Artificial Intelligence

1909 Submissions

[49] viXra:1909.0619 [pdf] submitted on 2019-09-28 15:59:43

Classifying Cardiotocography Data based on Rough Neural Network

Authors: Belal Amin, Mona Gamall, A.A.Salama, I.M.El-Henawy
Comments: 5 Pages.

—Cardiotocography is a medical device that monitors fetal heart rate and the uterine contraction during the period of pregnancy. It is used to diagnose and classify a fetus state by doctors who have challenges of uncertainty in data. The Rough Neural Network is one of the most common data mining techniques to classify medical data, as it is a good solution for the uncertainty challenge. This paper provides a simulation of Rough Neural Network in classifying cardiotocography dataset. The paper measures the accuracy rate and consumed time during the classification process. WEKA tool is used to analyse cardiotocography data with different algorithms (neural network, decision table, bagging, the nearest neighbour, decision stump and least square support vector machine algorithm). The comparison shows that the accuracy rates and time consumption of the proposed model are feasible and efficient.
Category: Artificial Intelligence

[48] viXra:1909.0606 [pdf] submitted on 2019-09-29 14:31:10

Fcnhsmra_hrs: Improve the Performance of the Movie Hybrid Recommender System Using Resource Allocation Approach

Authors: Mostafa Khalaji, Nilufar Mohammadnejad
Comments: 8 Pages. Conference: 4th International Conference on Researchers in Science & Engineering & International Congress on Civil, Architecture and Urbanism in Asia, Kasem Bundit University, Bangkok, Thailand, At: Kasem Bundit University, Bangkok- Thailand, March 2019.

Recommender systems are systems that are capable of offering the most suitable services and products to users. Through specific methods and techniques, the recommender systems try to identify the most appropriate items, such as types of information and goods and propose the closest to the user’s tastes. Collaborative filtering offering active user suggestions based on the rating of a set of users is one of the simplest and most comprehensible and successful models for finding people in the same tastes in the recommender systems. In this model, with increasing number of users and movie, the system is subject to scalability. On the other hand, it is important to improve the performance of the system when there is little information available on the ratings. In this paper, a movie hybrid recommender system based on FNHSM_HRS structure using resource allocation approach called FCNHSMRA_HRS is presented. The FNHSM_HRS structure was based on the heuristic similarity measure (NHSM), along with fuzzy clustering. Using the fuzzy clustering method in the proposed system improves the scalability problem and increases the accuracy of system suggestions. The proposed systems is based on collaborative filtering and, by using the heuristic similarity measure and applying the resource allocation approach, improves the performance, accuracy and precision of the system. The experimental results using MAE, Accuracy, Precision and Recall metrics based on MovieLens dataset show that the performance of the system is improved and the accuracy of recommendations in comparison of FNHSM_HRS and collaborative filtering methods that use other similarity measures for finding similarity, is increased.
Category: Artificial Intelligence

[47] viXra:1909.0605 [pdf] submitted on 2019-09-29 14:36:17

FNHSM_HRS: Hybrid Recommender System Using Fuzzy Clustering and Heuristic Similarity Measure

Authors: Mostafa Khalaji, Chitra Dadkhah
Comments: 6 Pages. Conference: 7th Iranian Joint Congress on Fuzzy and Intelligent Systems, 18th Conference on Fuzzy Systems and 17th Conference on Intelligent Systems, Bojnord, Iran, University of Bojnord, p.p. 562-568, January 2019. Persian formatted

