The diagnosis of kidney disease, often called chronic renal illness, is known as chronic kidney disease (CKD). Chronic kidney disease (CKD) is a widespread and chronic health issue that requires preventative measures for early identification in order to slow the disease's progression. Using complex techniques like Support Vector Machine (SVM) and Logistic Regression, this study explores the field of machine learning. For robust model construction, use Random Forest and Decision Tree. Through the use of Variance Inflation Factor (VIF) for feature engineering, the dataset is carefully refined to improve the visibility of relevant features. To address any possible data imbalance concerns, Synthetic Minority Over-sampling Technique (SMOTE) is also utilized, promoting a fairer representation of classes in the dataset. By means of a thorough assessment procedure, the study methodically pinpoints the key elements that contribute to a precise diagnosis of chronic kidney disease. Each algorithm's effectiveness is evaluated using performance indicators like recall, accuracy, precision, and Fl-score.

Keywords : Learning, Chronic Kidney Disease(CKD), Dataset, Support Vector Machine(SVM), Decision Tree, ANN.

Authors : Dr. R. Triveni

Title : Detection of Chronic Kidney Disease using Machine Learning Algorithms

Volume/Issue : 2024;6(3 (May - June))

Page No : 34 - 37

One of the world's largest exporters of tea is India. However, persistent pathogen exposure-related tea leaf diseases cause significant global crop output losses. Early detection of the tea leaf disease can lessen its detrimental effects on tea production. It might be ineffective and harmful to diagnose the illness with the unaided eye. Convolutional Neural Networks (CNNs) are frequently employed to apply an efficient technique for the classification of images. CNN is frequently used in plant disease detection. As a result, the suggested work considers using a Deep CNN with many hidden layers to classify damaged tea leaves into various groups. This aids the network in identifying more characteristics, increasing the precision of illness identification. The following leaf classifications are used for the classification process: Red Spot, Heliopolis, Brown Blight, Algal Spot, Gray Blight, and Healthy Leaves. Additionally, 5867 photos of healthy and diseased tea leaves have been tagged and posted to Kaggle. The proposed approach shows that the model has a 96.56% accuracy rate in identifying the type of persistent tea leaf disease. The following illness classes have the results show that Algal Spot has an accuracy of 98.23%, Brown Blight has an accuracy of 97.98%, Gray Blight has an accuracy of 93.46%, the Heliopolis disease class has an accuracy of 98.98%, and Red Spot has an accuracy of 92% accuracy In terms of accuracy, the model put forward in this literature is significantly better than the current approaches.

Keywords : Neural Network; Tea Leaf Disease Detection; Healthy and Diseased tea leaves;

Authors : N.Rama Kumar

Title : A Novel Approach for Detection of Tea Leaf Disease using Deep Natural Networks

Volume/Issue : 2024;6(3 (May - June))

Page No : 26 - 33

This paper presents the design and implementation of an Enhanced Reversible Logic Gates-Based Pipelined Arithmetic Logic Unit (ALU) using Verilog and FPGA technology. The proposed ALU architecture aims to achieve high performance and efficiency by employing reversible logic gates and pipelining techniques. The design leverages the benefits of reversible logic gates, which ensure zero energy dissipation and minimize heat generation, leading to energy-efficient computing systems. The pipelined architecture enhances the throughput of the ALU by breaking down the computation into smaller stages and processing multiple instructions concurrently. Verilog Hardware Description Language (HDL) is utilized for the design and simulation of the ALU. The implementation is carried out on a Field-Programmable Gate Array (FPGA) platform, providing flexibility and scalability in hardware realization. Experimental results demonstrate the effectiveness of the proposed ALU design in terms of performance, energy efficiency, and area utilization. Compared to conventional ALU implementations, the proposed design offers significant improvements in throughput and power consumption, making it suitable for various applications requiring high-speed arithmetic and logic operations.

Keywords : Reversible Logic Gates, Pipelined ALU, Verilog, FPGA, High Performance Computing.

