Redshine ArchivePub Date : 2020-07-07DOI: 10.25215/8119070771.33
Roshan D Suvaris, Dr. S Sathyanarayana
{"title":"A SURVEY ON RECENT OPTICAL CHARACTER RECOGNITION ALGORITHMS","authors":"Roshan D Suvaris, Dr. S Sathyanarayana","doi":"10.25215/8119070771.33","DOIUrl":"https://doi.org/10.25215/8119070771.33","url":null,"abstract":"Identifying and Recognition of characters in the document, images etc. is a tedious and complicated task. Many procedures already have been implemented to identify the characters in these documents. In this research paper, we are reviewing some of the important methods used to identify handwritten and printed characters of various languages and different types of documents such as text documents, number plates, captcha, camera-based images, banners etc… The documents considered for recognition may contain clear backgrounds or may contain unclear backgrounds with ink bleed-through, noisy background, variable contrast etc, which makes character recognition a difficult task.","PeriodicalId":441519,"journal":{"name":"Redshine Archive","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115433571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Redshine ArchivePub Date : 2020-07-07DOI: 10.25215/8119070771.03
Pearl Sylvia Rodrigues, Sharel Disha Cutinha, Dr Hemalatha N
{"title":"COMPUTATIONAL MODEL FOR DIABETES PREDICTION USING DECISION TREE","authors":"Pearl Sylvia Rodrigues, Sharel Disha Cutinha, Dr Hemalatha N","doi":"10.25215/8119070771.03","DOIUrl":"https://doi.org/10.25215/8119070771.03","url":null,"abstract":"Diabetes is a long-term metabolic disorder characterized by elevated blood sugar levels that, over time, can seriously harm the heart, blood vessels, eyes, kidneys, and nerves. Around 422 million individuals worldwide have diabetes, the majority of whom reside in low- and middle-income nations and the disease claims 1.5 million deaths annually. Type 2 diabetes is the most frequent and most common in adults. This occurs when the body either cannot produce enough insulin or develops a resistance to it. The goal of this analysis is to create a system that can predict an individual's diabetic risk level based on their lifestyle and family history with greater accuracy by merging the results of various machine learning. To select the best model for diabetes prediction we have applied certain classification algorithms namely, Logistic Regression (LR), K-Neighbors Classifier (KNN), Support Vector Machine (SVM), Decision Tree Classifier, and Random Forest Classifier. This paper contains all the methods and techniques used in determining the best accurate model and also contains various visualization tools utilized to understand the data in-depth. Various experiments lead to the conclusion that the Decision Tree has an accuracy of 96.36%.","PeriodicalId":441519,"journal":{"name":"Redshine Archive","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117310783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Redshine ArchivePub Date : 2020-07-07DOI: 10.25215/8119070771.13
Dr. Rakesh Kumar B, Sheetal U R, Shravya, Sneha
{"title":"STOCK MARKET PREDICTION USING LSTM","authors":"Dr. Rakesh Kumar B, Sheetal U R, Shravya, Sneha","doi":"10.25215/8119070771.13","DOIUrl":"https://doi.org/10.25215/8119070771.13","url":null,"abstract":"Predicting the future value of a company's stocks is the goal of stock market forecasting. Among the most pressing issues in the share market right is now predicting stock prices. The Integrated Prices of the National Association of Securities Dealers which offer a price of the stock for Microsoft Corporation (MSFT), will be examined in this (NASDAQ). The Opening Value, Highest and Lowest the values of company for each date. We'll use the Long Short-Term Memory technique to predict the stock value of Microsoft Corporation. They are used to alter the data in relatively small ways by multiplying and adding. RNN architecture for deep learning what long-term memory (LSTM). As an alternative to conventional feed-forward neural networks, the LSTM uses feedback connections. Both whole to as and particular data points can be handled by it (like photos).","PeriodicalId":441519,"journal":{"name":"Redshine Archive","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123554598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Redshine ArchivePub Date : 2020-07-07DOI: 10.25215/8119070771.15
Arun V, Dr Hemalatha N
