arXiv subjects

Ashish Kumar

Publications and source records attributed to Ashish Kumar.

At least 55 records · Page 3Linked to original sources

arXiv2021

Generative Adversarial Network (GAN) and Enhanced Root Mean Square Error (ERMSE): Deep Learning for Stock Price Movement Prediction

The prediction of stock price movement direction is significant in financial circles and academic. Stock price contains complex, incomplete, and fuzzy information which makes it an extremely difficult task to predict its development trend. Predicting and analysing financial data is a nonlinear, time-dependent problem. With rapid development in machine learning and deep learning, this task can be performed more effectively by a purposely designed network. This paper aims to improve prediction accuracy and minimizing forecasting error loss through deep learning architecture by using Generative Adversarial Networks. It was proposed a generic model consisting of Phase-space Reconstruction (PSR) method for reconstructing price series and Generative Adversarial Network (GAN) which is a combination of two neural networks which are Long Short-Term Memory (LSTM) as Generative model and Convolutional Neural Network (CNN) as Discriminative model for adversarial training to forecast the stock market. LSTM will generate new instances based on historical basic indicators information and then CNN will estimate whether the data is predicted by LSTM or is real. It was found that the Generative Adversarial Network (GAN) has performed well on the enhanced root mean square error to LSTM, as it was 4.35% more accurate in predicting the direction and reduced processing time and RMSE by 78 secs and 0.029, respectively. This study provides a better result in the accuracy of the stock index. It seems that the proposed system concentrates on minimizing the root mean square error and processing time and improving the direction prediction accuracy, and provides a better result in the accuracy of the stock index.

q-fin.ST↗

arXiv2021

Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robots

Legged locomotion is commonly studied and expressed as a discrete set of gait patterns, like walk, trot, gallop, which are usually treated as given and pre-programmed in legged robots for efficient locomotion at different speeds. However, fixing a set of pre-programmed gaits limits the generality of locomotion. Recent animal motor studies show that these conventional gaits are only prevalent in ideal flat terrain conditions while real-world locomotion is unstructured and more like bouts of intermittent steps. What principles could lead to both structured and unstructured patterns across mammals and how to synthesize them in robots? In this work, we take an analysis-by-synthesis approach and learn to move by minimizing mechanical energy. We demonstrate that learning to minimize energy consumption plays a key role in the emergence of natural locomotion gaits at different speeds in real quadruped robots. The emergent gaits are structured in ideal terrains and look similar to that of horses and sheep. The same approach leads to unstructured gaits in rough terrains which is consistent with the findings in animal motor control. We validate our hypothesis in both simulation and real hardware across natural terrains. Videos at https://energy-locomotion.github.io

cs.RO↗

arXiv2021

A Derivative-based Parser Generator for Visibly Pushdown Grammars

In this paper, we present a derivative-based, functional recognizer and parser generator for visibly pushdown grammars. The generated parser accepts ambiguous grammars and produces a parse forest containing all valid parse trees for an input string in linear time. Each parse tree in the forest can then be extracted also in linear time. Besides the parser generator, to allow more flexible forms of the visibly pushdown grammars, we also present a translator that converts a tagged CFG to a visibly pushdown grammar in a sound way, and the parse trees of the tagged CFG are further produced by running the semantic actions embedded in the parse trees of the translated visibly pushdown grammar. The performance of the parser is compared with a popular parsing tool ANTLR and other popular hand-crafted parsers. The correctness of the core parsing algorithm is formally verified in the proof assistant Coq.

cs.PL↗

arXiv2021

End-To-End Real-Time Visual Perception Framework for Construction Automation

In this work, we present a robotic solution to automate the task of wall construction. To that end, we present an end-to-end visual perception framework that can quickly detect and localize bricks in a clutter. Further, we present a light computational method of brick pose estimation that incorporates the above information. The proposed detection network predicts a rotated box compared to YOLO and SSD, thereby maximizing the object's region in the predicted box regions. In addition, precision P, recall R, and mean-average-precision (mAP) scores are reported to evaluate the proposed framework. We observed that for our task, the proposed scheme outperforms the upright bounding box detectors. Further, we deploy the proposed visual perception framework on a robotic system endowed with a UR5 robot manipulator and demonstrate that the system can successfully replicate a simplified version of the wall-building task in an autonomous mode.

