Browse Articles
Discover research articles across all indexed journals
IOT BASED SMART CASH CROP CULTIVATION USING RASPBERRY PI
The cash crops refer to items that return far more to farmers than the normal harvests and demands. While, such crops are not often easy to grow in India due to the country's climate obstacles and these plants meticulous attention is needed to provide the finest returns else easy to suffer from pests and illnesses. So ,a minimal expense nursery model which can be managed by the Indian ranchers for the development of money yields like saffron, vanilla, peppers, and so on and they can do the development under this mechanized nursery hence improving their social and monetary condition by an incredible degree. The proposed system had both farm monitoring and automated irrigation control along with the alert message feedback to the user. All the sensors data collected is farm monitoring and the equivalent control constitutes automated irrigation control. This makes the farmer to monitor the green house continuously and necessary actions are taken according to the sensor reading and thus the returns will increase.
A STUDY OF THE BENEFITS AND DRAWBACKS OF NOSQL DATABASES
NoSQL database management solutions are a departure from standard relational database management systems (RDBMS). Non-tabular NoSQL databases store data in a distinct way when compared to relational database tables. The data model of NoSQL databases is used to classify them. The most popular types are document, key-value, wide-column, and graph. They feature customizable schemas and can easily handle large amounts of data as well as significant user loads. They have adaptable schemas and can handle big amounts of data and high user loads with ease. Furthermore, their data models' flexibility and ease of use, in comparison to the relational model, can faster the development, especially in the field of cloud computing. This paper discusses the benefits of NoSQL databases, such as the ability to handle large volumes of data at high speeds with a scale-out architecture, the ability to store unstructured, semi-structured, or structured data, and the ability to easily update schemas and fields, making them developer friendly. Furthermore, this paper discusses the downsides, such as the lack of reliability features found in Relational Databases.
CLASSIFICATION ON PARKINSON DISEASE USING TRANSFER LEARN
These days, a basic appraisal effort in clinical affiliations biometrics is finding careful biomarkers that permit settling on clinical choice assistance instruments. Parkinson ’s disease (PD) is a chronic and progressive illness that affects hundreds of thousands of people worldwide. Although it is quite easy to identify someone affected by PD when the illness shows itself (e.g. tremors, slowness of movement and freezing-of-gait).Most works have focused on studying the working mechanism and detection of the disease in its very early stages. In such cases, drugs can be administered in order to increase the quality of life of the patients. Since the beginning, it is well-known that PD patients feature the micrography, which is related to muscle rigidity and tremors. As such, most of the approaches to detect Parkinson’s Disease make use of handwritten assessment tools, where the individual is asked to perform some predefined tasks, such as drawing spirals and meanders on a template paper. Later, an expert analyses the drawings in order to classify the progressive of the disease. In this work, we are interested into aiding physicians in such task by means of machine learning techniques, which can learn proper information from digitized versions of the exams, and them recommending a probability of a given individual being affected by PD depending on its handwritten skills. Particularly, we are interested in deep learning techniques (i.e. Convolutional Neural Networks) due to their ability into learning features without human interaction.
DEVELOPMENT AND VALIDATION OF A RP-HPLC METHOD FOR THE SIMULTANEOUS ESTIMATION OF CLARITHROMYCIN, TINIDAZOLE AND LANSOPRAZOLE IN FIXED DOSE COMBINATIONS
New RP-HPLC method was developed for the simultaneous estimation of Clarithromycin, tinidazole and lansoprazole in the fixed dose combination (PYLOKIT by CIPLA). RP-HPLC separation was carried out using Ultisil XB-CN column (250 x 4.6 mm) internal diameter and the packing material having 5µm size) using gradient mobile phase of Potassium dihydrogen phosphate: acetonitrile. 1 mL/min was the flow rate and UV detector at 210 nm wavelength was fixed for detection of the drug. The method validation was done as per ICH guideline and the parameters were included such as accuracy, precision specificity, linearity, and robustness were determined. Retention times for the clarithromycin, tinidazole and lansoprazole were 16.643, 5.493 and 12.940 minutes respectively. RP-HPLC method was a simple, reliable and acceptable and it confirmed that method is suitable for the intended use for routine quality control and assay of drugs. This method is successfully applied for the determination of commercial dosage form preparation. This method is validated as per ICH (International conference on harmonization) Guidelines.
