arXiv subjects

Neeraj Kumar

Publications and source records attributed to Neeraj Kumar.

At least 55 records · Page 3Linked to original sources

arXiv2022

An Overview of Violence Detection Techniques: Current Challenges and Future Directions

The Big Video Data generated in today's smart cities has raised concerns from its purposeful usage perspective, where surveillance cameras, among many others are the most prominent resources to contribute to the huge volumes of data, making its automated analysis a difficult task in terms of computation and preciseness. Violence Detection (VD), broadly plunging under Action and Activity recognition domain, is used to analyze Big Video data for anomalous actions incurred due to humans. The VD literature is traditionally based on manually engineered features, though advancements to deep learning based standalone models are developed for real-time VD analysis. This paper focuses on overview of deep sequence learning approaches along with localization strategies of the detected violence. This overview also dives into the initial image processing and machine learning-based VD literature and their possible advantages such as efficiency against the current complex models. Furthermore,the datasets are discussed, to provide an analysis of the current models, explaining their pros and cons with future directions in VD domain derived from an in-depth analysis of the previous methods.

cs.CV↗

arXiv2022

Phase transition structure and breaking of universal nature of central charge criticality in a Born-Infeld $AdS$ black hole

In this paper we have considered the thermodynamics of a Born-Infeld $AdS$ black hole using inputs from the dual boundary field theory. Here, we have varied the cosmological constant $Λ$ and the Newton's gravitational constant $G$ along with the Born-Infeld parameter $b$ in the bulk. A novel universal critical behaviour of the central charge (occurring in the boundary conformal field theory) in extended black hole thermodynamics for charged black holes has been recently observed \cite{mann1}, and we have extended this study to Born-Infeld $AdS$ black holes. The Born-Infeld parameter has the dimension of inverse length, therefore, when considered in the first law of thermodynamics of the bulk in the mixed form which includes the central charge of the boundary conformal field theory, it modifies the thermodynamic volume and the chemical potential (which are conjugate to pressure and central charge respectively). We observe that due to this inclusion of the Born-Infeld non-linearity in this analysis, the universal nature of the critical value of the central charge observed in \cite{mann1} breaks down. We also observe an interesting behaviour of the free energy of the black hole with Hawking temperature due to the variations in both the central charge and the Born-Infeld parameter. It is also observed in our analysis that for a sufficiently small value of the Born-Infeld parameter (small value of this parameter has more prominent non-linear effects), there exists a critical value of the temperature below which no black hole can exist.

gr-qc↗

arXiv2022

De novo design of protein target specific scaffold-based Inhibitors via Reinforcement Learning

Efficient design and discovery of target-driven molecules is a critical step in facilitating lead optimization in drug discovery. Current approaches to develop molecules for a target protein are intuition-driven, hampered by slow iterative design-test cycles due to computational challenges in utilizing 3D structural data, and ultimately limited by the expertise of the chemist - leading to bottlenecks in molecular design. In this contribution, we propose a novel framework, called 3D-MolGNN$_{RL}$, coupling reinforcement learning (RL) to a deep generative model based on 3D-Scaffold to generate target candidates specific to a protein building up atom by atom from the starting core scaffold. 3D-MolGNN$_{RL}$ provides an efficient way to optimize key features by multi-objective reward function within a protein pocket using parallel graph neural network models. The agent learns to build molecules in 3D space while optimizing the activity, binding affinity, potency, and synthetic accessibility of the candidates generated for infectious disease protein targets. Our approach can serve as an interpretable artificial intelligence (AI) tool for lead optimization with optimized activity, potency, and biophysical properties.

cs.LG↗

arXiv2022

Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery

We developed Distilled Graph Attention Policy Network (DGAPN), a reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention (sGAT) mechanism that leverages self-attention over both node and edge attributes as well as encoding the spatial structure -- this capability is of considerable interest in synthetic biology and drug discovery. An attentional policy network is introduced to learn the decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with stability. Exploration is driven by the stochasticity of the action space design and the innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while reducing the complexity of paths to chemical synthesis.

