Search

Serial-parallel redundancy is a reliable way to ensure service and systems will be available in cloud computing. That method involves making copies of the same system or program, with only one remaining active. When an error occurs, the inactive copy can step in as a backup right away, this provides continuous performance and uninterrupted operation. This approach is called parallel redundancy, otherwise known as active-active redundancy, and its exceptional when it comes to strategy. It creates duplicates of a system or service that are all running at once. By doing this fault tolerance increases since if one copy fails, the workload can be distributed across any replica thats functioning properly. Reliability allocation depends on features in a system and the availability and fault tolerance you want from it. Serial redundancy or parallel redundancies can be applied to increase the dependability of systems and services. To demonstrate how well this concept works, we looked into fixed serial parallel reliability redundancy allocation issues followed by using an innovative hybrid optimization technique to find the best possible allocation for peak dependability. We then measured our findings against other research., Comment: 5 Pages, 1 Figure, 2 Tables

Designing proper treatment plans to manage diabetes requires health practitioners to pay heed to the individuals remaining life along with the comorbidities affecting them. Older adults with Type 2 Diabetes Mellitus (T2DM) are prone to experience premature death or even hypoglycaemia. The structured dataset utilized has 68 potential mortality predictors for 275,190 diabetic U.S. military Veterans aged 65 years or older. A new target variable is invented by combining the two original target variables. Outliers are handled by discretizing the continuous variables. Categorical variables have been dummy encoded. Class balancing is achieved by random under-sampling. A benchmark regression model is built using Multinomial Logistic Regression with LASSO. Chi-Squared and Information Gain are the filter-based feature selection techniques utilized. Classifiers such as Multinomial Logistic Regression, Random Forest, Extreme Gradient Boosting (XGBoost), and One-vs-Rest classifier are employed to build various models. Contrary to expectations, all the models have constantly underperformed. XGBoost has given the highest accuracy of 53.03 percent with Chi-Squared feature selection. All the models have consistently shown an acceptable performance for Class 3 (remaining life is more than 10 years), significantly low for Class 1 (remaining life is up to 5 years), and the worst for Class 2 (remaining life is more than 5 but up to 10 years). Features analysis has deduced that almost all input variables are associated with multiple target classes. The high dimensionality of the input data after dummy encoding seems to have confused the models, leading to misclassifications. The approach taken in this study is ineffective in producing a high-performing predictive model but lays a foundation as this problem has never been viewed from a multiclass classification perspective., Comment: 146 Pages

With the widespread adoption of Large Language Models (LLMs), in this paper we investigate the multilingual capability of these models. Our preliminary results show that, translating the native language context, question and answer into a high resource language produced the best results.

Video foreground segmentation (VFS) is an important computer vision task wherein one aims to segment the objects under motion from the background. Most of the current methods are image-based, i.e., rely only on spatial cues while ignoring motion cues. Therefore, they tend to overfit the training data and don't generalize well to out-of-domain (OOD) distribution. To solve the above problem, prior works exploited several cues such as optical flow, background subtraction mask, etc. However, having a video data with annotations like optical flow is a challenging task. In this paper, we utilize the temporal information and the spatial cues from the video data to improve OOD performance. However, the challenge lies in how we model the temporal information given the video data in an interpretable way creates a very noticeable difference. We therefore devise a strategy that integrates the temporal context of the video in the development of VFS. Our approach give rise to deep learning architectures, namely MUSTAN1 and MUSTAN2 and they are based on the idea of multi-scale temporal context as an attention, i.e., aids our models to learn better representations that are beneficial for VFS. Further, we introduce a new video dataset, namely Indoor Surveillance Dataset (ISD) for VFS. It has multiple annotations on a frame level such as foreground binary mask, depth map, and instance semantic annotations. Therefore, ISD can benefit other computer vision tasks. We validate the efficacy of our architectures and compare the performance with baselines. We demonstrate that proposed methods significantly outperform the benchmark methods on OOD. In addition, the performance of MUSTAN2 is significantly improved on certain video categories on OOD data due to ISD., Comment: 10 pages, 8 figures

