SYSaneh Lata Yadav

Saneh Lata Yadav

*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


Saneh Lata Yadav has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Cryptanalysis-resistant SDN architecture for dynamic traffic management using applied algebra and elliptic curve cryptography for secure tenant isolation

    by Ashok Saini, Vikas Thada, Sanat Jain, Swati, Raghav Mehra, Prashant Vats, Saneh Yadav

    Software-Defined Networking (SDN) security is enhanced using algebraic structures and elliptic curve cryptography for secure, scalable, multi-tenant communicati...

  • Deep Learning for Handwritten Digit Recognition: A Convolutional Neural Network Approach

    by Saneh Lata Yadav, Aman Jatain, Tarang Balani, Tanvi Chawla, Yogita Yashveer Raghav

  • Open Access

    Benchmarking Machine Learning Models for Obesity Classification with SHAP-Based Interpretability

    by Vaibhav Gandhi, Yogesh Chaudhari, Ajay Kumar, Hitarth Revakar, Ankit D. Oza, Saneh Lata Yadav

    Obesity is a worldwide epidemic posing a significant threat to the general population in terms of chronic metabolic diseases and low longevity. Clinical intervention and preventive health care require the early identification and proper risk prioritization. This paper compares six machine learning models, namely, Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbors, and Gradient Boosting using a publicly available obesity dataset in Mexico, Peru, and Colombia (n = 2111, 17 attributes). To overcome this issue of the dominance of certain classes, the Synthetic Minority Oversampling Technique (SMOTE) was used during the pre-processing to give fair consideration of the model. Gradient Boosting was the best with highest 95.93 percent accuracy, 0.96 precision, 0.96 recall and 0.96 F1-score among all the models. SHAP (SHapley Additive Explanations) analysis was used in increasing the explain ability with each predictor indicating the most significant determinant; frequent high-calorie food consumption (FAVC, |human|) (0.18), physical activity frequency (FAF, 0.15), family history of overweight (0.12), and hydration level (0.09) significance. These quantitative insights do not only enhance interpretability, but also conform to clinical knowledge of behavioral and genetic risk factors. The suggested interpretable framework can provide a strong and clear background to the design of data-driven decision-support tools that can be used to prevent obesity, develop individual counselling, and design the policies needed by the population.


  • Open Access

    A Smart Agricultural System for Predictive Plant Health Diagnostics Using Machine Learning Techniques

    by Sushil Kumar, Saneh Lata Yadav, Aman Jatain, Tanvi Chawla, Yogita Yashveer Raghav

    Plant diseases have presented substantial hurdles to the agricultural industry in recent years, potentially resulting in lower crop yield and financial losses. Traditional disease detection methods usually rely on manual inspection, which can be time-consuming and prone to human mistakes. Our AI- Powered Plant Disease Detection System overcomes these issues by leveraging cutting-edge machine learning and artificial intelligence technology. This technology uses powerful image recognition algorithms to swiftly and precisely identify and diagnose plant illnesses. By analyzing photos of plant leaves and other components, the AI model may be able to detect early sickness symptoms, allowing for better disease control and earlier intervention. Plant diseases have a considerable influence on agricultural output, resulting in monetary losses and food shortages. Early and precise identification of plant illnesses is critical for prompt intervention, which can reduce the spread of infections and increase crop output. Manual examination is frequently used in traditional plant disease detection procedures. With advances in machine learning (ML) and deep learning (DL), automated plant disease detection systems have emerged as reliable options. Using datasets including photos of healthy and sick plants, the suggested technique seeks to achieve high accuracy, precision, recall, and F1-score while minimizing misclassification as indicated by the confusion matrix. The technique investigates a variety of machine learning and deep learning models, including basic methods such as Support Vector Machines (SVM) and Random Forests (RF), as well as sophisticated Convolutional Neural Networks (CNNs) and transformer-based architectures. Preprocessing methods like feature extraction and picture augmentation are used to make the models more resilient. The suggested technique is suited for practical implementation in agricultural settings as evaluation metrics guarantee that it not only detects illnesses with high precision but also reduces false positives and negatives.