cs.LG↗

arXiv2022

EEG based Emotion Recognition: A Tutorial and Review

Emotion recognition technology through analyzing the EEG signal is currently an essential concept in Artificial Intelligence and holds great potential in emotional health care, human-computer interaction, multimedia content recommendation, etc. Though there have been several works devoted to reviewing EEG-based emotion recognition, the content of these reviews needs to be updated. In addition, those works are either fragmented in content or only focus on specific techniques adopted in this area but neglect the holistic perspective of the entire technical routes. Hence, in this paper, we review from the perspective of researchers who try to take the first step on this topic. We review the recent representative works in the EEG-based emotion recognition research and provide a tutorial to guide the researchers to start from the beginning. The scientific basis of EEG-based emotion recognition in the psychological and physiological levels is introduced. Further, we categorize these reviewed works into different technical routes and illustrate the theoretical basis and the research motivation, which will help the readers better understand why those techniques are studied and employed. At last, existing challenges and future investigations are also discussed in this paper, which guides the researchers to decide potential future research directions.

eess.SP↗

arXiv2022

Point Separation and Obstacle Removal by Finding and Hitting Odd Cycles

Suppose we are given a pair of points $s, t$ and a set $S$ of $n$ geometric objects in the plane, called obstacles. We show that in polynomial time one can construct an auxiliary (multi-)graph $G$ with vertex set $S$ and every edge labeled from $\{0, 1\}$, such that a set $S_d \subseteq S$ of obstacles separates $s$ from $t$ if and only if $G[S_d]$ contains a cycle whose sum of labels is odd. Using this structural characterization of separating sets of obstacles we obtain the following algorithmic results. In the Obstacle-Removal problem the task is to find a curve in the plane connecting s to t intersecting at most q obstacles. We give a $2.3146^qn^{O(1)}$ algorithm for Obstacle-Removal, significantly improving upon the previously best known $q^{O(q^3)} n^{O(1)}$ algorithm of Eiben and Lokshtanov (SoCG'20). We also obtain an alternative proof of a constant factor approximation algorithm for Obstacle-Removal, substantially simplifying the arguments of Kumar et al. (SODA'21). In the Generalized Points-Separation problem, the input consists of the set S of obstacles, a point set A of k points and p pairs $(s_1, t_1),... (s_p, t_p)$ of points from A. The task is to find a minimum subset $S_r \subseteq S$ such that for every $i$, every curve from $s_i$ to $t_i$ intersects at least one obstacle in $S_r$. We obtain $2^{O(p)} n^{O(k)}$-time algorithm for Generalized Points-Separation problem. This resolves an open problem of Cabello and Giannopoulos (SoCG'13), who asked about the existence of such an algorithm for the special case where $(s_1, t_1), ... (s_p, t_p)$ contains all the pairs of points in A. Finally, we improve the running time of our algorithm to $f(p,k) n^{O(\sqrt{k})}$ when the obstacles are unit disks, where $f(p,k) = 2^O(p) k^{O(k)}$, and show that, assuming the Exponential Time Hypothesis (ETH), the running time dependence on $k$ of our algorithms is essentially optimal.

cs.CG↗

arXiv2022

Multiple mobile excitons manifested as sidebands in quasi-one-dimensional metallic TaSe3

Charge neutrality and their expected itinerant nature makes excitons potential transmitters of information. However, exciton mobility remains inaccessible to traditional optical experiments that only create and detect excitons with negligible momentum. Here, using angle-resolved photoemission spectroscopy, we detect dispersing excitons in the quasi-one-dimensional metallic trichalcogenide, TaSe3. The low density of conduction electrons and the low dimensionality in TaSe3 combined with a polaronic renormalization of the conduction band and the poorly screened interaction between these polarons and photo-induced valence holes leads to various excitonic bound states that we interpret as intrachain and interchain excitons, and possibly trions. The thresholds for the formation of a photo-hole together with an exciton appear as side valence bands with dispersions nearly parallel to the main valence band, but shifted to lower excitation energies. The energy separation between side and main valence bands can be controlled by surface doping, enabling the tuning of certain exciton properties.

