Search

Abstract: Noise in computed tomography (CT) images may occur due to low radiation doses. Hence, the main aim of this paper is to reduce the noise from low-dose CT images so that the risk of high radiation dose can be reduced. Background: The novel coronavirus outbreak has ushered in different new areas of research in medical instrumentation and technology. Medical diagnostics and imaging are one of the ways in which the area and level of infection can be detected. Objective: COVID-19 attacks people with less immunity, so infants, kids, and pregnant women are more vulnerable to the infection. So, they need to undergo CT scanning to find the infection level. But the high radiation diagnostic is also fatal for them, so the intensity of radiation needs to be reduced significantly, which may generate the noise in the CT images. Method: This paper introduces a new denoising technique for low-dose Covid-19 CT images using a convolution neural network (CNN) and noise-based thresholding method. The major concern of the methodology for reducing the risk associated with radiation while diagnosing. Results: The results are evaluated visually and using standard performance metrics. From comparative analysis, it was observed that proposed works give better outcomes. Conclusions: The proposed low-dose COVID-19 CT image denoising model is therefore concluded to have a better potential to be effective in various pragmatic medical image processing applications in noise suppression and clinical edge preservation.

Pattern recognition is highly possible due to the matching process of facial features. Matching is the process of collecting a young person's down and out enactment, accompanying skillfully anticipated persons. It is a main stage superior to landing at a maintenance resolution. Matching includes choices that concede the possibility to endlessly change a youth’s growth in an adoptive classification. It is a blame usually pretended by a crew of artists loyal to the care and welfare of youth, including psychologists, friendly traders, and jurists. Matching is a weighty and complex task that grants permission to influence negative results for two people: an adoptive classification and an adolescent if an inappropriate competition is created. VGG data set is profoundly known for facial images data set often called as VGG face descriptor. Specifically, what it will show is that there is a need for a very large size of culture in the corresponding philosophy of a new order to mirror the complex process that happens through uniformly cruel judgment and interpretation. When created and achieved correctly, creative equal electronics may be very valuable, more conversant selections that bring about better effects and a sleeker and understandable maintenance process. Using countenance treat science, the countenance in the face of the adopting father and mother is written, and the kid whose equal is equate is recognized and assigned to the ruling class. VGG face model dataset and Gaussian Mixture model is used to identify and match the facial features similarity to achieve the solution. Fortunately, the outcomes of this research work excels in its accuracy by over crossing the existing frameworks by 1.5%.

The emergence of Internet of Things (IoT) technologies has presented novel prospects for precision farming and agriculture. This paper presents a comprehensive analysis of recent research studies pertaining to Internet of Things (IoT) applications in the agricultural sector. The objective of this review is to furnish a thorough examination of the diverse facets and technologies linked with precision farming based on the Internet of Things (IoT). The aforementioned review presents a comprehensive overview of the primary discoveries and perspectives derived from said investigations. This study investigates the utilisation of sensor networks and data collection methodologies to facilitate the contemporaneous monitoring of soil moisture, temperature, humidity, and crop health. The utilisation of remote sensing methods, such as the utilisation of satellite imagery and drones, was examined as a means of monitoring crops and estimating yield. The study investigated the efficacy of resource optimisation and automation tactics, including intelligent irrigation systems, in the domains of resource conservation and productivity enhancement. The convergence of Internet of Things (IoT) technologies and Decision Support Systems (DSS) was a key area of focus, examining the creation of data-centric insights and suggestions for agricultural practitioners. The successful implementation of IoT-based agricultural systems was found to be influenced by critical factors such as connectivity and communication infrastructure, as well as security and privacy concerns. The present review article offers significant perspectives on the progress and constraints of precision farming and agriculture based on the Internet of Things (IoT), underscoring the significance of additional research and development endeavours in this swiftly developing domain.

ABSTRACT The Internet of Things, often known as IoT, is a sector that is seeing significant expansion due to the fact that billions of objects are now linked to the internet. The most effective way to transmit data from one device to another is one of the most significant obstacles presented by the Internet of Things. In this article, we present a Tree Structure Based Routing Algorithm with Mobile Gateway for Internet of Things-Wireless Sensor Networks (WSN), the goal of which is to increase the efficiency of routing data in Internet of Things-Wireless Sensor Networks (WSN). The algorithm that has been presented makes use of a tree-based structure to route data and integrates a mobile gateway in order to increase network coverage and minimise the amount of energy that is used. In terms of network longevity, packet delivery ratio, and energy efficiency, the results of the simulation show that our suggested method surpasses current routing algorithms.