cs.RO↗

arXiv2021

Arbitrage-free pricing of CVA for cross-currency swap with wrong-way risk under stochastic correlation modeling framework

A positive correlation between exposure and counterparty credit risk gives rise to the so-called Wrong-Way Risk (WWR). Even after a decade of the financial crisis, addressing WWR in both sound and tractable ways remains challenging. Academicians have proposed arbitrage-free set-ups through copula methods but those are computationally expensive and hard to use in practice. Resampling methods are proposed by the industry but they lack mathematical foundations. The purpose of this article is to bridge this gap between the approaches used by academicians and industry. To this end, we propose a stochastic correlation approach to asses WWR. The methods based on constant correlation to model the dependency between exposure and counterparty credit risk assume a linear dependency, thus fail to capture the tail dependence. Using a stochastic correlation we move further away from the Gaussian copula and can capture the tail risk. This effect is reflected in the results where the impact of stochastic correlation on calculated CVA is substantial when compared to the case when a high constant correlation is assumed between exposure and credit. Given the uncertainty inherent to CVA, the proposed method is believed to provide a promising way to model WWR.

q-fin.RM↗

arXiv2021

RMA: Rapid Motor Adaptation for Legged Robots

Successful real-world deployment of legged robots would require them to adapt in real-time to unseen scenarios like changing terrains, changing payloads, wear and tear. This paper presents Rapid Motor Adaptation (RMA) algorithm to solve this problem of real-time online adaptation in quadruped robots. RMA consists of two components: a base policy and an adaptation module. The combination of these components enables the robot to adapt to novel situations in fractions of a second. RMA is trained completely in simulation without using any domain knowledge like reference trajectories or predefined foot trajectory generators and is deployed on the A1 robot without any fine-tuning. We train RMA on a varied terrain generator using bioenergetics-inspired rewards and deploy it on a variety of difficult terrains including rocky, slippery, deformable surfaces in environments with grass, long vegetation, concrete, pebbles, stairs, sand, etc. RMA shows state-of-the-art performance across diverse real-world as well as simulation experiments. Video results at https://ashish-kmr.github.io/rma-legged-robots/

cs.LG↗

arXiv2021

Deep Learning Body Region Classification of MRI and CT examinations

Standardized body region labelling of individual images provides data that can improve human and computer use of medical images. A CNN-based classifier was developed to identify body regions in CT and MRI. 17 CT (18 MRI) body regions covering the entire human body were defined for the classification task. Three retrospective databases were built for the AI model training, validation, and testing, with a balanced distribution of studies per body region. The test databases originated from a different healthcare network. Accuracy, recall and precision of the classifier was evaluated for patient age, patient gender, institution, scanner manufacturer, contrast, slice thickness, MRI sequence, and CT kernel. The data included a retrospective cohort of 2,934 anonymized CT cases (training: 1,804 studies, validation: 602 studies, test: 528 studies) and 3,185 anonymized MRI cases (training: 1,911 studies, validation: 636 studies, test: 638 studies). 27 institutions from primary care hospitals, community hospitals and imaging centers contributed to the test datasets. The data included cases of all genders in equal proportions and subjects aged from a few months old to +90 years old. An image-level prediction accuracy of 91.9% (90.2 - 92.1) for CT, and 94.2% (92.0 - 95.6) for MRI was achieved. The classification results were robust across all body regions and confounding factors. Due to limited data, performance results for subjects under 10 years-old could not be reliably evaluated. We show that deep learning models can classify CT and MRI images by body region including lower and upper extremities with high accuracy.

