Susmita Ghosh

Susmita Ghosh, Abhiroop Chatterjee

This article aims to classify diabetic retinopathy (DR) disease into five different classes using an ensemble approach based on two popular pre-trained convolutional neural networks: VGG16 and Inception V3. The proposed model aims to leverage the strengths of the two individual nets to enhance the classification performance for diabetic retinopathy. The ensemble model architecture involves freezing a portion of the layers in each pre-trained model to utilize their learned representations effectively. Global average pooling layers are added to transform the output feature maps into fixed-length vectors. These vectors are then concatenated to form a consolidated representation of the input image. The ensemble model is trained using a dataset of diabetic retinopathy images (APTOS), divided into training and validation sets. During the training process, the model learns to classify the retinal images into the corresponding diabetic retinopathy classes. Experimental results on the test set demonstrate the efficacy of the proposed ensemble model for DR classification achieving an accuracy of 96.4%.

Susmita Ghosh, Abhiroop Chatterjee

In recent years, deep neural networks are yielding better performance in image classification tasks. However, the increasing complexity of datasets and the demand for improved performance necessitate the exploration of innovative techniques. The present work proposes a new deep neural network (called as, T-Fusion Net) that augments multiple localizations based spatial attention. This attention mechanism allows the network to focus on relevant image regions, improving its discriminative power. A homogeneous ensemble of the said network is further used to enhance image classification accuracy. For ensembling, the proposed approach considers multiple instances of individual T-Fusion Net. The model incorporates fuzzy max fusion to merge the outputs of individual nets. The fusion process is optimized through a carefully chosen parameter to strike a balance on the contributions of the individual models. Experimental evaluations on benchmark Covid-19 (SARS-CoV-2 CT scan) dataset demonstrate the effectiveness of the proposed T-Fusion Net as well as its ensemble. The proposed T-Fusion Net and the homogeneous ensemble model exhibit better performance, as compared to other state-of-the-art methods, achieving accuracy of 97.59% and 98.4%, respectively.

Susmita Ghosh, Abhiroop Chatterjee

Diabetic retinopathy (DR) is a leading cause of blindness among diabetic patients. Deep learning models have shown promising results in automating the detection of DR. In the present work, we propose a new methodology that integrates a feature attention module with a pretrained VGG19 convolutional neural network (CNN) for more accurate DR detection. Here, the pretrained net is fine-tuned with the proposed feature attention block. The proposed module aims to leverage the complementary information from various regions of fundus images to enhance the discriminative power of the CNN. The said feature attention module incorporates an attention mechanism which selectively highlights salient features from images and fuses them with the original input. The simultaneous learning of attention weights for the features and thereupon the combination of attention-modulated features within the feature attention block facilitates the network's ability to focus on relevant information while reducing the impact of noisy or irrelevant features. Performance of the proposed method has been evaluated on a widely used dataset for diabetic retinopathy classification e.g., the APTOS (Asia Pacific Tele-Ophthalmology Society) DR Dataset. Results are compared with/without attention module, as well as with other state-of-the-art approaches. Results confirm that the introduction of the fusion module (fusing of feature attention module with CNN) improves the accuracy of DR detection achieving an accuracy of 95.70%.

Susmita Ghosh, Abhiroop Chatterjee

The rapid spread of COVID-19 has necessitated efficient and accurate diagnostic methods. Computed Tomography (CT) scan images have emerged as a valuable tool for detecting the disease. In this article, we present a novel deep learning approach for automated COVID-19 CT scan classification where a modified Xception model is proposed which incorporates a newly designed channel attention mechanism and weighted global average pooling to enhance feature extraction thereby improving classification accuracy. The channel attention module selectively focuses on informative regions within each channel, enabling the model to learn discriminative features for COVID-19 detection. Experiments on a widely used COVID-19 CT scan dataset demonstrate a very good accuracy of 96.99% and show its superiority to other state-of-the-art techniques. This research can contribute to the ongoing efforts in using artificial intelligence to combat current and future pandemics and can offer promising and timely solutions for efficient medical image analysis tasks.

