Searcharxiv⌕ Search

arXiv subjects

Subhankar Mishra

Publications and source records attributed to Subhankar Mishra.

At least 37 records · Page 2Linked to original sources
arXiv2025

DiffCrysGen: A Score-Based Diffusion Model for Design of Diverse Inorganic Crystalline Materials

Crystal structure generation is a foundational challenge in materials discovery, particularly in designing functional inorganic crystalline materials with desired properties. Most existing diffusion-based generative models for crystals rely on complex, hand-crafted priors and modular architectures to separately model atom types, atomic positions, and lattice parameters. These methods often require customized diffusion processes and conditional denoising, which can introduce additional model complexities and inconsistencies. Here we introduce DiffCrysGen, a fully data-driven, score-based diffusion model that jointly learns the distribution of all structural components in crystalline materials. With crystal structure representation as unified 2D matrices, DiffCrysGen bypasses the need for task-specific priors or decoupled modules, enabling end-to-end generation of atom types, fractional coordinates, and lattice parameters within a single framework. Our model learns crystallographic symmetry and chemical validity directly from large-scale datasets, allowing it to scale to complex materials discovery tasks. As a demonstration, we applied DiffCrysGen to the design of rare-earth-free magnetic materials with high saturation magnetization, showing its effectiveness in generating stable, diverse, and property-aligned candidates for sustainable magnet applications.

cond-mat.mtrl-sci↗
arXiv2025

Retinal Fundus Multi-Disease Image Classification using Hybrid CNN-Transformer-Ensemble Architectures

Our research is motivated by the urgent global issue of a large population affected by retinal diseases, which are evenly distributed but underserved by specialized medical expertise, particularly in non-urban areas. Our primary objective is to bridge this healthcare gap by developing a comprehensive diagnostic system capable of accurately predicting retinal diseases solely from fundus images. However, we faced significant challenges due to limited, diverse datasets and imbalanced class distributions. To overcome these issues, we have devised innovative strategies. Our research introduces novel approaches, utilizing hybrid models combining deeper Convolutional Neural Networks (CNNs), Transformer encoders, and ensemble architectures sequentially and in parallel to classify retinal fundus images into 20 disease labels. Our overarching goal is to assess these advanced models' potential in practical applications, with a strong focus on enhancing retinal disease diagnosis accuracy across a broader spectrum of conditions. Importantly, our efforts have surpassed baseline model results, with the C-Tran ensemble model emerging as the leader, achieving a remarkable model score of 0.9166, surpassing the baseline score of 0.9. Additionally, experiments with the IEViT model showcased equally promising outcomes with improved computational efficiency. We've also demonstrated the effectiveness of dynamic patch extraction and the integration of domain knowledge in computer vision tasks. In summary, our research strives to contribute significantly to retinal disease diagnosis, addressing the critical need for accessible healthcare solutions in underserved regions while aiming for comprehensive and accurate disease prediction.

cs.CV↗
arXiv2025

Graph Neural Networks at a Fraction

Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations of graph-structured data. In addition to real-valued GNNs, quaternion GNNs also perform well on tasks on graph-structured data. With the aim of reducing the energy footprint, we reduce the model size while maintaining accuracy comparable to that of the original-sized GNNs. This paper introduces Quaternion Message Passing Neural Networks (QMPNNs), a framework that leverages quaternion space to compute node representations. Our approach offers a generalizable method for incorporating quaternion representations into GNN architectures at one-fourth of the original parameter count. Furthermore, we present a novel perspective on Graph Lottery Tickets, redefining their applicability within the context of GNNs and QMPNNs. We specifically aim to find the initialization lottery from the subnetwork of the GNNs that can achieve comparable performance to the original GNN upon training. Thereby reducing the trainable model parameters even further. To validate the effectiveness of our proposed QMPNN framework and LTH for both GNNs and QMPNNs, we evaluate their performance on real-world datasets across three fundamental graph-based tasks: node classification, link prediction, and graph classification.