GESTURE CONTROLLED ROBOT USING LABVIEW
Now a day’s Humans can interact to robot. These robots can be used in their work. These days we have to find the user interface which is of fundamental importance. The interface must be natural and user friendly. In the existing system the human hand gesture is directly sensed by robot and based on this it makes the movement. The sensors and accelerometer is carried by a human. Based on the person making the moves or changing the position this is sensed by the sensor along with the constraints and this is passed to robot and it will imitate the same. But in this paper work the hand gesture is captured in the form of image and is processed and sent to robot in the form of signals via Wi-Fi. The images are generated in vision assistant and processed via vision acquisition.
A REVIEW ON STEGANOGRAPHY AND DATA HIDING IN QR CODE
In comparison to 1D barcodes, a two-dimensional matrix is regarded as a Quick-Response (QR) code which is a programme that contains a vast quantity of data. QR codes offer quick scanning, omnidirectional reading, and a variety of other benefits, such as error correction. Barcode scanners can readily reveal the content of QR codes. In reality, however, gratified QR apps could contain confidential information, like an electronic-ticket or an electronic-coupon. To safeguard quick response essence from unauthorized users or scanners, it should be password protected. We'll look at QR codes and different sorts of QR barcode steganography mechanisms in this article.
IMAGE INSCRIPTION AND INTONATION -A NEURAL NETWORK APPROACH
Digital communication technologies have greatly influenced and expanded the way humans interact. The progress of information technology has opened wider opportunities for communication. Social networks have become the modern-day social communities connecting people from different parts of the globe, sharing images and videos on these platforms. By creating virtual communities, digital communication has expanded the scope of communication eliminating barriers. We aim to make further progress in this arena by describing an image in the form of audio to visually impaired people. A certain section of differently abled people is unfortunately isolated from this world. In-order to combat this issue we have come up with a system that describes an image shown in the form of plain text using an encoder-decoder architecture and is integrated with an end-to-end lexical articulator which produces a vocal description of the given image.
INTEGRATION OF MECHATRONICS SYSTEM WITH CLOUD BASED IOT DATA LOGGER USING ANDROID BASED APPLICATION
The Internet of things is a platform, which connects and controls the real word objects through a wireless network. This paper presents a novel approach to collect the data from the sensors, which resides on a Mechatronic devices. Using communication protocols these devices are integrated with the cloud based IoT data logger. There will be a communication between the data logger and the server. Android based application developed will monitor the action of devices.
COVID-19 CT SCAN IMAGE SEGMENTATION USING TRANSFER LEARNING APPROACH
The Computer tomography Scan imaging technique becomes an alternative approach of RTPCR test in COVID-19 diagnosis, disease staging and monitoring of treatment response evolution. The sensitivity of RTPCT is low neat about 70% with compare to the sensitivity of chest CT Scan images technique up to 98%. In this work, COVID-19 CT Scan image segmentation has been performed. The UNET Model has been selected as the baseline model for CT Scan Image Segmentation. The CT Scan Image segmentation performance of the deep learning models has been improved using the transfer learning approach. The IoU values have been improved from 86.94 to 88.90, 93.56, 94.34 using MobileNet as an encoder, DenseNet201 as an encoder, DenseNet169 as an encoder in Baseline UNET Models respectively.
INTEGRATION OF PINNING UNIT AND PORTAL UNIT WITH IOT DATA LOGGER AND DEVELOPMENT OF ANDROID BASED APPLICATION
The year 1999 was easily one among the foremost significant for the IOT history, as Kevin Ashton coined the term internet of things. This concept of connecting devices was started in early 1970’s, under the embedded internet and computing. The first internet application was a Coke machine at Carnegie Mellon University at 1980s. However, all complete IOT systems are an equivalent therein they represent the mixing of 4 distinct components: those are sensors/devices, connectivity, processing, and an interface. Generally IOT applications development is also called Machine-to-Machine app developments where devices exchange data anywhere at any time without human or man power need. They can be in the field of wearable’s, health automation, traffic monitoring, fleet management, agriculture automation, hospitality, industry automation, etc.
INFORMATION RETRIEVAL AND WEB SEARCH
This article discusses Web search engines; mainly the challenges in indexing the World Wide Web, the user behaviour, and the ranking factors used by these engines. Ranking factors are divided into query-dependent and query-independent factors, the latter of which have become more and more important within recent years. The possibilities of these factors are limited, mainly of those that are based on the widely used link popularity measures. The article concludes with an overview of factors that should be considered to determine the quality of Web search engines.