Debasrita Chakraborty, Susmita Ghosh, Ashish Ghosh

Stock prices are highly volatile and sudden changes in trends are often very problematic for traditional forecasting models to handle. The standard Long Short Term Memory (LSTM) networks are regarded as the state-of-the-art models for such predictions. But, these models fail to handle sudden and drastic changes in the price trend. Moreover, there are some inherent constraints with the open, high, low and close (OHLC) prices of the stocks. Literature lacks the study on the inherent property of OHLC prices. We argue that predicting the OHLC prices for the next day is much more informative than predicting the trends of the stocks as the trend is mostly calculated using these OHLC prices only. The problem mainly is focused on Buy-Today Sell-Tomorrow (BTST) trading. In this regard, AEs when pre-trained with the stock prices, may be beneficial. A novel framework is proposed where a pre-trained encoder is cascaded in front of the multi-task predictor network. This hybrid network can leverage the power of a combination of networks and can both handle the OHLC constraints as well as capture any sudden drastic changes in the prices. It is seen that such a network is much more efficient at predicting stock prices. The experiments have been extended to recommend the most profitable and most overbought stocks on the next day. The model has been tested for multiple Indian companies and it is found that the recommendations from the proposed model have not resulted in a single loss for a test period of 300 days.

Abhishek Dey, Debayan Goswami, Rahul Roy et al.

Purpose: Health recommenders act as important decision support systems, aiding patients and medical professionals in taking actions that lead to patients' well-being. These systems extract the information which may be of particular relevance to the end-user, helping them in making appropriate decisions. The present study proposes a feature recommender, as a part of a disease management system, that identifies and recommends the most important risk factors for an illness. Methods: A novel mutual information and ensemble-based feature ranking approach for identifying critical risk factors in healthcare prognosis is proposed. Results: To establish the effectiveness of the proposed method, experiments have been conducted on four benchmark datasets of diverse diseases (clear cell renal cell carcinoma (ccRCC), chronic kidney disease, Indian liver patient, and cervical cancer risk factors). The performance of the proposed recommender is compared with four state-of-the-art methods using recommender systems' performance metrics like average precision@K, precision@K, recall@K, F1@K, reciprocal rank@K. The method is able to recommend all relevant critical risk factors for ccRCC. It also attains a higher accuracy (96.6% and 98.6% using support vector machine and neural network, respectively) for ccRCC staging with a reduced feature set as compared to existing methods. Moreover, the top two features recommended using the proposed method with ccRCC, viz. size of tumor and metastasis status, are medically validated from the existing TNM system. Results are also found to be superior for the other three datasets. Conclusion: The proposed recommender can identify and recommend risk factors that have the most discriminating power for detecting diseases.

Subhajeet Das, Susmita Ghosh, Abhiroop Chatterjee

Aerial images play a vital role in urban planning and environmental preservation, as they consist of various structures, representing different types of buildings, forests, mountains, and unoccupied lands. Due to its heterogeneous nature, developing robust models for scene classification remains a challenge. In this study, we conduct a literature review of various machine learning methods for aerial image classification. Our survey covers a range of approaches from handcrafted features (e.g., SIFT, LBP) to traditional CNNs (e.g., VGG, GoogLeNet), and advanced deep hybrid networks. In this connection, we have also designed Aerial-Y-Net, a spatial attention-enhanced CNN with multi-scale feature fusion mechanism, which acts as an attention-based model and helps us to better understand the complexities of aerial images. Evaluated on the AID dataset, our model achieves 91.72% accuracy, outperforming several baseline architectures.

Surajit Ghosh, Arpan Dawn, Sneha Kour et al.

