Lalan Kumar

Shivani Ranjan, Ayush Tripathi, Harshal Shende et al.

Dementia is a neurological syndrome marked by cognitive decline. Alzheimer's disease (AD) and Frontotemporal dementia (FTD) are the common forms of dementia, each with distinct progression patterns. EEG, a non-invasive tool for recording brain activity, has shown potential in distinguishing AD from FTD and mild cognitive impairment (MCI). Previous studies have utilized various EEG features, such as subband power and connectivity patterns to differentiate these conditions. However, artifacts in EEG signals can obscure crucial information, necessitating advanced signal processing techniques. This study aims to develop a deep learning-based classification system for dementia by analyzing scout time-series signals from deep brain regions, specifically the hippocampus, amygdala, and thalamus. The study utilizes scout time series extracted via the standardized low-resolution brain electromagnetic tomography (sLORETA) technique. The time series is converted to image representations using continuous wavelet transform (CWT) and fed as input to deep learning models. Two high-density EEG datasets are utilized to check for the efficacy of the proposed method: the online BrainLat dataset (comprising AD, FTD, and healthy controls (HC)) and the in-house IITD-AIIA dataset (including subjects with AD, MCI, and HC). Different classification strategies and classifier combinations have been utilized for the accurate mapping of classes on both datasets. The best results were achieved by using a product of probabilities from classifiers for left and right subcortical regions in conjunction with the DenseNet model architecture. It yields accuracies of 94.17$\%$ and 77.72$\%$ on the BrainLat and IITD-AIIA datasets, respectively. This highlights the potential of this approach for early and accurate differentiation of neurodegenerative disorders.

Rajnish Kumar, Anand Gupta, Suriya Prakash Muthukrishnan et al.

Exoskeletons and rehabilitation systems have the potential to improve human strength and recovery by using adaptive human-machine interfaces. Achieving precise and responsive control in these systems depends on accurately estimating joint movement dynamics, such as joint angle, velocity, acceleration, external mass, and torque. While machine learning (ML) approaches have been employed to predict joint kinematics from surface electromyography (sEMG) data, traditional ML models often struggle to generalize across dynamic movements. In contrast, physics-informed neural networks integrate biomechanical principles, but their effectiveness in predicting full movement dynamics has not been thoroughly explored. To address this, we introduce the Physics-informed Gated Recurrent Network (PiGRN), a novel model designed to predict multi-joint movement dynamics from sEMG data. PiGRN uses a Gated Recurrent Unit (GRU) to process time-series sEMG inputs, estimate multi-joint kinematics and external loads, and predict joint torque while incorporating physics-based constraints during training. Experimental validation, using sEMG data from five participants performing elbow flexion-extension tasks with 0 kg, 2 kg, and 4 kg loads, showed that PiGRN accurately predicted joint torques for 10 novel movements. RMSE values ranged from 4.02\% to 11.40\%, with correlation coefficients between 0.87 and 0.98. These results underscore PiGRN's potential for real-time applications in exoskeletons and rehabilitation. Future work will focus on expanding datasets, improving musculoskeletal models, and investigating unsupervised learning approaches.

Rajnish Kumar, Suriya Prakash Muthukrishnan, Lalan Kumar et al.

In this research, we present an innovative method known as a physics-informed neural network (PINN) model to predict multi-joint kinematics using electromyography (EMG) signals recorded from the muscles surrounding these joints across various loads. The primary aim is to simultaneously predict both the shoulder and elbow joint angles while executing elbow flexion-extension (FE) movements, especially under varying load conditions. The PINN model is constructed by combining a feed-forward Artificial Neural Network (ANN) with a joint torque computation model. During the training process, the model utilizes a custom loss function derived from an inverse dynamics joint torque musculoskeletal model, along with a mean square angle loss. The training dataset for the PINN model comprises EMG and time data collected from four different subjects. To assess the model's performance, we conducted a comparison between the predicted joint angles and experimental data using a testing data set. The results demonstrated strong correlations of 58% to 83% in joint angle prediction. The findings highlight the potential of incorporating physical principles into the model, not only increasing its versatility but also enhancing its accuracy. The findings could have significant implications for the precise estimation of multi-joint kinematics in dynamic scenarios, particularly concerning the advancement of human-machine interfaces (HMIs) for exoskeletons and prosthetic control systems.