The purpose of the study is to find the best shells available in Linux Operating System. The study has been narrowed down to seven most prominent shells in use today. With so many different Linux distributions and a plethora of shells, there exists a problem of plenty, which is rather a good problem to have. Amid all this confusion, one wonders which shell to use. Which is most suitable to one’s requirement, is modern, up to date and provides all sort of features which fulfils the desire of the user as well as the developer. The article deals in brief about Linux and its distributions, its philosophy and the freedom it provides. Shells, its scripting and shell types have been explained, one gets an idea of the study from the introduction. The seven Linux shells have been explained in detail to familiarize the reader with the most popular and most used shells available. A clear, concise and comparative analysis of the shells based on their general, interactive, programming and security features has been given. Programming features are important for the developers while a good interface makes everyone happy. Security features are a must for anyone who values their privacy and would like no intrusion in their system or their files. The mechanism of communication is important for I/O handling, as well as managing, interrupts. The speed of the system is greatly affected by the level of efficiency of inter-process communication.

As the amount of information increases every day, there is a need of information retrieval for finding useful information from large amount of information. This paper presents and evaluates supervised word sense disambiguation (WSD) algorithms in information retrieval (IR). Word ambiguity problem is a key issue in the information retrieval systems. Supervised WSD is considered as the effective method than other methods in information retrieval. The effective usage of supervised WSD in IR is the main objectives of this research paper. The paper defines the role of supervised WSD in IR and discusses the best-known supervised algorithms in detail. We use Weikato environment for knowledge analysis (WEKA) tool to assess four supervised WSD algorithms Naive Bayes, support vector machine (SMO), decision tree (J48), and KNN (IBK) through a series of experiments, and the result concludes that the algorithms performance is based on the features of the datasets.

IoT is a new and upcoming trend in technology that finds its application in almost every field. Things, when connected to the internet and to each other, make the entire system smart. We have used IoT in every way of life: Smart Cities, Smart homes, Smart retail and many more. Using IoT in agriculture and farming practises is the need of the hour as the global population will hit a peak of 9.6 billion by 2050, to meet that kind of demand the agriculture industry needs to supply at an even faster rate. This is made possible by using modern technology and mainly IoT. IoT makes labour free farms a possibility. Not only in major farming practices but it can also be used in maintaining livestock, greenhouse farming, managing farms etc. The most important tool used for IoT is Sensors, sensors are devices that collect essential data which is interpreted to get the desired analysis. For agriculture, sensors are mainly used to get readings used to measure NPK values, detect diseases & moisture content in the soil. This paper explores its application in the agricultural sectors. Smart agriculture is called precision agriculture because it uses precise data to reach conclusions. It shows the various sensors which aid IoT and agriculture, their applications, challenges, advantages and disadvantages.

Gaussian noise has been the bane of any and every denoising process under the sun. Being a very corrosive noise with huge disruptive potential, this has received much attention form the image restoration community. Building on the premise, a novel framework is proposed to leverage multi-level image denoising that iteratively removes gaussian noise while recovering details lost during processing. This framework uses existing deep learning based CNN systems whilst enhancing the same by the addition of method denoising to the process. This framework is habile in competing with state-of-the-art technologies and outperforming them in some cases.

The Mobile Ad Hoc Network is an infrastructure less, multi-hop ad hoc network because the intermediate nodes are used to transmit data from source to destination. This paper represents the simulation based study of network protocols for varying network load and mobility. In this paper three protocols AODV, DSR and DYMO are compared by using random waypoint mobility in few nodes with varying packet sizes in CBR traffic. Different parameters or metrics are used to evaluate the performance of protocols, which are data throughput, end-to-end delay and packet loss with varying data traffic CBR(Constant Bit Ratio) load over UDP using QualNet 5. 0. 2 simulator.

The incentive for this work originates from the need of retrieving useful web news pages from the Indian news websites corpus. News web pages contrast from other web pages; it is mainly vital to recognize web news accurately for precise classification. We will likely locate a simple yet efficient technique to mine news articles from web corpus. To accomplish this task, the automatic recognition method has been recommended for news web page classification that uses classification rules based on a combination of content, structure and uniform resource locator (URL) attributes. We gathered news web documents from 10 different news websites. We use Naive Bayes algorithm to distinguish news articles from non-news articles examples advertisements, not related links.

Improvement in information retrieval performance relates to the accessibility, selection and management of large amounts of information on web that usually expressed as textual data and supervised machine learning approach is an important source of tool for automating information retrieval task. This paper provides a review of supervised machine learning approaches of text classification for information retrieval and present a comparative study of supervised machine learning algorithms namely Naive Bayes (NB), Support vector machine (SVM), K- nearest neighbor (KNN) and decision tree (DT). We used WEKA (Weikato Environment for Knowledge Analysis) tool to evaluate these four algorithms through a series of experiments. In WEKA Sequential Minimum Optimization (SMO) represents Support vector machine (SVM) classifier, IBK represents K- nearest neighbour and J48 version of Decision Tree is used. The result concludes that the performance of the algorithms depends on the characteristics of the datasets.