and computational efficiency in real time remains an open problem. Deep learning has proven to be very accurate in controlled settings, but bringing CNN-based solutions to deployment with high latency and substantial memory overhead is often a challenge to the end-to-end deployed Transformer solution. This thorough review provides a systematic analysis of recent developments in transformer-based detection architectures, consolidating 2024–2026 transformer- and CNN-based architectures for detection. It is a thorough review that systematically analyzes recent transformer-based detection architectures, summarizing the current transformer- and CNN-based detection architectures from 2024 to 2026. From our analysis, we can see that there is a clear lack of theoretical sophistication and the real-life edge-deployability of the hardware. In addition, there is a clear disconnection between the 2D camera-based detection approach and the 3D multimodal fusion approach in the literature. The critical research dimensions that are not well met by the current state-of-the-art are identified in this review, including small object detection in dense urban environments and robust inference under challenging weather conditions. This review provides a structured path forward by mapping these interrelated gaps and paving the way for the creation of lightweight, accurate and robust transformer detectors that can be deployed on their own in the field.
Published by: Muhammad Hamza
Author: Muhammad Hamza
Paper ID: V12I3-1176
Paper Status: published
Published: May 25, 2026
Do ESG Rating Divergences Predict Stock Underperformance?
While the ESG investing trend has shifted to the forefront, a rather worrying paradox is also becoming ever more evident, that of the dramatically divergent ESG evaluations rendered for the identical companies, consistently and by rating agencies across the industry. This paper investigates whether that difference of opinion, particularly when combined with unambiguous and highly optimistic environmental rhetoric in corporate filings, might be used as a quantifiable indicator of greenwashing, and if companies with that pattern of behaviour tend subsequently to underperform in equity markets. I employ a sample of 135 international firms from the S&P 500 and MSCI world indices, 2015-2023, providing a dataset of 1,080 firm-year observations. I calculated an aggregated ESG divergence index using pairwise disagreements from MSCI, Sustainalytics, and Bloomberg ESG ratings, and combined it with two text-based indicators from annual reports: a FinBERT sustainability sentiment index and a TF-IDF-based ESG keyword intensity measure for inclusion in my analysis. Ordinary Least Squares (OLS) regressions, two-way fixed effects panel models, and Fama-MacBeth cross-section estimation are used to carry out the empirical investigation. I find, throughout all specifications, that ESG rating divergence is negatively and significantly associated with risk-adjusted returns; each unit of added divergence relates to an annual excess return that is approximately 0.39–0.42% lower (p<0.01). Positive sustainability sentiment in disclosures correlates with better performance, whereas high keyword density unaccompanied by external rating agreement points in the opposite direction, consistent with rhetorical inflation rather than genuine ESG progress. A long-short portfolio sorted on divergence quintiles accumulates approximately 8.7 percentage points of excess return over the nine-year window. The results speak directly to the concerns of asset managers, index providers, and regulators engaged in the ongoing effort to bring rigour to sustainable finance.
Published by: Sheena Syed
Author: Sheena Syed
Paper ID: V12I3-1169
Paper Status: published
Published: May 22, 2026
Review of AI-Driven Methods to Enhance Search and Rescue Operations after Earthquakes
The devastating results of seismic events affect many people’s lives every time they occur. The main damage is caused to people being trapped under the rubble for long periods of time because rescue teams lack intelligent and prioritised plans. To address this problem, we will study the utilisation of various artificial intelligence (AI) technologies in accelerating and enhancing the efficiency of human spotting and rescuing processes after earthquakes. These applications include neural networks, AI-controlled robot systems, and multimodal data fusion, where thermal, visual, and acoustic data are integrated to detect survivors under building debris, in addition to other fusion ideas. This review will focus on studies published between 2023 and 2026. One main outcome of this work is the identification of key limitations in current AI solutions, such as real-time processing constraints, the noisy nature of disaster environments, and hardware deployment challenges in active disaster zones. In conclusion, this review aims to serve as a future research direction for optimising AI-driven methods to enhance detection accuracy, accelerate rescue timelines, and improve the overall survival outcomes in seismic emergencies.
