Artificial Intelligence

1907 Submissions

[21] viXra:1907.0605 [pdf] submitted on 2019-07-30 22:19:29

[ Python Theorem Provers+apache-Mxnet+restricted Boltzmann Machine (Rbm)/boltzmann Machines +qrng/quantum Device] in the Context of Dna/rna Based Informatics & Bio-Chemical Sensing Networks – an Interesting R&D Insight Into the World of [ Dna/rna ]

Authors: Nirmal Tej Kumar
Comments: 3 Pages. Short Communication & Simple Suggestion

[ Python Theorem Provers+Apache-MXNet+Restricted Boltzmann Machine (RBM)/Boltzmann Machines +QRNG/Quantum Device] in the Context of DNA/RNA based Informatics & Bio-Chemical Sensing Networks – An Interesting R&D insight into the World of [ DNA/RNA ] based Hybrid Machine Learning Informatics Framework/s.
Category: Artificial Intelligence

[20] viXra:1907.0489 [pdf] submitted on 2019-07-26 00:26:22

Taylor Series Prediction of Time Series Data with Error Propagated by Artificial Neural Network

Authors: B. Ravi Sankar, S. Alamelu Mangai, K. Alagarsamy, Ph D
Comments: 7 Pages.

Modeling and forecasting of a time series data is an integral part of the Data Mining. Sun spot numbers observed on the sun are a good candidate for a time series. A number of linear statistical models are discussed in this paper because Taylor series has similarity with an Auto Regressive model. A new algorithm based on Taylor series expansion and artificial neural network is presented. Based on Taylor series algorithm and ARIMA model, the Sunspot numbers are forecasted and compared
Category: Artificial Intelligence

[19] viXra:1907.0487 [pdf] submitted on 2019-07-26 00:37:42

Hybrid ARIMA-HyFIS Model for Forecasting Univariate Time Series

Authors: B. Ravi Sankar, S. Alamelu Mangai, K. Alagarsamy, Ph D, Kasinathan Subramanian
Comments: 7 Pages.

In this paper, a novel hybrid model for fitting and forecasting a univariate time series is developed based on ARIMA and HyFIS models. The linear part is fitted using ARIMA model whereas the non-linear residual is fitted using HyFIS model. Clustering technique is used to determine the number of inputs and the membership functions of the HyFIS model. The hybrid model is applied to the wind speed data. The result is analyzed and compared on the basis of standalone ARIMA, standalone HyFIS and for the hybrid ARIMA-HyFIS model.
Category: Artificial Intelligence

[18] viXra:1907.0474 [pdf] submitted on 2019-07-24 09:18:57

AI's Current Hype and Hysteria

Authors: George Rajna
Comments: 41 Pages.

Most discussions about artificial intelligence (AI) are characterised by hyperbole and hysteria. [25] The New York Times contacted IBM Research in late September asking for our help to use AI in a clever way to create art for the coming special section on AI. [24] Granting human rights to a computer would degrade human dignity. [23] IBM researchers are developing a new computer architecture, better equipped to handle increased data loads from artificial intelligence. [22] A computer built to mimic the brain's neural networks produces similar results to that of the best brain-simulation supercomputer software currently used for neural-signaling research, finds a new study published in the open-access journal Frontiers in Neuroscience. [21]
Category: Artificial Intelligence

[17] viXra:1907.0464 [pdf] submitted on 2019-07-25 00:02:32

[ Genetic Algorithms+Bayesian Networks ] in the Context of Anticipatory Systems Using a Quantum Device/QRNG – An AI/ML/DL based [ Java/JikesRVM(RVM - Research Virtual Machine)/Java Virtual Machine(JVM)/BNJ/Jenetics/JI Prolog/jBNCSoftware ] Approach

Authors: Nirmal Tej Kumar
Comments: 1 Page. Short Communication & Simple Suggestion

[ Genetic Algorithms+Bayesian Networks ] in the Context of Anticipatory Systems Using a Quantum Device/QRNG – An AI/ML/DL based [ Java/JikesRVM(RVM - Research Virtual Machine)/Java Virtual Machine(JVM)/BNJ/Jenetics/JI Prolog/jBNC Software ] Approach in the IoT/HPC Heterogeneous Computational R&D Environments. [ Java based Artificial Intelligence in Electron Microscopy/Medicine/Bio-informatics ]
Category: Artificial Intelligence

[16] viXra:1907.0389 [pdf] submitted on 2019-07-21 05:14:30

Machine Learning Polymers

Authors: George Rajna
Comments: 44 Pages.