cond-mat.str-el↗

arXiv2022

A Reliable Data-transmission Mechanism using Blockchain in Edge Computing Scenarios

With the advent of the Internet of things (IoT) era, more and more devices are connected to the IoT. Under the traditional cloud-thing centralized management mode, the transmission of massive data is facing many difficulties, and the reliability of data is difficult to be guaranteed. As emerging technologies, blockchain technology and edge computing (EC) technology have attracted the attention of academia in improving the reliability, privacy and invariability of IoT technology. In this paper, we combine the characteristics of the EC and blockchain to ensure the reliability of data transmission in the IoT. First of all, we propose a data transmission mechanism based on blockchain, which uses the distributed architecture of blockchain to ensure that the data is not tampered with; secondly, we introduce the three-tier structure in the architecture in turn; finally, we introduce the four working steps of the mechanism, which are similar to the working mechanism of blockchain. In the end, the simulation results show that the proposed scheme can ensure the reliability of data transmission in the Internet of things to a great extent.

cs.CR↗

arXiv2022

Resource Management and Security Scheme of ICPSs and IoT Based on VNE Algorithm

The development of Intelligent Cyber-Physical Systems (ICPSs) in virtual network environment is facing severe challenges. On the one hand, the Internet of things (IoT) based on ICPSs construction needs a large amount of reasonable network resources support. On the other hand, ICPSs are facing severe network security problems. The integration of ICPSs and network virtualization (NV) can provide more efficient network resource support and security guarantees for IoT users. Based on the above two problems faced by ICPSs, we propose a virtual network embedded (VNE) algorithm with computing, storage resources and security constraints to ensure the rationality and security of resource allocation in ICPSs. In particular, we use reinforcement learning (RL) method as a means to improve algorithm performance. We extract the important attribute characteristics of underlying network as the training environment of RL agent. Agent can derive the optimal node embedding strategy through training, so as to meet the requirements of ICPSs for resource management and security. The embedding of virtual links is based on the breadth first search (BFS) strategy. Therefore, this is a comprehensive two-stage RL-VNE algorithm considering the constraints of computing, storage and security three-dimensional resources. Finally, we design a large number of simulation experiments from the perspective of typical indicators of VNE algorithms. The experimental results effectively illustrate the effectiveness of the algorithm in the application of ICPSs.

cs.CR↗

arXiv2022

Dynamic Virtual Network Embedding Algorithm based on Graph Convolution Neural Network and Reinforcement Learning

Network virtualization (NV) is a technology with broad application prospects. Virtual network embedding (VNE) is the core orientation of VN, which aims to provide more flexible underlying physical resource allocation for user function requests. The classical VNE problem is usually solved by heuristic method, but this method often limits the flexibility of the algorithm and ignores the time limit. In addition, the partition autonomy of physical domain and the dynamic characteristics of virtual network request (VNR) also increase the difficulty of VNE. This paper proposed a new type of VNE algorithm, which applied reinforcement learning (RL) and graph neural network (GNN) theory to the algorithm, especially the combination of graph convolutional neural network (GCNN) and RL algorithm. Based on a self-defined fitness matrix and fitness value, we set up the objective function of the algorithm implementation, realized an efficient dynamic VNE algorithm, and effectively reduced the degree of resource fragmentation. Finally, we used comparison algorithms to evaluate the proposed method. Simulation experiments verified that the dynamic VNE algorithm based on RL and GCNN has good basic VNE characteristics. By changing the resource attributes of physical network and virtual network, it can be proved that the algorithm has good flexibility.

cs.NI↗

arXiv2022

Space-Air-Ground Integrated Multi-domain Network Resource Orchestration based on Virtual Network Architecture: a DRL Method

