P. Ajitha

P. Ajitha

Auto-generated profile, based on publicly available information

P. Ajitha

Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai, India

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
1 September 2025 in Natural and Engineering Sciences
Verified
Journal Article
Open access
DHDebashish Hota
Debashish Hota
KRK Rajasekar
K Rajasekar
TPTarun Parashar
Tarun Parashar
SSSakshi Sobti
Sakshi Sobti
ARAshutosh Roy
Ashutosh Roy
PAP. Ajitha
P. Ajitha
Forecasting habitat suitability for species under scenarios of climate change is a crucial approach for biodiversity conservation and resource management. This study used the Maximum Entropy (MaxEnt) modelling algorithm to evaluate and predict habitat suitability for [target species] among current and projected climate conditions. Environmental data were extracted from authenticated global databases, and a range of environmental variables, including bioclimatic and topography, were selected to train the MaxEnt model. Future climate data were mapped for the years 2050 and 2070, based on projections from multiple General Circulation Models (GCMs) and Representative Concentration Pathways (RCPs) 4.5 and 8.5. The MaxEnt model's accuracy was estimated using the Area Under the Receiver Operating Characteristics Curve (AUC), and all models demonstrated high predictive performance. The predicted future habitat suitability and estimated percentage changes, distinctly demonstrated significant range shift with contraction of potential suitable habitat or expansion depending on the scenario. [key environmental variables, e.g., temperature seasonality, annual precipitation] were the most important environmental variables to influence distribution in the models. Ultimately, it was clear that the species modeled could be vulnerable to climate change, both in the present and in the future. Considering the potential impacts on biodiversity, it would be prudent to research predictive modeling in conservation planning further. Predictive modeling can yield beneficial outcomes, particularly for considering habitat changes in response to climate impacts, and may aid conservation biologists in developing adaptive responses to reduce the effects of climate change.

17 October 2024
Verified
Book Chapter
Closed access
TMT. Vamshi Mohana
T. Vamshi Mohana
HBH. S. Abzal Basha
H. S. Abzal Basha
HBH. K. Bhargav
H. K. Bhargav
MPMadhu Patil
Madhu Patil
PAP. Ajitha
P. Ajitha
AKArsala Zamir Khan
Arsala Zamir Khan
This chapter examines how combining time series study and deep learning can optimize business models using traffic information. It starts by explaining why traffic data is important in today's business settings and lists old ways to analyze it. The chapter continues by exploring how to use deep learning methods like recurrent neural networks (RNNs) and convolutional neural networks (CNNs) to predict and recognize patterns in traffic. Case studies and examples show how useful these methods are in making business operations more efficient, enhancing the customer experience, and helping make better business decisions. It explores upcoming trends and obstacles to using deep learning to help businesses grow.

10 September 2024
Verified
Book
Closed access
PAP Ajitha
P Ajitha
The evolution of search engines from simple keyword-based systems to more sophisticated semantic-based models marks a significant advancement in the field of information retrieval. This monograph presents a comprehensive study on the development of a Semantic-Based Pattern Search Engine, designed to enhance the accuracy and relevance of search results by understanding the contextual and semantic relationships within data. The research encompasses the creation of various engines, including a concept search engine, topic search engine, affective term detection engine, and emotion prediction engine. Additionally, the application of these technologies in online opinion mining is explored, demonstrating their practical value. The findings of this research contribute to the broader understanding of semantic search and offer valuable insights for future advancements in the domain. Keywords: Semantic-Based Pattern Search Engine, Concept Search Engine, Topic Search Engine, Affective Term Detection, Emotion Prediction, Online Opinion Mining, Information Retrieval, Semantic Search, Contextual Search