Reporting their findings in the open-access journal npj Computational Materials, the researchers show that their ML method, involving "transfer learning," enables the discovery of materials with desired properties even from an exceeding small data set. [26] The analysis of sensor data of machines, plants or buildings makes it possible to detect anomalous states early and thus to avoid further damage. [25] Physicists in the US have used machine learning to determine the phase diagram of a system of 12 idealized quantum particles to a higher precision than ever before. [24] The research group took advantage of a system at SLAC's Stanford Synchrotron Radiation Lightsource (SSRL) that combines machine learning-a form of artificial intelligence where computer algorithms glean knowledge from enormous amounts of data-with experiments that quickly make and screen hundreds of sample materials at a time. [23] Researchers at the UCLA Samueli School of Engineering have demonstrated that deep learning, a powerful form of artificial intelligence, can discern and enhance microscopic details in photos taken by smartphones. [22] Such are the big questions behind one of the new projects underway at the MIT-IBM Watson AI Laboratory, a collaboration for research on the frontiers of artificial intelligence. [21]
Category: Artificial Intelligence

[15] viXra:1907.0324 [pdf] submitted on 2019-07-16 10:57:35

Artificial Intelligence Design Metamaterials

Authors: George Rajna
Comments: 42 Pages.

Metamaterials are artificial materials engineered to have properties not found in naturally occurring materials, and they are best known as materials for invisibility cloaks often featured in sci-fi novels or games. [24] The research group took advantage of a system at SLAC's Stanford Synchrotron Radiation Lightsource (SSRL) that combines machine learning-a form of artificial intelligence where computer algorithms glean knowledge from enormous amounts of data-with experiments that quickly make and screen hundreds of sample materials at a time. [23] Researchers at the UCLA Samueli School of Engineering have demonstrated that deep learning, a powerful form of artificial intelligence, can discern and enhance microscopic details in photos taken by smartphones. [22] Such are the big questions behind one of the new projects underway at the MIT-IBM Watson AI Laboratory, a collaboration for research on the frontiers of artificial intelligence. [21]
Category: Artificial Intelligence

[14] viXra:1907.0306 [pdf] submitted on 2019-07-17 03:13:14

An Insight Into [ Random Numbers-QRNG-Ai/machine Learning Libraries/mruby/ruby/ruby-Machine Learning/jiprolog ] Interaction Within the Context of Telecom Hardware Configuration & Prevention of Cyber Threats.

Authors: Nirmal Tej Kumar
Comments: 2 Pages. Short Communication & Simple Suggestion

An Insight into [ Random Numbers-QRNG-AI/Machine Learning Libraries/mruby/Ruby/Ruby-Machine Learning/JIProlog ] interaction within the Context of Telecom Hardware Configuration & Prevention of Cyber Threats. [AI/ML/Randomness/Random Numbers & Challenging Applications in IT/Telecom Domains ]
Category: Artificial Intelligence

[13] viXra:1907.0239 [pdf] submitted on 2019-07-14 09:45:59

Machine Learning Butterfly Wings

Authors: George Rajna
Comments: 52 Pages.

Researchers from the University of Pittsburgh's Swanson School of Engineering have created a nanostructure glass that takes inspiration from the wings of the glasswing butterfly to create a new type of glass that is not only very clear across a wide variety of wavelengths and angles, but is also antifogging. [28] Machine learning and automation technologies are gearing up to transform the radiation-therapy workflow while freeing specialist clinical and technical staff to dedicate more time to patient care. [27] Navid Borhani, a research-team member, says this machine learning approach is much simpler than other methods to reconstruct images passed through optical fibers, which require making a holographic measurement of the output. [26]
Category: Artificial Intelligence

[12] viXra:1907.0201 [pdf] submitted on 2019-07-13 04:22:30

Testing a Combination of [ AI/ML/IoT/HPC ] Heterogeneous Computing Concepts based on MXNet/Flux in the Context of Cryo-EM Image Processing & Informatics Using [ Julia+JNI+Java+(ImageJ/Fiji)+JikesRVM - Research Virtual Machine ] - A Simple Suggestion

Authors: Nirmal Tej Kumar
Comments: 5 Pages. Short Communication & Simple Suggestion