Nowadays, Recommender Systems have become a comprehensive system for helping and guiding users in a huge amount of data on the Internet. Collaborative Filtering offers to active users based on the rating of a set of users. One of the simplest and most comprehensible and successful models is to find users with a taste in recommender systems. In this model, with increasing number of users and items, the system is faced to scalability problem. On the other hand, improving system performance when there is little information available from ratings, that is important. In this paper, a hybrid recommender system called FNHSM_HRS which is based on the new heuristic similarity measure (NHSM) along with a fuzzy clustering is presented. Using the fuzzy clustering method in the proposed system improves the scalability problem and increases the accuracy of system recommendations. The proposed system is based on the collaborative filtering model and is partnered with the heuristic similarity measure to improve the system's performance and accuracy. The evaluation of the proposed system based results on the MovieLens dataset carried out the results using MAE, Recall, Precision and Accuracy measures Indicating improvement in system performance and increasing the accuracy of recommendation to collaborative filtering methods which use other measures to find similarities.
Category: Artificial Intelligence

[46] viXra:1909.0604 [pdf] submitted on 2019-09-29 14:41:06

CUPCF: Combining Users Preferences in Collaborative Filtering for Better Recommendation

Authors: Mostafa Khalaji, Nilufar Mohammadnejad
Comments: 12 Pages. Accepted in SN applied sciences journal, August 2019, DOI: 10.1007/s42452-019-1071-6.

How to make the best decision between the opinions and tastes of your friends and acquaintances? Therefore, recommender systems are used to solve such issues. The common algorithms use a similarity measure to predict active users’ tastes over a particular item. According to the cold start and data sparsity problems, these systems cannot predict and suggest particular items to users. In this paper, we introduce a new recommender system is able to find user preferences and based on it, provides the recommendations. Our proposed system called CUPCF is a combination of two similarity measures in collaborative filtering to solve the data sparsity problem and poor prediction (high prediction error rate) problems for better recommendation. The experimental results based on MovieLens dataset show that, combined with the preferences of the user’s nearest neighbor, the proposed system error rate compared to a number of state-of-the-art recommendation methods improved. Furthermore, the results indicate the efficiency of CUPCF. The maximum improved error rate of the system is 15.5% and the maximum values of Accuracy, Precision and Recall of CUPCF are 0.91402, 0.91436 and 0.9974 respectively.
Category: Artificial Intelligence

[45] viXra:1909.0601 [pdf] submitted on 2019-09-27 07:58:36

AI for Data Analysis

Authors: George Rajna
Comments: 49 Pages.

Applying AI know-how to the giant pool of data gathered from the world’s leading and most powerful scientific instruments could accelerate the process of scientific discovery. [28] Scientists from the University of Oxford, in collaboration with University of Basel and Lancaster University, have developed an algorithm that can be used to measure quantum dots automatically. [27] A research team from the RIKEN Center for Advanced Intelligence Project (AIP) has successfully developed a new method for machine learning that allows an AI to make classifications without what is known as "negative data," a finding which could lead to wider application to a variety of classification tasks. [26]
Category: Artificial Intelligence

[44] viXra:1909.0596 [pdf] submitted on 2019-09-27 11:14:50

Capacity Building of Client-Server Disruption Network Over Cloud Server Using Network Forensics

Authors: Rohit Sansiya, V. Jackins
Comments: 9 Pages.

Cloud computing is growing now-a-days in the interest of technical approach can be improved much instead of using traditional ICT. A significant number of secure systems are concerned with monitoring the environment. There are some equipment to measuring consumption of utilities but data loss can be a common experience of computer users, that lots of respondents had lost files on their home PC. The features included in Backup and Restore may differ depending on the edition of Windows. It is challenging for cloud providers to quickly interpret which events to act upon and the priority of events [8]. Unlimited host systems though realistically, you probably only need enough to host the number of VMs your license provides. Unlimited Virtual systems under management, So if you have a dozen real systems and they have Virtualization on them, you can manage all of them, without it effecting your Cloud hosted licensed virtual machine count. The server must also be granted permissions to make kerberos login just as they would if services creation was going to be done from client systems over disruption network and then administrator could be fetch the particular network using wireshark.
Category: Artificial Intelligence

