Predicting the time period of extension of lockdown due to increase in rate of COVID-19 cases in India using machine learning

Abstract Counterfeiting is an increasing concern for businesses and governments as greater numbers of counterfeit integrated circuits (IC) infiltrate the global market. There is an ongoing effort in experimental and national labs inside the United States to detect and prevent such counterfeits in the most efficient time period. However, there is still a missing piece to automatically detect and properly keep record of detected counterfeit ICs. Here, we introduce a web application database that allows users to share previous examples of counterfeits through an online database and to obtain statistics regarding the prevalence of known defects. We also investigate automated techniques based on image processing and machine learning to detect different physical defects and to determine whether or not an IC is counterfeit.

Download Full-text

Early Detection of Diabetic Retinopathy Using PCA-Firefly Based Deep Learning Model

Electronics ◽

10.3390/electronics9020274 ◽

2020 ◽

Vol 9 (2) ◽

pp. 274 ◽

Cited By ~ 30

Author(s):

Thippa Reddy Gadekallu ◽

Neelu Khare ◽

Sweta Bhattacharya ◽

Saurabh Singh ◽

Praveen Kumar Reddy Maddikunta ◽

...

Keyword(s):

Machine Learning ◽

Diabetic Retinopathy ◽

Deep Learning ◽

Early Detection ◽

Dimensionality Reduction ◽

Vision Loss ◽

Principal Component ◽

Screening Methods ◽

Learning Approaches ◽

Time Period

Diabetic Retinopathy is a major cause of vision loss and blindness affecting millions of people across the globe. Although there are established screening methods - fluorescein angiography and optical coherence tomography for detection of the disease but in majority of the cases, the patients remain ignorant and fail to undertake such tests at an appropriate time. The early detection of the disease plays an extremely important role in preventing vision loss which is the consequence of diabetes mellitus remaining untreated among patients for a prolonged time period. Various machine learning and deep learning approaches have been implemented on diabetic retinopathy dataset for classification and prediction of the disease but majority of them have neglected the aspect of data pre-processing and dimensionality reduction, leading to biased results. The dataset used in the present study is a diabetes retinopathy dataset collected from the UCI machine learning repository. At its inceptions, the raw dataset is normalized using the Standardscalar technique and then Principal Component Analysis (PCA) is used to extract the most significant features in the dataset. Further, Firefly algorithm is implemented for dimensionality reduction. This reduced dataset is fed into a Deep Neural Network Model for classification. The results generated from the model is evaluated against the prevalent machine learning models and the results justify the superiority of the proposed model in terms of Accuracy, Precision, Recall, Sensitivity and Specificity.

Download Full-text

Application of Benford’s Law on Cryptocurrencies

10.20944/preprints202111.0472.v1 ◽

2021 ◽

Author(s):

Jernej Vičič ◽

Aleksandar Tošić

Keyword(s):

Machine Learning ◽

Anomalous Behavior ◽

Use Cases ◽

Disruptive Technology ◽

Graph Analysis ◽

Established Method ◽

Fine Grained ◽

The Past ◽

Time Period ◽

The Law

Blockchain-based currencies or cryptocurrencies have become a global phenomenon known to most people as a disruptive technology, and a new investment vehicle. However, due to their decentralized nature, regulating these markets has presented regulators with difficulties in finding a balance between nurturing innovation, and protecting consumers. The growing concerns about illicit activity have forced regulators to seek new ways of detecting, analyzing, and ultimately policing public blockchain transactions. Extensive research on machine learning, and transaction graph analysis algorithms has been done to track suspicious behaviour. However, having a macro view of a public ledger is equally important before pursuing a more fine-grained analysis. Benford’s law, the law of first digit, has been extensively used as a tool to discover accountant frauds (many other use cases exist). The basic motivation that drove our research presented in this paper was to test he applicability of the well established method to a new domain, in this case the identification of anomalous behavior using Benford’s law conformity test to the cryptocurrency domain. The research focused on transaction values in all major cryptocurrencies. A suitable time-period was identified that was long enough to sport sufficiently large number of observations for Benford’s law conformity tests and was also situated long enough in the past so that the anomalies were identified and well documented. The results show that most of the cryptocurrencies that did not conform to Benford’s law had well documented anomalous incidents, the first digits of aggregated transaction values of all well known cryptocurrency projects were conforming to Benford’s law. Thus the proposed method is applicable to the new domain.