eess.IV↗

arXiv2021

Real Time Incremental Foveal Texture Mapping for Autonomous Vehicles

We propose an end-to-end real time framework to generate high resolution graphics grade textured 3D map of urban environment. The generated detailed map finds its application in the precise localization and navigation of autonomous vehicles. It can also serve as a virtual test bed for various vision and planning algorithms as well as a background map in the computer games. In this paper, we focus on two important issues: (i) incrementally generating a map with coherent 3D surface, in real time and (ii) preserving the quality of color texture. To handle the above issues, firstly, we perform a pose-refinement procedure which leverages camera image information, Delaunay triangulation and existing scan matching techniques to produce high resolution 3D map from the sparse input LIDAR scan. This 3D map is then texturized and accumulated by using a novel technique of ray-filtering which handles occlusion and inconsistencies in pose-refinement. Further, inspired by human fovea, we introduce foveal-processing which significantly reduces the computation time and also assists ray-filtering to maintain consistency in color texture and coherency in 3D surface of the output map. Moreover, we also introduce texture error (TE) and mean texture mapping error (MTME), which provides quantitative measure of texturing and overall quality of the textured maps.

cs.CV↗

arXiv2021

Semi Supervised Deep Quick Instance Detection and Segmentation

In this paper, we present a semi supervised deep quick learning framework for instance detection and pixel-wise semantic segmentation of images in a dense clutter of items. The framework can quickly and incrementally learn novel items in an online manner by real-time data acquisition and generating corresponding ground truths on its own. To learn various combinations of items, it can synthesize cluttered scenes, in real time. The overall approach is based on the tutor-child analogy in which a deep network (tutor) is pretrained for class-agnostic object detection which generates labeled data for another deep network (child). The child utilizes a customized convolutional neural network head for the purpose of quick learning. There are broadly four key components of the proposed framework semi supervised labeling, occlusion aware clutter synthesis, a customized convolutional neural network head, and instance detection. The initial version of this framework was implemented during our participation in Amazon Robotics Challenge (ARC), 2017. Our system was ranked 3rd, 4th and 5th worldwide in pick, stow-pick and stow task respectively. The proposed framework is an improved version over ARC17 where novel features such as instance detection and online learning has been added.

cs.CV↗

arXiv2021

Shape Back-Projection In 3D Scenes

In this work, we propose a novel framework shape back-projection for computationally efficient point cloud processing in a probabilistic manner. The primary component of the technique is shape histogram and a back-projection procedure. The technique measures similarity between 3D surfaces, by analyzing their geometrical properties. It is analogous to color back-projection which measures similarity between images, simply by looking at their color distributions. In the overall process, first, shape histogram of a sample surface (e.g. planar) is computed, which captures the profile of surface normals around a point in form of a probability distribution. Later, the histogram is back-projected onto a test surface and a likelihood score is obtained. The score depicts that how likely a point in the test surface behaves similar to the sample surface, geometrically. Shape back-projection finds its application in binary surface classification, high curvature edge detection in unorganized point cloud, automated point cloud labeling for 3D-CNNs (convolutional neural network) etc. The algorithm can also be used for real-time robotic operations such as autonomous object picking in warehouse automation, ground plane extraction for autonomous vehicles and can be deployed easily on computationally limited platforms (UAVs).

cs.CV↗

arXiv2021

Towards Deep Learning Assisted Autonomous UAVs for Manipulation Tasks in GPS-Denied Environments

In this work, we present a pragmatic approach to enable unmanned aerial vehicle (UAVs) to autonomously perform highly complicated tasks of object pick and place. This paper is largely inspired by challenge-2 of MBZIRC 2020 and is primarily focused on the task of assembling large 3D structures in outdoors and GPS-denied environments. Primary contributions of this system are: (i) a novel computationally efficient deep learning based unified multi-task visual perception system for target localization, part segmentation, and tracking, (ii) a novel deep learning based grasp state estimation, (iii) a retracting electromagnetic gripper design, (iv) a remote computing approach which exploits state-of-the-art MIMO based high speed (5000Mb/s) wireless links to allow the UAVs to execute compute intensive tasks on remote high end compute servers, and (v) system integration in which several system components are weaved together in order to develop an optimized software stack. We use DJI Matrice-600 Pro, a hex-rotor UAV and interface it with the custom designed gripper. Our framework is deployed on the specified UAV in order to report the performance analysis of the individual modules. Apart from the manipulation system, we also highlight several hidden challenges associated with the UAVs in this context.