[43] viXra:1909.0591 [pdf] submitted on 2019-09-27 23:31:25

Towards Performing Customized Cryo-Em/sem/tem Image Processing Applications by Combining [ Qupath + Imagej/ Fiji+jikesrvm/rvm-Research Virtual Machine ] Via Groovy a JVM Language in the Context of [ Iot/hpc High Performance Computing/ji Prolog/linux os

Authors: Nirmal Tej Kumar
Comments: 4 Pages. Short Communication & Technical Notes

Towards Performing Customized cryo-EM/SEM/TEM Image Processing Applications by Combining [ QuPath + ImageJ/ Fiji+JikesRVM/RVM-Research Virtual Machine ] via Groovy- a JVM Language in the Context of [ IoT/HPC- High Performance Computing/ JI Prolog/Linux OS ] Heterogeneous Environments. [ Exploring Novel Algorithms Using Java/Groovy/RVM – for Advanced Electron Microscopy Image Processing Frameworks ]
Category: Artificial Intelligence

[42] viXra:1909.0589 [pdf] submitted on 2019-09-28 03:26:09

Machine Learning Energy Harvesting

Authors: George Rajna
Comments: 34 Pages.

Electrical engineers at Duke University have harnessed the power of machine learning to design dielectric (non-metal) metamaterials that absorb and emit specific frequencies of terahertz radiation. [22] Understanding how a robot will react under different conditions is essential to guaranteeing its safe operation. [21] Marculescu, along with ECE Ph.D. student Chieh Lo, has developed a machine learning algorithm-called MPLasso-that uses data to infer associations and interactions between microbes in the GI microbiome. [20] A team of researchers from the University of Muenster in Germany has now demonstrated that this combination is extremely well suited to planning chemical syntheses-so-called retrosyntheses-with unprecedented efficiency. [19] Two physicists at ETH Zurich and the Hebrew University of Jerusalem have developed a novel machine-learning algorithm that analyses large data sets describing a physical system and extract from them the essential information needed to understand the underlying physics. [18]
Category: Artificial Intelligence

[41] viXra:1909.0575 [pdf] submitted on 2019-09-26 13:00:57

Machine Learning Quantum Devices

Authors: George Rajna
Comments: 41 Pages.

Scientists from the University of Oxford, in collaboration with University of Basel and Lancaster University, have developed an algorithm that can be used to measure quantum dots automatically. [27] A research team from the RIKEN Center for Advanced Intelligence Project (AIP) has successfully developed a new method for machine learning that allows an AI to make classifications without what is known as "negative data," a finding which could lead to wider application to a variety of classification tasks. [26] Artificial intelligence is helping improve safety along a stretch of Las Vegas' busiest highway. [25]
Category: Artificial Intelligence

[40] viXra:1909.0553 [pdf] submitted on 2019-09-25 11:38:33

Smart Pots for Cuddles(™) Based Therapy, for Autism and Psychosis Spectrum Disorders.

Authors: Bheemaiah, Anil Kumar
Comments: 3 Pages.

A smart pot design with Sonoff TH10/TH16 is developed for a DIY therapy based on the Cuddles(™) thermo regulation device. This paper is a supplement to already published literature by the author. The paper extends the therapy hardware to a version two, which includes polled wake word actions based on an ultrasound signalling from the plant, a way to listen to stress and ill-health signals from the plant for a stronger plant human interface and meaningful cuddles. The following paper is on the DIY series and published on Hackster.io(“Smart Pots for Cuddles(TM) Based Therapy, for Autism” n.d.) For other solutions see, (“iPot ‘The Worlds First Intelligent Plant Pot’” n.d., “Smart Garden” n.d., “Automatic Watering System for Plants with Arduino” n.d., “Smart Plant Monitoring with SMS Alert: Keep Plants Hydrated!” n.d.) Keywords: Cuddles(™), IFTTT, RAVATTT, Ultrasound plant signalling, Alexa, pots, succulents, Sonoff, DSP, wake words, IOT, actions
Category: Artificial Intelligence

[39] viXra:1909.0548 [pdf] submitted on 2019-09-25 22:42:26

Exploring Software Tools like Gaelyk+JikesRVM+JI Prolog in the Context of IoT/HPC/Cloud/AI Applications – An Intelligent Informatics Framework Using Groovy Language+RVM-Research Virtual Machine+JI Prolog for Heterogeneous Environments.