Floods are one of the most common disasters globally. Flood affects humans in many ways. Therefore, rapid assessment is needed to assess the effect of floods and to take early action to support the vulnerable community in time. Sentinel-1 is one such Earth Observation (EO) mission widely used for mapping the flooding conditions at a 10m scale. However, various preprocessing steps are involved before analyses of the Sentinel-1 data. Researchers sometimes avoid a few necessary corrections since it is time-consuming and complex. Standardization of the Sentinel-1 data is the need of the hour, specifically for supporting researchers to use the Standardized Analysis-Ready (STAR) data cube without experiencing the complexity of the Sentinel-1 data processing. In the present study, we proposed a workflow to use STAR in Google Earth Engine (GEE) environment. The Nigeria Flood of 2022 has been used as a case study for assessing the model performance.

Soumen Sinha, Tanisha Rana, Susmita Ghosh et al.

In this article, we propose a novel approach for plant hierarchical taxonomy classification by posing the problem as an open class problem. It is observed that existing methods for medicinal plant classification often fail to perform hierarchical classification and accurately identifying unknown species, limiting their effectiveness in comprehensive plant taxonomy classification. Thus we address the problem of unknown species classification by assigning it best hierarchical labels. We propose a novel method, which integrates DenseNet121, Multi-Scale Self-Attention (MSSA) and cascaded classifiers for hierarchical classification. The approach systematically categorizes medicinal plants at multiple taxonomic levels, from phylum to species, ensuring detailed and precise classification. Using multi scale space attention, the model captures both local and global contextual information from the images, improving the distinction between similar species and the identification of new ones. It uses attention scores to focus on important features across multiple scales. The proposed method provides a solution for hierarchical classification, showcasing superior performance in identifying both known and unknown species. The model was tested on two state-of-art datasets with and without background artifacts and so that it can be deployed to tackle real word application. We used unknown species for testing our model. For unknown species the model achieved an average accuracy of 83.36%, 78.30%, 60.34% and 43.32% for predicting correct phylum, class, order and family respectively. Our proposed model size is almost four times less than the existing state of the art methods making it easily deploy able in real world application.

Sagar Lekhak, Emmett J. Ientilucci, Jasper Baur et al.

This paper introduces a novel benchmark dataset of Visible and Near-Infrared (VNIR) hyperspectral imagery acquired via an unmanned aerial vehicle (UAV) platform for landmine and unexploded ordnance (UXO) detection research. The dataset was collected over a controlled test field seeded with 143 realistic surrogate landmine and UXO targets, including surface, partially buried, and fully buried configurations. Data acquisition was performed using a Headwall Nano-Hyperspec sensor mounted on a multi-sensor drone platform, flown at an altitude of approximately 20.6 m, capturing 270 contiguous spectral bands spanning 398-1002 nm. Radiometric calibration, orthorectification, and mosaicking were performed followed by reflectance retrieval using a two-point Empirical Line Method (ELM), with reference spectra acquired using an SVC spectroradiometer. Cross-validation against six reference objects yielded RMSE values below 1.0 and SAM values between 1 and 6 degrees in the 400-900 nm range, demonstrating high spectral fidelity. The dataset is released alongside raw radiance cubes, GCP/AeroPoint data, and reference spectra to support reproducible research. This contribution fills a critical gap in open-access UAV-based hyperspectral data for landmine detection and offers a multi-sensor benchmark when combined with previously published drone-based electromagnetic induction (EMI) data from the same test field.

Sagar Lekhak, Emmett J. Ientilucci, Dimah Dera et al.

Detecting surface landmines and unexploded ordnances (UXOs) using deep learning has shown promise in humanitarian demining. However, deterministic neural networks can be vulnerable to noisy conditions and adversarial attacks, leading to missed detection or misclassification. This study introduces the idea of uncertainty quantification through Monte Carlo (MC) Dropout, integrated into a fine-tuned ResNet-50 architecture for surface landmine and UXO classification, which was tested on a simulated dataset. Integrating the MC Dropout approach helps quantify epistemic uncertainty, providing an additional metric for prediction reliability, which could be helpful to make more informed decisions in demining operations. Experimental results on clean, adversarially perturbed, and noisy test images demonstrate the model's ability to flag unreliable predictions under challenging conditions. This proof-of-concept study highlights the need for uncertainty quantification in demining, raises awareness about the vulnerability of existing neural networks in demining to adversarial threats, and emphasizes the importance of developing more robust and reliable models for practical applications.

