arXiv subjects

Mohit Kumar

Publications and source records attributed to Mohit Kumar.

At least 55 records · Page 3Linked to original sources

arXiv2023

Non-Linear Signal Processing methods for UAV detections from a Multi-function X-band Radar

This article develops the applicability of non-linear processing techniques such as Compressed Sensing (CS), Principal Component Analysis (PCA), Iterative Adaptive Approach (IAA) and Multiple-input-multiple-output (MIMO) for the purpose of enhanced UAV detections using portable radar systems. The combined scheme has many advantages and the potential for better detection and classification accuracy. Some of the benefits are discussed here with a phased array platform in mind, the novel portable phased array Radar (PWR) by Agile RF Systems (ARS), which offers quadrant outputs. CS and IAA both show promising results when applied to micro-Doppler processing of radar returns owing to the sparse nature of the target Doppler frequencies. This shows promise in reducing the dwell time and increase the rate at which a volume can be interrogated. Real-time processing of target information with iterative and non-linear solutions is possible now with the advent of GPU-based graphics processing hardware. Simulations show promising results.

eess.SP↗

arXiv2022

AI-based Fog and Edge Computing: A Systematic Review, Taxonomy and Future Directions

Resource management in computing is a very challenging problem that involves making sequential decisions. Resource limitations, resource heterogeneity, dynamic and diverse nature of workload, and the unpredictability of fog/edge computing environments have made resource management even more challenging to be considered in the fog landscape. Recently Artificial Intelligence (AI) and Machine Learning (ML) based solutions are adopted to solve this problem. AI/ML methods with the capability to make sequential decisions like reinforcement learning seem most promising for these type of problems. But these algorithms come with their own challenges such as high variance, explainability, and online training. The continuously changing fog/edge environment dynamics require solutions that learn online, adopting changing computing environment. In this paper, we used standard review methodology to conduct this Systematic Literature Review (SLR) to analyze the role of AI/ML algorithms and the challenges in the applicability of these algorithms for resource management in fog/edge computing environments. Further, various machine learning, deep learning and reinforcement learning techniques for edge AI management have been discussed. Furthermore, we have presented the background and current status of AI/ML-based Fog/Edge Computing. Moreover, a taxonomy of AI/ML-based resource management techniques for fog/edge computing has been proposed and compared the existing techniques based on the proposed taxonomy. Finally, open challenges and promising future research directions have been identified and discussed in the area of AI/ML-based fog/edge computing.

cs.DC↗

arXiv2022

Membership-Mappings for Data Representation Learning: Measure Theoretic Conceptualization

A fuzzy theoretic analytical approach was recently introduced that leads to efficient and robust models while addressing automatically the typical issues associated to parametric deep models. However, a formal conceptualization of the fuzzy theoretic analytical deep models is still not available. This paper introduces using measure theoretic basis the notion of \emph{membership-mapping} for representing data points through attribute values (motivated by fuzzy theory). A property of the membership-mapping, that can be exploited for data representation learning, is of providing an interpolation on the given data points in the data space. An analytical approach to the variational learning of a membership-mappings based data representation model is considered.

cs.LG↗

arXiv2022

Differentially Private Transferrable Deep Learning with Membership-Mappings

This paper considers the problem of differentially private semi-supervised transfer and multi-task learning. The notion of \emph{membership-mapping} has been developed using measure theory basis to learn data representation via a fuzzy membership function. An alternative conception of deep autoencoder, referred to as \emph{Conditionally Deep Membership-Mapping Autoencoder (CDMMA)}, is considered for transferrable deep learning. Under practice-oriented settings, an analytical solution for the learning of CDMMA can be derived by means of variational optimization. The paper proposes a transfer and multi-task learning approach that combines CDMMA with a tailored noise adding mechanism to achieve a given level of privacy-loss bound with the minimum perturbation of the data. Numerous experiments were carried out using MNIST, USPS, Office, and Caltech256 datasets to verify the competitive robust performance of the proposed methodology.

