arXiv subjects

Sandeep Yadav

Publications and source records attributed to Sandeep Yadav.

6 recordsLinked to original sources

arXiv2026

Scene Representation using 360{\deg} Saliency Graph and its Application in Vision-based Indoor Navigation

A Scene, represented visually using different formats such as RGB-D, LiDAR scan, keypoints, rectangular, spherical, multi-views, etc., contains information implicitly embedded relevant to applications such as scene indexing, vision-based navigation. Thus, these representations may not be efficient for such applications. This paper proposes a novel 360{\deg} saliency graph representation of the scenes. This rich representation explicitly encodes the relevant visual, contextual, semantic, and geometric information of the scene as nodes, edges, edge weights, and angular position in the 360{\deg} graph. Also, this representation is robust against scene view change and addresses challenges of indoor environments such as varied illumination, occlusions, and shadows as in the case of existing traditional methods. We have utilized this rich and efficient representation for vision-based navigation and compared it with existing navigation methods using 360{\deg} scenes. However, these existing methods suffer from limitations of poor scene representation, lacking scene-specific information. This work utilizes the proposed representation first to localize the query scene in the given topological map, and then facilitate 2D navigation by estimating the next required movement directions towards the target destination in the topological map by using the embedded geometric information in the 360{\deg} saliency graph. Experimental results demonstrate the efficacy of the proposed 360{\deg} saliency graph representation in enhancing both scene localization and vision-based indoor navigation.

cs.CV↗

arXiv2025

PNN: A Novel Progressive Neural Network for Fault Classification in Rotating Machinery under Small Dataset Constraint

Fault detection in rotating machinery is a complex task, particularly in small and heterogeneous dataset scenarios. Variability in sensor placement, machinery configurations, and structural differences further increase the complexity of the problem. Conventional deep learning approaches often demand large, homogeneous datasets, limiting their applicability in data-scarce industrial environments. While transfer learning and few-shot learning have shown potential, however, they are often constrained by the need for extensive fault datasets. This research introduces a unified framework leveraging a novel progressive neural network (PNN) architecture designed to address these challenges. The PNN sequentially estimates the fixed-size refined features of the higher order with the help of all previously estimated features and appends them to the feature set. This fixed-size feature output at each layer controls the complexity of the PNN and makes it suitable for effective learning from small datasets. The framework's effectiveness is validated on eight datasets, including six open-source datasets, one in-house fault simulator, and one real-world industrial dataset. The PNN achieves state-of-the-art performance in fault detection across varying dataset sizes and machinery types, highlighting superior generalization and classification capabilities.

cs.LG↗

arXiv2024

A Volumetric Saliency Guided Image Summarization for RGB-D Indoor Scene Classification

Image summary, an abridged version of the original visual content, can be used to represent the scene. Thus, tasks such as scene classification, identification, indexing, etc., can be performed efficiently using the unique summary. Saliency is the most commonly used technique for generating the relevant image summary. However, the definition of saliency is subjective in nature and depends upon the application. Existing saliency detection methods using RGB-D data mainly focus on color, texture, and depth features. Consequently, the generated summary contains either foreground objects or non-stationary objects. However, applications such as scene identification require stationary characteristics of the scene, unlike state-of-the-art methods. This paper proposes a novel volumetric saliency-guided framework for indoor scene classification. The results highlight the efficacy of the proposed method.

cs.CV↗

arXiv2019

Analysis and Comparison of Different Fuzzy Inference Systems used in Decision Making for Secondary Users in Cognitive Radio Network

Spectrum scarcity is one of the major challenges that the modern communication engineers are going through because of inefficient utilization of allocated frequency spectrum. The spectrum scarcity is a problem because there is not enough wavelengths/frequency to match the number of channels which are required to broadcast in a given bandwidth. Therefore, the utilization of available allocated spectrum when licensed users are not in use offers an opportunity as well as challenge, also, to increase the efficiency of spectrum utilization. Cognitive Radio offers a promising solution by reutilisation of unused allocated frequency spectrum. It helps to fulfil the demand of frequency requirement for modern communication system to accommodate more data transmission. In this optimum utilization of reuse of frequency spectrum required optimising algorithms in all parts of Cognitive Cycle. This paper focuses on designing a system based on fuzzy logic with a set of input and output parameters to obtain an optimised solution. A comparative analysis is also carried out among various types of membership functions of input and output on Mamdani Fuzzy Inference System and Sugeno Fuzzy Inference System. The proposed approach is applicable to design a better system model for a given set of rules.

eess.SP↗

arXiv2017

High yield synthesis and liquid exfoliation of two-dimensional belt like hafnium disulphide

Producing monolayers and few-layers in high yield with environment-stability is still a challenge in hafnium disulphide (HfS2), which is a layered two-dimensional material of group-IV transition metal dichalcogenides, to reveal its unlocked electronic and optoelectronic applications. For the first time, to the best of our knowledge, we demonstrate a simple and cost-effective method to grow layered belt-like nano-crystals of HfS2 with surprisingly large interlayer spacing followed by its chemical exfoliation. Various microscopic and spectroscopic techniques reveal these as-grown crystals exfoliate into single or few layers in some minutes using solvent assisted ultrasonification method in N-Cyclohexyl-2-pyrrolidone. The exfoliated nanosheets of HfS2 exhibit an indirect bandgap of 1.3 eV with high stability against ambient degradation. Further, we demonstrate that these nanosheets holds potential for electronic applications by fabricating field-effect transistors based on few layered HfS2 exhibiting field-effect mobility of 0.95 cm2/V-s with a high current modulation ratio (Ion/Ioff) of 10^4 in ambient. The method is scalable and has potential significance for both academy and industry.

cond-mat.mtrl-sci↗

arXiv2016

Large Area Fabrication of Semiconducting Phosphorene by Langmuir Blodgett Assembly

Although a considerable number of solvent based methodologies have been developed for exfoliating black phosphorus, so far there are no reports on controlled organization of these exfoliated nanosheets on substrates. Here, for the first time to the best of our knowledge, a mixture of N-Methyl-2-pyrrolidone (NMP) and deoxygenated water is employed as a subphase in Langmuir Blodgett (LB) trough for assembling the nanosheets followed by their deposition on substrates and studied its field effect transistor (FET) characteristics. Electron microscopy reveals the presence of densely aligned, crystalline, ultra-thin sheets of pristine phosphorene having lateral dimensions larger than hundred of microns. Furthermore, these assembled nanosheets retain their electronic properties and show a high current modulation of 10^4 at room temperature in FET devices. The proposed technique provides semiconducting phosphorene thin films that are amenable for large area applications.

cond-mat.mtrl-sci↗