cs.RO↗

arXiv2020

OffWorld Gym: open-access physical robotics environment for real-world reinforcement learning benchmark and research

Success stories of applied machine learning can be traced back to the datasets and environments that were put forward as challenges for the community. The challenge that the community sets as a benchmark is usually the challenge that the community eventually solves. The ultimate challenge of reinforcement learning research is to train real agents to operate in the real environment, but until now there has not been a common real-world RL benchmark. In this work, we present a prototype real-world environment from OffWorld Gym -- a collection of real-world environments for reinforcement learning in robotics with free public remote access. Close integration into existing ecosystem allows the community to start using OffWorld Gym without any prior experience in robotics and takes away the burden of managing a physical robotics system, abstracting it under a familiar API. We introduce a navigation task, where a robot has to reach a visual beacon on an uneven terrain using only the camera input and provide baseline results in both the real environment and the simulated replica. To start training, visit https://gym.offworld.ai

cs.LG↗

arXiv2020

MACE: Model Agnostic Concept Extractor for Explaining Image Classification Networks

Deep convolutional networks have been quite successful at various image classification tasks. The current methods to explain the predictions of a pre-trained model rely on gradient information, often resulting in saliency maps that focus on the foreground object as a whole. However, humans typically reason by dissecting an image and pointing out the presence of smaller concepts. The final output is often an aggregation of the presence or absence of these smaller concepts. In this work, we propose MACE: a Model Agnostic Concept Extractor, which can explain the working of a convolutional network through smaller concepts. The MACE framework dissects the feature maps generated by a convolution network for an image to extract concept based prototypical explanations. Further, it estimates the relevance of the extracted concepts to the pre-trained model's predictions, a critical aspect required for explaining the individual class predictions, missing in existing approaches. We validate our framework using VGG16 and ResNet50 CNN architectures, and on datasets like Animals With Attributes 2 (AWA2) and Places365. Our experiments demonstrate that the concepts extracted by the MACE framework increase the human interpretability of the explanations, and are faithful to the underlying pre-trained black-box model.

cs.LG↗

arXiv2020

A novel group based cryptosystem based on electromagnetic rotor machine

In this paper, an algorithm is aimed to make a cryptosystem for gray level images based on voice features, secret sharing scheme and electromagnetic rotor machine. Here, Shamir secret sharing (k n) threshold scheme is used to secure a key along with voice features of (n k) users. Keystream is molded by coefficients of a voice sample, using this key stream, rotor machines rotating cylinders positions are initialized and internal wiring is decided by pseudo random number of Henon chaotic map, where initial seed for chaotic system is chosen from keystream. And furthermore, shares of key stream are distributed among users. Speech processing is fused with electromagnetic machine to provide authentication as well as group based encryption. Perceptual linear predication (PLP) coefficients are utilized for formation of secret key. Simulation experiments and statistical analysis demonstrate that the proposed algorithm is sensitive to initial secret keystream, entropy, mean value analysis and histogram of the encrypted image is admirable. Hence, the proposed scheme is resistible to any vulnerable situation.

cs.CR↗

arXiv2020

Thermoelectric Properties of GaN with Carrier Concentration Modulation: An Experimental and Theoretical Investigation

