Abstract

The avenue of deep learning is scarcely explored in the domain of thermal imaging. Recovering a high-resolution output from images and videos is a classical problem in many computer vision applications. In this paper, we propose an optimized pipeline for a real-time video super-resolution task using thermal camera on embedded edge device. To tackle the challenges, we make contributions in the following several aspects: 1) comparative study of selected deep learning super-resolution models; 2) constructing and optimizing an end-to-end inference pipeline; 3) using cutting edge technology to integrate the whole workflow; 4) a real-time performance was achieved using less data; 5) we have also experimented the entire pipeline on our custom thermal dataset. As a consequence, the chosen model was able to achieve a real-time speed of over 29, 36 and 45 high FPS; 32.9dB/0.889, 31.86dB/0.801 and 30.94dB/0.728 PSNR/SSIM values for 2x, 3x and 4x scaling factors respectively.

Abstract

The ramp generator is a crucial circuit component in the design of switching power supply, analog to digital converters, CMOS image sensors, and many other essential circuits. Conventionally, the ramp generator has been implemented with a CMOS comparator that works on the hysteresis principle, which leads to an inherent systemic delay. This paper aims at improving the overall circuit speed by proposing the design of a ramp generator using CMOS proteretic comparator in 180nm TSMC process. It is established from the post-layout simulation that a speedup of 25% is achieved by replacing a hysteretic comparator with a proteretic comparator, and this is done with a trade-off in power consumption and circuit area.

Abstract

The effect of Residual Mechanical Jitter (RMJ) has been analysed on the incoherent beam combination through various atmospheric turbulences. It is observed that the RMJ effect is more prominent for lower turbulence than higher turbulence.

Abstract

In this study, we characterize biosamples using a microstrip patch based Radio Frequency (RF) sensor by integrating both resonant and non-resonant parameters. In particular, the resonance frequency, the resonance amplitude, −10 dB bandwidth, range of operation, and return loss at center frequency were employed to perform the analysis. The idea was to utilize multiple parameters to build a comprehensive understanding of different bio-samples. In order to demonstrate the working of the methodology, two sets of analytes were studied-(i) aqueous solutions of biomolecules and (ii) body fluids. For both sets of analytes, the method demonstrated significant efficiency in performing qualitative characterization.

Abstract

In this article, we present a novel target classification technique by mmWave frequency modulated continuous wave (FMCW) Radars using the Machine Learning on raw data features obtained from range fast Fourier transform (FFT) plot. FFT plots are extracted from the measured raw data obtained with a Radar operating in the frequency range of 77 - 81 GHz. The features such as peak, width, area, standard deviation, and range on range FFT plot peaks are extracted and fed to a machine learning model. Two light weight classification models such as Logistic Regression, Naive Bayes are explored to assess the performance. Based on the results, we demonstrate and achieve an accuracy of 86.9% using Logistic Regression. The proposed technique will be highly useful for several applications in cost-effective and reliable ground station traffic management systems for autonomous systems. The end-to-end framework presented here, expands the capabilities of mmWave Radar beyond range detection to classification. The implications of this added functionalities will facilitate utilization of mmWave Radars in computer vision, object recognition, and towards fully autonomous traffic control and management systems.

Abstract

In classification models fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging. We propose a neural network-based framework, FNNC, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better. The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints.

Abstract

Around 40% of global energy produced is consumed by buildings. By using renewable energy resources we can alleviate the dependence on electrical grids. Recent trends focus on incentivizing consumers to reduce their demand consumption during peak hours for sustainable demand response. To minimize the loss, the distributor companies should target the right set of consumers and demand the right amount of electricity reductions.This paper proposes a novel bounded integer min-knapsack algorithm and shows that the algorithm, while allowing for multiple unit reduction, also optimizes the loss to the distributor company within a factor of two (multiplicative) and a problem dependent additive constant. Existing CMAB algorithms fail to work in this setting due to nonmonotonicity of reward function and time varying optimal sets. We propose a novel algorithm (TwinMinKPDR-CB) to learn these compliance probabilities efficiently. Twin-MinKPDR-CB works for non-monotone reward functions, bounded minknapsack constraints, and time-varying optimal sets. We find that Twin-MinKPDR-CB achieves sub-linear regret of O(log T) with T being the number of rounds demand response is run.

Abstract

Generative Adversarial Networks (GANs) are by far the most successful generative models. Learning the transformation which maps a low dimensional input noise to the data distribution forms the foundation for GANs. Although they have been applied in various domains, they are prone to certain challenges like mode collapse and unstable training. To overcome the challenges, researchers have proposed novel loss functions, architectures, and optimization methods. In our work here, unlike the previous approaches, we focus on the input noise and its role in the generation. We aim to quantitatively and qualitatively study the effect of the dimension of the input noise on the performance of GANs. For quantitative measures, typically Fr´echet Inception Distance (FID) and Inception Score (IS) are used as performance measure on image data-sets. We compare the FID and IS values for DCGAN and WGAN-GP. We use three different image data-sets – each consisting of different levels of complexity. Through our experiments, we show that the right dimension of input noise for optimal results depends on the data-set and architecture used. We also observe that the state of the art performance measures does not provide enough useful insights. Hence we conclude that we need further theoretical analysis for understanding the relationship between the low dimensional distribution and the generated images. We also require better performance measures.

Abstract

Bitcoin is the first of its kind, a truly decentralized and anonymous cryptocurrency. To realize it, it has developed a blockchain technology using the concept of ‘Proof of Work’ (PoW). The miners, nodes responsible for writing transaction database, solve a cryptographic puzzle to claim the right to write to the database. Though bitcoin and many other relevant cryptocurrencies such as ether use revolutionary ideas, the main criticism involves the computing resource and energy consump- tion to solve the puzzles that have otherwise no use. There are attempts to use the PoW to do something useful, commonly referred to as Proof-of-Useful-Work (PoUW). In this paper, we attempt to (i) make PoUW more usable – describe how a central problem setter can crowdsource their work as PoUW and (ii) in the true spirit of blockchains, decentralize the role of problem setter, whom we call puzzlers. We propose a formal framework to do so, namely PUPoW. PUPoW has an inbuilt provision of payments from puzzler to the miner who solves its puzzle. Additionally, miners have the option to not rely on continuous feed of the puzzles and instead use original PoW puzzles. We also propose a way to use PUPoW for solving TOR vanity URL generation and bitcoin vanity address generation problems. We call this PUPoW blockchain solving vanity address generation problems as VanityCoin. Both the problems need to generate public keys from private keys such that resultant addresses are of interest. Such key pairs are found only by a brute force search. However, there are privacy concerns that miners would know the private keys of the puzzlers. We resolve this by splitting the private keys, and the miners would know only one part of it. In summary, we are proposing how PoW can be made practically useful, and we believe such an approach is needed for PoW blockchains to survive.

Abstract

Several optimization scenarios involve multiple agents that desire to protect the privacy of their preferences. There are distributed algorithms for constraint optimization that provide improved privacy protection through secure multiparty computation. However, it comes at the expense of high computational complexity and does not constitute a rigorous privacy guarantee for optimization outcomes, as the result of the computation itself may compromise agents’ preferences. In this work, we show how to achieve privacy, specifically differential privacy, through the randomization of the solving process. In particular, we present P-Gibbs, which adapts the SD-Gibbs algorithm to obtain differential privacy guarantees with much higher computational efficiency. Experiments on graph coloring and meeting scheduling show the algorithm’s privacy-performance trade-off for varying privacy budgets, and the SD-Gibbs algorithm.