Papers by sridevi hosmani
Acadlore transactions on AI and machine learning, Mar 14, 2024
Skin cancer, a significant health concern globally, necessitates innovative strategies for its ea... more Skin cancer, a significant health concern globally, necessitates innovative strategies for its early detection and classification. In this context, a novel methodology employing the state-of-the-art EfficientNetB0 deep learning architecture has been developed, aiming to augment the accuracy and efficiency of skin cancer diagnoses. This approach focuses on automating the classification of skin lesions, addressing the challenges posed by their complex structures and the subjective nature of conventional diagnostic methods. Through the adoption of advanced training techniques, including adaptive learning rates and Rectified Adam (RAdam) optimization, a robust model for skin cancer classification has been constructed. The findings underscore the model's capability to achieve convergence during training, illustrating its potential to transform dermatological diagnostics significantly. This research contributes to the broader fields of medical imaging and artificial intelligence (AI), underscoring the efficacy of deep learning in enhancing diagnostic processes. Future endeavors will explore the realms of explainable AI (XAI), collaboration with medical professionals, and adaptation of the model for telemedicine, ensuring its continued relevance and applicability in the dynamic landscape of skin cancer diagnosis.
Survey on cluster based routing protocol in VANET
2017 International Conference on Electrical, Electronics, Communication, Computer, and Optimization Techniques (ICEECCOT), Dec 1, 2017
Vehicular Ad hoc Networks (VANETs) are normally derivative from Mobile Ad hoc Networks (MANETs) w... more Vehicular Ad hoc Networks (VANETs) are normally derivative from Mobile Ad hoc Networks (MANETs) which are a class of infrastructure-less network design. VANETs include vehicles or mobile nodes communicating with each other over wireless associations with or without existing infrastructure. For well-organized communication between the nodes in the network, secure clustering is essential. There are different types of cluster based routing protocols to attain efficient communication. But still there are many issues and challenges namely clustering with respect to model of bidirectional traffic during which transportation are unspecified to be approaching the RSUs from both directions, data dissemination techniques, routing, QOS guarantee, security etc. In this approach, we present a study on different clustering algorithms in VANETs.
QOS Aware Routing Protocol for VANETS
Journal of Advanced Research in Dynamic and Control Systems, 2019
R2SCDT: robust and reliable secure clustering and data transmission in vehicular ad hoc network using weight evaluation
Journal of Ambient Intelligence and Humanized Computing, Aug 5, 2021
Vehicular ad hoc networks (VANETs) gained the probable to change transportations perspectives usi... more Vehicular ad hoc networks (VANETs) gained the probable to change transportations perspectives using wireless communication network entities such as buses, cars, cell phones, traffic signals, etc. But factors like the heavy reliance on control technologies, computing, communication, severe mobility, etc. lead to several vulnerabilities in the network. The communication among two vehicles in VANETs should be secure as it mainly includes one or more intermediate vehicles to forward the data from the source to the objective. Hence the intermediate vehicles must be reliable for guaranteed data transmission. The malicious nodes may become part of such communications that can accept the data and drop (or misuse) data to create congestion. This paper proposed the Robust and Reliable Secure Clustering and Data Transmission (R2SCDT/RRSCDT) protocol to mitigate the challenges of malicious vehicles in the network. The methodology is dependent on the trust evaluation of vehicles to detect malicious nodes for secure Cluster Head (CH) selection and data transmission. The clustering performs to isolate the vehicles into clusters and choose the CH for each cluster. The CH choice performed using the trust evaluation of each vehicle and detects the attackers with less trust value. During the data transmission phase, the nodes are selected via the trust evaluation model and raise the alarm if any node has been detected as malicious. The purpose of trust-based clustering and data transmission functionality R2SCDT is to achieve guaranteed QoS performance with minimum time and control overheads. The simulation result shows the proposed model significantly improves performance compared to state-of-art security solutions of VANET.