cs.LG↗
arXiv2024

MIMA 2.0 -- Compact and Portable Multifunctional IoT integrated Menstrual Aid

The shredding intrauterine lining or the endometrium is known as Menstruation. It occurs every month and causes several issues like Menstrual Cramps and aches in the abdominal region, stains, menstrual malodor, rashes in intimate areas, and many more. In our research, almost all of the products available in the market do not cater to these problems single-handedly. There are few remedies available to cater to the cramps, among which heat therapy is the most commonly used. Our methodology, involved surveys regarding problems and the solutions to these problems that are deemed optimal. This inclusive approach helped us infer about the gaps in available menstrual aids which has become our guide towards developing MIMA (Multifunctional IoT Integrated Menstrual Aid). In this paper, we have featured an IOT incorporated multifunctional smart intimate wear that aims to provide for the multiple necessities of women during menstruation like leakproof, antibacterial, anti-odor, rash-free experience along with an integrated Bluetooth-controlled intimate heat-pad for relieving abdominal cramps. The entire process of product development has been done in phases according to feedback from target users in each stage. This paper is an extension to our paper [1] which serves as the proof of concept for our approach. The development has led us towards MIMA 2.0 featuring a completely concealed and integrated design that includes a safe Bluetooth-controlled heating system for the intimate area. The product has received incredibly positive feedback from survey participants.

cs.HC↗
arXiv2024

A Survey on Robotic Prosthetics: Neuroprosthetics, Soft Actuators, and Control Strategies

The field of robotics is a quickly evolving feat of technology that accepts contributions from various genres of science. Neuroscience, Physiology, Chemistry, Material science, Computer science, and the wide umbrella of mechatronics have all simultaneously contributed to many innovations in the prosthetic applications of robotics. This review begins with a discussion of the scope of the term robotic prosthetics and discusses the evolving domain of Neuroprosthetics. The discussion is then constrained to focus on various actuation and control strategies for robotic prosthetic limbs. This review discusses various soft robotic actuators such as EAP, SMA, FFA, etc., and the merits of such actuators over conventional hard robotic actuators. Options in control strategies for robotic prosthetics, that are in various states of research and development, are reviewed. This paper concludes the discussion with an analysis regarding the prospective direction in which this field of robotic prosthetics is evolving in terms of actuation, control, and other features relevant to artificial limbs. This paper intends to review some of the emerging research and development trends in the field of robotic prosthetics and summarize many tangents that are represented under this broad domain in an approachable manner.

cs.RO↗
arXiv2024

Advances in Differential Privacy and Differentially Private Machine Learning

There has been an explosion of research on differential privacy (DP) and its various applications in recent years, ranging from novel variants and accounting techniques in differential privacy to the thriving field of differentially private machine learning (DPML) to newer implementations in practice, like those by various companies and organisations such as census bureaus. Most recent surveys focus on the applications of differential privacy in particular contexts like data publishing, specific machine learning tasks, analysis of unstructured data, location privacy, etc. This work thus seeks to fill the gap for a survey that primarily discusses recent developments in the theory of differential privacy along with newer DP variants, viz. Renyi DP and Concentrated DP, novel mechanisms and techniques, and the theoretical developments in differentially private machine learning in proper detail. In addition, this survey discusses its applications to privacy-preserving machine learning in practice and a few practical implementations of DP.

cs.CR↗
arXiv2024

Estimation of Electronic Band Gap Energy From Material Properties Using Machine Learning

Machine learning techniques are utilized to estimate the electronic band gap energy and forecast the band gap category of materials based on experimentally quantifiable properties. The determination of band gap energy is critical for discerning various material properties, such as its metallic nature, and potential applications in electronic and optoelectronic devices. While numerical methods exist for computing band gap energy, they often entail high computational costs and have limitations in accuracy and scalability. A machine learning-driven model capable of swiftly predicting material band gap energy using easily obtainable experimental properties would offer a superior alternative to conventional density functional theory (DFT) methods. Our model does not require any preliminary DFT-based calculation or knowledge of the structure of the material. We present a scheme for improving the performance of simple regression and classification models by partitioning the dataset into multiple clusters. A new evaluation scheme for comparing the performance of ML-based models in material sciences involving both regression and classification tasks is introduced based on traditional evaluation metrics. It is shown that on this new evaluation metric, our method of clustering the dataset results in better performance.