Testing a Combination of [ AI/ML/IoT/HPC ] Heterogeneous Computing Concepts based on MXNet/Flux in the Context of Cryo-EM Image Processing & Informatics Using [ Julia+JNI+Java+(ImageJ/Fiji)+JikesRVM - Research Virtual Machine ] - A Simple Suggestion towards Novel Design of Electron Microscopy(EM) Image Processing Frameworks for better [ Nano-Bio] Informatics R&D. [ Exploring EM Images With Julia +Java – an Interesting ML based Intelligent Approach ] [ Julia - “Walks like python. Runs like C.” ]
Category: Artificial Intelligence

[11] viXra:1907.0195 [pdf] submitted on 2019-07-11 23:08:30

Understanding & Probing [ Orvil Perl Library+ai::mxnet Perl Interface to Mxnet Machine Learning Library ] in the Context of Bio-Chemical Information Systems Framework W.r.t R&D of Drug Design Aspects – an Interesting Insight Into Perl Interfacing Concep

Authors: Nirmal Tej Kumar
Comments: 3 Pages. Short Communication & Simple Suggestion

Understanding & Probing [ Orvil Perl Library+AI::MXNet - Perl interface to MXNet Machine Learning Library ] in the Context of Bio-Chemical Information Systems Framework w.r.t R&D of Drug Design Aspects – An Interesting Insight into Perl Interfacing Concepts & Anticipatory Chemical Computing Paradigms. [ Understanding ‘Scaffold Hopping’ from Chemical Computing & ML View Point ] [ AI::MXNet - Perl interface to MXNet machine learning library ]
Category: Artificial Intelligence

[10] viXra:1907.0188 [pdf] submitted on 2019-07-12 04:53:53

Nanophotonic Artificial Vision

Authors: George Rajna
Comments: 54 Pages.

A simple, passive photonic structure made only of glass and air bubbles could perform artificial neural computing for applications in areas like facial recognition. [30] Most artificial intelligence (AI) systems try to replicate biological mechanisms and behaviors observed in nature. [29] "We basically combined advances in neural networks and machine-learning with quantum Monte Carlo tools," says Savona, referring to a large toolkit of computational methods that physicists use to study complex quantum systems. [28] As cosmologists and astrophysicists delve deeper into the darkest recesses of the universe, their need for increasingly powerful observational and computational tools has expanded exponentially. [27] Now, a team of scientists at MIT and elsewhere has developed a neural network, a form of artificial intelligence (AI), that can do much the same thing, at least to a limited extent: It can read scientific papersand render a plain-English summary in a sentence or two. [26] To address this gap in the existing literature, a team of researchers at SRI International has created a human-AI image guessing game inspired by the popular game 20 Questions (20Q), which can be used to evaluate the helpfulness of machine explanations. [25]
Category: Artificial Intelligence

[9] viXra:1907.0182 [pdf] submitted on 2019-07-12 07:47:56

A Novel Low Complexity Fast Response Time Fuzzy PID Controller for Antenna Adjusting Using Two Direct Current Motors

Authors: Vahid Rahmati, Amir Ghorbani
Comments: 8 Pages.

Objectives: A novel PID Controller (PIDC) for the purpose of adjusting an antenna in 360 degrees range by direct current (DC) motors using Fuzzy method is designed and simulated. Methods: For this, first, an accurate model for DC motor in simulations is developed- that can be replaced by any other dynamic, for e.g., a high power low speed motor, however, the response in this case will be different. The controller mentioned uses the Mamdani type in two working modes with 3 and 4 inputs setting the full control of two independent DC Motors (DCMs). Findings: Clearly, the modes with 3 and 4 inputs occupy 27 and 81 commands respectively to have smooth overshoot and under shoot responses. Some of the parameters are acquired experimentally that can be modified for various applications, although these values are also remarked for the possible re-simulation by the readers. Application: However the PIDCs have many applications in industry, the main application of our PIDC is intended for radar systems where the antenna needs to quickly rotate in order to accurately receive the reflections from certain paths.
Category: Artificial Intelligence

[8] viXra:1907.0179 [pdf] submitted on 2019-07-12 09:06:31

Intuitionistic Fuzzy Decision-Making in the Framework of Dempster-Shafer Structures

Authors: Liguo Fei
Comments: 15 Pages.

