The rapid advancement of generative models and their misuse have made deepfake detection a crucial area of research. However, existing datasets and detection techniques predominantly focus on frontal-face perspectives, leaving sideface views largely underexplored. To bridge this gap, we present IndicSideFace, a novel dataset specifically curated for advancing deepfake detection on side-face perspectives of Indian subjects. This dataset encompasses a diverse range of side-face angles, varying lighting conditions, and demographic attributes, providing a comprehensive benchmark for evaluating detection algorithms. Our experiments using state-of-the-art models highlight the unique challenges posed by side-face deepfakes, such as partial facial feature visibility and uncommon head poses. The findings reveal significant limitations in existing detection approaches when applied to side-face perspectives, underscoring the need for specialized solutions. With IndicSideFace, we aim to strengthen the resilience of deepfake detectors and stimulate further research in this critical yet underexplored domain.

The interpretability of machine learning model is crucial in healthcare as it fosters reliability and supports clinicians in making informed decisions based on predictions. However, recent approaches for vital parameter estimation often act as black boxes, lacking clarity in their predictive reasoning. Therefore, accurate estimation of vital parameters is crucial not only for timely diagnosis and effective patient monitoring but also for ensuring that clinicians can trust and understand the model’s predictions. In this study, we introduce XVPE-Net, an explainable framework aimed at improving the state-of-the-art VPE-Net model for estimating vital parameters: heart rate (HR), respiratory rate (RR), systolic blood pressure (SBP), and diastolic blood pressure (DBP). Our model enhances interpretability by visually highlighting key parts of the PPG signal that significantly influence VPE-Net’s predictions of vital parameters. We test our model using 1,000 PPG segments from 38 subjects in the MIMIC-III dataset, which is available in the Physionet repository. The results show strong predictive capabilities, along with better transparency and reliability. This study helps us understand how the model makes decisions and supports the use of explainable AI in health monitoring, contributing to the development of more reliable models for medical applications.

Synthetic datasets constructed from formal languages allow fine-grained examination of the learning and generalization capabilities of machine learning systems for sequence classification. This article presents a new benchmark for machine learning systems on sequence classification called MLRegTest, which contains training, development, and test sets from 1,800 regular languages. Different kinds of formal languages represent different kinds of long-distance dependencies, and correctly identifying long-distance dependencies in sequences is a known challenge for ML systems to generalize successfully. MLRegTest organizes its languages according to their logical complexity (monadic second order, first order, propositional, or restricted propositional) and the kind of logical literals (string, tier-string, subsequence, or combinations thereof). The logical complexity and choice of literal provides a systematic way to understand different kinds of long-distance dependencies in regular languages, and therefore to understand the capacities of different ML systems to learn such long-distance dependencies. Finally, the performance of different neural networks (simple RNN, LSTM, GRU, transformer) on MLRegTest is examined. The main conclusion is that performance depends significantly on the kind of test set, the class of language, and the neural network architecture.

Active queue management (AQM) policies are mechanisms for congestion avoidance, which pro-actively drop packets in order to provide an early congestion notification to the sources. We propose a new adaptive prediction based approach for congestion estimation (APACE) in active queue management that predicts the instantaneous queue length at a future time using adaptive filtering techniques. We compare the performance of APACE with other existing AQM schemes like RED (random early detection), SRED (stabilized RED), AVQ (adaptive virtual queue) and PAQM (predictive AQM) in networks having both single and multiple bottleneck links. We show that the performance of APACE in terms of the stability of the instantaneous queue is comparable to that of PAQM, which is one of the best AQM strategies. Moreover, APACE performs better than PAQM in terms of link utilization and in networks with multiple bottleneck links. APACE is not very sensitive to parameter settings, adapts quickly to changes in traffic and can achieve a given delay or packet loss by varying just one parameter, thus giving the network operator a better tool to manage congestion and improve the performance of the network.