Abstract

Biomolecules play indispensable roles in all life processes, including disease development, so their accurate detection is critical to cell investigation, medical diagnosis, and treatment. Radio Frequency (RF) sensing has become a popular testing technique compared to traditional methods for biomolecule analysis, providing results in less time using less volume of samples. It allows rapid, sensitive, real-time measurements and label-free techniques. However, for taking the signals from biomolecules over the RF-based sensors we need to connect them with the Vector Network Analyzer (VNA) which is a bulky and costly device. To develop an RF sensing based a true lab-on-chip (LoC) device, the paper presents a fully integrated low-power less-area on-chip single port CMOS VNA designed in 65nm CMOS technology to detect the bio-molecule The proposed design works in a tunable frequency range of 0.5 GHz to 2.5 GHz, ensuring much higher precision. Using an RLC equivalent of an Interdigitated capacitor (IDC) sensor, a fully integrated architecture for detecting $S_{11}$ of the biomolecules has been introduced. A resistive bridge coupler is used for wideband operation with a directivity of 14.89dB up to 2.5 GHz. Also, a high-linearity LNA (low noise amplifier) is designed with a linearity of -13dB and a gain of 14dB. The LNA has a low NF of 3.21dB. The design occupies an active area of 0.01767mm^2 and consumes power of 41mW from a 1 V supply.

Abstract

Molecular spectroscopy studies the interaction of molecules with electromagnetic radiation, and interpreting the resultant spectra is invaluable for deducing the molecular structures. However, predicting the molecular structure from spectroscopic data is a strenuous task that requires highly specific domain knowledge. DeepSPInN is a deep reinforcement learning method that predicts the molecular structure when given Infrared and 13C Nuclear magnetic resonance spectra by formulating the molecular structure prediction problem as a Markov decision process (MDP) and employs Monte-Carlo tree search to explore and choose the actions in the formulated MDP. On the QM9 dataset, DeepSPInN is able to predict the correct molecular structure for 91.5% of the input spectra in an average time of 77 seconds for molecules with less than 10 heavy atoms. This study is the first of its kind that uses only infrared and 13C nuclear magnetic resonance spectra for molecular structure prediction without referring to any pre-existing spectral databases or molecular fragment knowledge bases, and is a leap forward in automated molecular spectral analysis.

Abstract

This paper introduces a novel approach for fault detection and localization in a motor of a Hexacopter UAV. The proposed two-stage architecture leverages Long Short-Term Memory (LSTM) networks for latent temporal feature extraction and Random Forest for localization. By combining them, we see improved fault detection and isolation performance. Our evaluations show the robustness of this approach in varying noise levels and real-world-like environments. Analysis of computational efficiency in rapid detection shows that the model identified faults within 2-5 time steps of the flight. Finally, we show that the proposed method surpasses classical statistical models and deep learning techniques in terms of overall accuracy (96.78%).

Abstract

Aggressive scaling down of transistor dimensions has made process-aware circuit modeling a crucial task. Achieving accurate circuit modeling requires lengthy and resource intensive simulations. Machine Learning-based surrogate models, offering computational efficiency and speed, are viable alternatives to traditional simulators. This paper introduces a meta-learning approach designed to accurately capture process induced variations in the leakage power of VLSI circuits. The impact of a wide range of fluctuations in operating conditions, including temperature (-55°C to 125°C) and supply voltage (±10%) has also been incorporated for leakage modeling. The proposed meta-learning model is versatile, enhancing the performance of underlying baseline machine learning models while eliminating the need for time-consuming hyperparameter optimization. Our experiments on leakage estimation using 16 and 7 nanometer FinFET technology nodes demonstrate an average improvement of up to 50% and 48% in Mean Absolute Percentage Error compared to stand-alone baseline models.

Abstract

Knowledge graphs (KGs) have been playing a crucial role in leveraging informa- tion on web for several downstream tasks, making it vital to construct and maintain them. Despite previous efforts in populating KGs, these methods typically do not focus on analyzing entity-specific content exclusively but rely on a fixed collection of documents. We define an approach to populate such KGs by utilizing entity-specific content on the web, for generating entity embeddings to establish entity-category interconnections. We empirically prove our ap- proach’s effectiveness, by utilizing it for a downstream task of Notability detection, associated with one of the most popular and important Knowledge Graphs - Wikipedia platform. To mod- erate the content uploaded to Wikipedia, “Notability” guidelines are defined by its editors to identify named entities that warrant their article on Wikipedia. So far notability is enforced by humans, which makes scalability an issue, and there has been no significant work on automat- ing this process. In this paper, we define a multipronged category-agnostic approach based on web-based entity features and their text-based salience encodings, to construct entity embed- dings for determining an entity’s notability. We distinguish entities based on their categories and utilize neural networks to perform classification. For validation, we utilize accuracy and prediction confidence on popular Wikipedia pages. Our system outperforms machine learning- based classifier approaches and handcrafted entity salience detection algorithms, by achieving performance accuracy of around 88%. Our system provides an efficient and scalable alterna- tive to manual decision-making about the importance of a topic, which could be extended to other such KG-based tasks

Abstract

Wikipedia is a highly essential platform because of its informative, dynamic, and easily accessible nature. To identify topics/titles warranting their own Wikipedia article, editors of Wikipedia defined “Notability” guidelines. So far notability is enforced by humans, which makes scalability an issue. There has been no significant work on Notability determination for titles with complex category dependencies. We design a mechanism to identify such titles. We construct a dataset with 9k such titles and propose a category-agnostic approach utilizing Graph neural networks, for their notability determination. Our system outperforms machine learning-based, transformer-based classifiers and entity salience methods. It provides a scalable alternative to manual decision-making about notability.

Abstract

No Results Found

Abstract

No Results Found

Abstract

No Results Found

Abstract

Despite recent advancements showcasing the impressive capabilities of Large Language Models (LLMs) in conversational systems, we show that even state-of-the-art LLMs are morally inconsistent in their generations, questioning their reliability (and trustworthiness in general). Prior works in LLM evaluation focus on developing ground-truth data to measure accuracy on specific tasks. However, for moral scenarios that often lack universally agreed-upon answers, consistency in model responses becomes crucial for their reliability. To address this issue, we propose an information-theoretic measure called Semantic Graph Entropy (SaGE), grounded in the concept of "Rules of Thumb" (RoTs) to measure a model's moral consistency. RoTs are abstract principles learned by a model and can help explain their decision-making strategies effectively. To this extent, we construct the Moral Consistency Corpus (MCC), containing 50K moral questions, responses to them by LLMs, and the RoTs that these models followed. Furthermore, to illustrate the generalizability of SaGE, we use it to investigate LLM consistency on two popular datasets -- TruthfulQA and HellaSwag. Our results reveal that task-accuracy and consistency are independent problems, and there is a dire need to investigate these issues further.