{"title":"MALWARE DETECTION USING MACHINE LEARNING ALGORITHMS","authors":"Arun V, Dr Hemalatha N","doi":"10.25215/8119070771.15","DOIUrl":"https://doi.org/10.25215/8119070771.15","url":null,"abstract":"Malware is a serious threat that weakens computer security. Malware detection is a branch of computer security concerned with the investigation and prevention of malicious software. It is not the only way to protect a company from a cyber-attack. Companies must analyse their risks and vulnerabilities in order to be effective. With this increase in cyber fraud and other malicious activities, traditional methods are not enough to block computers from it as this method has many drawbacks. In order to tackle these issues, researchers have been developing new techniques such as heuristic analysis, and static & dynamic analysis which can detect more than 90% of malware samples. In this paper, we will look at various techniques for detecting computer malware and malicious websites, as well as a versatile framework in which different machine-learning algorithms can be used to successfully distinguish between malware and clean files while attempting to reduce the number of false positives. In this paper, we have reviewed the rise of computer malware and how traditional methods of detection are being replaced by innovative techniques such as the behavioural-based model and the signature-based model.","PeriodicalId":441519,"journal":{"name":"Redshine Archive","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128899059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Redshine ArchivePub Date : 2020-07-07DOI: 10.25215/8119070771.18
Dr Ruban S, Shiva Sharan Navada K S, Abhishek K, Mohammed Moosa Jabeer
{"title":"HAND FRACTURE DETECTION USING DEEP LEARNING TECHNIQUES","authors":"Dr Ruban S, Shiva Sharan Navada K S, Abhishek K, Mohammed Moosa Jabeer","doi":"10.25215/8119070771.18","DOIUrl":"https://doi.org/10.25215/8119070771.18","url":null,"abstract":"The effect of Artificial Intelligence Technology on healthcare is growing by the day. Numerous musculoskeletal disorders can be caused by common bone illnesses (MC). Worldwide, musculoskeletal conditions affect an estimated 1.71 billion people. A lot of work is being done to improve the efficiency of Bone fracture in the early stages, where medical imaging is crucial. In order to aid radiologists in the identification of bone fractures, deep learning (DL) and artificial intelligence (AI) are currently gaining a lot of interest. The application of DL in medical image analysis is widespread.. The most prevalent type of fracture has a large incidence rate, and that is the hand fracture. Hand fractures are typically detected by conventional radiography (i.e., X-ray imaging), however on occasion fracture delineation presents problems, necessitating a second confirmation by computed tomography (CT) for diagnosis. Recent developments in the Artificial Intelligence (AI) discipline of Deep Learning (DL) have demonstrated that Hand fracture identification may be automated using Convolutional Neural Networks. This study aims to detect a fracture on hand X-ray images using Deep learning to help orthopaedics in the diagnosis.","PeriodicalId":441519,"journal":{"name":"Redshine Archive","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127903303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Redshine ArchivePub Date : 2020-07-07DOI: 10.25215/8119070771.10
Akshay B, Tintu George, Suchetha Vijayakumar
{"title":"A REVIEW ON TEXT MATCHING TECHNIQUES AND APPROACHES IN NATURAL LANGUAGE PROCESSING","authors":"Akshay B, Tintu George, Suchetha Vijayakumar","doi":"10.25215/8119070771.10","DOIUrl":"https://doi.org/10.25215/8119070771.10","url":null,"abstract":"Text matching is the process of relating and locating particular text matches in raw data. Text matching is a vital element in practical operations and an essential process in several fields. It has been applied in numerous tasks, similar as textual similarity, information retrieval and question answering. For most of the text matching methods, the primary step is removing spacing, punctuation, and common phrases like ”AND”, “THE”, etc . The target of text matching is to model the relation between two input text. likewise, several dynamic ways have been introduced in this environment in order to produce ease in pattern generation from words. The process contains matching of text mining, text files, text clustering, association rule extraction, world cloud, natural language processing, and text similarity measures( knowledge- based, corpus- based, string- based, and hybrid similarities). The string- based approach makes the most conspicuous form of text mining which can be applied in different cases. In this paper, we aim to give a check on techniques used in matching two Strings and analyse the results and discuss about the advantages of one technique over the other and also discuss about the drawbacks of these techniques.","PeriodicalId":441519,"journal":{"name":"Redshine Archive","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132290224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Redshine ArchivePub Date : 2020-07-07DOI: 10.25215/8119070771.06
Delvin Dcunha, Listen Veigas, Mr. Srinivas B.L
