International Journal on Recent and Innovation Trends in Computing and Communication
Not a member yet
8613 research outputs found
Sort by
A Novel Architecture of ADPLL Using Cordic Algorithm for Low-Frequency Application
Get PDFAll Digital Phase Locked Loop (ADPLL) has many applications in digital communication. It is difficult for low-frequency applications to achieve the lock state quickly. Therefore, proposed a novel particle swarm based ADPLL (PS-ADPLL) with Coordinate Rotation Digital Computer (CORDIC) algorithm to attain the lock state of the ADPLL for the low-frequency applications. In the proposed architecture, the D flip-flop matches the frequency and the phase of the output and reference pulses and produces an error signals up and down signal. The up/down counter removes the higher frequency part and produces a carry and the borrow signal. These carry and borrow signals are then fed into the increment decrement counters to produce the output signal matching the frequency of the reference signal. However, the time delay is increased for low-frequency applications, which is critical for the lock state. So, the delay line length is calculated by the CORDIC algorithm and is optimized by the particle swarm activated in the phase detector to match the output pulse with the reference pulse and make ADPLL into a locked state. The presented PS-ADPLL is tested in FPGA. Furthermore, the performance parameters are evaluated and compared with other current techniques to calculate the improvement score
Investigation of Different Pre-processing Quality Enhancement Techniques on X-ray Images
Get PDFTo maximize the accuracy of classification for medical images especially in chest- X ray, we need to improve quality of CXR images or high resolute images will be needed. Pneumonia is a lung infection caused by organism like bacteria or virus. Mostly Chest X-Ray (CXR) is used to detect the infection, but due to limitation of existing equipment, bandwidth, storage space we obtain low quality images. Spatial resolution of medical images is reduced due to image acquisition time, low radiation dose. Quality in medical images plays a major role for clinical diagnosis of disease in deep learning. There is no doubt that noise, low resolution and annotations in chest images are major constraint to the performance of deep learning. Researchers used famous image enhancement algorithms: Histogram equalization (HE), Contrast-limited Adaptive Histogram Equalization (CLAHE), De-noising, Discrete Wavelet Transform (DWT), Gamma Correction (GC), but it is still a challenging task to improve features in images. Computer vision and Super resolution are growing fields of deep learning. Super resolution is also feasible for mono chromatic medical images, which improve the region of interest. Multiple low-resolution images mix with high resolution and then reconstruct a target input image to high quality image by using Super Convolution Neural Network (SRCNN). The objective evaluation based on pixel difference-based PSNR and Human visual system SSIM metric are used for quality measurement. In this study we achieve effective value of PSNR (40 to 43 dB) by considering 30 images of different category (normal, viral or bacterial pneumonia) and SSIM value varies from 97% to 98%. The experiment shows that image quality of CXR is increased by SRCNN, and then high qualitative images will be used for further classification, so that significant parameter of accuracy will be finding in diagnosis of disease in deep learning
Predicting Diabetes Risk Using an Improved Apriori Algorithm
Get PDFThe data mining is able to analyze data and recover the valuable insights from the data. These insights are used for serving in different applications. In this context different data mining algorithms has been developed among them frequent pattern mining has an essential role. In this paper, the frequent pattern mining technique has been implemented for analyzing the diabetic risk. In this context, the popular diabetic dataset has been obtained. Then, the preprocessing has been done on dataset for cleaning the dataset. Next, an encoding process has been developed to transform the dataset. This transform dataset is an effort to deal with the continuous values using the frequent pattern algorithm. Further a modified apriori algorithm has been employed to understand and establish the relationships between diabetic attributes. The experiments have been carried out and theexperimental performance of the improved apriori algorithms has been measured. Additionally a comparison has also been performed with three popular frequent pattern mining algorithms. According, to the performance, we found that the proposed apriori algorithm is efficient and accurate algorithm to predict the diabetic risk
Examine the Properties of Nanostructured Ni, Mn, and Co Synthesized Materials using precipitation method and synthesized material used battery.