Download Full-text

Recursive Stock Price Prediction With Machine Learning And Web Scrapping For Specified Time Period

2019 Sixteenth International Conference on Wireless and Optical Communication Networks (WOCN) ◽

10.1109/wocn45266.2019.8995080 ◽

2019 ◽

Author(s):

Bikrant Bikram P. Maurya ◽

Ayush Ray ◽

Aman Upadhyay ◽

Bhupesh Gour ◽

Asif Ullah Khan

Keyword(s):

Machine Learning ◽

Stock Price ◽

Stock Price Prediction ◽

Price Prediction ◽

Time Period

Download Full-text

Road Accidents Analysis Using Comparative Study & Application of Machine Learning Algorithms

WSEAS TRANSACTIONS ON COMPUTER RESEARCH ◽

10.37394/232018.2021.9.9 ◽

2021 ◽

Vol 9 ◽

pp. 78-86

Author(s):

Arnav Saini ◽

Nipun Gauba ◽

Hardik Chawla ◽

Jabir Ali

Keyword(s):

Machine Learning ◽

Real World ◽

Autonomous Vehicles ◽

Human Life ◽

Analysis Data ◽

Road Accident ◽

Machine Learning Algorithms ◽

Road Accidents ◽

Time Period ◽

Real World Problems

Model predictive contrTraffic Collisions are one of the major sources of deaths, injuries & property damage every year. Road accidents are one of the most difficult real world problems to tackle with, due to its high order of unpredictability. The persistence as well as existence of this problem may be prevalent to a different degree for each & every place. The consequences of this may result in loss of human life & capital. To avoid this, every place needs to tackle the problem with a customized approach depending on the causes that are responsible for the accidents. Even in today's world, where the mass operation of autonomous vehicles is still grim or out of sight, the possibility of predicting a road accident before it takes place, is practically impossible. The only idea or approach that can help to decrease the number of road accidents, is to analyze the reasons that lead to these accidents. The concepts of Data Analysis, Data Visualization & Machine Learning help to tackle real world problems, by exploring & deriving valuable insights, which in turn help in taking measures to solve the targeted problem & drive business growth. In this research study, the dataset pertaining to road mishaps that occurred in UK over time period 2005 - 2015 will be analyzed using these concepts. The defined approach can help the concerned authorities & respective government, to take every possible step & amendment, & hence mitigate the identified causes & scenarios that lead to road accidents.

Download Full-text

Improving Pre-eclampsia Risk Prediction by Modeling Individualized Pregnancy Trajectories Derived from Routinely Collected Electronic Medical Record Data

10.1101/2021.03.23.21254178 ◽

2021 ◽

Author(s):

Shilong Li ◽

Zichen Wang ◽

Luciana A. Vieira ◽

Amanda B. Zheutlin ◽

Boshu Ru ◽

...

Keyword(s):

Machine Learning ◽

Risk Factors ◽

At Risk ◽

Complete Blood Count ◽

Early Recognition ◽

Training Dataset ◽

Validation Dataset ◽

Time Period ◽

Patients At Risk ◽

Mount Sinai

ABSTRACTPreeclampsia (PE) is a heterogeneous and complex disease associated with rising morbidity and mortality in pregnant women and newborns in the US. Early recognition of patients at risk is a pressing clinical need to significantly reduce the risk of adverse pregnancy outcomes. We assessed whether information routinely collected and stored on women in their electronic medical records (EMR) could enhance the prediction of PE risk beyond what is achieved in standard of care assessments today. We developed a digital phenotyping algorithm to assemble and curate 108,557 pregnancies from EMRs across the Mount Sinai Health System (MSHS), accurately reconstructing pregnancy journeys and normalizing these journeys across different hospital EMR systems. We then applied machine learning approaches to a training dataset from Mount Sinai Hospital (MSH) (N = 60,879) to construct predictive models of PE across three major pregnancy time periods (ante-, intra-, and postpartum). The resulting models predicted PE with high accuracy across the different pregnancy periods, with areas under the receiver operating characteristic curves (AUC) of 0.92, 0.83 and 0.89 at 37 gestational weeks, intrapartum and postpartum, respectively. We observed comparable performance in two independent patient cohorts with diverse patient populations (MSH validation dataset N = 38,421 and Mount Sinai West dataset N = 9,257). While our machine learning approach identified known risk factors of PE (such as blood pressure, weight and maternal age), it also identified novel PE risk factors, such as complete blood count related characteristics for the antepartum time period and ibuprofen usage for the postpartum time period. Our model not only has utility for earlier identification of patients at risk for PE, but given the prediction accuracy substantially exceeds what is achieved today in clinical practice, our model provides a path for promoting personalized precision therapeutic strategies for patients at risk.