Abhiroop Chatterjee, Susmita Ghosh

As data requirements continue to grow, efficient learning increasingly depends on the curation and distillation of high-value data rather than brute-force scaling of model sizes. In the case of a hyperspectral image (HSI), the challenge is amplified by the high-dimensional 3D voxel structure, where each spatial location is associated with hundreds of contiguous spectral channels. While vision and language models have been optimized effectively for natural image or text tasks, their cross-modal alignment in the hyperspectral domain remains an open and underexplored problem. In this article, we make an attempt to optimize a Vision-Language Model (VLM) for hyperspectral scene understanding by exploiting a CLIP-style contrastive training framework. Our framework maps voxel-level embeddings from a vision backbone onto the latent space of a frozen large embedding model (LEM), where a trainable probe aligns vision features with the model's textual token representations. The two modalities are aligned via a contrastive loss restricted to a curated set of hard (closest wrong classes) and semi-hard (random distractors) negatives, along with positive pairs. To further enhance alignment, descriptive prompts that encode class semantics are introduced and act as structured anchors for the HSI embeddings. It is seen that the proposed method updates only 0.07 percent of the total parameters, yet yields state-of-the-art performance. For example, on Indian Pines (IP) the model produces better results over unimodal and multimodal baselines by +0.92 Overall Accuracy (OA) and +1.60 Kappa ($κ$), while on Pavia University (PU) data it provides gains of +0.69 OA and +0.90 $κ$. Moreover, this is achieved with the set of parameters, nearly 50$\times$ smaller than DCTN and 90$\times$ smaller than SS-TMNet.

Debasrita Chakraborty, Debayan Goswami, Susmita Ghosh et al.

The current COVID-19 pandemic has put a huge challenge on the Indian health infrastructure. With more and more people getting affected during the second wave, the hospitals were over-burdened, running out of supplies and oxygen. In this scenario, prediction of the number of COVID-19 cases beforehand might have helped in the better utilization of limited resources and supplies. This manuscript deals with the prediction of new COVID-19 cases, new deaths and total active cases for multiple days in advance. The proposed method uses gated recurrent unit networks as the main predicting model. A study is conducted by building four models that are pre-trained on the data from four different countries (United States of America, Brazil, Spain and Bangladesh) and are fine-tuned or retrained on India's data. Since the four countries chosen have experienced different types of infection curves, the pre-training provides a transfer learning to the models incorporating diverse situations into account. Each of the four models then give a multiple days ahead predictions using recursive learning method for the Indian test data. The final prediction comes from an ensemble of the predictions of the combination of different models. This method with two countries, Spain and Brazil, is seen to achieve the best performance amongst all the combinations as well as compared to other traditional regression models.

Namita Jain, Susmita Ghosh, C. A. Murthy

The existing biclustering algorithms for finding feature relation based biclusters often depend on assumptions like monotonicity or linearity. Though a few algorithms overcome this problem by using density-based methods, they tend to miss out many biclusters because they use global criteria for identifying dense regions. The proposed method, RelDenClu uses the local variations in marginal and joint densities for each pair of features to find the subset of observations, which forms the bases of the relation between them. It then finds the set of features connected by a common set of observations, resulting in a bicluster. To show the effectiveness of the proposed methodology, experimentation has been carried out on fifteen types of simulated datasets. Further, it has been applied to six real-life datasets. For three of these real-life datasets, the proposed method is used for unsupervised learning, while for other three real-life datasets it is used as an aid to supervised learning. For all the datasets the performance of the proposed method is compared with that of seven different state-of-the-art algorithms and the proposed algorithm is seen to produce better results. The efficacy of proposed algorithm is also seen by its use on COVID-19 dataset for identifying some features (genetic, demographics and others) that are likely to affect the spread of COVID-19.