VVVibha Vyas

Vibha Vyas

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

Vibha Vyas has a total of 62 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Advances in Intrusion Detection Approach in Industry 4.0 Systems Using Evolving Continual Deep Learning

    by Shubhangee Kishan Varma, Vibha Vyas

    Deep Learning (DL) detects intrusions in Industry 4.0 applications based on the Internet of Things (IoT) since it can grasp complex patterns from large datasets and identify irregularities. Current DL-based techniques for IoT-based Industry 4.0 suffer from catastrophic forgetting, computational inefficiency, security and privacy concerns, and false positive predictions. A new intrusion detection method for Industry 4.0 systems employing Evolving Continual DL (ECDL) addresses these issues. Model flexibility, accuracy, computational efficiency, security, and privacy are ECDL goals. ECDL includes local IoT model data gathering, pre-processing, feature engineering, and classification. In pre-processing, the problem of missing values and noisy data is addressed, and then it is normalized to facilitate the training process. In ECDL, each IoT model pre-processes and trains locally obtained data with advanced DL layers. The methodology is adaptable since the proposed DL layers are connected with Incremental Learning (IL), allowing for the integration of new IoT data and learning without the need for extensive re-training. The locally trained models are sent to the global model, where the Federated Learning (FL) technique is employed for aggregation. FL-based trained model disseminated to each local IoT model and SoftMax classifier for intrusion detection. In ECDL, FL with IL trains feature learning locally and adaptively in dynamic IoT contexts, resulting in complete efficiency. Implemented in real time using relevant IoT datasets, ECDL is assessed for accuracy, computational complexity, model flexibility, security, and privacy. Each IoT model uses Raspberry Pi, and the global server model uses Jetson Xavier. ECDL has 3.9% greater accuracy and 16.77% lower computing complexity than previous methods. The ECDL delivers effective security for Industry 4.0 design and implementation with model flexibility.


  • A 2.4 GHz PLL Design Using a Source Switched Charge Pump and An Active Loop Filter

    by Sayali Pralhad Joshi, Vibha Vyas, Vaishali Ingale, Vanita Agarwal

  • Graphene Oxide-Based Surface Plasmon Optical Fiber Biosensor for Thiamine Detection

    by Anamika Kumari, Kuldeep Choudhary, Vibha Vyas, Santosh Kumar

    The work proposes a localized surface plasmon resonance (LSPR)-based optical fiber sensor for detecting thiamine. Thiamine, commonly known as vitamin $B_1$ , is a water-soluble vitamin that is essential for human health. It is required for the heart, muscles, and neurological system to function properly and for the metabolism of carbohydrates. Measurement of its concentration is essential in treating many diseases caused by its deficiency. The present work proposes and fabricates an optical fiber sensor for measuring its concentration in the range of 200–500 $\mu$ g/mL. The role of gold nanoparticles (AuNPs) and graphene oxide (GO) in enhancing the sensor’s performance is studied. The article also describes the method involved in synthesizing and characterizing AuNPs and GO. The details of the sensor fabrication that involves the functionalization of AuNPs and GO have also been discussed along with the experimental setup. The sensitivity of the proposed sensor is found to be 0.0061 nm/( $\mu$ g/mL) with a calibration correlation factor of 0.9656 in the range of 200–500 $\mu$ g/mL.


  • Etched SMS-based lossy mode resonance sensor for ascorbic acid detection

    by Anamika Kumari, Vibha Vyas, Kuldeep Choudhary, Santosh Kumar

    The current study proposes a lossy mode resonance (LMR) sensor for ascorbic acid detection. LMR sensors are significant in the field of biosensing because of their high sensitivity, specificity, and versatility. The detection of proteins in blood or other biological fluids, DNA hybridization in genetic testing, and bacteria or viruses in environmental or clinical samples are all applications of the use of LMR sensors in biosensing. With the ability to detect biomolecules with enhanced performance, the use of nanomaterials in biosensing has the potential to revolutionize the area. It can have substantial effects on identifying diseases, developing new drugs, and environmental monitoring. With graphene oxide (GO), a novel SMS (single mode fiber-multi mode fiber-single mode fiber) structure has been developed to detect ascorbic acid. GO nanoparticles have been used in this work over an etched optical fiber for higher sensitivity. Experimental testing is done to determine the sensor's effectiveness in the detection of the analyte.

  • Predictive Analytics in Hospital Readmission for Diabetes Risk Patients

    by Kaustubh V. Sakhare, Vibha Vyas, Mousami Munot

    Reducing or preventing hospital readmissions, particularly caused due to inpatient or outpatient care, has been a priority, as it will always improve patient care, patient satisfaction, and healthcare costs. Per research carried out at American College of Cardiology, the post-discharge readmission rates for acute myocardial infarction (AMI) (in days) were around 8%, and the readmission rates (median) for 1–30 days were roughly 19%. As a result of this investigation, it was determined that increasing patient care quality must be the objective. Because it will enable hospitals to make necessary plans, the prediction of a patient’s readmission will be beneficial. However, the majority of data-driven research for risk forecast in a healthcare context has yielded models with limited utility in the hospital’s decision support system. Where these models have only been applied to a few portions and have not been connected with other significant workflows, they are isolated from continuity of patient care. Based on two processes, the methods suggested in this chapter aim to estimate readmission risk. Interpretable models used in predicting readmissions use the first phase as addition of healthcare domain knowledge to the decision system. In the second stage, the risk level of patients is anticipated. The findings of the study indicated that the majority of patients were classified as medium risk. In comparison to patients without diabetes and circulatory disorders or patients with only circulatory diseases, it was observed that patients with co-morbidity of diabetes are expected to have more readmissions.


  • Black Phosphorous-Based Highly Sensitive Surface Plasmonic Sensor for Detection of Formalin

    by Anamika Kumari, Vibha Vyas, Baljinder Kaur, Brajesh Kumar Kaushik, Santosh Kumar

    In the present work, a highly sensitive prism-based surface plasmon resonance (SPR) sensor for the detection of formalin using multilayer black phosphorous (BP) is proposed. Formalin, which is widely used as a preservative, can cause a variety of diseases, making its detection crucial. The transfer matrix method is utilized to compare and analyze the proposed structures of the SPR-based prism sensor in the Kretschmann configuration. The effect of prism materials (BAK3, BK7, SF10, SF11, and 2S2G), metals (gold, silver, copper, and aluminum), and 2-D materials (graphene, MoS $_2$ , WS $_2$ , and BP) on the performance of the sensor for formalin detection has been analyzed and discussed. The analysis of the impact of employing multilayer 2-D materials is carried out. Optimization of the thickness of the 2-D material is performed to achieve a structure that gives better sensitivity. The sensitivity achieved for structures with multilayer graphene, MoS $_2$ , and WS $_2$ are 172.82 $^{\circ}$ /RIU, 195.97 $^{\circ}$ /RIU, and 218.04 $^{\circ}$ /RIU, respectively. A highly sensitive structure for formalin detection is proposed with BK7, silver, and nine layers of BP. A sensitivity of 289.4565 $^{\circ}$ /RIU and a detection accuracy (DA) of 0.3125/ $^{\circ}$ are obtained. The limit of detection of the proposed sensor for different concentrations of formalin lies in the range of 3.45–3.56 $ \mu $ RIU.