The main emphasis of this paper is placed on the problem of multi-criteria decision making (MCDM) in intuitionistic fuzzy environments. Some limitations in the existing literature that explains Atanassov’ intuitionistic fuzzy sets (A-IFS) from the perspective of Dempster-Shafer theory (DST) of evidence have been analyzed. To address the issues of using Dempster’s rule to aggregate intuitionistic fuzzy values (IFVs), a novel aggregation operator named OWA-based MOS is proposed based on ordered weighted averaging (OWA) aggregation operator, which allows the expression of decision makers’ subjectivity by introducing the attitudinal character. The effectiveness of the developed OWAbased MOS approach in aggregating IFVs is demonstrated by the known example of MCDM problem. To compare different IFVs obtained from the OWA-based MOS approach, the golden rule representative value for IFVs comparison is introduced, which can get over the shortcomings of score functions. The hierarchical structure of the proposed decision approach is presented based on the above researches, which allow us to solve MCDM problem without intermediate defuzzification when not only criteria, but their weights are represented by IFVs. The proposed OWA-based MOS approach is illustrated as a more flexible decision-making method, which can better solve the problem of intuitionistic fuzzy multi-criteria decision making in the framework of DST.
Category: Artificial Intelligence

[7] viXra:1907.0173 [pdf] submitted on 2019-07-10 13:46:57

Outlier Modeling in Gear Bearing Using Autoencoder for Remaining Useful Life Prediction

Authors: Sunny Singh, Atif Ahmed, Praneet Shiv
Comments: 7 Pages.

In this paper, we introduce the Prognostics and Health Management of gear bearing system using autoencoder neural networks. Bearings and gears are the most common mechanical components in rotating machines, and their health conditions are of great concern in practice. This study presents an outlier modeling method for forecasting the gear bearing system failure using the health indicators constructed from mechanical signal processing and modeling. Outlier modeling aims to find patterns in data that are significantly different from what is defined as normal. In the unsupervised outlier modeling setting, prior labels about the anomalousness of data points are not available. In such cases, the most common techniques for scoring data points for outlyingness include distance-based methods density-based methods, and linear methods. The conventional outlier modeling methods have been used for a long time to detect anomalous observations in data. However, this paper shows that autoencoders are a very competitive technique compared to other existing methods. The developed method is demonstrated using the IMS bearing data from NASA Acoustics and Vibration Database.
Category: Artificial Intelligence

[6] viXra:1907.0083 [pdf] submitted on 2019-07-06 01:12:42

Revisiting “Nucleic Acids Data Sequencing using Higher Order Logic-A Suggestion of Basic Computational Framework Towards Bio-Sensors and Gene-Chips Design, Implementation and Verification”.

Authors: D.N.T.Kumar
Comments: 2 Pages. Short Communication & Simple Suggestion

Revisiting “Nucleic Acids Data Sequencing using Higher Order Logic-A Suggestion of Basic Computational Framework Towards Bio-Sensors and Gene-Chips Design, Implementation and Verification”. [“Novel Design by modification/extension of the above mentioned TITLE/IDEA Using HOL & HOL based Deep Learning(DL) Library”].Deep Learning for Next Generation DNA/RNA Sequencing Applications.
Category: Artificial Intelligence

[5] viXra:1907.0072 [pdf] submitted on 2019-07-04 13:05:11

Artificial Synapsis for Pattern Recognition

Authors: George Rajna
Comments: 51 Pages.

Most artificial intelligence (AI) systems try to replicate biological mechanisms and behaviors observed in nature. [29] "We basically combined advances in neural networks and machine-learning with quantum Monte Carlo tools," says Savona, referring to a large toolkit of computational methods that physicists use to study complex quantum systems. [28] As cosmologists and astrophysicists delve deeper into the darkest recesses of the universe, their need for increasingly powerful observational and computational tools has expanded exponentially. [27] Now, a team of scientists at MIT and elsewhere has developed a neural network, a form of artificial intelligence (AI), that can do much the same thing, at least to a limited extent: It can read scientific papersand render a plain-English summary in a sentence or two. [26] To address this gap in the existing literature, a team of researchers at SRI International has created a human-AI image guessing game inspired by the popular game 20 Questions (20Q), which can be used to evaluate the helpfulness of machine explanations. [25]
Category: Artificial Intelligence

[4] viXra:1907.0059 [pdf] submitted on 2019-07-03 08:13:47

Smartphone Uncover Anti-Cancer Food

Authors: George Rajna
Comments: 35 Pages.

