Machine Learning in the Hands of a Malicious Adversary: A Near Future If Not Reality 1

With the widespread use of artificial intelligence (AI) systems and applications in our everyday lives, accounting for fairness has gained significant importance in designing and engineering of such systems. AI systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that these decisions do not reflect discriminatory behavior toward certain groups or populations. More recently some work has been developed in traditional machine learning and deep learning that address such challenges in different subdomains. With the commercialization of these systems, researchers are becoming more aware of the biases that these applications can contain and are attempting to address them. In this survey, we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and ways they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields.

Download Full-text

An Application of Predictive Analytics in Manufacturing Sector for Price Prediction and Demand Prediction

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.h6465.079920 ◽

2020 ◽

Vol 9 (9) ◽

pp. 196-199

Keyword(s):

Machine Learning ◽

Historical Data ◽

Predictive Analytics ◽

Manufacturing Sector ◽

Regression Tree ◽

Machine Learning Algorithms ◽

Demand Prediction ◽

Price Prediction ◽

Near Future ◽

Overall Functioning

Predictive analytics is the examination of concerned data so that we can recognize the problem that may arise in the near future. Manufacturers are interested in quality control, and making sure that the whole factory is functioning at the best possible efficiency. Hence, it’s feasible to increase manufacturing quality, and expect needs throughout the factory with predictive analytics. Hence, we have proposed an application of predictive analytics in manufacturing sector especially focused on price prediction and demand prediction of various products that get manufactured on regular basis. We have trained and tested different machine learning algorithms that can be used to predict price as well as demand of a particular product using historical data about that product’s sales and other transactions. Out of these different tested algorithms, we have selected the regression tree algorithm which gives accuracy of 95.66% for demand prediction and 88.85% for price prediction. Therefore, Regression Tree is best suited for use in manufacturing sector as long as price prediction and demand prediction of a product is concerned. Thus, the proposed application can help the manufacturing sector to improve its overall functioning and efficiency using the price prediction and demand prediction of products.

Download Full-text

Deep Learning Network

Advances in Computer and Electrical Engineering - Neural Networks for Natural Language Processing ◽

10.4018/978-1-7998-1159-6.ch001 ◽

2020 ◽

pp. 1-30

Author(s):

Bhanu Chander

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Deep Learning ◽

Great Power ◽

Human Being ◽

Technology Improvement ◽

Deep Learning Network ◽

High Level ◽

Human Brains ◽

Near Future

Artificial intelligence (AI) is defined as a machine that can do everything a human being can do and produce better results. Means AI enlightening that data can produce a solution for its own results. Inside the AI ellipsoidal, Machine learning (ML) has a wide variety of algorithms produce more accurate results. As a result of technology, improvement increasing amounts of data are available. But with ML and AI, it is very difficult to extract such high-level, abstract features from raw data, moreover hard to know what feature should be extracted. Finally, we now have deep learning; these algorithms are modeled based on how human brains process the data. Deep learning is a particular kind of machine learning that provides flexibility and great power, with its attempts to learn in multiple levels of representation with the operations of multiple layers. Deep learning brief overview, platforms, Models, Autoencoders, CNN, RNN, and Appliances are described appropriately. Deep learning will have many more successes in the near future because it requires very little engineering by hand.

Download Full-text

The Ultimate Data Flow for Ultimate Super Computers-on-a-Chip

Advances in Systems Analysis, Software Engineering, and High Performance Computing - Handbook of Research on Methodologies and Applications of Supercomputing ◽

10.4018/978-1-7998-7156-9.ch021 ◽

2021 ◽

pp. 312-318

Author(s):

Veljko Milutinović ◽

Miloš Kotlar ◽

Ivan Ratković ◽

Nenad Korolija ◽

Miljan Djordjevic ◽

...

Keyword(s):

Machine Learning ◽

Systolic Array ◽

Data Flow ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Flexible Structure ◽

Quantum Optical ◽

Many Core ◽

Fixed Structure ◽

Near Future

This chapter starts from the assumption that near future 100BTransistor SuperComputers-on-a-Chip will include N big multi-core processors, 1000N small many-core processors, a TPU-like fixed-structure systolic array accelerator for the most frequently used machine learning algorithms needed in bandwidth-bound applications, and a flexible-structure reprogrammable accelerator for less frequently used machine learning algorithms needed in latency-critical applications. The future SuperComputers-on-a-Chip should include effective interfaces to specific external accelerators based on quantum, optical, molecular, and biological paradigms, but these issues are outside the scope of this chapter.

