- Recommender Systems and Techniques
- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Software Engineering Research
- Software Reliability and Analysis Research
- Imbalanced Data Classification Techniques
- Remote Sensing and Land Use
- Remote Sensing in Agriculture
- Remote-Sensing Image Classification
- Complex Network Analysis Techniques
- Blind Source Separation Techniques
- Advanced Clustering Algorithms Research
- EEG and Brain-Computer Interfaces
- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Misinformation and Its Impacts
- Image and Video Quality Assessment
- Software System Performance and Reliability
- Smart Grid and Power Systems
- Smart Grid Energy Management
- Advanced Graph Neural Networks
- Land Use and Ecosystem Services
- Caching and Content Delivery
- Advanced Malware Detection Techniques
- Advanced Steganography and Watermarking Techniques
KIIT University
2018-2024
XIM University
2021
<span>One of the most commonly used techniques in recommendation framework is collaborative filtering (CF). It performs better with sufficient records user rating but not good sparse data. Content-based works well dataset as it finds similarity between movies by using attributes movies. RBM an energy-based model serving a backbone deep learning and prediction. However, prediction preferable single model. The hybrid achieves results integrating more than one This paper analyses weighted...
Objectives: This study is about developing an accurate and efficient NDVI forecasting framework using remote sensing data from the Landsat 8 satellite. The objective to vegetation changes over time compare performance of classical statistical models (ARIMA) with deep learning (LSTM, RNN) in predicting trends. focuses on Kendrapara district Odisha, India, investigates both weekly monthly variations improve granularity. Method: proposed methodology involves acquiring imagery for area 2015...
Objectives: The primary objective of this study is to evaluate and compare the performance machine learning deep models for Land Use Cover (LULC) classification using remote sensing data. Specifically, it assesses Support Vector Machine (SVM), XGBoost, an ensemble model (SVM + XGBoost), a Deep Neural Network (DNN) on pre-processed hyperspectral datasets (Pavia University, Indian Pines) raw satellite imagery from Twin Cities Odisha, India. Method: follows systematic workflow, including data...
<p>An ensemble model has been proposed in this work by combining the extreme gradient boosting classification (XGBoost) with support vector machine (SVM) for land use and cover (LULCC). We have used multispectral Landsat-8 operational imager sensor (OLI) data six spectral bands electromagnetic spectrum (EM). The area of study is administrative boundary twin cities Odisha. Data collected 2020 classified into seven classes/labels: river, canal, pond, forest, urban, agricultural land,...
BACKGROUND: The internet has become an integral part of our lives, especially for adolescents who use it extensively various purposes such as socializing, entertainment, and education. However, excessive unmonitored can negatively affect adolescents' health. Sleep is a vital component health, but nowadays, youth often neglect sleep due to social media binge-watching. Excessive exposure expansive content contribute negative impacts may lead poor mental OBJECTIVES: To study the level usage...
Power system deregulation enables the power industry to provide residential customers choose retailing electricity plan. This allows competition among retailers or traders and also minimises energy expenditure with quality of services. We have proposed an XGBoost regression model for tariff plan recommendation. Firstly, basic statistical features is compared support vector (SVR), decision tree (DT), Bayesian ridge KNN model. Secondly, performance extensively studied by combining from other...
Diabetes is a chronic disease that has been impacting an increasing number of people throughout the years. Each year, it results in huge deaths. Due to fact late diagnosis severe health complications and significant deaths each critical develop methods for early detection this pathology. As result, critical. Machine learning techniques aid prediction diabetes. However, machine models do not perform well with missing values dataset. Imputation improves outcome. In work, we have used extreme...
Epilepsy causes repeated seizures in an individual's life, which transient irregularities the brain's electrical activity. It results different physical symptoms that are abnormal. Various antiepileptic drugs fail to minimize patient seizures. The electroencephalogram (EEG) signal recordings provide us with time-series data set for epileptic seizure detection and analysis. These signals highly nonlinear inconsistent, they recorded over time. Predicting ictal period (seizure at time of...
Many centroid-based clustering algorithms cannot guarantee convergence to global optima and suffer in local optimal cluster center because they are sensitive outliers noise. A heuristic technique like particle swarm optimization (PSO) can find solution with the cost of extensive computation. In this paper, a PSO based algorithm (PSOBC) has been proposed avoid analysis. The utilizes both search capability K-Means. Proposed method tested various multidimensional datasets performance comparison...
The Extreme Learning Machine (ELM) has sparked a lot of attention since it can learn fast and be applied to various problems. In this study, convolutional layer-based extreme learning machine (CELM) architecture been designed implemented recognize handwritten characters reduce execution time. Furthermore, validate the robustness approach, are chosen from four different languages, mainly Indian including English. recognition performed on both numerals alphabets. experimental results regarding...
Recommender System or Recommendation Engine gaining popularity as it can tackle information overload problem. Initially was considered a domain of Information Retrieval system and limited to few applications. With the advancement different state-of-the-art modeling approaches recommender be applicable many application domains. Movie (MRS) is widely explored used by streaming service providers like Netflix, Amazon Prime, YouTube more. This makes use users’ data explore recommends personally...
Abstract The Follower Link Prediction is an emerging application preferred by social networking sites to increase their user network. It helps in finding potential unseen individual and can be used for identifying relationship between nodes With the rapid growth of many users media, which follow leads information overload problems. Previous works on link prediction problem are generally based local global features a graph limited smaller dataset. number media increasing extraordinary rate....
Uncontrolled and fast rate of growth population, industry, deforestation causes a great change in Land Use Cover (LULC) developed developing countries. Changes LULC have become vital aspect conventional strategies for environmental monitoring. To conserve existing natural resources better understand the implications soil water resource overexploitation, land cover mapping detection exercise was conducted research region, namely Puri District, Odisha. Satellite photos from 1 January 2019 to 4...
Software product development is an indispensible part of the society we live in. In order to produce quality products economically, efficiently and within targeted completion date, estimation for needs be fairly precise. This work comes up with quite a viable efforts current day web applications. The modus operandi in this collects facts existing Unified Modeling Language Sequence models generated Object based systems. These facts, combination customized regression analysis programs...
Bankruptcy is a legal proceeding initiated when an entity fails to repay their outstanding financial obligations its creditors. Given the growing intricacy of market, precise identification companies susceptible bankruptcy emerges as pivotal concern for investors, creditors, and other regulatory authorities alike. This study endeavors discern likelihood facing by analysis diverse data metrics, encompassing ROA (Return on Asset), Gross Margin, Profit Rate, equally significant parameters....