Abstract

This paper studies the contextual multi-armed bandit problem with fairness and privacy guarantees in a federated setting. It proposes a collaborative algorithm, Fed-FairX-LinUCB that achieves sublinear fairness regret and can be adapted to ensure differential privacy. The key challenge is designing a communication protocol that balances privacy and regret. The proposed protocol achieves both sub-linear fairness regret and effective use of privacy budget. Experiments validates the efficacy of both Fed-FairX-LinUCB and its private counterpart, Priv-FairX-LinUCB.

Abstract

Automated Sleep stage classification using raw single channel EEG is a critical tool for sleep quality assessment and disorder diagnosis. However, modelling the complexity and variability inherent in this signal is a challenging task, limiting their practicality and effectiveness in clinical settings. To mitigate these challenges, this study presents an end-to-end deep learning (DL) model which integrates squeeze and excitation blocks within the residual network to extract features and stacked Bi-LSTM to understand complex temporal dependencies. A distinctive aspect of this study is the adaptation of GradCam for sleep staging, marking the first instance of an explainable DL model in this domain with alignment of its decision-making with sleep expert's insights. We evaluated our model on the publically available datasets (SleepEDF-20, SleepEDF-78, and SHHS), achieving Macro-F1 scores of 82.5, 78.9, and 81.9, respectively. Additionally, a novel training efficiency enhancement strategy was implemented by increasing stride size, leading to 8x faster training times with minimal impact on performance. Comparative analyses underscore our model outperforms all existing baselines, indicating its potential for clinical usage.

Abstract

Reconfigurable intelligent surfaces (RIS) are emerging as a promising technology for 6G networks due to their ability to shape the radio propagation environment. This ability helps to overcome propagation challenges, such as high path loss, absorption loss, etc., that are particularly needed at millimetre wave (mmWave) bands. Thus, RIS can enhance the capacity of next-generation mmWave communication networks. However, one critical aspect in the design of RIS-aided systems is channel estimation, as it involves estimating two channels (i.e., base stationRIS and RIS-user terminal) separately based on the compound channel observed by the receiver. In this paper, we address this problem by proposing an algorithm that estimates both channels separately by leveraging the advantages of sparsity of the mmWave channel. Specifically, the proposed algorithm uses the parallel factor (PARAFAC) decomposition of the tensor, which is constructed using the received signal matrices observed under different RIS phase shift configurations. Our numerical analysis shows that the proposed algorithm provides significantly smaller normalized mean square error (NMSE) than the widely used alternating least squares (ALS) algorithm, particularly when the number of RIS phase shift configurations is smaller than the number of RIS elements.

Abstract

Identifying correct human postures is crucial in areas like patient care in hospitals. However, the traditional vision-based methods widely used for this purpose raise privacy concerns for the subject, and the other wearable sensor-based approaches are impractical for real-world scenarios. In this paper, we propose a contactless, privacy-conscious, and memoryefficient posture classification system based on millimeter wave (mmWave) radar. This system utilizes threedimension(3D) point-cloud data captured using Texas Instrument’s IWR1843BOOST Frequency Modulated Continuous Wave (FMCW) radar module to classify the posture of the subject. Two types of datasets are extracted from this radar data: (i) image dataset derived from the isometric view of the point-cloud data, and (ii) spatial coordinates dataset also extracted from the point-cloud data. A low-computational Tiny Machine Learning (TinyML) model is employed on the datasets for efficient implementation on embedded hardware, Raspberry Pi 3 B+. The proposed model’s parameters were quantized to 8 bits (int8), which accurately classify four postures, i.e., standing, sitting, lying, and bending, with an accuracy of 98.97% for the image data. However, to make it more computationally efficient, the int8 quantized TinyML model was trained on the spatial coordinates dataset, giving an accuracy of 96.12%. This highlights the efficiency and effectiveness of our proposed lightweight model that can be deployed on edge devices for real-world applications.

Abstract

The current study examines the interaction between predis- posed mood, perceptual processing, and induced mood us- ing music. We conducted an experiment in which partici- pants were asked to identify stimuli at global or local (G/L) perceptual levels with four different background music con- ditions, which had different valence and arousal ratings. We used BMIS to assess current mood and PHQ-9 and GAD-7 to assess depression and anxiety, and divided the participants into two groups: distress and no distress (encompassing both disor- ders). We found a main effect of background music on mood. However, the distress group showed an overall low mood. Fur- ther, we observed an overarching effect of predisposed mood, encompassing depression and anxiety, on individuals’ transient mood experience and perceptual task performance. Individuals in the non-distress group showed a larger global-precedence effect. The results are discussed in light of emotional reactiv- ity theories and the theory of positive emotion.

Abstract

Accurately recognizing a revisited place is crucial for embodied agents to localize and navigate. This requires visual representations to be distinct, despite strong variations in camera viewpoint and scene appearance. Existing visual place recognition pipelines encode the whole image and search for matches. This poses a fundamental challenge in matching two images of the same place captured from different camera viewpoints: the similarity of what overlaps can be dominated by the dissimilarity of what does not overlap. We address this by encoding and searching for image segments instead of the whole images. We propose to use open-set image segmentation to decompose an image into `meaningful' entities (i.e., things and stuff). This enables us to create a novel image representation as a collection of multiple overlapping subgraphs connecting a segment with its neighboring segments, dubbed SuperSegment. Furthermore, to efficiently encode these SuperSegments into compact vector representations, we propose a novel factorized representation of feature aggregation. We show that retrieving these partial representations leads to significantly higher recognition recall than the typical whole image based retrieval. Our segments-based approach, dubbed SegVLAD, sets a new state-of-the-art in place recognition on a diverse selection of benchmark datasets, while being applicable to both generic and task-specialized image encoders. Finally, we demonstrate the potential of our method to revisit anything by evaluating our method on an object instance retrieval task, which bridges the two disparate areas of research: visual place recognition and object-goal navigation, through their common aim of recognizing goal objects specific to a place.