Traditional ground wireless communication networks cannot provide high-quality services for artificial intelligence (AI) applications such as intelligent transportation systems (ITS) due to deployment, coverage and capacity issues. The space-air-ground integrated network (SAGIN) has become a research focus in the industry. Compared with traditional wireless communication networks, SAGIN is more flexible and reliable, and it has wider coverage and higher quality of seamless connection. However, due to its inherent heterogeneity, time-varying and self-organizing characteristics, the deployment and use of SAGIN still faces huge challenges, among which the orchestration of heterogeneous resources is a key issue. Based on virtual network architecture and deep reinforcement learning (DRL), we model SAGIN's heterogeneous resource orchestration as a multi-domain virtual network embedding (VNE) problem, and propose a SAGIN cross-domain VNE algorithm. We model the different network segments of SAGIN, and set the network attributes according to the actual situation of SAGIN and user needs. In DRL, the agent is acted by a five-layer policy network. We build a feature matrix based on network attributes extracted from SAGIN and use it as the agent training environment. Through training, the probability of each underlying node being embedded can be derived. In test phase, we complete the embedding process of virtual nodes and links in turn based on this probability. Finally, we verify the effectiveness of the algorithm from both training and testing.

cs.NI↗

arXiv2022

IoV Scenario: Implementation of a Bandwidth Aware Algorithm in Wireless Network Communication Mode

The wireless network communication mode represented by the Internet of vehicles (IoV) has been widely used. However, due to the limitations of traditional network architecture, resource scheduling in wireless network environment is still facing great challenges. This paper focuses on the allocation of bandwidth resources in the virtual network environment. This paper proposes a bandwidth aware multi domain virtual network embedding algorithm (BA-VNE). The algorithm is mainly aimed at the problem that users need a lot of bandwidth in wireless communication mode, and solves the problem of bandwidth resource allocation from the perspective of virtual network embedding (VNE). In order to improve the performance of the algorithm, we introduce particle swarm optimization (PSO) algorithm to optimize the performance of the algorithm. In order to verify the effectiveness of the algorithm, we have carried out simulation experiments from link bandwidth, mapping cost and virtual network request (VNR) acceptance rate. The final results show that the proposed algorithm is better than other representative algorithms in the above indicators.

cs.NI↗

arXiv2021

Decoding the Protein-ligand Interactions Using Parallel Graph Neural Networks

Protein-ligand interactions (PLIs) are fundamental to biochemical research and their identification is crucial for estimating biophysical and biochemical properties for rational therapeutic design. Currently, experimental characterization of these properties is the most accurate method, however, this is very time-consuming and labor-intensive. A number of computational methods have been developed in this context but most of the existing PLI prediction heavily depends on 2D protein sequence data. Here, we present a novel parallel graph neural network (GNN) to integrate knowledge representation and reasoning for PLI prediction to perform deep learning guided by expert knowledge and informed by 3D structural data. We develop two distinct GNN architectures, GNNF is the base implementation that employs distinct featurization to enhance domain-awareness, while GNNP is a novel implementation that can predict with no prior knowledge of the intermolecular interactions. The comprehensive evaluation demonstrated that GNN can successfully capture the binary interactions between ligand and proteins 3D structure with 0.979 test accuracy for GNNF and 0.958 for GNNP for predicting activity of a protein-ligand complex. These models are further adapted for regression tasks to predict experimental binding affinities and pIC50 is crucial for drugs potency and efficacy. We achieve a Pearson correlation coefficient of 0.66 and 0.65 on experimental affinity and 0.50 and 0.51 on pIC50 with GNNF and GNNP, respectively, outperforming similar 2D sequence-based models. Our method can serve as an interpretable and explainable artificial intelligence (AI) tool for predicted activity, potency, and biophysical properties of lead candidates. To this end, we show the utility of GNNP on SARS-Cov-2 protein targets by screening a large compound library and comparing our prediction with the experimentally measured data.

stat.ML↗

arXiv2021

Learning from learning machines: a new generation of AI technology to meet the needs of science

We outline emerging opportunities and challenges to enhance the utility of AI for scientific discovery. The distinct goals of AI for industry versus the goals of AI for science create tension between identifying patterns in data versus discovering patterns in the world from data. If we address the fundamental challenges associated with "bridging the gap" between domain-driven scientific models and data-driven AI learning machines, then we expect that these AI models can transform hypothesis generation, scientific discovery, and the scientific process itself.

