KSKalpana Sharma

Kalpana Sharma

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Kalpana Sharma has a total of 63 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Idle Nodes Detection and Reactivation-Aware-Buffer Management in Delay-Tolerant Network Using IEMATA and SPKO

    by Ajay Prasad, Sandeep Gurung, Kalpana Sharma

    In Delay Tolerant Networks (DTNs), buffer management is crucial for optimized message delivery by focusing on message storage and prioritization. However, existing studies do not determine the state of a node, leading to buffer space wastage. Therefore, this paper presents a buffer management framework based on Idle Node Detection and Reactivation in DTN. Initially, nodes are initialized in DTN, followed by assessment of Time To Live (TTL) and message expiry detection. Non-expired and new messages are then load-balanced using Kolmogorov-Smirnov Logarithmic Jaynes K-Means (KSLJK-Means). Subsequently, the load-balanced messages are signed with the Digital Logarithmic Double Hashing Probing Signature Algorithm (DLDHPSA). Before message transmission, the idle/active state of nodes is identified using the Idle Exponential Moving Average Timer Algorithm (IEMATA). If a node is idle, it is activated via periodic beaconing. Next, messages are prioritized using Lorentzian Raised Cosine Fuzzy (LRC-Fuzzy). Afterward, messages are allocated to buffers following successful digital signature verification. Buffer utilization rates are estimated to determine available space; if space is available, messages are stored in the buffer. If the buffer is full, messages are dropped according to the Message Utility Score (MUS) based drop policy. The Shubert Pied Kingfisher Optimizer (SPKO) is employed for buffer allocation. The proposed model achieves a low buffer allocation time of 2165 ms. It offers significant benefits when deployed in satellite communications, vehicular networks, and IoT systems. Overall, the model provides resource-centric solutions to enhance the reliability of DTN environments.

  • Top Cited Papers
    Open Access

    AI-Powered Career Guidance: A Scalable Model for Personalized Recommendations

    by Minakshi Roy, Kalpana Sharma

    The primary objective of this study is to enhance career guidance in higher education institutions (HEIs) by integrating Holland’s RIASEC model with advanced machine learning algorithms. Traditional career counselling methods, which often rely on matching interests with vocational categories, struggle to accommodate the complexities of the modern job market. This works aims to bridge that gap by utilizing data-driven techniques to provide more accurate, personalized, and scalable career recommendations. By aligning students’ interests with real-world employability factors, the study seeks to improve the effectiveness of career decision-making processes in HEIs. The study uses the RIASEC model to identify student’s professional interests and uses three well-known machine learning algorithms: Decision Trees, XGBoost, and Support Vector Machine (SVM) to predict students’s; career pathways. To improve interpretability and reduce categorization mistakes, the models were further refined, making the results easier for HEI administrators to comprehend. In terms of prediction accuracy, the XGBoost algorithm outperformed other machine learning models as well as conventional techniques. It performed better in suggesting career pathways that closely matched participants’s interests, as seen by its greater hit rates and smaller Euclidean distances. Promising outcomes were also displayed by the SVM algorithm, notably an increase in prediction accuracy above traditional career advising models. Graphs and charts, among other visual aids, were utilized to make complex patterns in the data easier to comprehend and analyze for administrators. Overall, compared to conventional RIASEC-based models, the machine learning-enhanced framework offered more precise and useful career choices. Applying machine learning techniques might significantly increase the accuracy and customisation of career advising in the RIASEC model. HEIs may provide more accurate job suggestions by utilizing algorithms like SVM and XGBoost, which efficiently match student’s interests with future employability. Furthermore, the study offers organizations helpful policy recommendations that support the use of data- driven methods in career counseling services. In a labor market that is changing quickly, our insights help students and educational institutions make more strong and informed career decisions.


