The Emergence of chatbots represents a pivotal advancement in Artificial Intelligence (AI) and Machine Learning (ML), impacting various sectors like Healthcare, Sports, Automation, and Education. Specifically, a recent application in education involves crafting chatbots capable of engaging with students, aiming to enhance the learning experience. This research paper targets Bachelor's programs, particularly in Computer Science Engineering and allied programs, by introducing a software bot named AI Sciences chatbot. Leveraging NLTK-Corpus library and Machine Learning models, this bot focuses on aiding the learning process of fundamental AI Science concepts within B.Sc Computer Science. The proposed system is to develop an online software bot that enables direct interaction between users and the bot, empowering students to pose queries without human intervention by using NLTK features and the ML model. The chatterbot is capable and proficient in comprehending and responding to inquiries based on a pre-defined dictionary, supplementing its knowledge by autonomously seeking information. The primary objective of this research is to implement a software bot within an online learning platform, facilitating seamless access for students to seek guidance, ask questions, and receive support 24/7, fostering a more efficient approach to their studies without constant human intervention.

Keywords : Python. Artificial Intelligence, ML, AI sciences chatbot, NLTK-Corpus, Punkt, Tokenization, BS4.

Authors : S.S.D. Maha Laxmi

Title : A Chatbot using NLTK without Human Interaction

Volume/Issue : 2024;1(1 (January - March))

Page No : 25 - 34

Magnetic Resonance Imaging (MRI) is a medical imaging technique used to make the diagnosis of a disease, Schizophrenia, and Multiple Sclerosis. To address the above issues, a blind IQA metric termed as the Nonreference Quality Index for Denoised Images (NQIDI), It is suggested in this paper for evaluating the standard of denoised MR pictures.Precise assessment of residue noise and edge sharpness within denoised MR images are required for the calculation of NQIDI. Hence, a principal components-based noise estimation model for quantifying the strength of noise in MR images and a quantitative IQA metric termed as Objective Measure of Sharpness of Edges (OMSE) that accounts for the perceptual sharpness of MR images are also introduced in this thesis. This paper an anonymous IQA measure, the No Reference Quality Index for Denoised Pictures (NQIDI), for evaluating the quality of denoised magnetic resonance pictures in order to overcome the aforementioned problems. Precise assessment of residual noise and edge sharpness in the denoised MR images are required for the calculation of NQIDI. Therefore, this thesis also introduces a quantitative IQA measure called the Objective Measure of Sharpness of Edges (OMSE), which accounts for the subjective sharpness of MR images, and a principle components-based noise estimation model for measuring the level of noise in MR images. The thesis includes three scientific contributions: a no-reference measure for evaluating the quality of denoised MR pictures, an objective metric for assessing the sharpness underlying edges in MR images, and a noise model for predicting the statistics and noise in MR images. The NQIDI is the algebraic product of two different quality factors, known as the Noise Suppression Factor (NSF) and the Edge-Preservation Factor (EPF), or Gradient Singular Value Decomposition (GSVD). The NSF is calculated using the standard deviation of latent noise in the picture and the standard dispersion of noise in the input image, whereas the EPF is calculated using the sharpness of edges in both the noisy output and denoised images.

Keywords : CNN, Machine Learning, X-ray image, Gradient Boost Algorithm, Python.

Authors : R. Obhuakonda Reddy , N. Sreevani , B. Santhosh Kumar , Y. Monoohar Reddy

Title : Noise Estimation Model for Quantifying the Strength of Noise in MR Images Using Objective Measure of Sharpness of Edges

Volume/Issue : 2024;1(1 (January - March))

Page No : 15 - 19

This paper proposes a new technique for energy managing in hybrid power systems. The proposed management system is designed to manage the power flow between the hybrid power system in order to satisfy the load requirements based on artificial neural network (ANN) and fuzzy logic controllers. The neural network controller is employed to achieve the maximum power point tracking (MPPT) for different types of sources like Photovoltaic(PV), wind energy and Fuel cell at DC-link.The developed fuzzy logic controller (FLC)-based MPPT method and ANN based method was assessed using a hybrid system comprised PV panels, wind turbine (WT) and Fuel Cell with DC–DC converters. The dynamic behaviour of the proposed model is examined under different operating conditions. The analysis of the proposed hybrid system provides higher power as compared to PV, WT and FC systems at different loads. This research is utilized for the stand-alone system as well as a grid. ANN gives a better performs compared to the Fuzzy in the MPPT method for the PV panels, wind turbine (WT) and Fuel Cell with DC–DC converters for the DC loads. The result analysis of the Fuzzy and the ANN are simulated in the MATLAB/Simulink.

Keywords : Hybrid Power Supply, ANN, ML, Python, Non-Conventional Energy Sources

Authors : K. Krishna Reddy , S. Hareesh

Title : An Integrated Hybrid Power Supply For Distributed Generation Applications Fed by Non Conventional Energy Sources

Volume/Issue : 2024;1(1 (January - March))

Page No : 10 - 14

Effective SARS- CoV- 2 webbing allows for a speedy and accurate opinion of COVID- 19, reducing the cargo on healthcare systems. In order to estimate the threat of infection, vaticination models that integrate numerous variables have been developed. These are intended to prop medical help around the world in triaging patients, particularly in areas where healthcare coffers are scarce. We developed a machine-learning algorithm that was trained on the records of 51,831 people who had been tested( of whom 4769 were verified to have COVID- 19). The data in the test set came from the coming week( tested individualities of whom 3624 were verified to have COVID- 19). Overall, we created a model that detects COVID- 19 cases using simple variables available by asking introductory questions grounded on civil data intimately released by the Israeli Ministry of Health. When testing coffers are limited, our approach can be used to precedence testing for COVID- 19, among other effects. In this design, we proposed the CNN grounded x-ray image for the discovery of covid and xgboost for the discovery of symptoms.

Keywords : CNN, Machine Learning, X-ray image, Gradient Boost Algorithm, Python

Authors : Dekka Satish , K. Narasimha Raju

Title : Covid-19 Identification and Surveillance System using AI

Volume/Issue : 2024;1(1 (January - March))

Page No : 5 -9

Harmonic amplification presents a significant challenge in power system networks, often leading to power quality degradation. This study aims to address and mitigate the impact of such harmonic disturbances. A novel control strategy based on artificial intelligence (AI) is introduced and integrated into a Distribution Static Synchronous Compensator (DSTATCOM). As a type of Flexible AC Transmission System (FACTS) device, the DSTATCOM provides efficient reactive power compensation, playing a key role in suppressing or minimizing harmonic amplification within the network. The performance and effectiveness of the proposed approach are validated through simulations carried out in the MATLAB/Simulink environment.

Keywords : Distribution Static Synchronous Compensator (DSTATCOM), Neural Network, Harmonics, Power Quality

Authors : K. Krishna Reddy , N V Kishore Kumar

Title : DSTATCOM enhanced Controller for Harmonic Reduction using Artificial Neural Networks

Volume/Issue : 2024;1(1 (January - March))

Page No : 1 - 4