Abstract

In this paper, we propose an FPGA based system for non-contact monitoring of respiration rates (RR) using a mmWave frequency modulated continuous wave (FMCW) radar. The novel FPGA based hardware architecture presented in this paper classifies normal and abnormal RR with a Support Vector Machine (SVM) model using mmWave radar-based sensing. SVM with various kernels are evaluated in order to identify the most effective approach for respiratory rate (RR) classification. SVM with a quadratic polynomial kernel shows a high classification accuracy of 95%. While the accuracy was comparable to other kernels, the quadratic polynomial kernel achieved a substantial reduction in the number of support vectors and other parameters. This optimisation results in lower resource utilisation and power consumption, making it highly efficient for FPGA implementa- tion.

Abstract

This letter presents the development of a real-time object detection system using frequency modulated continuous wave millimeter-wave (mmWave) radar signals and the python productivity for zynq ultrascale + mpsocs (PYNQ-ZU) field-programmable gate array (FPGA) board, which is widely used in advanced driving assistance system and robotic applications. A hardware FPGA platform serves as a valid embedded architecture for the purpose of validating object detection and recognition applications. We used our experiment’s point cloud images to apply different machine learning models to detect these objects. Using a top-view (TV) filter to convert 3-D point cloud images into 2-D representations made object detection more accurate. Following the use of filtration techniques, we extracted features from the filtered 2-D image using the visual geometry group (VGG) 16 model. We then assessed four machine learning models for object detection and found that the support vector machine (SVM) model and logistic regression (LR) had better results, obtaining an accuracy of 97%. Our proposed work uses mmWave radar, TV filter, VGG 16 Model, and LR to highly increase object detection accuracy over existing methods.

Abstract

We introduce a new information-theoretic measure to characterize non-Markovianity in a tripartite quantum state of genuine quantum origin. This measure reveals a novel tripartite quantum correlation and may be interpreted as entanglement between two systems when conditioned on the third (memory) system. We formulate a convex resource-theoretic framework to characterize genuine quantum non-Markovianity in states as a quantum resource and provide operational meaning to this resource in various information processing tasks.

Abstract

In this work, we introduce and characterize a broad class of quantum operations with a unique fixed point, termed quantum ergodic channels. We derive Lindblad-type master equations for these channels in arbitrary finite dimensions and analyze their non-Markovian dynamics using established measures. When the fixed point is a passive state, the channels exhibit ergotropy dynamics with notable thermodynamic implications. Specifically, under Markovian processes, ergotropy (a measure of the extractable work from a system under unitary evolution) monotonically decreases. However, in non-Markovian dynamics, ergotropy fluctuates, leading to a backflow effect that highlights memory-induced resource recovery. Our findings suggest that this ergotropy backflow could serve as an operationally meaningful indicator of non-Markovianity, offering new perspectives on the interplay between memory effects and thermodynamic behavior in open quantum systems. This study enhances the theoretical framework for understanding energy dynamics under ergodic channels and highlights new avenues for exploring the implications of memory effects in quantum batteries.

Abstract

In decision making settings such as medical diagnosis, investment choices, or sentencing in a court of law, an individual’s background and experience influence their decisions. In the legal domain, multiple factors like personal bias/beliefs, recent events, and the contemporary state of mind could affect decision-making, leading to inconsistencies in judgments between and within jurisdictions. It is widely reported in the literature that anomalies and disparities exist in judicial decisions, such as bail grants and sentence impositions, stemming from implicit bias or other contextual factors. Notably, in domains like sales and marketing, data cube-based systems are being used to extract interesting trends and anomalies in subspaces from large multidimensional databases. In this paper, we extend the data cube framework to explore possible anomalies and disparities in court sentences by conducting experiments on a sample Indian judgment dataset of criminal cases. The results show that the data cube-based framework could identify anomalies in the legal domain. We hope this work will encourage researchers to investigate a compre- hensive data cube-based framework to reduce disparities and improve justice delivery worldwide.

Abstract

Large Language Models (LLMs) often inherit biases from the web data they are trained on, which contains stereotypes and prejudices. Current methods for evaluating and mitigating these biases rely on bias-benchmark datasets. These benchmarks measure bias by observing an LLM’s behavior on biased statements. However, these statements lack contextual considerations of the situations they try to present. To address this, we introduce a contextual reliability framework, which evaluates model robustness to biased statements by considering the various contexts in which they may appear. We develop the Context-Oriented Bias Indicator and Assessment Score (COBIAS) to measure a biased statement’s reliability in detecting bias, based on the variance in model behavior across different contexts. To evaluate the metric, we augmented 2,291 stereotyped statements from two existing benchmark datasets by adding contextual information. We show that COBIAS aligns with human judgment on the contextual reliability of biased statements (Spearman’s 𝜌 = 0.65, 𝑝 = 3.4 ∗ 10−60) and can be used to create reliable benchmarks, which would assist bias mitigation works.

