Usharani Shola

Dr. Usharani Shola

Vellore Institute of Technology Chennai, Chennai, India
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 July 2022 in Processes
Verified
Journal Article
Open access
PDF file
GRGayathri Rajakumaran
Gayathri Rajakumaran
USUsharani Shola
Usharani Shola
Lenka CepovaLenka Cepova
Lenka Cepova
MRM Rajesh
M Rajesh
KANAK KALITAKANAK KALITA
KANAK KALITA
Predicting the mechanical properties of cement-based mortars is essential in understanding the life and functioning of structures. Machine learning (ML) algorithms in this regard can be especially useful in prediction scenarios. In this paper, a comprehensive comparison of nine ML algorithms, i.e., linear regression (LR), random forest regression (RFR), support vector regression (SVR), AdaBoost regression (ABR), multi-layer perceptron (MLP), gradient boosting regression (GBR), decision tree regression (DT), hist gradient boosting regression (hGBR) and XGBoost regression (XGB), is carried out. A multi-attribute decision making method called TOPSIS (technique for order of preference by similarity to ideal solution) is used to select the best ML metamodel. A large dataset on cement-based mortars consisting of 424 sample points is used. The compressive strength of cement-based mortars is predicted based on six input parameters, i.e., the age of specimen (AS), the cement grade (CG), the metakaolin-to-total-binder ratio (MK/B), the water-to-binder ratio (W/B), the superplasticizer-to-binder ratio (SP) and the binder-to-sand ratio (B/S). XGBoost regression is found to be the best ML metamodel while simple metamodels like linear regression (LR) are found to be insufficient in handling the non-linearity in the process. This mapping of the compressive strength of mortars using ML techniques will be helpful for practitioners and researchers in identifying suitable mortar mixes.

3 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
GRGayathri Rajakumaran
Gayathri Rajakumaran
USUsharani Shola
Usharani Shola
MMMiroslav Mahdal
Miroslav Mahdal
RVRajasekharan Vezhavendhan
Rajasekharan Vezhavendhan
RVRajiv Vincent
Rajiv Vincent
Muniyandy ElangovanMuniyandy Elangovan
Muniyandy Elangovan
This paper proposes a solution for ensuring the security of IoT devices in the cloud environment by protecting against distributed denial-of-service (DDoS) and false data injection attacks. The proposed solution is based on the integration of simple network management protocol (SNMP), Kullback–Leibler distance (KLD), access control rules (ACL), and moving target defense (MTD) techniques. The SNMP and KLD techniques are used to detect DDoS and false data sharing attacks, while the ACL and MTD techniques are applied to mitigate these attacks by hardening the target and reducing the attack surface. The effectiveness of the proposed framework is validated through experimental simulations on the Amazon Web Service (AWS) platform, which shows a significant reduction in attack probabilities and delays. The integration of IoT and cloud technologies is a powerful combination that can deliver customized and critical solutions to major business vendors. However, ensuring the confidentiality and security of data among IoT devices, storage, and access to the cloud is crucial to maintaining trust among internet users. This paper demonstrates the importance of implementing robust security measures to protect IoT devices in the cloud environment and highlights the potential of the proposed solution in protecting against DDoS and false data injection attacks.

1 February 2025 in IAES International Journal of Artificial Intelligence (IJ-AI)
Verified
Journal Article
Open access
PDF file
USUsharani Shola
Usharani Shola
RLRama Parvathy Lakshmanan
Rama Parvathy Lakshmanan
GRGayathri Rajakumaran
Gayathri Rajakumaran
ABAritra Basu
Aritra Basu
ANAnjana Devi Nandam
Anjana Devi Nandam
SDSivakumar Depuru
Sivakumar Depuru
Mutations or abnormalities in genes can occasionally cause cells to grow uncontrolled, resulting in a tumor, which is very dangerous. These are the most prevalent cancer causes. They are caused by significant damage to genes in a specific cell during a person's existence. Brain tumors are increasing rapidly, majorly brain tumor cases in the US are projected to rise from 27,000 in 2020 to 31,000 in 2023 at an annual growth rate of 1.5%, all the cases are rising because of the detection of the tumors in the late phase. Thus, it needs the hour to create something which can solve this anomaly and help us detect the tumor rapidly and efficiently. While major research papers on brain tumor detection mainly focus on the detection and classification of the tumors, the presented research aims to first detect the tumor using pre-recognized photos using machine learning object detection models. Then after successful detection of the tumor, the study team plans to determine its precise coordinates and display the tumor and its location in the picture.

1 April 2017 in Asian Journal of Pharmaceutical and Clinical Research
Verified
Journal Article
Open access
PDF file
USUsharani Shola
Usharani Shola
NVNeelanarayanan VN
Neelanarayanan VN
PCA is a patient-controlled analgesia infusion pump, which is used to infuse the medicine into the patients after surgery. It contains a syringe with pain medicine to infuse that is prescribed by the physician. The drugs used for pain control are high-alert medicines, since overmedication may cause death to the patients. These types of unbearable events may happen due to medical errors, prescription errors, adverse events (AEs), etc. Hence, it requires a precautionary attention or continuous monitoring for PCA pump infusion patients. However, always physicians or nurses may not monitor a patient continuously. To provide safety to the patient, the PCA pump needs a smart care process to alert the physician. This study represents the survey on PCA pump errors, AEs, and solutions for it to avoid them. The solution will automatically alert the infusion-related situation of the patients, those are taking the intravenous drug infusion at different procedure rooms in the hospitals. Moreover, it increases the safety to infusion pump with advances of decision-making in health, patient monitoring, alert notification to nursing, and productivity. This quality care can be achieved by integrating the PCA pump with other intelligent systems.  

5 June 2022
Verified
Book Chapter
Closed access
PDF file
USUsharani Shola
Usharani Shola
KAKarmel Arockiasamy
Karmel Arockiasamy

1 January 2024 in AIP Conference Proceedings
Verified
Conference Paper
Open access
PDF file
MGMihir Ashish Gupte
Mihir Ashish Gupte
NJNeelesh Ranjan Jha
Neelesh Ranjan Jha
USUsharani Shola
Usharani Shola
SAS. Asha
S. Asha
The advances in innovations of IoT and individual mobile phone facilities allow connecting the real world very easily. IoT can be used in different use cases. It would be starting from our home, connecting home appliances to the nearby grocery stores, connecting the people, things and objects using smart technology applications. All this happened because of increase in demand of internet that will collect, process it and exchange the information among all efficiently. It has created revolution all over the world and positively acting as an integral part of life. The IoT involves extending internet connectivity beyond standard devices such as desktops, laptops, smartphones, and tablets, to any range of traditionally dumb or non-internet enabled physical devices and everyday objects. The technology is embedded the devices and communicates the information all over the internet. All these information is remotely monitored and controlled. In this paper a method is proposed to Convert Non-Smart Devices into IoT Enabled devices. It is a cost effective method to control the non-smart devices through IoT communication technology. This is done using a microcontroller to convert a cheap or already installed electrical device into IoT Enabled devices. The Internet of Things can help make people’s lives easier. IoT devices are usually very expensive. Moreover, homes that already have bulbs and devices installed which are not IoT enabled would find it very uneconomic to upgrade to ones that can be controlled. Therefore, Microcontrollers can help us control these devices without needing to actually have devices that are IoT enabled. These devices can be anything like a light bulb, a fan, or any other appliances controlled from a switchboard. These devices are used in an IoT smart home scenario, without any additional Bluetooth/Wi-Fi chips being installed. After experimentation, we demonstrated that such “non-smart” devices can be utilized in a “smart” home scenario with some modifications to the way they are connected.