Authors: Nirmal Tej Kumar
Comments: 2 Pages. Short Communication & Technical Notes

Exploring Software Tools like Gaelyk+JikesRVM+JI Prolog in the Context of IoT/HPC/Cloud/AI Applications – An Intelligent Informatics Framework Using Groovy Language+RVM-Research Virtual Machine+JI Prolog for Heterogeneous Environments.
Category: Artificial Intelligence

[38] viXra:1909.0546 [pdf] submitted on 2019-09-26 03:23:27

Machine Learning Metamaterial Design

Authors: George Rajna
Comments: 45 Pages.

Electrical engineers at Duke University have harnessed the power of machine learning to design dielectric (non-metal) metamaterials that absorb and emit specific frequencies of terahertz radiation. [27] 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

[37] viXra:1909.0513 [pdf] submitted on 2019-09-24 23:10:03

Captcha Generation and Identification Using Generative Adversarial Networks

Authors: Hardik Ajmani, Mrinal Wahal
Comments: 10 Pages.

Adversarial attacking is an emerging worrying angle in the field of AI, capable of fooling even the most efficiently trained models to produce results as and when required. Inversely, the same design powering adversarial attacks can be employed for efficient white-hat modeling of deep neural networks. Recently introduced GANs (Generative Adversarial Networks) serve precisely this purpose by generating forged data. Consequently, authentic data identification is a crucial problem to be done away with, considering increased adversarial attacks. This paper proposes an approach using DCGANs (Deep Convolutional Generative Adversarial Networks) to both - generate and distinguish artificially produced fake captchas. The generator model produces a significant number of unseen images, and the discriminatory model classifies them as fake (0) or genuine (1). Interestingly enough, both the models can be configured to learn from each other and become better as they train along.
Category: Artificial Intelligence

[36] viXra:1909.0490 [pdf] submitted on 2019-09-24 02:44:50

An Insight into HOL-Isabelle/Coq Theorem Provers based Design of Algorithms Using [ Minsky Machines+Scala NLP/Scala/Akka/JikesRVM-Research Virtual Machine/JVM/LLVM ] in the Context of Electronic Health Record [ EHR ] Software R&D - A Simple Suggestion

Authors: Nirmal Tej Kumar
Comments: 6 Pages. Short Communication & Technical Notes

An Insight into HOL-Isabelle/Coq Theorem Provers based Design of Algorithms Using [ Minsky Machines+Scala NLP/Scala/Akka/JikesRVM-Research Virtual Machine/JVM/LLVM ] in the Context of Electronic Health Record [ EHR ] Software R&D - A Simple Suggestion on Using [ NLP+IoT+HPC ]. [ Exploring Challenges involving HOL/Coq+Minsky Machines Theory + NLP Theory Raspberry PI+IoT+HPC Informatics Better Health Care ]
Category: Artificial Intelligence

[35] viXra:1909.0489 [pdf] submitted on 2019-09-24 03:06:17

Digital Computers Model Chaos

Authors: George Rajna
Comments: 30 Pages.