Abstract

Chemical reaction prediction, encompassing forward synthesis and retrosynthesis, stands as a fundamental challenge in organic synthesis. A widely adopted computational approach frames synthesis prediction as a sequence-to-sequence translation task, using the commonly used SMILES representation for molecules. The current evaluation of machine learning methods for retrosynthesis assumes perfect training data, overlooking imperfections in reaction equations in popular datasets, such as missing reactants, products, other physical and practical constraints such as temperature and cost, primarily due to a focus on the target molecule. This limitation leads to an incomplete representation of viable synthetic routes, especially when multiple sets of reactants can yield a given desired product. In response to these shortcomings, this study examines the prevailing evaluation methods and introduces comprehensive metrics designed to address imperfections in the dataset. Our novel metrics not only assess absolute accuracy by comparing predicted outputs with ground truth but also introduce a nuanced evaluation approach. We provide scores for partial correctness and compute adjusted accuracy through graph matching, acknowledging the inherent complexities of retrosynthetic pathways. Additionally, we explore the impact of small molecular augmentations while preserving chemical properties and employ similarity matching to enhance the assessment of prediction quality. We introduce SynFormer, a sequence-to-sequence model tailored for SMILES representation. It incorporates architectural enhancements to the original transformer, effectively tackling the challenges of chemical reaction prediction. SynFormer achieves a Top-1 accuracy of 53.2% on the USPTO-50k dataset, matching the performance of widely accepted models like Chemformer, but with greater efficiency by eliminating the need for pre-training.

Abstract

Automatic detection of prominence at the word and syllable-levels is critical for building computer-assisted language learning systems. It has been shown that prosody embeddings learned by the current state-of-the-art (SOTA) text-to-speech (TTS) systems could generate word- and syllable-level prominence in the synthesized speech as natural as in native speech. To understand the effectiveness of prosody embeddings from TTS for prominence detection under nonnative context, a comparative analysis is conducted on the embeddings extracted from native and non-native speech considering the prominence-related embeddings: duration, energy, and pitch from a SOTA TTS named FastSpeech2. These embeddings are extracted under two conditions considering: 1) only text, 2) both speech and text. For the first condition, the embeddings are extracted directly from the TTS inference mode, whereas for the second condition, we propose to extract from the TTS under training mode. Experiments are conducted on native speech corpus: Tatoeba, and non-native speech corpus: ISLE. For experimentation, word-level prominence locations are manually annotated for both corpora. The highest relative improvement on word & syllable-level prominence detection accuracies with the TTS embeddings are found to be 13.7% & 5.9% and 16.2% & 6.9% compared to those with the heuristic-based features and self-supervised Wav2Vec-2.0 representations, respectively.

Abstract

Vision-language models (VLMs) excel at tasks requiring joint understanding of visual and linguistic information. A particularly promising yet under-explored application for these models lies in answering questions based on various kinds of maps. This study investigates the efficacy of VLMs in answering questions based on choropleth maps, which are widely used for data analysis and representation. To facilitate and encourage research in this area, we introduce a novel map-based question-answering benchmark, consisting of maps from three geographical regions (United States, India, China), each containing around 1000 questions. Our benchmark incorporates 43 diverse question templates, requiring nuanced understanding of relative spatial relationships, intricate map features, and complex reasoning. It also includes maps with discrete and continuous values, covering variations in color mapping, category ordering, and stylistic patterns, enabling a comprehensive analysis. We evaluated the performance of multiple VLMs on this benchmark, highlighting gaps in their abilities, and providing insights for improving such models. Our dataset, along with all necessary code scripts, is available at map-wise.github.io

Abstract

We present EditIQ, a completely automated framework for cinematically editing scenes captured via a stationary, large field-of-view and high-resolution camera. From the static camera feed, EditIQ initially generates multiple virtual feeds, emulating a team of cameramen. These virtual camera shots termed rushes are subsequently assembled using an automated editing algorithm, whose objective is to present the viewer with the most vivid scene content. To understand key scene elements and guide the editing process, we employ a two-pronged approach: (1) a large language model (LLM)-based dialogue understanding module to analyze conversational flow, coupled with (2) visual saliency prediction to identify meaningful scene elements and camera shots therefrom. We then formulate cinematic video editing as an energy minimization problem over shot selection, where cinematic constraints determine shot choices, transitions, and continuity. EditIQ synthesizes an aesthetically and visually compelling representation of the original narrative while maintaining cinematic coherence and a smooth viewing experience. Efficacy of EditIQ against competing baselines is demonstrated via a psychophysical study involving twenty participants on the BBC Old School dataset plus eleven theatre performance videos. Video samples from EditIQ can be found at https://editiq-ave.github.io/.