Manuscripts

Recent Papers

Research Paper

Comparative Yield Analysis of Black Pepper (Piper Nigrum L.) Genotypes of Uttara Kannada District, Karnataka

Indian black pepper fetches a premium price in major international spices markets because of its intrinsic quality. But the continuous use of low yielding cultivars, non-availability of planting materials, losses due to biotic and abiotic stresses and also non adoption of appropriate agronomic practices are some of the prominent factors contributing to lower productivity of black pepper in India. There is no reliable information on the availability of improved local genotypes of Uttara Kannada district for the arecanut based mixed system of cultivation in Karnataka. However, some of the superior genotypes are believed to be high yielders with superior quality and tolerant to drought situation, pest and diseases, that may be available in the farmers fields. In this connection present experiment conducted at Uttara Kannada district of Karnataka using 52 genotypes. Among the genotypes, green pepper yield per vine was the highest in Panniyur 1 and was on par with the genotypes viz., SV 11, SV 7 and Kudure Bala. Whereas, maximum dry pepper yield per vine was recorded by the genotype SV 11 and was on par with genotype Kudure Bala, national check var. Panniyur 1 and SV 7. However, the highest recovery of black pepper was observed in farmer variety Sigandini (37.74 %) and was at par with the genotypes Magod Jaddi, Kudure bala, SV 11, Sambar Dadiga, Kari Dadiga, Havali Special and Kurimale compared to national var. Panniyur 1

Published by: Sudheesh Kulkarni, N K Hegde, Laxminarayan Hegde, Vijayakumar Narayanpur, Mukesh Chavan, Sadananda G K, Prashantha A, Mahantesh Naika

Author: Sudheesh Kulkarni

Paper ID: V10I5-1385

Paper Status: published

Published: October 27, 2024

Full Details
Research Paper

User-Friendly Data Migration: An Integrated GUI Tool For Different Excel Formats to PostgreSQL Database Conversion

The exponential growth of data in various formats has necessitated efficient methods for data management and integration into relational databases. Traditional approaches to importing data from Excel and CSV files into PostgreSQL can be cumbersome and time-consuming, often requiring intricate coding or manual input. This paper introduces a user-friendly graphical user interface (GUI) application that automates the import process, thereby addressing these challenges. The application allows users to effortlessly select folders containing multiple data files, streamlining the data ingestion process. By employing Python libraries such as Pandas and SQLAlchemy, it facilitates seamless data transfer while ensuring data integrity. Significant benefits include enhanced productivity through automation, reduced human error, and improved accessibility for users with varying technical skills. Ultimately, this tool not only simplifies the workflow for researchers and data analysts but also emphasizes the growing need for effective data handling solutions in an increasingly data-driven world

Published by: Sushil Chandra, Rajeev Sonkar, Pragati Srivastava

Author: Sushil Chandra

Paper ID: V10I5-1371

Paper Status: published

Published: October 27, 2024

Full Details
Research Paper

IoT-Based Data Logging System using Cloud

The shift from the digital to the smart era is ongoing due to the ongoing advancements in information technology. IoT is being incorporated into government business operations. Remote data monitoring and measuring systems are essential for the business sector. Data gathering in the manufacturing of electronic systems requires the usage of data loggers. Data loggers, which are gadgets that record different data like temperature and humidity, are employed for this purpose. To collect data from the data logger, create a framework. The program is made to collect data continuously and in real time without interfering with normal business operations. Sensor data is gathered and sent to the system for further processing.

Published by: Alok More, Atharva Khopade, Yash Kakade, Vivek Hande, Ritesh Nikam

Author: Alok More

Paper ID: V10I5-1388

Paper Status: published

Published: October 27, 2024

Full Details
Research Paper

AFBAP : Attention For Binding Affinity Prediction

This paper introduces the AFBAP model, a novel machine learning model that leverages transfer learning benefits from pre-trained transformers ProtBert and ChemBERTa for feature extraction, and utilises a CNN-based prediction module prefaced by a task-adaptive feature transformation to predict protein-ligand binding affinity with state-of-the-art accuracy. It accepts one-dimensional sequential inputs for both proteins and ligands, in the form of amino acid strings and SMILES strings respectively. AFBAP’s performance over a number of datasets using standard evaluation metrics validates the fact that the model achieves higher accuracy with lower training times and lower compute. AFBAP democratizes access to computational methods of optimizing drug discovery, paving the way for rapid and accessible innovation in drug discovery research.

Published by: Harihar Prasad

Author: Harihar Prasad

Paper ID: V10I5-1386

Paper Status: published

Published: October 27, 2024

Full Details
Case Study

Building a Comprehensive Enterprise Data Lake Architecture

Organizations need to be driven by “data” more than ever to stay ahead of the curve and be competitive. With the tremendous data growth of data both by volume as well as variety, it is no longer sustainable to store the data in traditional data warehouses as they are not designed to be scalable. Data lake architecture which is typically built on top of cheap hardware is the most economically viable solution for this problem as they are elastic and can scale up based on the increasing data needs of an organization. While the solution might seemingly look straightforward there are many nuances associated with this shift in paradigm and a very careful and thoroughly thought through design is necessary when building an enterprise data lake architecture. This white paper explores various aspects related to setting up a comprehensive enterprise data lake which can steer towards the success of the organization. It also touches up on the pit falls and opportunities based on the research and case studies relevant in this area. Finally, a summary and outlook on data lake management is presented to the readers.

Published by: Ramla Suhra

Author: Ramla Suhra

Paper ID: V10I5-1324

Paper Status: published

Published: October 25, 2024

Full Details
Review Paper

Crops and Weeds Detection System using Machine Learning

Weeds are one of the most harmful agricultural pests for crops. For the waste of crops, Weeds are highly responsible. For the solution of this problem research community as build up a crops and weeds detection system. This technology is build up by using Machine learning. In this paper, we present a literature review on current state-of-the-art ML techniques for weed detection. Our study presents a detailed analysis of ML.

Published by: Shrusti Jasani, Spandan Kathiriya, Sneh Patel, Ms. Manisha Vasava

Author: Shrusti Jasani

Paper ID: V10I5-1372

Paper Status: published

Published: October 25, 2024

Full Details