Download Full-text

Understanding and predicting ciprofloxacin minimum inhibitory concentration in Escherichia coli with machine learning

Scientific Reports ◽

10.1038/s41598-020-71693-5 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Bálint Ármin Pataki ◽

◽

Sébastien Matamoros ◽

Boas C. L. van der Putten ◽

Daniel Remondini ◽

...

Keyword(s):

Machine Learning ◽

Escherichia Coli ◽

Minimum Inhibitory Concentration ◽

Inhibitory Concentration ◽

Model Concept ◽

Susceptibility Data ◽

Genome Wide ◽

Antimicrobial Resistance Genes ◽

Machine Learning Approach ◽

Near Future

Abstract It is important that antibiotics prescriptions are based on antimicrobial susceptibility data to ensure effective treatment outcomes. The increasing availability of next-generation sequencing, bacterial whole genome sequencing (WGS) can facilitate a more reliable and faster alternative to traditional phenotyping for the detection and surveillance of AMR. This work proposes a machine learning approach that can predict the minimum inhibitory concentration (MIC) for a given antibiotic, here ciprofloxacin, on the basis of both genome-wide mutation profiles and profiles of acquired antimicrobial resistance genes. We analysed 704 Escherichia coli genomes combined with their respective MIC measurements for ciprofloxacin originating from different countries. The four most important predictors found by the model, mutations in gyrA residues Ser83 and Asp87, a mutation in parC residue Ser80 and presence of the qnrS1 gene, have been experimentally validated before. Using only these four predictors in a linear regression model, 65% and 93% of the test samples’ MIC were correctly predicted within a two- and a four-fold dilution range, respectively. The presented work does not treat machine learning as a black box model concept, but also identifies the genomic features that determine susceptibility. The recent progress in WGS technology in combination with machine learning analysis approaches indicates that in the near future WGS of bacteria might become cheaper and faster than a MIC measurement.

Download Full-text

Unlocking the Universe with Astroinformatics

Proceedings of the International Astronomical Union ◽

10.1017/s1743921318002570 ◽

2017 ◽

Vol 14 (S339) ◽

pp. 201-201

Author(s):

M. Lochner

Keyword(s):

Machine Learning ◽

Data Mining ◽

Bayesian Statistics ◽

Time Domain ◽

Meaningful Information ◽

Broad Field ◽

Near Future ◽

The Universe

AbstractIn the last decade Astronomy has been transformed by a deluge of data that will grow exponentially when near-future telescopes such as LSST and the SKA begin routine observing. Astroinformatics, a broad field encompassing many techniques in statistics, machine learning and data mining, is the key to extracting meaningful information from large amounts of data. This talk outlined Astroinformatics as a field, and gave a few examples of the use of machine learning and Bayesian statistics from my own work in survey Astronomy. The era of massive surveys in which we now find ourselves has the potential to revolutionise completely many fields, including time-domain Astronomy, but only if coupled with the powerful tools of Astroinformatics.

Download Full-text

Recognition and Classification of Human Activity by Posture Sensing and Machine Learning

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.468-471.2916 ◽

2012 ◽

Vol 468-471 ◽

pp. 2916-2919

Author(s):

Fan Yang ◽

Yu Chuan Wu

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Human Activity ◽

Learning Algorithm ◽

Optimal Parameter ◽

Support Vector ◽

Rbf Kernel ◽

Human Activity Detection ◽

Near Future

This paper describes how to use a posture sensor to validate human daily activity and by machine learning algorithm - Support Vector Machine (SVM) an outstanding model is built. The optimal parameter σ and c of RBF kernel SVM were obtained by searching automatically. Those kinematic data was carried out through three major steps: wavelet transformation, Principle Component Analysis (PCA) -based dimensionality reduction and k-fold cross-validation, followed by implementing a best classifier to distinguish 6 difference actions. As an activity classifier, the SVM (Support Vector Machine) algorithm is used, and we have achieved over 94.5% of mean accuracy in detecting differential actions. It shows that the verification approach based on the recognition of human activity detection is valuable and will be further explored in the near future.