Published by: Lin M.Saleh Aouto
Author: Lin M.Saleh Aouto
Paper ID: V12I3-1179
Paper Status: published
Published: May 22, 2026
A Comparative Review of Deep Learning Methods for Landmine Detection from Vision Transformers to Ground-Penetrating Radar
Landmines present a real problem around the world, causing injuries and a real threat to deminers’ lives. Due to that, the search for safe and efficient demining methods has been a humanitarian priority for a long time. Traditional methods rely on physical probing and manual demining. However, these methods give high false-alarm rates, risks, costs, and are time-consuming. Thus, there is an urgent need to find innovative technologies and study their potential to give 100% efficient solution. This paper provides a comparative review of recent research in landmine detection and classification, focusing on the application of Artificial Intelligence and Deep Learning. We will evaluate the number of recently used deep learning methodologies, datasets and achieved performance results. This will help identify how Artificial Intelligence can succeed in solving the problems of demining operations. In this study, we will analyse the use of different algorithms with the overall goal of specifying the best findings to ensure high territory clearance, as well as specifying the challenges. This review provides important insights into the current state of the field, highlighting solutions that can enhance demining operations and improve detection accuracy.
Published by: Leidi M.Saleh Aouto
Author: Leidi M.Saleh Aouto
Paper ID: V12I3-1180
Paper Status: published
Published: May 21, 2026
Comparative Evaluation of Machine Learning Approaches for Physiological Stress Detection Using ECG and EEG Signal Modalities
Stress is a complicated physiological and psychological phenomenon that has a huge impact on the health and performance of people. Conventional methods of measuring stress are dependent upon self-reports, making it difficult to determine if they are truthful and cannot be noted in real-time. In this study, the use of machine learning techniques to identify stress objectively based on physiological signals taken from ECG and EEG was examined. While other studies have only examined one signal type (either ECG or EEG), this study compared the two modalities side-by-side under the same experimental conditions, using equal amounts of data from publicly available datasets. Multiple machine learning models (Logistic Regression, Support Vector Machine, Random Forest, XGBoost, LSTM) were compared and contrasted using available datasets. Physiological signal features (heart rate variability, electrodermal activity) were taken into account and analysed to understand both autonomic and neural activation due to stress. The results demonstrated that the Random Forest model yielded the highest level of performance (F1-score=.86, AUC=.90), indicating that Random Forest is better suited to handling complex physiological signals than any other machine learning model. An analysis of the physiological signals indicated that stress causes a decrease in heart rate variability, an increase in skin conductance, and an increase in cardiovascular activity (during the physical response) due to increased sympathetic nervous system stimulation. In summary, this research points to machine learning-based techniques yielding dependable, non-invasive means for detecting stress. This research indicates that there is an opportunity to use physiologic signal analysis in combination with AI to provide future possibilities for monitoring mental health and wearable technology.
Published by: Kevin Shah
Author: Kevin Shah
Paper ID: V12I3-1185
Paper Status: published
Published: May 21, 2026
IoT-Enabled Smart Parking and Blind Spot Detection
Accelerating urbanisation, combined with a sharp rise in privately owned automobiles, has placed considerable pressure on city infrastructures, particularly with respect to parking management and vehicular safety. Locating an available parking slot consumes significant driver time, indirectly amplifying fuel usage, traffic density, and urban air pollution. Simultaneously, limited driver visibility around a vehicle—especially in blind-spot regions—continues to be a leading contributor to low-speed accidents during parking manoeuvres. This paper offers a thorough review of prevailing technological frameworks, with particular emphasis on deploying ESP32 microcontrollers alongside arrays of heterogeneous sensors to achieve real-time proximity monitoring and obstacle awareness. The study traces the evolution from conventional camera-only solutions toward affordable, omnidirectional IoT architectures designed to strengthen situational awareness comprehensively. Key findings underscore the value of ultrasonic sensing paired with cloud-connected dashboards and smartphone interfaces in building a safer, fully networked vehicular ecosystem.
Published by: Rahul G P, Prithviraj R, KS Maneesh Kumar, Manvith DO, Raghuveer C M
Author: Rahul G P
Paper ID: V12I3-1182
Paper Status: published
Published: May 20, 2026