Abstract

Lupus Nephritis classification has historically relied on labor-intensive and meticulous glomerular-level labeling of renal structures in whole slide images (WSIs). However, this approach presents a formidable challenge due to its tedious and resource-intensive nature, limiting its scalability and practicality in clinical settings. In response to this challenge, our work introduces a novel methodology that utilizes only slide-level labels, eliminating the need for granular glomerular-level labeling. A comprehensive multi-stained lupus nephritis digital histopathology WSI dataset was created from the Indian population, which is the largest of its kind. LupusNet, a deep learning MIL-based model, was developed to classify LN subtypes. The results underscore its effectiveness, achieving an AUC score of 91.0%, an F1 score of 77.3%, and an accuracy of 81.1% on our dataset in distinguishing membranous and diffused classes of LN

Abstract

The histone methyltransferase ASH1L, first discovered for its role in transcription, has been shown to accelerate the removal of ultraviolet (UV) light-induced cyclobutane pyrimidine dimers (CPDs) by nucleotide excision repair. Previous reports demonstrated that CPD excision is most efficient at transcriptional regulatory elements, including enhancers, relative to other genomic sites. Therefore, we analyzed DNA damage maps in ASH1L-proficient and ASH1L-deficient cells to understand how ASH1L controls enhancer stability. This comparison showed that ASH1L protects enhancer sequences against the induction of CPDs besides stimulating repair activity. ASH1L reduces CPD formation at C–containing but not at TT dinucleotides, and no protection occurs against pyrimidine-(6,4)-pyrimidone photoproducts or cisplatin crosslinks. The diminished CPD induction extends to gene promoters but excludes retrotransposons. This guardian role against CPDs in regulatory elements is associated with the presence of H3K4me3 and H3K27ac histone marks, which are known to interact with the PHD and BRD motifs of ASH1L, respectively. Molecular dynamics simulations identified a DNA-binding AT hook of ASH1L that alters the distance and dihedral angle between neighboring C nucleotides to disfavor dimerization. The loss of this protection results in a higher frequency of C–>T transitions at enhancers of skin cancers carrying ASH1L mutations compared to ASH1L-intact counterparts.

Abstract

Manuguru, located in Telangana, India, is a significant coal mining hub in the Godavari Valley Coalfield, with over a century of mining history. The region, experiencing rapid industrialization and urbanization, undergoes comprehensive landscape changes, impacting natural ecosystems, agricultural lands, and water resources beyond the coal-bearing areas. This study presents an analysis of the dynamic land use and land cover (LULC) patterns in Manuguru, utilizing multi-spectral/multi-temporal Landsat satellite imagery from 1987 to 2020. Focused on understanding the impact of mining activities on the region's landscape, advanced band indices, namely, Normalized Difference Vegetation Index( NDVI) and Normalized Difference Water Index(NDWI) are employed alongside visual interpretation techniques helps validate these indices by visually inspecting the actual features on the ground.. The interpretation of Landsat images helped delineate 8 land cover categories: agricultural land, barren land, forest, mining sites, built-up areas, rivers, stagnant water bodies, and dried water bodies. In addition to traditional analysis methods, the study incorporates rate of change calculations and transition matrices to quantify and understand the temporal dynamics of LULC composition. Comparative analysis reveals significant shifts in LULC composition over the study period where the expansion of coal mining activities emerges as a dominant driver of change. This resulted in the loss of ecologically rich forests and the proliferation of overburden hills. Despite the prevalent industrial activities, there is a visible dedication to environmental stewardship by reclaiming overburden dumps through reforestation efforts of open scrub areas. The transition of agricultural lands to built-up areas signifies rapid urban expansion, driven by burgeoning population and economic activities. Similarly, the transformation of water bodies into agricultural lands underscores the human demand for arable land, often at the expense of natural ecosystems. The combined effect of transitions within the land use classes can be attributed to the increase of extractive industries and urbanization.

Abstract

How can we effectively estimate the quality of translated texts in the medical field, where back-translation is usually available and/or recommended for sensitive documents. This paper proposes a novel metric, GATE 1 , for translation quality estimation task, leveraging the Resource Description Framework (RDF) to encode both semantic and syntactical information of the original and back-translated sentences into RDF graphs. The distance between these graphs is measured to get the semantic similarity score to assess the quality of the translation. Unlike traditional metrics like BLEU and METEOR, our approach is reference-less, capturing both semantic and syntactical information for a comprehensive assessment of translation quality. Our results correlate better with human judgment, giving a better Pearson correlation (0.357) as compared to BLEU (0.200), thereby showing ~70% improvement over BLEU. Our research shows that, in the field of translation evaluation, existing resources like back-translation and RDF could be useful.