cond-mat.mtrl-sci↗
arXiv2024

Enhancing Neural Theorem Proving through Data Augmentation and Dynamic Sampling Method

Theorem proving is a fundamental task in mathematics. With the advent of large language models (LLMs) and interactive theorem provers (ITPs) like Lean, there has been growing interest in integrating LLMs and ITPs to automate theorem proving. In this approach, the LLM generates proof steps (tactics), and the ITP checks the applicability of the tactics at the current goal. The two systems work together to complete the proof. In this paper, we introduce DS-Prover, a novel dynamic sampling method for theorem proving. This method dynamically determines the number of tactics to apply to expand the current goal, taking into account the remaining time compared to the total allocated time for proving a theorem. This makes the proof search process more efficient by adjusting the balance between exploration and exploitation as time passes. We also augment the training dataset by decomposing simplification and rewrite tactics with multiple premises into tactics with single premises. This gives the model more examples to learn from and helps it to predict the tactics with premises more accurately. We perform our experiments using the Mathlib dataset of the Lean theorem prover and report the performance on two standard datasets, MiniF2F and ProofNet. Our methods achieve significant performance gains on both datasets. We achieved a state-of-the-art performance (Pass@1) of 14.2% on the ProofNet dataset and a performance of 29.8% on MiniF2F, slightly surpassing the best-reported Pass@1 of 29.6% using Lean.

cs.AI↗
arXiv2023

Introspecting the Happiness amongst University Students using Machine Learning

Happiness underlines the intuitive constructs of a specified population based on positive psychological outcomes. It is the cornerstone of the cognitive skills and exploring university student's happiness has been the essence of the researchers lately. In this study, we have analyzed the university student's happiness and its facets using statistical distribution charts; designing research questions. Furthermore, regression analysis, machine learning, and clustering algorithms were applied on the world happiness dataset and university student's dataset for training and testing respectively. Philosophy was the happiest department while Sociology the saddest; average happiness score being 2.8 and 2.44 respectively. Pearson coefficient of correlation was 0.74 for Health. Predicted happiness score was 5.2 and the goodness of model fit was 51%. train and test error being 0.52, 0.47 respectively. On a Confidence Interval(CI) of 5% p-value was least for Campus Environment(CE) and University Reputation(UR) and maximum for Extra-curricular Activities(ECA) and Work Balance(WB) (i.e. 0.184 and 0.228 respectively). RF with Clustering got the highest accuracy(89%) and F score(0.98) and the least error(17.91%), hence turned out to be best for our study

cs.CY↗
arXiv2023

IndoorGNN: A Graph Neural Network based approach for Indoor Localization using WiFi RSSI

Indoor localization is the process of determining the location of a person or object inside a building. Potential usage of indoor localization includes navigation, personalization, safety and security, and asset tracking. Commonly used technologies for indoor localization include WiFi, Bluetooth, RFID, and Ultra-wideband. Among these, WiFi's Received Signal Strength Indicator (RSSI)-based localization is preferred because of widely available WiFi Access Points (APs). We have two main contributions. First, we develop our method, 'IndoorGNN' which involves using a Graph Neural Network (GNN) based algorithm in a supervised manner to classify a specific location into a particular region based on the RSSI values collected at that location. Most of the ML algorithms that perform this classification require a large number of labeled data points (RSSI vectors with location information). Collecting such data points is a labor-intensive and time-consuming task. To overcome this challenge, as our second contribution, we demonstrate the performance of IndoorGNN on the restricted dataset. It shows a comparable prediction accuracy to that of the complete dataset. We performed experiments on the UJIIndoorLoc and MNAV datasets, which are real-world standard indoor localization datasets. Our experiments show that IndoorGNN gives better location prediction accuracies when compared with state-of-the-art existing conventional as well as GNN-based methods for this same task. It continues to outperform these algorithms even with restricted datasets. It is noteworthy that its performance does not decrease a lot with a decrease in the number of available data points. Our method can be utilized for navigation and wayfinding in complex indoor environments, asset tracking and building management, enhancing mobile applications with location-based services, and improving safety and security during emergencies.