{"title":"A STUDY ON VM SELECTION ALGORITHM IN CLOUD DATACENTRE","authors":"Delvin Dcunha, Listen Veigas, Mr. Srinivas B.L","doi":"10.25215/8119070771.06","DOIUrl":"https://doi.org/10.25215/8119070771.06","url":null,"abstract":"The expansion of cloud computing has resulted in the establishment of a large number of data centers all over the world. Cloud computing enables users to use and access resources from data centers on demand rather than owning them. Large energy-hungry data centers is growing at an alarming rate, making energy management as one of many key design constraints for cloud datacenters. The goal is to dynamically consolidate virtual machines to optimize the energy-performance tradeoff online. The VM selection algorithm aims to find the best VM which can be considered for the migration, leads to lower power consumption of the server. In this study, we are trying to study the performance of VM selection algorithm in cloud datacenters.","PeriodicalId":441519,"journal":{"name":"Redshine Archive","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115670527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Redshine ArchivePub Date : 2020-07-07DOI: 10.25215/8119070771.30
K. Annapoorneshwari Shetty, Albin Mathew, Alan Mat
{"title":"GENDER DETERMINATION AND FACE RECOGNITION USING SIMPLE METHOD","authors":"K. Annapoorneshwari Shetty, Albin Mathew, Alan Mat","doi":"10.25215/8119070771.30","DOIUrl":"https://doi.org/10.25215/8119070771.30","url":null,"abstract":"This system is a focused variation of a more comprehensive object recognition system. Face-related images are displayed as graphs that are tagged with topographical data and local templates. Different graphs are used to illustrate different poses.By comparing the new face with a set of computerized graphs, the \"generic face knowledge,\" an elastic graph matching technique creates new graphs of faces. A composite image of a person's face can be created during the last phase of the matching process, and Additionally, it can identify elements that are comprised of the general face knowledge, such as gender or the existence of spectacles or a beard. A similarity function that compares the graphs makes the system effective at recognizing faces.","PeriodicalId":441519,"journal":{"name":"Redshine Archive","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115412751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Redshine ArchivePub Date : 2020-07-07DOI: 10.25215/8119070771.28
Dr Ruban S, Vishnu M, Nithin KJ,, Nandu Krishnan, Mohammed Moosa Jabeer
{"title":"LUNG CANCER PREDICTION USING MACHINE LEARNING","authors":"Dr Ruban S, Vishnu M, Nithin KJ,, Nandu Krishnan, Mohammed Moosa Jabeer","doi":"10.25215/8119070771.28","DOIUrl":"https://doi.org/10.25215/8119070771.28","url":null,"abstract":"Lung cancer is one of the cancers with the highest mortality rate in world. With the rapid development of high-throughput sequencing technology and the research and application of deep learning methods in recent years, deep neural network based on gene expression has become a research direction. hot in the diagnosis of lung cancer in recent years, providing an effective means in the diagnosis of lung cancer. early diagnosis of lung cancer. Therefore, building a deep neural network model is of great importance for the early diagnosis of lung cancer. However, the main challenges in exploring gene expression datasets are the curse of dimensional and unbalanced data. In this paper we are trying to study the lung cancer detection using Machine Learning.","PeriodicalId":441519,"journal":{"name":"Redshine Archive","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123998600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Redshine ArchivePub Date : 2020-07-07DOI: 10.25215/8119070771.12
Gladson Dcosta, Anston Joachim Dcunha, Hansel Priston Lobo, Nausheeda B.S
{"title":"COMPARATIVE ANALYSIS AND EVALUATION OF FACIAL EXPRESSION RECOGNITION USING DEEP LEARNING","authors":"Gladson Dcosta, Anston Joachim Dcunha, Hansel Priston Lobo, Nausheeda B.S","doi":"10.25215/8119070771.12","DOIUrl":"https://doi.org/10.25215/8119070771.12","url":null,"abstract":"Facial emotion recognition (FER) is vital for human-computer interactions such as clinical practice and behavioral description. Accurate and robust FER using computer models remains a difficulty, because of the non-uniformity of human features and visual differences such as diverse facial positions and illumination. Among all FER model strategies, Convolutional Neural Networks (CNNs) show considerable promise owing to their excellent automated feature extraction and computational efficiency. In this study, we obtained the greatest single-network classification accuracy on the FER2013 dataset. We take the VGG Net architecture, carefully tweak its hyperparameters, and experiment with several optimization strategies. According to our experiments, our model has accuracy of 88.62 percent on FER2013 without needing extra training data. In this study, we apply Resnet and Dense Net models and use the FER2013 dataset to show algorithmic differences and performance implications. The Resnet model produced an accuracy of 88.62 percent, while the Dense Net model produced an accuracy of 85.83 percent.","PeriodicalId":441519,"journal":{"name":"Redshine Archive","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122925845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}