  • Swin-ResNeST: A CNN-Transformer-Based Hybrid Model for Skin Image Lesion Segmentation

    by Aaditya Lochan Sharma, Kalpana Sharma, Kunal Purkayastha, Palash Ghosal

  • Open Access

    QWLCPM: A Method for QoS-Aware Forwarding and Caching Using Simple Weighted Linear Combination and Proximity for Named Data Vehicular Sensor Network

    by Dependra Dhakal, Kalpana Sharma

    The named data vehicular sensor network (NDVSN) has become an increasingly important area of research because of the increasing demand for data transmission in vehicular networks. In such networks, ensuring the quality of service (QoS) of data transmission is essential. The NDVSN is a mobile ad hoc network that uses vehicles equipped with sensors to collect and disseminate data. QoS is critical in vehicular networks, as the data transmission must be reliable, efficient, and timely to support various applications. This paper proposes a QoS-aware forwarding and caching algorithm for NDVSNs, called QWLCPM (QoS-aware Forwarding and Caching using Weighted Linear Combination and Proximity Method). QWLCPM utilizes a weighted linear combination and proximity method to determine stable nodes and the best next-hop forwarding path based on various metrics, including priority, signal strength, vehicle speed, global positioning system data, and vehicle ID. Additionally, it incorporates a weighted linear combination method for the caching mechanism to store frequently accessed data based on zone ID, stability, and priority. The performance of QWLCPM is evaluated through simulations and compared with other forwarding and caching algorithms. QWLCPM’s efficacy stems from its holistic decision-making process, incorporating spatial and temporal elements for efficient cache management. Zone-based caching, showcased in different scenarios, enhances content delivery by utilizing stable nodes. QWLCPM’s proximity considerations significantly improve cache hits, reduce delay, and optimize hop count, especially in scenarios with sparse traffic. Additionally, its priority-based caching mechanism enhances hit ratios and content diversity, emphasizing QWLCPM’s substantial network-improvement potential in vehicular environments. These findings suggest that QWLCPM has the potential to greatly enhance QoS in NDVSNs and serve as a promising solution for future vehicular sensor networks. Future research could focus on refining the details of its implementation, scalability in larger networks, and conducting real-world trials to validate its performance under dynamic conditions.

  • Open Access

    Resolution Enhancement of Brain MRI Images Using Deep Learning

    by Minakshi Roy, Biraj Upadhyaya, Jyoti Rai, Kalpana Sharma

    One of the most widely used imaging techniques in medicine is magnetic resonance imaging (MRI). It is a tool that doctors use to comprehend human anatomy and carry out more accurate analyses. In the study of brain anatomy, image processing super resolution technology has become important to overcome physical restrictions due to image deterioration caused by hardware constraints, lengthier scanning periods, and artefacts. Super resolution is an approach to raise an image’s resolution while improving the image’s quality from a low-resolution (LR) image to a higher-resolution (HR) image. The study provides an overview of deep learning techniques for creating super-resolution (SR) MRI brain images. A widely used deep learning (DL) technique, accessible brain MRI dataset, and quantity evaluation matrices have been presented, mostly used for image super resolution. Factors affecting hardware constraints and artifacts, including magnetic field homogeneity, gradient nonlinearity, radiofrequency (RF) coil sensitivity, signal-to-noise ratio (SNR), and gradient coil performance, have been taken into account. This research focuses mostly on brain MRI images as a contribution to the medical industry for super resolution.


  • Open Access

    An Open-Source Platform for Real-Time Preliminary Diagnosis amongst Adults using Data Analytics

    by Kalpana Sharma, Sital Sharma, Sunil Dhimal, Biswaraj Sen, Ashis Pradhan, Vikash Kumar Singh

    Depression can be defined as a mental health disorder characterized by persistently depressed mood, loss of interest in activities, causing significant impairment in daily life. Technical intervention to screen depression in non-clinical population which records, classify depression on the basis of severity and provide features or predictors that discriminate the classification of depression among non-clinical population comprising of college students is the main area of the study. Beck Depression Inventory – II (BDI-II), as per Diagnostic and Statistical manual of Mental disorder (DSM IV) is used to screen depression and its severity. Indicators are determined on the basis of how well the features or predictors can discriminate the classes of depression severity. Providing quality indicators which help in supporting the process can be considered as symptoms for screening depression. Descriptive analytics is used in order to find the underlying pattern of the responses captured, factor analysis groups variables on the basis of correlation between patterns of the responses to reduce dimension. The approach for supervised descriptive analysis method that takes BDI-II questions as features and refine the features using information gain and linear discriminant analysis as feature selection algorithm. The classification of severity of depression is done using Support vector machine (SVM)..

  • IoT-Based Landslide Monitoring System Using LiDAR Sensors: A Review

    by Bishal Gupta, Kalpana Sharma, Tawal Koirala, Sital Sharma