RKRia Kanjilal

Ria Kanjilal

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ria Kanjilal has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Genomic Anomaly Detection with Functional Data Analysis

    by Ria Kanjilal, Andre Luiz Campelo dos Santos, Sandipan Paul Arnab, Michael DeGiorgio, Raquel Assis

    Background: Genetic variation provides a foundation for understanding evolution. With the rise of artificial intelligence, machine learning has emerged as a powerful tool for identifying genomic footprints of evolutionary processes through simulation-based predictive modeling. However, existing approaches require prior knowledge of the factors shaping genetic variation, whereas uncovering anomalous genomic regions regardless of their causes remains an equally important and complementary endeavor. Methods: To address this problem, we introduce ANDES (ANomaly DEtection using Summary statistics), a suite of algorithms that apply statistical techniques to extract features for unsupervised anomaly detection. A key innovation of ANDES is its ability to account for autocovariation due to linkage disequilibrium by fitting curves to contiguous windows and computing their first and second derivatives, thereby capturing the “velocity” and “acceleration” of genetic variation. These features are then used to train models that flag biologically significant or artifactual regions. Results: Application to human genomic data demonstrates that ANDES successfully detects anomalous regions that colocalize with genes under positive or balancing selection. Moreover, these analyses reveal a non-uniform distribution of anomalies, which are enriched in specific autosomes, intergenic regions, introns, and regions with low GC content, repetitive sequences, and poor mappability. Conclusions: ANDES thus offers a novel, model-agnostic framework for uncovering anomalous genomic regions in both model and non-model organisms.


  • Open Access

    Intelligent Clustering and Adaptive Energy Management in Wireless Sensor Networks with KDE-Based Deployment

    by Mainak Kundu, Ria Kanjilal, Ismail Uysal

    Wireless sensor networks (WSNs) are widely used in IoT, environmental monitoring, and industrial systems, but ensuring energy efficiency, extended network lifetime, and reliable communication under real-world constraints remains challenging. This work proposes a novel clustering framework that integrates kernel density estimation (KDE)-based adaptive node deployment, silhouette-optimized K-means clustering, Bayesian cluster head (CH) selection with Gaussian noise-based energy uncertainty modeling, energy-efficient coverage control, and carrier sense multiple access with collision avoidance-based data transmission. Unlike conventional approaches that rely on fixed clustering and uniform deployments, our framework supports terrain-aware node placement and dynamic CH selection based on residual energy and distance under imperfect sensing conditions. Simulation results demonstrate significant improvements in performance, including over 35% extension in network lifetime and higher coverage retention under energy constraints, compared to baseline methods such as LEACH and K-LEACH. While detailed metrics vary per run due to adaptive parameters and stochastic node behavior, these outcomes validate the scalability, robustness, and practical relevance of the proposed method for real-world WSN deployments.


  • Human Activity Recognition: A Review of RFID and Wearable Sensor Technologies Powered by AI

    by Ria Kanjilal, Muhammed Furkan Kucuk, Ismail Uysal

    Human activity recognition (HAR) has garnered significant attention across diverse domains such as fitness enhancement, safety, elderly care, clinical monitoring, and smart environments. However, despite its potential, HAR faces challenges like handling noisy and diverse data, ensuring real-time performance, maintaining user privacy, and achieving high accuracy across varying contexts and activities. A primary challenge of HAR lies in maintaining consistency and accuracy during data collection amidst varied activities and environments. This review article provides a comprehensive overview of the advancements in AI-enhanced HAR methods, with a focus on radio frequency identification system, wearable devices, and smartphone sensor technologies. We delve into the frameworks of these technologies, detailing processes like data collection, preprocessing, and the application of machine learning and deep learning algorithms. Additionally, we outline the advantages and drawbacks of these techniques and provide a brief comparison between them.


  • Subtransfer Learning in Human Activity Recognition: Boosting the Outlier User Accuracy

    by Ria Kanjilal, Muhammed F. Kucuk, Ismail Uysal

    Human activity recognition has become one of the most active areas of sensory healthcare research due to its potential in improving the quality of life both for patients in healthcare settings who are susceptible to falls or undergo physical therapy and the public to promote more active lifestyle. The state-of-the-art machine learning and artificial intelligence algorithms analyze sensory data from multiple users to achieve unprecedented performance in recognizing daily activities. Most research focuses on the average performance across the population of users however, it is evident that the performance distribution across different users is anything but uniform. In fact, the outlier users demonstrate performance degradations of up to 30% compared to median accuracy on any given dataset. This study investigates the impact of outlier users on activity recognition and proposes a novel approach called sub-transfer learning to demonstrate that transfer learning principles can be applied within the same dataset when coupled with augmentation techniques. Our results show that sub-transfer learning outperforms the source model on four datasets with different age groups and sensor placements, even when using a few additional samples. Specifically, in the most challenging dataset, the proposed approach outperforms the source model accuracy on low-accuracy subjects (80% compared to 60%) and median-accuracy subjects (98% compared to 91%) while maintaining the same levels for high-accuracy subjects. A statistical significance test further demonstrates performance improvements compared to both source and subject-specific models with p-values 0.009 and 0.0005 respectively across a range of dataset with demographically diverse users and sensor locations.


  • Open Access

    Sub-transfer Learning in Human Activity Recognition: Boosting the Outlier User Accuracy

    by Ria Kanjilal, Muhammed F. Kucuk, Ismail Uysal

    In this human activity recognition dataset, there are a total of 53 participants, consisting of 33 adults and 20 youths. In a laboratory experiment, individuals were given a set of synchronized sensors that were attached to their wrist and ankle using customized Velcro bands. These sensors, which were called Triaxial Wocket accelerometers, were lightweight, small, and thin. While wearing these sensors, the participants performed everyday tasks, and the raw acceleration data was collected at a rate of 90 Hz and transmitted wirelessly to a smartphone via Bluetooth.