The study, published today in Advanced Theory and Simulations, shows that digital computers cannot reliably reproduce the behaviour of 'chaotic systems' which are widespread. [20] It sounds like science fiction: controlling electronic devices with brain waves. But researchers have developed a new type of electroencephalogram (EEG) electrode that can do just that, without the sticky gel required for conventional electrodes. [19] U.S. Army Research Laboratory scientists have discovered a way to leverage emerging brain-like computer architectures for an age-old number-theoretic problem known as integer factorization. [18]
Category: Artificial Intelligence

[34] viXra:1909.0458 [pdf] submitted on 2019-09-22 00:31:02

An Interesting Insight Into Using [ Ruby Machine Learning Library+qrng+entropy+signal Processing ] Towards co-Designing of Novel [ Hardware/software/firmware ] in the Context of Smart Platforms Based Heterogeneous Environments to Probe Circadian Rhythms

Authors: Nirmal Tej Kumar
Comments: 6 Pages. Short Communication & Technical Notes

An Interesting Insight into Using [ Ruby Machine learning Library+QRNG+Entropy+Signal Processing ] towards Co-Designing of Novel [ Hardware/Software/Firmware ] in the Context of Smart Platforms based Heterogeneous Environments to Probe Circadian Rhythms[CR] +Data. [ Exploring Testing of Pin Configurations + Firmware Using Above Mentioned Concepts ]
Category: Artificial Intelligence

[33] viXra:1909.0441 [pdf] submitted on 2019-09-20 10:51:04

ANN-based Shear Capacity of Steel Fiber-Reinforced Concrete Beams Without Stirrups

Authors: M. Abambres, E. Lantsoght
Comments: Pages.

Comparing experimental results on the shear capacity of steel fiber-reinforced concrete (SFRC) beams without mild steel stirrups, to the ones predicted by current design equations and other available formulations, still shows significant differences. In this paper we propose the use of artificial intelligence to estimate the shear capacity of these members. A database of 430 test results reported in the literature is used to develop an artificial neural network-based formula that predicts the shear capacity of SFRC beams without shear reinforcement. The proposed model yields maximum and mean relative errors of 0.0% for the 430 data points, which represents a better prediction (mean Vtest / VANN = 1.00 with a coefficient of variation of 1E-15) than the existing expressions, where the best model yields a mean value of Vtest / Vpred = 1.01 and a coefficient of variation of 27%.
Category: Artificial Intelligence

[32] viXra:1909.0414 [pdf] submitted on 2019-09-19 11:06:09

Brain-Computer Interfaces

Authors: George Rajna
Comments: 28 Pages.

It sounds like science fiction: controlling electronic devices with brain waves. But researchers have developed a new type of electroencephalogram (EEG) electrode that can do just that, without the sticky gel required for conventional electrodes. [19] U.S. Army Research Laboratory scientists have discovered a way to leverage emerging brain-like computer architectures for an age-old number-theoretic problem known as integer factorization. [18] Now researchers at the Department of Energy's Lawrence Berkeley National Laboratory (Berkeley Lab) and UC Berkeley have come up with a novel machine learning method that enables scientists to derive insights from systems of previously intractable complexity in record time. [17]
Category: Artificial Intelligence

[31] viXra:1909.0407 [pdf] submitted on 2019-09-20 01:02:49

Implementation of Python Based Ehr/emr Software Prototyping Informatics Framework – a Novel & Simple Algorithm Using Spacy+theorem Prover+data Bases+qrng Concepts+deep Learning Methods.

Authors: Nirmal Tej Kumar
Comments: 2 Pages. Short Communication & Technical Notes

Implementation of Python based EHR/EMR Software Prototyping Informatics Framework – A Novel & Simple Algorithm Using spaCy+Theorem Prover+Data Bases+QRNG Concepts+Deep Learning Methods.
Category: Artificial Intelligence

[30] viXra:1909.0398 [pdf] submitted on 2019-09-20 06:00:27

Unboxing AI - Radiological Insights Into a Deep Neural Network for Lung Nodule Characterization

Authors: Vasantha Kumar Venugopal, Kiran Vaidhya, Abhijith Chundur, Vidur Mahajan, Murali Murugavel, Suthirth Vaidya, Digvijay Mahra, Akshay Rangasai, Harsh Mahajan
Comments: 18 Pages.