Authors : B.R.Darshan

Title : Enhanced Reversible Logic Gates based Pipelined ALU Implementation using Verilog and FPGA

Volume/Issue : 2024;6(3 (May - June))

Page No : 22 – 25

The high-speed carry look ahead adder (CLA), however, has become a very powerful tool for carrying out addition operations quickly in today’s computer architecture. Its strong point is its fast processing of binary inputs used to make arithmetic possible .This paper looks at the design principles and benefits that support the high speed CLA in modern computing systems .One of the most impressive attributes of the high-speed CLA is parallelism where carries are generated concurrently with arithmetic operations on binary numbers. Through this feature, computation delays are minimized thereby increasing efficiency especially when dealing with time critical scenarios . Another interesting characteristic of the CLA is its ability to perform consistently even when it comes to inputs having multiple bit widths which makes it suitable for solving more complex computational problems. Additionally, by incorporating XOR gates into the structure, subtraction processes are seamlessly embedded within the CLA, thereby enhancing performance in both addition and subtraction tasks . Although it is mainly used in addition and addition only as a matter of fact, versatility alone makes Carry lookahead Adder an essential building block for many digital circuits.

Keywords : Learning, Chronic Kidney Disease(CKD),Dataset, SVM, Random Forest, ANN.

Authors : kurumala vishnu chaitanya

Title : Design and Implementation of a High-Speed Carry Look-Ahead Adder and Subtractor Using Xilinx ISE

Volume/Issue : 2024;6(3 (May - June))

Page No : 16 - 21

This project focuses on the development of an adaptive vest for soldier health monitoring and temperature control. The vest incorporates advanced sensing technologies and control mechanisms to ensure the well-being of soldiers in various environmental conditions. The adaptive vest utilizes an array of sensors, including heart rate and temperature sensors, to continuously monitor the soldier's vital signs. These sensors provide real- time data that is processed by an embedded microcontroller. The microcontroller employs adaptive algorithms to analyze the sensor data and identify any anomalies or health risks. In addition to health monitoring and temperature control, the vest incorporates wireless communication capabilities. It enables seamless transmission of the sensor data to a central monitoring station or a portable device carried by medical personnel. This facilitates remote monitoring and enables timely intervention in case of emergencies.

Keywords : Solders, Defense, Vehicles, Security, Traffic, Health.

Authors : R.pradeep kumar

Title : Developing an Adaptive Vest for Soldier Health Monitoring and Temperature Control

Volume/Issue : 2024;6(3 (May - June))

Page No : 11 - 15

Convolutional Neural Networks (CNNs) have currently acquired focus from researchers to address computer vision and medical image processing problems. Popular though they may be, most methods can only handle 2D pictures, but in medical liver tumor segmentation 3D volumes are normally analyzed in clinical data. Here, we offer a technique for segmenting 3D images using a fully convolutional neural network that has been trained on volumetric data. Our CNN is taught to predict segmentation for the entire volume simultaneously after being trained from scratch on prostate Magnetic Resonance Imaging (MRI) data. Liver cancer is second among male cancers in terms of mortality and sixth among female cancers in terms of mortality. Diagnosing, treating and assessing the efficacy of liver cancer all rely on accurate segmentation of hepatic lesions. As a standardized benchmark, LiTS (Liver Tumor Segmentation Challenge) allows researchers to evaluate and compare several automated liver lesion segmentation approaches. Computed tomography (CT) allows for early diagnosis, which is key to a high recovery rate. However, manually reviewing CT slices for thousands or millions of patients is difficult, tiring, costly, time-consuming, and prone to mistakes. Thus, we need a trustworthy, easy, and precise approach to automating this procedure. This work contains convolutional neural networks (CNNs) to solve all those problems; specifically, a trained RA-UNet(or) Res U-Net model using the 3D-IRCADb01 dataset, which includes CT slices from patients and masks for liver, tumors, and other organs. RA-UNet model combines the U-Net and ResNet models, instead of using convolutional blocks, it employs Residual blocks A second CNN was trained to segment the tumours based on the output of the first CNN after a first Cascaded Convolutional Neural Network (CNN) was used to segment the liver and extract the ROI. The dice coefficient was 95%, while the True Value Accuracy was 99%.

Keywords : Liver, Computed Tomography, Segmentation, Tumor Extraction, U-Net, Residual Learning.

Authors : P. GANGADHARA REDDY

Title : CT Liver Tumor Segmentation using a Hybrid Deep Convolutional Neural Network RA-UNet

Volume/Issue : 2024;6(3 (May - June))

Page No : 1 - 10