eess.SP↗
arXiv2023

Perceiving University Student's Opinions from Google App Reviews

Google app market captures the school of thought of users from every corner of the globe via ratings and text reviews, in a multilinguistic arena. The potential information from the reviews cannot be extracted manually, due to its exponential growth. So, Sentiment analysis, by machine learning and deep learning algorithms employing NLP, explicitly uncovers and interprets the emotions. This study performs the sentiment classification of the app reviews and identifies the university student's behavior towards the app market via exploratory analysis. We applied machine learning algorithms using the TP, TF, and TF IDF text representation scheme and evaluated its performance on Bagging, an ensemble learning method. We used word embedding, Glove, on the deep learning paradigms. Our model was trained on Google app reviews and tested on Student's App Reviews(SAR). The various combinations of these algorithms were compared amongst each other using F score and accuracy and inferences were highlighted graphically. SVM, amongst other classifiers, gave fruitful accuracy(93.41%), F score(89%) on bigram and TF IDF scheme. Bagging enhanced the performance of LR and NB with accuracy of 87.88% and 86.69% and F score of 86% and 78% respectively. Overall, LSTM on Glove embedding recorded the highest accuracy(95.2%) and F score(88%).

cs.CL↗
arXiv2023

Tirtha -- An Automated Platform to Crowdsource Images and Create 3D Models of Heritage Sites

Digital preservation of Cultural Heritage (CH) sites is crucial to protect them against damage from natural disasters or human activities. Creating 3D models of CH sites has become a popular method of digital preservation thanks to advancements in computer vision and photogrammetry. However, the process is time-consuming, expensive, and typically requires specialized equipment and expertise, posing challenges in resource-limited developing countries. Additionally, the lack of an open repository for 3D models hinders research and public engagement with their heritage. To address these issues, we propose Tirtha, a web platform for crowdsourcing images of CH sites and creating their 3D models. Tirtha utilizes state-of-the-art Structure from Motion (SfM) and Multi-View Stereo (MVS) techniques. It is modular, extensible and cost-effective, allowing for the incorporation of new techniques as photogrammetry advances. Tirtha is accessible through a web interface at https://tirtha.niser.ac.in and can be deployed on-premise or in a cloud environment. In our case studies, we demonstrate the pipeline's effectiveness by creating 3D models of temples in Odisha, India, using crowdsourced images. These models are available for viewing, interaction, and download on the Tirtha website. Our work aims to provide a dataset of crowdsourced images and 3D reconstructions for research in computer vision, heritage conservation, and related domains. Overall, Tirtha is a step towards democratizing digital preservation, primarily in resource-limited developing countries.

cs.CV↗
arXiv2023

Neural Networks at a Fraction with Pruned Quaternions

Contemporary state-of-the-art neural networks have increasingly large numbers of parameters, which prevents their deployment on devices with limited computational power. Pruning is one technique to remove unnecessary weights and reduce resource requirements for training and inference. In addition, for ML tasks where the input data is multi-dimensional, using higher-dimensional data embeddings such as complex numbers or quaternions has been shown to reduce the parameter count while maintaining accuracy. In this work, we conduct pruning on real and quaternion-valued implementations of different architectures on classification tasks. We find that for some architectures, at very high sparsity levels, quaternion models provide higher accuracies than their real counterparts. For example, at the task of image classification on CIFAR-10 using Conv-4, at $3\%$ of the number of parameters as the original model, the pruned quaternion version outperforms the pruned real by more than $10\%$. Experiments on various network architectures and datasets show that for deployment in extremely resource-constrained environments, a sparse quaternion network might be a better candidate than a real sparse model of similar architecture.

cs.LG↗
arXiv2023

Neural directional distance field object representation for uni-directional path-traced rendering