Chiral molecule sensing is currently performed using chromatography, electrophoresis, enzymatic-assays, mass spectrometry, and chiroptical sensing techniques. Currently polarimetry is the only method having in-vivo sensing capabilities, while other techniques analyze chiral molecules in body fluids. Polarimetry demonstrated in-vivo performance upto depths of 1 mm while using UV-Visbile light, beyond which light scattering tends to be dominant. We hypothesize that photoacoustic sensing while operating at the Near-Infrared (NIR)-II window can allow for deep-tissue sensing, due to reduced scattering/autofluorescence effects. Herein, a Photoacoustic based Polarization Enhanced Optical Rotation Sensing (PAPEORS) system was developed for the first time to estimate optical rotation parameter using the recorded PA signals at larger depths. This optical rotation was then used to correlate with the chiral molecular concentration at depths of about 3.5 mm. Experimental evaluations were performed with aqueous glucose solution, naproxen drug, and serum-based glucose samples. PAPEORS has achieved a detection limit of 80 mg/dL using circular incidence polarization with serum-based glucose samples. Further ex-vivo experiments were performed to demonstrate the ability of PAPEORS for deep-tissue sensing, which can be extended for in-vivo chiral molecular sensing. PAPEORS uses single wavelength for sensing chiral biomolecules, hence can be miniaturized, allowing for many point-of-care applications., Comment: 30 pages, 5 figures

Audio Question Answering (AQA) constitutes a pivotal task in which machines analyze both audio signals and natural language questions to produce precise natural language answers. The significance of possessing high-quality, diverse, and extensive AQA datasets cannot be overstated when aiming for the precision of an AQA system. While there has been notable focus on developing accurate and efficient AQA models, the creation of high-quality, diverse, and extensive datasets for the specific task at hand has not garnered considerable attention. To address this challenge, this work makes several contributions. We introduce a scalable AQA data generation pipeline, denoted as the AQUALLM framework, which relies on Large Language Models (LLMs). This framework utilizes existing audio-caption annotations and incorporates state-of-the-art LLMs to generate expansive, high-quality AQA datasets. Additionally, we present three extensive and high-quality benchmark datasets for AQA, contributing significantly to the progression of AQA research. AQA models trained on the proposed datasets set superior benchmarks compared to the existing state-of-the-art. Moreover, models trained on our datasets demonstrate enhanced generalizability when compared to models trained using human-annotated AQA data. Code and datasets will be accessible on GitHub~\footnote{\url{https://github.com/swarupbehera/AQUALLM}}.

This report introduces a novel optofluidic platform based on piezo-MEMS technology, capable of identifying subtle variations in the fluid concentration. The system utilizes piezoelectric micromachined ultrasound transducers (PMUTs) as receivers to capture sound waves produced by nanosecond photoacoustic (PA) pulses emanating from a fluid target housed in PDMS microchannels. Additionally, a dedicated low-noise single-channel amplifier has been developed to extract the minute analog voltage signals from the PMUTs, given the inherently weak ultrasound signals generated by fluid targets. The PMUTs' proficiency in detecting changes in fluid concentration under both static and time-varying conditions has been documented and verified, confirming the platform's efficacy in monitoring fluid concentrations., Comment: 9 pages, 10 figures

Quantum key distribution (QKD) provides a method of ensuring security using the laws of physics, avoiding the risks inherent in cryptosystems protected by computational complexity. Here we investigate the feasibility of satellite-based quantum key exchange using low-cost compact nano-satellites. This paper demonstrates the first prototype of system level quantum key distribution aimed at the Cube satellite scenario. It consists of a transmitter payload, a ground receiver and simulated free space channel to verify the timing and synchronisation (T&S) scheme designed for QKD and the required high loss tolerance of both QKD and T&S channels. The transmitter is designed to be deployed on various up-coming nano-satellite missions in the UK and internationally. The effects of channel loss, background noise, gate width and mean photon number on the secure key rate (SKR) and quantum bit error rate (QBER) are discussed. We also analyse the source of QBER and establish the relationship between effective signal noise ratio (ESNR) and noise level, signal strength, gating window and other parameters as a reference for SKR optimization. The experiment shows that it can tolerate the 40 dB loss expected in space to ground QKD and with small adjustment decoy states can be achieved. The discussion offers valuable insight not only for the design and optimization of miniature low-cost satellite-based QKD systems but also any other short or long range free space QKD on the ground or in the air.