cs.LG↗

arXiv2022

An Energy Aware Clustering Scheme for 5G-enabled Edge Computing based IoMT Framework

In recent years, 5G network systems start to offer communication infrastructure for Internet of Things (IoT) applications, especially for health care service pro-viders. In smart health care systems, edge computing enabled Internet of Medical Things (IoMT) is an innovative technology to provide online health care monitor-ing facility to patients. Here, energy consumption, along with extending the lifespan of biosensor network, is a key concern. In this contribution, a Chicken Swarm Optimization algorithm, based on Energy Efficient Multi-objective clus-tering scheme is applied in the context of IoMT system. An effective fitness func-tion is designed for cluster head selection., using multiple objectives, such as re-sidual energy, queuing delay, communication cost, link quality and node centrali-ty. Simulated outcomes of the proposed scheme are compared with the existing schemes in terms of parameters such as cluster formation time, energy consump-tion, network lifetime, throughput and propagation delay.

cs.NI↗

arXiv2022

Information Theoretic Evaluation of Privacy-Leakage, Interpretability, and Transferability for Trustworthy AI

In order to develop machine learning and deep learning models that take into account the guidelines and principles of trustworthy AI, a novel information theoretic trustworthy AI framework is introduced. A unified approach to "privacy-preserving interpretable and transferable learning" is considered for studying and optimizing the tradeoffs between privacy, interpretability, and transferability aspects. A variational membership-mapping Bayesian model is used for the analytical approximations of the defined information theoretic measures for privacy-leakage, interpretability, and transferability. The approach consists of approximating the information theoretic measures via maximizing a lower-bound using variational optimization. The study presents a unified information theoretic approach to study different aspects of trustworthy AI in a rigorous analytical manner. The approach is demonstrated through numerous experiments on benchmark datasets and a real-world biomedical application concerned with the detection of mental stress on individuals using heart rate variability analysis.

cs.LG↗

arXiv2022

Membership-Mappings for Practical Secure Distributed Deep Learning

This study leverages the data representation capability of fuzzy based membership-mappings for practical secure distributed deep learning using fully homomorphic encryption. The impracticality issue of secure machine (deep) learning with fully homomorphic encrypted data, arising from large computational overhead, is addressed via applying fuzzy attributes. Fuzzy attributes are induced by globally convergent and robust variational membership-mappings based local deep models. Fuzzy attributes combine the local deep models in a robust and flexible manner such that the global model can be evaluated homomorphically in an efficient manner using a boolean circuit composed of bootstrapped binary gates. The proposed method, while preserving privacy in a distributed learning scenario, remains accurate, practical, and scalable. The method is evaluated through numerous experiments including demonstrations through MNIST dataset and Freiburg Groceries Dataset. Further, a biomedical application related to mental stress detection on individuals is considered.

cs.LG↗

arXiv2022

Learning MAX-SAT from Contextual Examples for Combinatorial Optimisation

Combinatorial optimisation problems are ubiquitous in artificial intelligence. Designing the underlying models, however, requires substantial expertise, which is a limiting factor in practice. The models typically consist of hard and soft constraints, or combine hard constraints with an objective function. We introduce a novel setting for learning combinatorial optimisation problems from contextual examples. These positive and negative examples show - in a particular context - whether the solutions are good enough or not. We develop our framework using the MAX-SAT formalism as it is simple yet powerful setting having these features. We study the learnability of MAX-SAT models. Our theoretical results show that high-quality MAX-SAT models can be learned from contextual examples in the realisable and agnostic settings, as long as the data satisfies an intuitive "representativeness" condition. We also contribute two implementations based on our theoretical results: one leverages ideas from syntax-guided synthesis while the other makes use of stochastic local search techniques. The two implementations are evaluated by recovering synthetic and benchmark models from contextual examples. The experimental results support our theoretical analysis, showing that MAX-SAT models can be learned from contextual examples. Among the two implementations, the stochastic local search learner scales much better than the syntax-guided implementation while providing comparable or better models.