Faster rendering of synthetic images is a core problem in the field of computer graphics. Rendering algorithms, such as path-tracing is dependent on parameters like size of the image, number of light bounces, number of samples per pixel, all of which, are fixed if one wants to obtain a image of a desired quality. It is also dependent on the size and complexity of the scene being rendered. One of the largest bottleneck in rendering, particularly when the scene is very large, is querying for objects in the path of a given ray in the scene. By changing the data type that represents the objects in the scene, one may reduce render time, however, a different representation of a scene requires the modification of the rendering algorithm. In this paper, (a) we introduce directed distance field, as a functional representation of a object; (b) how the directed distance functions, when stored as a neural network, be optimized and; (c) how such an object can be rendered with a modified path-tracing algorithm.

cs.GR↗
arXiv2023

A Comparative Study of Face Detection Algorithms for Masked Face Detection

Contemporary face detection algorithms have to deal with many challenges such as variations in pose, illumination, and scale. A subclass of the face detection problem that has recently gained increasing attention is occluded face detection, or more specifically, the detection of masked faces. Three years on since the advent of the COVID-19 pandemic, there is still a complete lack of evidence regarding how well existing face detection algorithms perform on masked faces. This article first offers a brief review of state-of-the-art face detectors and detectors made for the masked face problem, along with a review of the existing masked face datasets. We evaluate and compare the performances of a well-representative set of face detectors at masked face detection and conclude with a discussion on the possible contributing factors to their performance.

cs.CV↗
arXiv2023

3D GANs and Latent Space: A comprehensive survey

Generative Adversarial Networks (GANs) have emerged as a significant player in generative modeling by mapping lower-dimensional random noise to higher-dimensional spaces. These networks have been used to generate high-resolution images and 3D objects. The efficient modeling of 3D objects and human faces is crucial in the development process of 3D graphical environments such as games or simulations. 3D GANs are a new type of generative model used for 3D reconstruction, point cloud reconstruction, and 3D semantic scene completion. The choice of distribution for noise is critical as it represents the latent space. Understanding a GAN's latent space is essential for fine-tuning the generated samples, as demonstrated by the morphing of semantically meaningful parts of images. In this work, we explore the latent space and 3D GANs, examine several GAN variants and training methods to gain insights into improving 3D GAN training, and suggest potential future directions for further research.

cs.CV↗
arXiv2022

MIMA -- Multifunctional IoT Integrated Menstrual Aid

Menstruation is the monthly shedding of the endometrium lining of a woman's uterus. The average age when girls start menstruating is around the age of 12 years (menarche), and the cycle continues until they attain menopause (about the age of 51). Medical research and analysis in this field reveal that most women have to go through a painful cycle of abdominal cramps along with sanitary pad rashes, while painkillers or endurance ability are their go-to solution. Heat pads or hot water bags also help in pain reduction. Currently, the concept of period pants revolves around pad-free and hassle-free periods for women, whereas most women still prefer sanitary pads during their period cycle. MIMA aims at the development of IoT integrated smart, functional intimate wear for women that would help women comfort during menstruation by catering to issues of menstrual cramps, rashes, leakage and stains, malodor, etc. The proposed methodology has been implemented by referring to the online survey conducted from Indian women (17-58 years old). MIMA can provide comfort during the menstruation cycle with IoT integrated Heat-Pad and functional alterations in the garment for a rash-free, anti-odor, and leak-proof period.

eess.SY↗
arXiv2022

Dict-NMT: Bilingual Dictionary based NMT for Extremely Low Resource Languages

Neural Machine Translation (NMT) models have been effective on large bilingual datasets. However, the existing methods and techniques show that the model's performance is highly dependent on the number of examples in training data. For many languages, having such an amount of corpora is a far-fetched dream. Taking inspiration from monolingual speakers exploring new languages using bilingual dictionaries, we investigate the applicability of bilingual dictionaries for languages with extremely low, or no bilingual corpus. In this paper, we explore methods using bilingual dictionaries with an NMT model to improve translations for extremely low resource languages. We extend this work to multilingual systems, exhibiting zero-shot properties. We present a detailed analysis of the effects of the quality of dictionaries, training dataset size, language family, etc., on the translation quality. Results on multiple low-resource test languages show a clear advantage of our bilingual dictionary-based method over the baselines.

cs.CL↗