Ayush Tripathi, Arnab Kumar Mondal, Lalan Kumar et al.

Airwriting Recognition is the problem of identifying letters written in free space with finger movement. It is essentially a specialized case of gesture recognition, wherein the vocabulary of gestures corresponds to letters as in a particular language. With the wide adoption of smart wearables in the general population, airwriting recognition using motion sensors from a smart-band can be used as a medium of user input for applications in Human-Computer Interaction. There has been limited work in the recognition of in-air trajectories using motion sensors, and the performance of the techniques in the case when the device used to record signals is changed has not been explored hitherto. Motivated by these, a new paradigm for device and user-independent airwriting recognition based on supervised contrastive learning is proposed. A two stage classification strategy is employed, the first of which involves training an encoder network with supervised contrastive loss. In the subsequent stage, a classification head is trained with the encoder weights kept frozen. The efficacy of the proposed method is demonstrated through experiments on a publicly available dataset and also with a dataset recorded in our lab using a different device. Experiments have been performed in both supervised and unsupervised settings and compared against several state-of-the-art domain adaptation techniques. Data and the code for our implementation will be made available at https://github.com/ayushayt/SCLAiR.

Kuldeep Singh Yadav, Lalan Kumar

Suspiciousness estimation is critical for proactive threat detection and ensuring public safety in complex environments. This work introduces a large-scale annotated dataset, USE50k, along with a computationally efficient vision-based framework for real-time suspiciousness analysis. The USE50k dataset contains 65,500 images captured from diverse and uncontrolled environments, such as airports, railway stations, restaurants, parks, and other public areas, covering a broad spectrum of cues including weapons, fire, crowd density, abnormal facial expressions, and unusual body postures. Building on this dataset, we present DeepUSEvision, a lightweight and modular system integrating three key components, i.e., a Suspicious Object Detector based on an enhanced YOLOv12 architecture, dual Deep Convolutional Neural Networks (DCNN-I and DCNN-II) for facial expression and body-language recognition using image and landmark features, and a transformer-based Discriminator Network that adaptively fuses multimodal outputs to yield an interpretable suspiciousness score. Extensive experiments confirm the superior accuracy, robustness, and interpretability of the proposed framework compared to state-of-the-art approaches. Collectively, the USE50k dataset and the DeepUSEvision framework establish a strong and scalable foundation for intelligent surveillance and real-time risk assessment in safety-critical applications.

Gary P. T. Choi, Amita Giri, Lalan Kumar

The parameterization of open and closed anatomical surfaces is of fundamental importance in many biomedical applications. Spherical harmonics, a set of basis functions defined on the unit sphere, are widely used for anatomical shape description. However, establishing a one-to-one correspondence between the object surface and the entire unit sphere may induce a large geometric distortion in case the shape of the surface is too different from a perfect sphere. In this work, we propose adaptive area-preserving parameterization methods for simply-connected open and closed surfaces with the target of the parameterization being a spherical cap. Our methods optimize the shape of the parameter domain along with the mapping from the object surface to the parameter domain. The object surface will be globally mapped to an optimal spherical cap region of the unit sphere in an area-preserving manner while also exhibiting low conformal distortion. We further develop a set of spherical harmonics-like basis functions defined over the adaptive spherical cap domain, which we call the adaptive harmonics. Experimental results show that the proposed parameterization methods outperform the existing methods for both open and closed anatomical surfaces in terms of area and angle distortion. Surface description of the object surfaces can be effectively achieved using a novel combination of the adaptive parameterization and the adaptive harmonics. Our work provides a novel way of mapping anatomical surfaces with improved accuracy and greater flexibility. More broadly, the idea of using an adaptive parameter domain allows easy handling of a wide range of biomedical shapes.