cs.AI↗

arXiv2021

Mid-Infrared Photon-Pair Generation in AgGaS$_2$

We demonstrate non-degenerate photon-pair generation by spontaneous parametric down conversion in a silver gallium sulfide AgGaS$_2$ crystal. By tuning the pump wavelength, we achieve phase matching over a large spectral range. This allows to generate idler photons in the mid-infrared spectral range above 6 $μm$ wavelength with corresponding signal photons in the visible. Also, we show photon pair generation with broad spectral bandwidth. These results are a valuable step towards the development of quantum imaging and sensing techniques in the mid-infrared.

physics.optics↗

arXiv2021

Two Mechanisms of Remote Synchronization in a Chain of Stuart-Landau Oscillators

Remote synchronization implies that oscillators interacting not directly but via an additional unit (hub) adjust their frequencies and exhibit frequency locking while the hub remains asynchronous. In this paper, we analyze the mechanisms of remote synchrony in a small network of three coupled Stuart-Landau oscillators using recent results on high-order phase reduction. We analytically demonstrate the role of two factors promoting remote synchrony. These factors are the non-isochronicity of oscillators and the coupling terms appearing in the second-order phase approximation. We show a good correspondence between our theory and numerical results for small and moderate coupling strengths.

nlin.CD↗

arXiv2021

Few-shot calibration of low-cost air pollution (PM2.5) sensors using meta-learning

Low-cost particulate matter sensors are transforming air quality monitoring because they have lower costs and greater mobility as compared to reference monitors. Calibration of these low-cost sensors requires training data from co-deployed reference monitors. Machine Learning based calibration gives better performance than conventional techniques, but requires a large amount of training data from the sensor, to be calibrated, co-deployed with a reference monitor. In this work, we propose novel transfer learning methods for quick calibration of sensors with minimal co-deployment with reference monitors. Transfer learning utilizes a large amount of data from other sensors along with a limited amount of data from the target sensor. Our extensive experimentation finds the proposed Model-Agnostic- Meta-Learning (MAML) based transfer learning method to be the most effective over other competitive baselines.

cs.LG↗

arXiv2021

Learning Mixed-Integer Linear Programs from Contextual Examples

Mixed-integer linear programs (MILPs) are widely used in artificial intelligence and operations research to model complex decision problems like scheduling and routing. Designing such programs however requires both domain and modelling expertise. In this paper, we study the problem of acquiring MILPs from contextual examples, a novel and realistic setting in which examples capture solutions and non-solutions within a specific context. The resulting learning problem involves acquiring continuous parameters -- namely, a cost vector and a feasibility polytope -- but has a distinctly combinatorial flavor. To solve this complex problem, we also contribute MISSLE, an algorithm for learning MILPs from contextual examples. MISSLE uses a variant of stochastic local search that is guided by the gradient of a continuous surrogate loss function. Our empirical evaluation on synthetic data shows that MISSLE acquires better MILPs faster than alternatives based on stochastic local search and gradient descent.

cs.AI↗

arXiv2020

A Comprehensive Survey on Real-Time Voltage Stability Assessment for Power Systems

Accurate real-time assessment of power systems voltage stability has been an active area of research in the past few decades. In the past decade, after the development of phasor measurement units (PMU), a lot of discussions has been going on phasor measurement techniques for real-time voltage stability. The fundamental idea behind these methods is to find the Thevenin equivalents of the system, and then determine the voltage stability margin based on the equivalent circuits. Some approaches also include the use of Artificial Neural Networks (ANN), for online monitoring of voltage stability margins. These methods are really fast as compared to the other methods. It has been shown that if we can obtain the phase angles and voltage magnitude in real-time from the phasor measurement units (PMU), then the voltage stability margins can be obtained in real-time and we can initiate voltage stability control methods. We are going to discuss Thevenin's equivalent methods and Artificial Intelligence methods in detail in this paper. We will also introduce the traditional methods which were earlier used for power systems stability assessment such as Time Domain methods, Static Methods, and Sensitivity methods. We are going to finally compare these methods and try to give general guidance on choosing a power stability method.