Get PDFLibatteries are secondary batteries containing a lithium anode and Li+ ions dissolved in carbon. The cathode material contains a solution that releaseslithium. With high energy density and low resistivity, it is "one of the three types of electric power acid, or battery, and is heavy and has more energy than nickel-ion batteries." Twice the size of a hydrogen battery, it is only half the size andweight of a nickel-metal hydride battery for the same energy. These advantages make lithium ion batteries an important factor in driving the technological revolution. Lithium-ion batteries also work well in temperatures from 20 degrees Celsius to +50 degrees Celsius and can with stand hundreds of charges and discharges. In this paper we are using nano material (Ni0.250Mn0.750) CO3 for synthesis to get the porous nano material, that synthesized nano porous material we are characterizing under different technique to know the characteristics of that material like size and shape, thermal effect and other. The same material will be used to prepare battery and the performance of that battery will be analysed and study on the performance will be done
An Efficacious Deep Fusion based Tomato Leaf and Fruit Classifier using Convolutional Gated Recurrent Unit and Bonobo Optimizer
Get PDFAgriculture is suffering a drastic blow because of sudden changes in environmental conditions and novel pathogenic attacks. These attacks have brought in heavy disruptionto the integrity of the food supply chain. In order to meet the growing global food demand,an automated system is needed for early identification of diseases and to enable smart farming with the advent of upcoming technologies. This paper proposes such an expert system that augments farming returns both economically and productively. Tomato leaf images are obtained from Kaggle repository and fruit images are self- captured, both making a total of 3676 images. Data is augmented using techniques like rotation, zooming, width shift, height shift, horizontal flip etc.Under preprocessing block, Wiener filter and Contrast Limited Adaptive Histogram Equalization model are used for noise smoothing and contrast enhancement.The U2Net architecture of convolutional neural networks is used for image segmentation after whichfeatures are extracted from a fusion layer based on InceptionV3 and EfficientNetB2 models. The final stage involves aConvolutional Gated Recurrent Unit classifier along with Bonobo optimizationfor obtaining optimal results.Evaluation metrics like accuracy, precision, recall, F1 score,Matthew’s correlation coefficient are calculated to find the effectiveness of the proposed system. The proposed algorithm is compared with currently prevailing algorithms like InceptionV3, MobileNet, VGG16, CNNandKernel Extreme Learning Machine and is found to produce promising results with an astounding accuracy of 96.90%
Exploring Sentiment Analysis in Social Media: A Natural Language Processing Case Study
Get PDFSocial media plays an integral role in our daily lives, influencing and reflecting global perspectives through the consumption and creation of content. Platforms like YouTube are incredibly active, with a constant influx of video uploads, views, and comments. While the YouTube app allows us to browse videos and comments, it offers only a limited glimpse into the interests and trends of others. Analysing this vast data pool, encompassing diverse language styles, presents a significant challenge. This article delves into the YouTube Data API and its application in Python for accessing raw data. The process involves data cleaning using advanced Natural Language Processing (NLP) techniques, harnessing Python-based machine learning to explore social media interactions, and automating the extraction of trends and influential factors. The journey towards trend analysis is meticulously detailed, featuring examples that leverage a variety of open-source Python tools
Building a Database System for Electronic Medical Records to Ensure Efficient Data Management and Interpretation
Get PDFThis research presents the design and implementation of an e-database system of medical records. The system comprises various modules, including data entry, user login, data storage, data management, and query analysis. The data entry module enables the input of electronic medical record data, while the user login module provides secure access and identity authentication. The data storage module stores the medical records and user information, and the data management module handles data manipulation and user authorization. The query analysis module allows users to search and analyze medical records based on specified criteria. This system aims to enhance the management and analysis of electronic medical records, providing medical professionals with valuable insights for diagnosis and treatment
Stream Applications: A Consistent Active Management Approach for Multi-Core Cache
Get PDFThis paper proposes a novel method for managing cache consistency in multi-core systems when executing stream applications. The method involves arranging a mark cache for private data caches, which includes an optional integrality descriptor for shared reading and writing data states and shared data manipulation positions. The integrality descriptor identifies the current mode of operation for shared data in the private data cache. Additionally, the method utilizes a two-dimensional array register, referred to as the shared data manipulation position, with width N and depth M, where N distinguishes between different cache blocks and locking territories, while M corresponds to the number of cache blocks. This enables the identification of the cache capable or block corresponding to shared data during read and write operations. The proposed method offers simplicity, ease of operation, low hardware implementation cost, good extensibility, and strong configurability, ultimately improving system effectiveness
Technique for Cache Management in Solid
Get PDFThis research presents a novel cache management method for solid-state discs (SSDs) that aims to efficiently utilize the limited cache space and improve the cache hit rate. The method involves the establishment of various data structures, including a page cache, a replace block module, a new page linked list, a physical block chain list, and a physical page state list. When an input/output (IO) request from a host is received, it is processed through the page cache. In cases where a writing request is executed and the page cache is full, a block replace process is triggered within the SSD to free up space. To minimize erasure and page copy operations, the method selects a candidate replace block with the highest failure ratio from the rear half of the physical block chain list as a replacement. This ensures that a block written in the flash medium contains a maximum number of dirty data pages and a minimum number of effective data pages. The proposed cache management method is designed to enhance the overall performance of SSDs by reducing sequential rubbish recovery caused by the presence of dirty data pages, and it is also user-friendly and easy to operate.
 
Face Mask Detection System Using Machine Learning Algorithms
Get PDFThe project presented in this report is a real-time face mask detection system using computer vision and deep learning techniques. The primary objective of this project is to develop a system that can detect whether a person is wearing a face mask or not, with a focus on real-time performance.
The system utilizes pre-trained deep learning models for face detection and mask classification. It leverages the MobileNetV2 architecture as a feature extractor and deploys the model in real-time video streams. When a face is detected, the system classifies it as "Mask" or "No Mask" with associated confidence scores. The project involves key components, including the use of OpenCV for image processing and real-time video capture, TensorFlow/ Keras for deep learning, and the integration of pre-trained models. The code is well- structured, and it demonstrates proficiency in model loading, image preprocessing, and real-time video processing.
The findings of the project showcase a practical application for face mask detection, which has gained significance in the context of public health and safety. The system provides a valuable tool for monitoring mask compliance in public spaces and can contribute to efforts to mitigate the spread of contagious diseases. The project demonstrates the importance of combining computer vision and deep learning in real-world applications, and it serves as a reference for those interested in similar projects or applications in the field of image processing and object detection. In summary, this project illustrates the successful implementation of a real-time face mask detection system and underscores its potential contributions to public health and safety measures