AN EXAMINATION OF EXPERT SYSTEM NEURAL NETWORK AND DATA MINING FOR CARDIAC DISEASES
Now a day’s neural network are being used successfully in an increasing number of application areas. Expert system is used comprehensively in several research domains. Heart disease diagnosis is a complicated process and requires high level of expertise. This paper examines and aiming to study a expert system for diagnosing of heart disease using support vector machine, feed forward Back propagation technique, Radial Basis Function, Generalized Regression Neural Network etc with other Data mining techniques that are used for diagnosis for heart diseases. This paper studies the analysis and examines the different approaches used for the detection of heart disease using different neural network techniques and data mining techniques.
SENTIMENT ANALYSIS USING SUPPORT VECTOR MACHINE BASED ON FEATURE SELECTION AND SEMANTIC ANALYSIS
Social media is a popular network through which user can share their reviews about various topics, news, products etc. People use internet to access or update reviews so it is necessary to express opinion. Sentiment analysis is to classify these reviews based on its opinion as either positive or negative category. First we have preprocessed the dataset to convert unstructured reviews into structured form. Then we have used lexicon based approach to convert structured review into numerical score value. In lexicon based approach we have preprocessed dataset using feature selection and semantic analysis. Stop word removal, stemming, POS tagging and calculating sentiment score with help of SentiWordNet dictionary have been done in preprocessing part. Then we have applied classification algorithm to classify opinion as either positive or negative. Support vector machine algorithm is used to classify reviews where RBF kernel SVM is modified by its hyper parameters which are soft margin constant C , Gamma γ. So optimized SVM gives good result than SVM and naïve bayes. At last we have compared performance of all classifier with respect to accuracy.
A COMPREHENSIVE SURVEY OF GRAPE LEAF DISEASE DETECTION AND CLASSIFICATION USING MACHINE LEARNING BASED MODELS
Plant diseases are becoming a major danger to agricultural productivity as the world's population expands, causing farmers to incur serious consequences. Plant disease can be detected early, which can assist ensure food security and save financial losses. Grape (Vitis Vinifera), a member of the Vitaceae family, is one of India's most important commercial fruit crops. It's a wide-ranging temperate crop that's adapted to the subtropical environment of India's peninsula. Grapefruits and their leaves are more likely to contract illnesses in a grape vineyard. For experts and agronomists, manual observation is impracticable and time-consuming. We conduct a literature study on alternate disease identification and classification methodologies in order to predict disease progression at an early stage. A review of automated classifying and sorting grape leaf disease, including machine learning and deep learning approaches, is also discussed.
APPLICATION OF GAME THEORY IN HIERARCHICAL NETWORK SECURITY
Such hierarchical network structures, omnipresent in modern organizations, give rise to particular security challenges. In this paper, we study the application of game theory to model an attacker-defender game in these layered networks. In such models, aiming at optimal resource allocation, threat prediction, and adaptive defense, we discuss game theoretic models of Stackelberg, Bayesian, and Signalling games among others. A survey of recent literature on hierarchical network security demonstrates both strengths and limitations of these models.
PROTOCOLS FOR QUANTUM-RESISTANT NETWORKS
With the progression of quantum computing technology, traditional cryptographic protocols encounter flaws that may compromise their efficacy against quantum-based assaults. This study examines quantum-resistant protocols that include post-quantum cryptography (PQC) to enhance the security of existing network protocols, particularly the Transport Layer Security (TLS) protocol. This research examines the efficiency, compatibility, and adaptability of post-quantum algorithms, including lattice-based, code-based, and hash-based cryptographic methods, inside the TLS protocol architecture. The study's findings emphasize the comparative performance metrics and compatibility factors, providing insights into the future of secure network communications in the post-quantum age.