cs.LG↗

arXiv2021

Effects of Gauss-Bonnet gravity on thermodynamics of (3+1)$-D$ AdS black holes

We studied the thermodynamics of the black holes with Gauss-Bonnet correction term in $3+1-$ dimensional AdS spacetime. It is known that the term has no effect on the equation of motion, however, it modifies the entropy formula of Wald as it has an effect of the Gauss-Bonnet parameter term. We studied charged black holes, namely, Reissner-Nordström and Born-Infeld under this regime. We encountered divergences in heat capacity. After eliminating the possibility of first order phase transition, we applied two well trusted methods from standard thermodynamics, namely, Ehrenfest scheme and Ruppeiner's state space geometry analysis to ensure the second order nature of phase transition points. Effects of Gauss-Bonnet and Born-Infeld parameter are also discussed.

gr-qc↗

arXiv2021

Tuning the electronic band structure in a kagome ferromagnetic metal via magnetization

Materials with zero energy band gap display intriguing properties including high sensitivity of the electronic band structure to external stimulus such as pressure or magnetic field. An interesting candidate for zero energy band gap are Weyl nodes at the Fermi level EF. A prerequisite for the existence of Weyl nodes is to either have inversion or time reversal symmetry broken. Weyl nodes in systems with broken time reversal symmetry are ideal to realize the tunability of the electronic band structure by magnetic field. Theoretically, it has been shown that in ferromagnetic Weyl materials, the band structure is dependent upon the magnetization direction and thus the electronic bands can be tuned by controlling the magnetization direction. Here, we demonstrate tuning of the band structure in a kagome Weyl ferromagnetic metal Fe3Sn2 with magnetization and magnetic field. Owing to spin-orbit coupling, we observe changes in the band structure depending on the magnetization direction that amount to a decrease in the carrier density by a factor of four when the magnetization lies in the kagome plane as compared to when the magnetization is along the c axis. Our discovery opens a way for tuning the carrier density in ferromagnetic materials.

cond-mat.str-el↗

arXiv2021

Blockchain based Attack Detection on Machine Learning Algorithms for IoT based E-Health Applications

The application of machine learning (ML) algorithms are massively scaling-up due to rapid digitization and emergence of new tecnologies like Internet of Things (IoT). In today's digital era, we can find ML algorithms being applied in the areas of healthcare, IoT, engineering, finance and so on. However, all these algorithms need to be trained in order to predict/solve a particular problem. There is high possibility of tampering the training datasets and produce biased results. Hence, in this article, we have proposed blockchain based solution to secure the datasets generated from IoT devices for E-Health applications. The proposed blockchain based solution uses using private cloud to tackle the aforementioned issue. For evaluation, we have developed a system that can be used by dataset owners to secure their data.

cs.CR↗

arXiv2021

Few Shot Activity Recognition Using Variational Inference

There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of recognising novel action categories which are represented by few instances in the training data. We propose a novel variational inference based architectural framework (HF-AR) for few shot activity recognition. Our framework leverages volume-preserving Householder Flow to learn a flexible posterior distribution of the novel classes. This results in better performance as compared to state-of-the-art few shot approaches for human activity recognition. approach consists of base model and an adapter model. Our architecture consists of a base model and an adapter model. The base model is trained on seen classes and it computes an embedding that represent the spatial and temporal insights extracted from the input video, e.g. combination of Resnet-152 and LSTM based encoder-decoder model. The adapter model applies a series of Householder transformations to compute a flexible posterior distribution that lends higher accuracy in the few shot approach. Extensive experiments on three well-known datasets: UCF101, HMDB51 and Something-Something-V2, demonstrate similar or better performance on 1-shot and 5-shot classification as compared to state-of-the-art few shot approaches that use only RGB frame sequence as input. To the best of our knowledge, we are the first to explore variational inference along with householder transformations to capture the full rank covariance matrix of posterior distribution, for few shot learning in activity recognition.

cs.CV↗