Large language models (LLMs) are trained on huge datasets, which allow them to answer questions from various domains. However, their expertise is confined to the data that they were trained on. In order to specialize LLMs in niche domains like healthcare, various training methods can be employed. Two of these commonly known approaches are retrieval-augmented Generation and model fine-tuning. Five models—Llama-3.1-8B, Gemma-2-9B, Mistral-7B-Instruct, Qwen2.5-7B, and Phi-3.5-Mini-Instruct—were fine-tuned on healthcare data. These models were trained using three distinct approaches: retrieval-augmented generation (RAG) alone, fine-tuning (FT) alone, and a combination of both (FT+RAG) on the MedQuAD dataset, which covers a wide range of medical topics including disease symptoms, treatments, medications, and more. Our findings revealed that RAG and FT+RAG consistently outperformed FT alone across most models, particularly LLAMA and PHI. LLAMA and PHI excelled across multiple metrics, with LLAMA showing superior overall performance and PHI demonstrating strong RAG/FT+RAG capabilities. QWEN lagged behind in most metrics, while GEMMA and MISTRAL showed mixed results.

The performance of the system is affected by parameter variations. The parameter variations can effectively be analysed by interval system. In this work, Doha water treatment plant is modeled as interval system. After this, reduced-order modeling is accomplished for such interval modeled Doha water treatment plant. Initially, uncertainty is considered in each coefficient of the transfer function to obtain the interval model of Doha water treatment plant. Later, time moments and Markov parameters are utilized to determine the reduced-order model of obtained interval modeled Doha water treatment plant. An error function is formed in between time moments and Markov parameters for the determination of reduced-order model. Sine-cosine algorithm (SCA) is used for minimization of thus obtained error function. SCA is population-based stochastic optimization technique which uses sine and cosine functions for the exploration and exploitation of search space to find the solutions. The analysis of results shows that reduced-order model is effectively describing and approaching the response of the system under consideration.

Due to the rapid growth of the Industrial IoT (IIoT), social media and digitization, and wireless communication technology in various sectors, data volume is increasing rapidly. Cloud computing is an emerging solution with fog computing assistance for handling and processing a huge volume of data. It is a soar of means to improve the quality of services provided to users through cloud computing, which has been more overwhelmed by the massive data flow. Transmitting all the data to the cloud and getting it back from the cloud causes high latency and requires high network bandwidth. In the IIoT applications, there is enough energy needed in the fog layer, a promising area to be handled by the cloud service providers. An important factor that contributes to the energy consumption in fog servers is VM allocation. This paper proposes EVMAS, i.e., an energy-aware VM allocation scheme based on Lagrange’s undetermined multiplier with the Hessian matrix, which improves the Quality of Service (QoS) in parallel with service level agreement (SLA). The suggested technique outperforms in comparison to the other state of the algorithm.

Air quality has a significant impact on agricultural productivity, with pollutants such as ozone (O3), particulate matter (PM), and carbon monoxide (CO) posing serious threats to crop yields. Plant growth and yields can be disrupted by these pollutants, highlighting the need for effective solutions. Strategies, including improvements in air quality management to reduce pollutant levels and the development of advanced predictive models, have been proposed. The concentrations of air pollutants and their potential impacts on agriculture can be forecasted by these models, allowing proactive measures to be taken to mitigate adverse effects on crop yields. In this research, the challenges associated with predicting the impact of key air pollutants on rice yield in India are addressed. Satellite data from the Giovanni Data Centre was utilized to monitor concentrations of O?, PM, and CO, and to calculate the Air Quality Index (AQI). The Prophet model is employed to predict future pollutant levels and AQI. Soil temperature and air moisture data were incorporated to assess their combined impact on crop yield. Nineteen years of monthly rice yield data from FAOSTAT was used to train a feed-forward neural network with inputs including PM, O?, CO, AQI, soil temperature, and air moisture. A high accuracy of 94% was achieved by the model, effectively predicting crop yields based on these factors, and a clear inverse relationship between air quality and crop yield was demonstrated: significant decreases in yield were correlated with higher concentrations of O?, PM, and CO. Concrete evidence of the detrimental effects of air pollution on crop productivity is provided by these findings.

In today's digital age, data storage has become an increasingly important issue. The exponential growth of data has led to the need for secure and private storage solutions. Unfortunately, without a standardized protocol, the security and privacy of sensitive data can be a challenge. However, blockchain technology has emerged as a promising solution for secure data storage. Blockchain's decentralized and immutable nature provides a comprehensive solution for the security and privacy of all types of data. In this research, we propose an innovative framework that leverages the benefits of blockchain technology to securely handle and store data in a serverless environment of distributed nodes. To ensure the highest level of security, we evaluated four encryption algorithms - Blowfish, RC4, DES, and AES - for storing data in a permissioned blockchain network. We found that AES encryption and decryption algorithms provide the best solution for creating a decentralized, immutable coordinate system. Our proposed framework is based on a permissioned blockchain network that enables multiple users to join the network through suitable identity verification processes, and each user is assigned certain special and designated permissions to perform actions. This framework provides a secure and efficient solution for the storage of all types of data, ensuring privacy and security. Our proposed framework offers an innovative solution for secure data storage and management in a decentralized environment. This research has practical implications for organizations that need to store sensitive data securely, and it also contributes to the ongoing development of blockchain technology.

Lung cancer persists to be considered as the primary cause of rising mortality rates worldwide with clinical projection depending upon early-stage detection. Detection at the preliminary stage is crucial for treatment of the disease also to further the prognosis process. In this study IQOTHNCCD dataset is used. An innovative model is constructed for distinguishing images into three categories. The dataset comprises of three types of images such as malignant images, benign images and normal images. Preprocessing of the images is done with intensive steps in order to remove unwanted data. Deep learning along with transfer learning have been applied to the image dataset for classifying the images into various categories. In biomedical image classification deep learning serves as the most effective technique for classification and detecting the abnormal pulmonary nodules. Techniques such as InceptionV3, ResNet50, VGG16, VGG19, MobileNetV2 are evaluated through experiment for ensuring the credibility of the designed model. Key performance indicators were used which includes accuracy, sensitivity, precision and F1 score. The results obtained through the proposed model which is the custom CNN model yielded an accuracy of 98.79%, sensitivity of 98.97%, precision of 96.6% and F1 score of 97.7%.