Download Full-text

A Comparative Study using Feature Selection to Predict the Behaviour of Bank Customers

E3S Web of Conferences ◽

10.1051/e3sconf/202018401011 ◽

2020 ◽

Vol 184 ◽

pp. 01011

Author(s):

Sreethi Musunuru ◽

Mahaalakshmi Mukkamala ◽

Latha Kunaparaju ◽

N V Ganapathi Raju

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Random Forest ◽

Random Forest Classifier ◽

Customer Behavior ◽

Machine Learning Algorithms ◽

The Status ◽

Personal Level ◽

Near Future ◽

Structure Communication

Though banks hold an abundance of data on their customers in general, it is not unusual for them to track the actions of the creditors regularly to improve the services they offer to them and understand why a lot of them choose to exit and shift to other banks. Analyzing customer behavior can be highly beneficial to the banks as they can reach out to their customers on a personal level and develop a business model that will improve the pricing structure, communication, advertising, and benefits for their customers and themselves. Features like the amount a customer credits every month, his salary per annum, the gender of the customer, etc. are used to classify them using machine learning algorithms like K Neighbors Classifier and Random Forest Classifier. On classifying the customers, banks can get an idea of who will be continuing with them and who will be leaving them in the near future. Our study determines to remove the features that are independent but are not influential to determine the status of the customers in the future without the loss of accuracy and to improve the model to see if this will also increase the accuracy of the results.

Download Full-text

State of the Art in Computational Bioacoustics and Machine Learning: How far have we come?

Biodiversity Information Science and Standards ◽

10.3897/biss.3.37227 ◽

2019 ◽

Vol 3 ◽

Author(s):

Dan Stowell

Keyword(s):

Machine Learning ◽

Big Data ◽

Deep Learning ◽

State Of The Art ◽

Learning Networks ◽

Recent Developments ◽

Audio Data ◽

Ecological Applications ◽

Near Future ◽

Statistical Ecology

Terrestrial bioacoustics, like many other domains, has recently witnessed some transformative results from the application of deep learning and big data (Stowell 2017, Mac Aodha et al. 2018, Fairbrass et al. 2018, Mercado III and Sturdy 2017). Generalising over specific projects, which bioacoustic tasks can we consider "solved"? What can we expect in the near future, and what remains hard to do? What does a bioacoustician need to understand about deep learning? This contribution will address these questions, giving the audience a concise summary of recent developments and ways forward. It builds on recent projects and evaluation campaigns led by the author (Stowell et al. 2015, Stowell et al. 2018), as well as broader developments in signal processing, machine learning and bioacoustic applications of these. We will discuss which type of deep learning networks are appropriate for audio data, how to address zoological/ecological applications which often have few available data, and issues in integrating deep learning predictions with existing workflows in statistical ecology.

Download Full-text

Discovering hidden information in biosignals from patients using artificial intelligence

Korean Journal of Anesthesiology ◽

10.4097/kja.19475 ◽

2020 ◽

Vol 73 (4) ◽

pp. 275-284

Author(s):

Dukyong Yoon ◽

Jong-Hwan Jang ◽

Byung Jin Choi ◽

Tae Young Kim ◽

Chang Ho Han

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Deep Learning ◽

Medical Condition ◽

Real Life ◽

Black Box ◽

Basic Knowledge ◽

Hidden Information ◽

Near Future ◽

Invasive Evaluation

Biosignals such as electrocardiogram or photoplethysmogram are widely used for determining and monitoring the medical condition of patients. It was recently discovered that more information could be gathered from biosignals by applying artificial intelligence (AI). At present, one of the most impactful advancements in AI is deep learning. Deep learning-based models can extract important features from raw data without feature engineering by humans, provided the amount of data is sufficient. This AI-enabled feature presents opportunities to obtain latent information that may be used as a digital biomarker for detecting or predicting a clinical outcome or event without further invasive evaluation. However, the black box model of deep learning is difficult to understand for clinicians familiar with a conventional method of analysis of biosignals. A basic knowledge of AI and machine learning is required for the clinicians to properly interpret the extracted information and to adopt it in clinical practice. This review covers the basics of AI and machine learning, and the feasibility of their application to real-life situations by clinicians in the near future.

Download Full-text