FINGERPRINT AND FACE RECOGNITION BASED ATM SYSTEM USING RASPBERRY PI
ATMs (Automatic Teller Machine) are becoming widely used in today's world because they are easy to use and offer convenience. However, today's ATM technology comes with some security risks such as the theft and misuse of cards, the possibility of losing a card, and forgetting PIN numbers. A growing number of frauds committed against automatic teller machines over the last decade motivated us to use biometrics to ensure the accuracy and security of personal identification. In this paper, we describe a biometric fingerprint and face recognition system that can replace ATM cards and PINs. The transaction is successful when fingerprint, OTP, and face match. If the fingerprint does not match, the customer is guided to enter the aadhaar number. Similarly, if face matching fails, the customer is given an option to answer the question. Here aadhaar number and correct answer to the question must be entered correctly to proceed. Aadhaar number entry and question & answer options are mainly provided for those who are unable to access the system because of damage to their physical attributes (finger and face).
CATCH ANALYSIS AT THE TIME OF FISHING OPERATIONS AND IMMERSING SURFACE GILL NETS IN SEMARANG WATERS, CENTRAL JAVA, INDONESIA
The purpose of this study was to catch analysis at the time of fishing operations and immersing surface gill nets in Semarang Waters, Central Java, Indonesia. The research was carried out in March 2021. The research method was experimental fishing. The treatment variables included the morning operating time with 30 minutes and 60 minutes of immersion time, and the evening operating time with 30 minutes and 60 minutes of soaking. All treatments were repeated 7 times each. Data analysis using the Two Way Anova test. The composition of the catch obtained was Milkfish (Chanos Chanos), Long Jawed Mackerel (Rastrelliger sp.), Anchovy Fish (Mystacoleucus padangesis), Threadfin (Eleutheronema tetradactylum), Queen Fish (Scomberoides lysan), Grouper Fish (Epinephelus sp.), Pony Fish (Leiognatus tauvina), Emperors (Lethrinus sp.), Silver Pennah Croaker (Aspericovina jubata), Black Pomfret (Formio niger), Torpedo Scad (Megalaspis cordyla), Spanish Mackerel Fish (Scomberomorus sp.), John’s Snapper (Lutjanidae sp.), Streaked Spinefoot (Sinagus sp.), Tholi Shad (Tenualosa macrura), and Tongue fish (Cynoglossus lingua). The most catches (biomass) were treated in the morning operating time with 60 minutes of immersion. Data analysis showed that there was a significant effect on the best catch with fishing operation time in the morning (sign 0.05) and immersing time for 60 minutes (sign 0.05). There is no significance between the fishing operation time and the immersing time. The most catches (biomass) were treated in the morning operating time with 60 minutes of immersion. Data analysis showed that there was a significant effect on the best catch with fishing operation time in the morning (sign 0.05) and immersing time for 60 minutes (sign 0.05). There is no significance between the fishing operation time and the immersing time.
DEVELOPMENT OF A CONCEPTUAL FRAMEWORK AND A MEASUREMENT MODEL FOR THE DETECTION OF FAKE NEWS
Fake news has been there since before the advent of the Internet. It has had an immense impact on our modern society. Detecting fake news is an important step. Although there are various ways and methods in which fake news can be detected and solved. In this research paper we discuss the various conceptual frameworks and how they affect fake news. It further shows the development of the conceptual framework and the measurement model used; showing which of the frameworks fake news is most likely to surface through. The objective of the research is to design a conceptual framework for fake news detection, whereby developing measurement model for fake news detection, and the framework and model are evaluated for fake news detection. Fake news detection approaches can be divided as: creator and user features, news content features and social context features. A survey was taken based on this feature via questionnaire to determine in which feature, fake news can be quickly spotted. Results: Results shows that fake news can be easily spotted in the creator and user feature, this feature was then used to perform a feature selection on a fake news dataset which gave better accuracy.
AMAZON PRODUCT REVIEW SENTIMENT ANALYSIS USING MACHINE LEARNING
As online marketplaces have been popular during the past decades, online sellers and merchants ask their purchasers to share their opinions about the products they have bought. As a result, millions of reviews are being generated daily which makes it difficult for a potential consumer to make a good decision on whether to buy the product. Analyzing this enormous amount of opinions is also hard and time-consuming for product manufacturers. But in this prospering day of machine learning, going through thousands of reviews would be much easier if a model is used to polarize those reviews and learn from it. This thesis considers the problem of classifying reviews by their overall semantic (positive, negative, or neutral). To conduct the study different supervised machine learning techniques, Support Vector Machine, Naive Bayes, Decision Tree, Random Forest, and Logistic Regression have been attempted on products review dataset from Amazon. Their accuracies have then been compared.