  • Open Access

    Transforming Healthcare Delivery: Assessing the Role of E-Governance Strategies in IOMT and AIML-Based Medical System Administration during the Pandemic in the Indian Subcontinent

    by Susheela Vishnoi, Saneh Lata Yadav, Ashok Kumar Saini, Prashant Vats

    This paper investigates the transformative impacts of e-governance strategies on the Internet of Medical Things (IOMT) and IOMT-based medical system administration in the context of the COVID-19 pandemic within the Indian Subcontinent, leveraging applications of Artificial Intelligence and Machine Learning (AIML). As the pandemic continues to strain healthcare systems worldwide, effective utilization of digital technologies becomes paramount in ensuring efficient healthcare delivery. E-governance initiatives play a crucial role in facilitating the integration of IOMT devices and AIML algorithms into medical systems, thereby enhancing healthcare accessibility, quality, and responsiveness during crises. This study examines the implementation and outcomes of e-governance measures in leveraging IOMT technologies and AIML applications to address pandemic-related challenges in the Indian Subcontinent's healthcare sector. Through a comprehensive analysis, it elucidates the synergistic relationship between e-governance strategies, IOMT adoption, and AIML utilization, highlighting their collective contributions to strengthening medical system administration and mitigating the impact of the pandemic on public health. E-Governance began by offering citizens e-services that help them deal with the challenges of technological advances, and since then has extended to include consumer networking, demographic forecasting, financial management, and e-healthcare operations. E-governance is defined as the provision of social programs via the use of information systems, which indicates the amount, and sharing of information, the implementation of innumerable electronic systems, and subtypes between both the government and its constituents, the business and government environments, and government and state organizations. Using SPSS tools to collect data from 433 employees in India's tourist industry, the links mentioned above were verified. The data reveal that the information governance approach does have a significant impact on health catastrophes, particularly joblessness negatively forecasting emergencies. As per the data, parental involvement reduced the link between E-Governance programs and rising unemployment. The study's outcomes backed up this theory, indicating that employees with strong family support are less likely to be unemployed than those with a lower degree of interpersonal assistance.


  • Information Retrieval in the Hidden Web

    by Shakeel Ahmed, Shubham Sharma, Saneh Lata Yadav

    Information retrieval is finding material of unstructured nature within large collections stored on computers. Surface web consists of indexed content accessible by traditional browsers whereas deep or hidden web content cannot be found with traditional search engines and requires a password or network permissions. In deep web, dark web is also growing as new tools make it easier to navigate hidden content and accessible with special software like Tor. According to a study by Nature, Google indexes no more than 16% of the surface web and misses all of the deep web. Any given search turns up just 0.03% of information that exists online. So, the key part of the hidden web remains inaccessible to the users. This chapter deals with positing some questions about this research. Detailed definitions, analogies are explained, and the chapter discusses related work and puts forward all the advantages and limitations of the existing work proposed by researchers. The chapter identifies the need for a system that will process the surface and hidden web data and return integrated results to the users.

  • Sensor data fusion and clustering : A congestion detection and avoidance approach in wireless sensor networks

    by Saneh Lata Yadav, R. L. Ujjwal

    A wireless sensor network is gaining more popularity as it is easy to maintain, manage and inexpensive to establish. A group of sensor nodes with sensing and computing capability are deployed in network. When these nodes are deployed in remote areas, an adequate energy of the nodes becomes major issue. As the sensor nodes are battery operated, so energy is an important resource that must be utilized efficiently. Therefore, the most preferable method to tackle such issue efficiently is to divide the network into clusters and data communication by data fusion techniques. Data fusion is a technique which enables gathering data from several sensor nodes thus to provide a unified scenario in order to reduce redundancy of data which consumes lots of energy. The proposed method is clustered based data fusion to avoid congestion. One node from each cluster is elected as cluster head which is elected after observing various parameters like enduring energy of the node, distance from base station, and chances of traffic in near future. The cluster head node gathers data from cluster members hence applies local level data fusion on this information and then forward it to base station for final decision level data fusion. This method improves the reliability of data, reduced traffic and improve network link. The level of congestion is predicted periodically. It is taken as congestion indicator. This method helps in reducing power consumption and packet drop rate. The performance of this technique is investigated to prove its superiority to different state of art algorithms. The performance is validated using numerical analysis derivations and MATLAB.