Download Full-text

Forecasting Financial Distress With Machine Learning – A Review

Future Studies Research Journal Trends and Strategies ◽

10.24023/futurejournal/2175-5825/2020.v12i3.533 ◽

2020 ◽

Vol 12 (3) ◽

pp. 528-574

Author(s):

Denize Lemos Duarte ◽

Flávio Luiz de Moraes Barboza

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Credit Risk ◽

Financial Distress ◽

Computational Models ◽

Web Of Science ◽

Time Period ◽

Credit Risk Analysis ◽

New Variables ◽

Computational Technology

Purpose – Evaluate the various academic researches with multiple views on credit risk and artificial intelligence (AI) and their evolution.Theoretical framework – The study is divided as follows: Section 1 introduces the article. Section 2 deals with credit risk and its relationship with computational models and techniques. Section 3 presents the methodology. Section 4 addresses a discussion of the results and challenges on the topic. Finally, section 5 presents the conclusions.Design/methodology/approach – A systematic review of the literature was carried out without defining the time period and using the Web of Science and Scopus database.Findings – The application of computational technology in the scope of credit risk analysis has drawn attention in a unique way. It was found that the demand for identification and introduction of new variables, classifiers and more assertive methods is constant. The effort to improve the interpretation of data and models is intense.Research, Practical Social implications – It contributes to the verification of the theory, providing information in relation to the most used methods and techniques, it brings a wide analysis to deepen the knowledge of the factors and variables on the theme. It categorizes the lines of research and provides a summary of the literature, which serves as a reference, in addition to suggesting future research.Originality/value – Research in the area of Artificial Intelligence and Machine Learning is recent and requires attention and investigation, thus, this study contributes to the opening of new views in order to deepen the work on this topic.

Download Full-text

Use of Machine Learning in Stock Market Prediction

European Journal of Technology ◽

10.47672/ejt.634 ◽

2020 ◽

Vol 4 (1) ◽

pp. 60-73

Author(s):

Memoona Shaheen ◽

Mehreen Arshad

Keyword(s):

Machine Learning ◽

Policy Implications ◽

Machine Learning Techniques ◽

Support Vector ◽

Hybrid Techniques ◽

Current Trends ◽

Time Period ◽

Learning Techniques ◽

Vector Machines ◽

Prediction Problems

Objective: The objective of this study was to examine and determine future directions in regard to future machine learning techniques based on the review of the current literature. Methodology: A systematic review has been used to review the current trends from the peer-reviewed journal articles in the past twenty years. For this study, four categories have been categorized, the use of neural networks, support vector machines, the use of a genetic algorithm, and the combination of hybrid techniques. Studies in each of these categorize have been evaluated. Finding: Firstly, there is a strong link between machine learning methods and the prediction problems they are associated with. The second conclusion that we can conclude from this review is that past studies need to improve its generalizability results. Most of the studies that have been reviewed in this analysis has only used the machine learning systems through the use of one market or during only a one time period without taking into consideration whether the system would be adaptable in other situations and conditions. Limitations, future trends, as well as policy implications have been defined.

Download Full-text

Parametric model for flora detection in Middle Himalayas

International Journal of Decision Support System Technology ◽

10.4018/ijdsst.286698 ◽

2022 ◽

Vol 14 (1) ◽

pp. 0-0

Keyword(s):

Machine Learning ◽

Parametric Model ◽

Plant Family ◽

Common People ◽

Major Drawback ◽

Time Period ◽

Plant Sciences

Plant detection forms an integral part of the life of the forest guards, researchers, and students in the field of Botany and for common people also who are curious about knowing a plant. But detecting plants suffer a major drawback that the true identifier is only the flower and in certain species flowering occurs at major time period gaps spanning from few months to over 100 years (in certain types of bamboos). Machine Learning-based systems could be used in developing models where the experience of researchers in the field of plant sciences can be incorporated into the model. In this paper, we present a machine learning-based approach based upon other quantifiable parameters for the detection of the plant presented. The system takes plant parameters as the inputs and will detect the plant family as the output.

Download Full-text