eess.SY↗

arXiv2020

Machine Guides, Human Supervises: Interactive Learning with Global Explanations

We introduce explanatory guided learning (XGL), a novel interactive learning strategy in which a machine guides a human supervisor toward selecting informative examples for a classifier. The guidance is provided by means of global explanations, which summarize the classifier's behavior on different regions of the instance space and expose its flaws. Compared to other explanatory interactive learning strategies, which are machine-initiated and rely on local explanations, XGL is designed to be robust against cases in which the explanations supplied by the machine oversell the classifier's quality. Moreover, XGL leverages global explanations to open up the black-box of human-initiated interaction, enabling supervisors to select informative examples that challenge the learned model. By drawing a link to interactive machine teaching, we show theoretically that global explanations are a viable approach for guiding supervisors. Our simulations show that explanatory guided learning avoids overselling the model's quality and performs comparably or better than machine- and human-initiated interactive learning strategies in terms of model quality.

cs.LG↗

arXiv2020

Use of adaptive filtering techniques and deconvolution to obtain low range sidelobe samples

In this paper the use of adaptive filtering techniques to obtain better peak sidelobe suppression and integrated sidelobe energy will be discussed with regard to weather radars and obtaining better sensitivity with this technique. The performance of these new coefficient sets obtained with adaptive filter (using RLS optimization) will be discussed and presented. They will also be compared with the existing techniques and their peak sidelobe levels.

eess.SP↗

arXiv2020

Toward Machine-Guided, Human-Initiated Explanatory Interactive Learning

Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of the model being learned. The reason is that the machine illustrates its beliefs by predicting and explaining the labels of the query instances: if the machine is unaware of its own mistakes, it may end up choosing queries on which it performs artificially well. This biases the "narrative" presented by the machine to the user.We address this narrative bias by introducing explanatory guided learning, a novel interactive learning strategy in which: i) the supervisor is in charge of choosing the query instances, while ii) the machine uses global explanations to illustrate its overall behavior and to guide the supervisor toward choosing challenging, informative instances. This strategy retains the key advantages of explanatory interaction while avoiding narrative bias and compares favorably to active learning in terms of sample complexity. An initial empirical evaluation with a clustering-based prototype highlights the promise of our approach.

cs.AI↗

arXiv2020

Intermediate frequency Upgrade design features of NASA D3R Weather Radar System

The NASA dual-frequency, dual-polarization, Doppler radar (D3R) is an important ground validation tool for the global precipitation measurement (GPM) mission dual-frequency precipitation radar (DPR). The D3R has undergone extensive field trials starting in 2011 and continues to provide observations that enhance our scientific knowledge. To further enhance its capabilities, the Intermediate frequency (IF) electronics, digital receiver and waveform generation subsystems have been upgraded. Due to the new, more flexible architecture, this upgrade enables more research frontiers to be explored with better performance. One of the primary motivations for this upgrade is to enable enhanced radar sensitivity and increase range resolution to 30 meters. In this work, the D3R system upgrade will be discussed with a focus on the key upgrade design features to obtain better sensitivity and a flexible waveform capability.

eess.SP↗

arXiv2020

Inter Pulse Frequency Diversity System for Second Trip Suppression and Retrieval in a Weather Radar

This paper develops the use of Inter-pulse frequency diversity scheme for a weather radar system. It establishes the performance of frequency diversity technique comparing it with other inter-pulse schemes for weather radar systems. Inter-pulse coding is widely used for second trip suppression or cross-polarization isolation. Here, a new inter-pulse scheme is discussed taking advantage of frequency diverse waveforms. The simulations and tests of performance are evaluated keeping in mind NASA dual-frequency, dual-polarization, Doppler radar (D3R). A new method is described to recover velocity and spectral width due to incoherence in samples from change of frequency pulse to pulse. This technique can recover the weather radar moments over a much higher dynamic range of the other trip contamination as compared with the popular systematic phase code, for second trip suppression and retrieval.

eess.SP↗