A crowdsourcing project which uses thousands of idling smartphones has helped to uncover anti-cancer properties of everyday foods and medicines. [25] New work from Los Alamos National Laboratory, the University of North Carolina at Chapel Hill, and the University of Florida is showing that artificial neural nets can be trained to encode quantum mechanical laws to describe the motions of molecules, supercharging simulations potentially across a broad range of fields. [24] But in a new study, physicists have made the surprising discovery that two spherical like-charged metal nanoparticles with unequal charges can attract one another in a dilute electrolyte solution. [23] There are two sound velocities in a Bose-Einstein condensate. In addition to the normal sound propagation there is second sound, which is a quantum phenomenon. [22] Quantum sensors can reach sensitivities that are impossible according to the laws of conventional physics that govern everyday life. [21] An international team of physicists at ETH Zurich, Aalto University, the Moscow Institute of Physics and Technology, and the Landau Institute for Theoretical Physics in Moscow has demonstrated that algorithms and hardware developed originally in the context of quantum computation can be harnessed for quantum-enhanced sensing of magnetic fields. [20] Scientists at Forschungszentrum Jülich have now discovered another class of particle-like magnetic object that could take the development of data storage devices a significant step forward. [19] A team of researchers with members from IBM Research-Zurich and RWTH Aachen University has announced the development of a new PCM (phase change memory) design that offers miniaturized memory cell volume down to three nanometers. [18] Monatomic glassy antimony might be used as a new type of single-element phase change memory. [17] Physicists have designed a 3-D quantum memory that addresses the tradeoff between achieving long storage times and fast readout times, while at the same time maintaining a compact form. [16]
Category: Artificial Intelligence

[3] viXra:1907.0030 [pdf] submitted on 2019-07-03 03:16:11

Neural Nets Simulate Molecular Motion

Authors: George Rajna
Comments: 33 Pages.

New work from Los Alamos National Laboratory, the University of North Carolina at Chapel Hill, and the University of Florida is showing that artificial neural nets can be trained to encode quantum mechanical laws to describe the motions of molecules, supercharging simulations potentially across a broad range of fields. [24] But in a new study, physicists have made the surprising discovery that two spherical like-charged metal nanoparticles with unequal charges can attract one another in a dilute electrolyte solution. [23]
Category: Artificial Intelligence

[2] viXra:1907.0024 [pdf] submitted on 2019-07-01 10:05:59

Neural Networks Simulating Quantum Systems

Authors: George Rajna
Comments: 49 Pages.

"We basically combined advances in neural networks and machine-learning with quantum Monte Carlo tools," says Savona, referring to a large toolkit of computational methods that physicists use to study complex quantum systems. [28] As cosmologists and astrophysicists delve deeper into the darkest recesses of the universe, their need for increasingly powerful observational and computational tools has expanded exponentially. [27] Now, a team of scientists at MIT and elsewhere has developed a neural network, a form of artificial intelligence (AI), that can do much the same thing, at least to a limited extent: It can read scientific papersand render a plain-English summary in a sentence or two. [26] To address this gap in the existing literature, a team of researchers at SRI International has created a human-AI image guessing game inspired by the popular game 20 Questions (20Q), which can be used to evaluate the helpfulness of machine explanations. [25]
Category: Artificial Intelligence

[1] viXra:1907.0020 [pdf] submitted on 2019-07-01 12:48:07

Machine Learning Design Proteins

Authors: George Rajna
Comments: 52 Pages.

According to researchers at Massachusetts Institute of Technology (MIT) in the US they both gain from being composed of structures over a range of scales be that notes, chords and melodies or amino acids, proteins and collagen matrices. [29] "We basically combined advances in neural networks and machine-learning with quantum Monte Carlo tools," says Savona, referring to a large toolkit of computational methods that physicists use to study complex quantum systems. [28] As cosmologists and astrophysicists delve deeper into the darkest recesses of the universe, their need for increasingly powerful observational and computational tools has expanded exponentially. [27] Now, a team of scientists at MIT and elsewhere has developed a neural network, a form of artificial intelligence (AI), that can do much the same thing, at least to a limited extent: It can read scientific papersand render a plain-English summary in a sentence or two. [26] To address this gap in the existing literature, a team of researchers at SRI International has created a human-AI image guessing game inspired by the popular game 20 Questions (20Q), which can be used to evaluate the helpfulness of machine explanations. [25]
Category: Artificial Intelligence