International journal of information technology, Oct 14, 2020
The Vehicular Ad Hoc Network (VANET) technology is similar to the Mobile Ad Hoc Network (MANET) i... more The Vehicular Ad Hoc Network (VANET) technology is similar to the Mobile Ad Hoc Network (MANET) in operations. But due to high dynamics of vehicles as compare to mobile nodes in MANET, the routing protocols of MANET cannot be applicable for the VANET communications. The high mobility leads the challenges of frequent link breaks and hence poor Quality of Service (QOS) performance. The clustering based routing protocols solves this problems to some extent, however performing the efficient and lightweight clustering and cluster head (CH) selections is still the complex problem for VANETs. The main causes of such problems are related to key parameters such as mobility and geographical distances of vehicles while performing the clustering tasks. In given paper we present a lightweight CH selection and cluster formation by considering mobility and number of neighbors based on geographical distances of the vehicle key parameter at every clustering interval to achieve the stability in network. The superiority of this method is that it is simple and inclusively the part of regular routing operations. For each vehicle the weight is computed to become the CH using mobility and neighbors parameter, hence this method is called as Weight based Clustering for VANET (WCV) routing protocol. The simulation result proves the QOS efficient performance compared to the state-of-art protocols. The WCV protocols improved the overall throughput by 10% as compared to the recent clustering protocol and reduced the delay 7% approximately.
Journal of Autonomous Intelligence
Melanoma is deadly kind of skin cancer as it gets metastasized soon. It is really essential to re... more Melanoma is deadly kind of skin cancer as it gets metastasized soon. It is really essential to recognize melanoma and start treatment at early stage. It is also necessary to determine the stage of melanoma in order to treat melanoma patients. Non-invasive technique is required to detect the stage of melanoma. Proposed system presents novel technique to classify the stages of melanoma based on thickness of tumor. This system uses dimensionality reduction technique to reduce the number of features and it also uses combine approach of deep learning (DL) and machine learning (ML) algorithm which include multilayer perception (MLP) and random forest (RF). Deep learning method is always better for training as they can reduce the need for data preprocessing and feature engineering and can provide simple trainable models built using only five or six different operations. Secondly, they are scalable, as they can be easily parallelized on GPUs or TPUs and can be trained by iterating over smal...
International Journal of Scientific Research in Science and Technology
Cloud storage is one of the service of cloud comput- ing. Cloud storage services are commercially... more Cloud storage is one of the service of cloud comput- ing. Cloud storage services are commercially popular because to their advantages. It allows data owners to move data from their local computing systems to the cloud. It offers high quality and on-demand data storage services to users. A cloud is essentially a large-scale distributed system; each piece of data is replicated on multiple geographically distributed servers to achieve high availability and high performance. A cloud service provider (CSP) keeps multiple replicas for user’s data on geographically distributed servers. A main problem of using the replication technique in clouds is that it is very expensive to achieve strong consistency on a worldwide scale. In this paper, we are reviewing consistency as a service (CaaS) model, a two-level auditing architecture and a heuristic auditing strategy (HAS) that reveals as many violations as possible.
QOS Aware Routing Protocol for VANETS
R2SCDT: robust and reliable secure clustering and data transmission in vehicular ad hoc network using weight evaluation
Vehicular ad hoc networks (VANETs) gained the probable to change transportations perspectives usi... more Vehicular ad hoc networks (VANETs) gained the probable to change transportations perspectives using wireless communication network entities such as buses, cars, cell phones, traffic signals, etc. But factors like the heavy reliance on control technologies, computing, communication, severe mobility, etc. lead to several vulnerabilities in the network. The communication among two vehicles in VANETs should be secure as it mainly includes one or more intermediate vehicles to forward the data from the source to the objective. Hence the intermediate vehicles must be reliable for guaranteed data transmission. The malicious nodes may become part of such communications that can accept the data and drop (or misuse) data to create congestion. This paper proposed the Robust and Reliable Secure Clustering and Data Transmission (R2SCDT/RRSCDT) protocol to mitigate the challenges of malicious vehicles in the network. The methodology is dependent on the trust evaluation of vehicles to detect malici...
Survey on cluster based routing protocol in VANET
Vehicular Ad hoc Networks (VANETs) are normally derivative from Mobile Ad hoc Networks (MANETs) w... more Vehicular Ad hoc Networks (VANETs) are normally derivative from Mobile Ad hoc Networks (MANETs) which are a class of infrastructure-less network design. VANETs include vehicles or mobile nodes communicating with each other over wireless associations with or without existing infrastructure. For well-organized communication between the nodes in the network, secure clustering is essential. There are different types of cluster based routing protocols to attain efficient communication. But still there are many issues and challenges namely clustering with respect to model of bidirectional traffic during which transportation are unspecified to be approaching the RSUs from both directions, data dissemination techniques, routing, QOS guarantee, security etc. In this approach, we present a study on different clustering algorithms in VANETs.
Efficient Vehicular Ad Hoc Network routing protocol using weighted clustering technique
International Journal of Information Technology
Uploads
Papers by sridevi hosmani