The present work investigates the less explored thermoelectric properties of n-type GaN semiconductors by combined both the experimental and computational tools. Seebeck coefficients of epitaxial thin films of GaN were experimentally measured in the wide temperature range from 77 K to 650 K in steps of ~10 K covering both low and high-temperature regimes as a function of carrier concentration 2 x1016, 2 x 1017, 4 x 1017 and 8 x 1017 cm-3. The measured Seebeck coefficient at room temperature was found to be highest, -374 microV/K, at the lowest concentration of 4 x 1016 cm-3 and decreases in magnitude monotonically (-327.6 microV/K, -295 microV/K, -246 microV/K for 2 x 1017, 4 x 1017, 8 x 1017 cm-3, respectively) as the carrier concentration of samples increases. Seebeck coefficient remains negative in the entire temperature range under study indicate that electrons are dominant carriers. To understand the temperature-dependent behavior, we have also carried out the electronic structure, and transport coefficients calculations by using Tran-Blaha modified Becke-Johnson (TB-mBJ) potential, and semiclassical Boltzmann transport theory implemented in WIEN2k and BoltzTraP code, respectively. The experimentally observed carrier concentrations were used in the calculations. The estimated results obtained under constant relaxation time approximations provide a very good agreement between theoretical and experimental data of Seebeck coefficients in the temperature range of 260 to 625 K.

cond-mat.mtrl-sci↗

arXiv2020

Wide range temperature-dependent (80-630 K) study of Hall effect and the Seebeck coefficient of \b{eta}-Ga2O3 single crystals

Investigation of Seebeck coefficient in ultra-wide bandgap materials presents a challenge in measurement, nevertheless, it is essential for understanding fundamental transport mechanisms involved in electrical and thermal conduction. \b{eta}-Ga2O3 is a strategic material for high power optoelectronic applications. Present work reports Seebeck coefficient measurement for single crystal Sn doped \b{eta}-Ga2O3 in a wide temperature range (80-630 K). The non-monotonic trend with large magnitude and negative sign in the entire temperature range shows electrons are dominant carriers. The structural and Raman characterization confirms the single-phase and presence of low, mid, and high-frequency phonon modes, respectively. Temperature dependent (90-350 K) Hall effect measurement was carried out as supplementary study. Hall mobility showed T1.12 for T less than 135 K and T-0.70 for T more than 220 K. Activation energies from Seebeck coefficient and conductivity analysis revealed presence of inter band conduction due to impurity defects. The room temperature Seebeck coefficient, power factor and thermal conductivity were found as 68.57 microV/K, 0.15 microW/K2cm and 14.2 W/mK, respectively. The value of the figure-of-merit for \b{eta}-Ga2O3 was found to be aprox. 0.01 (300 K).

cond-mat.mtrl-sci↗

arXiv2020

Using random numbers to obtain Kohn-Sham potential for a given density

Most of the density-to-potential inversion methods developed over the years follow a general algorithm $ v_{xc}^{i+1}(\textbf{r}) = v_{xc}^{i}(\textbf{r}) + Δv_{xc}(\textbf{r})$, where $Δv_{xc}(\textbf{r}) = \frac{δS[ρ]}{δρ(\textbf{r})} \Big |_{ ρ_i(\textbf{r})} - \frac{δS[ρ]}{δρ(\textbf{r})}\Big|_{ ρ_0(\textbf{r})}$ and $S[ρ]$ is an appropriately chosen density functional. In this work we show that this algorithm can be used with random numbers to obtain the exchange-correlation potential for a given density. This obviates the need to evaluate the functional $S[ρ]$ in each iterative step. The method is demonstrated by calculating exchange-correlation potential of atoms, clusters and the Hookium.

physics.atom-ph↗

arXiv2020

A general penalty method for density-to-potential inversion

A general penalty method is presented for the construction of of Kohn-Sham system for given density through Levy's constrained-search. The method uses a functional $S[ρ]$ of one's choice. Different forms of $S[ρ]$ are employed to calculate the kinetic energy and exchange-correlation potential of atoms, jellium spheres, and Hookium and consistency among results obtained from them is shown.

physics.atom-ph↗