Rationale and Objectives: To explain predictions of a deep residual convolutional network for characterization of lung nodule by analyzing heat maps Materials and Methods A 20-layer deep residual CNN was trained on 1245 Chest CTs from NLST trial to predict the malignancy risk of a nodule. We used occlusion to systematically block regions of a nodule and map drops in malignancy risk score to generate clinical attribution heatmaps on 103 nodules from LIDC-IDRI dataset, which were analyzed by a thoracic radiologist. The features were described as heat inside nodule (IH)-bright areas inside nodule, peripheral heat (PH)-continuous/interrupted bright areas along nodule contours, heat in adjacent plane (AH)-brightness in scan planes juxtaposed with the nodule, satellite heat (SH)- a smaller bright spot in proximity to nodule in the same scan plane, heat map larger than nodule (LH)-bright areas corresponding to the shape of the nodule seen outside the nodule margins and heat in calcification (CH) Results These six features were assigned binary values. This feature vector was fed into a standard J48 decision tree with 10-fold cross-validation, which gave an 85 % weighted classification accuracy with a 77.8 %TP rate, 8% FP rate for benign cases and 91.8% TP and 22.2 %FP rates for malignant cases. IH was more frequently observed in nodules classified as malignant whereas PH, AH, and SH were more commonly seen in nodules classified as benign. Conclusion We discuss the potential ability of a radiologist to visually parse the deep learning algorithm-generated 'heat map' to identify features aiding classification
Category: Artificial Intelligence

[29] viXra:1909.0392 [pdf] submitted on 2019-09-18 08:02:33

Artificial Intelligence Probes Dark Matter

Authors: George Rajna
Comments: 52 Pages.

A team of physicists and computer scientists at ETH Zurich has developed a new approach to the problem of dark matter and dark energy in the universe. Using machine learning tools, they programmed computers to teach themselves how to extract the relevant information from maps of the universe. [31] These results, important for the construction of new theoretical models and for the development of new hypotheses about the nature of dark matter, offer much more precise indications for tracing the intricate path to understanding one of the largest mysteries of the cosmos. [30] New research lends further support to the idea that a detection of surprisingly strong absorption by primordial hydrogen gas, reported earlier this year, could be evidence of dark matter. [29] Physicists in Italy are about to start up a new experiment designed to hunt for hypothetical particles such as the "dark photon" and carriers of a possible fifth force of nature. [28] A signal caused by the very first stars to form in the universe has been picked up by a tiny but highly specialised radio telescope in the remote Western Australian desert. [27] This week, scientists from around the world who gathered at the University of California, Los Angeles, at the Dark Matter 2018 Symposium learned of new results in the search for evidence of the elusive material in Weakly Interacting Massive Particles (WIMPs) by the DarkSide-50 detector. [26] If they exist, axions, among the candidates for dark matter particles, could interact with the matter comprising the universe, but at a much weaker extent than previously theorized. New, rigorous constraints on the properties of axions have been proposed by an international team of scientists. [25] The intensive, worldwide search for dark matter, the missing mass in the universe, has so far failed to find an abundance of dark, massive stars or scads of strange new weakly interacting particles, but a new candidate is slowly gaining followers and observational support. [24]
Category: Artificial Intelligence

[28] viXra:1909.0383 [pdf] submitted on 2019-09-19 01:01:48

[ Spacy+imageai+spin Glass Theory+z3 Api ] All in Python Language – an Insight Into the World of Natural Language Processing(nlp) Towards Understanding Informatics of Finite Automata Involving DNA Sequencing & Some Interesting Applications Like Gene Chips

Authors: Nirmal Tej Kumar
Comments: 3 Pages. Short Communication & Technical Notes

[ spaCy+ImageAI+Spin Glass Theory+Z3 API ] all in Python Language – An Insight into the World of Natural Language Processing(NLP) towards Understanding Informatics of Finite Automata involving DNA Sequencing & Some Interesting Applications like Gene Chips. [ Exploring – NLP+Spin Glass Theory+AI+Theorem Proving in the Context of Developing Next Generation Bio-informatics ]
Category: Artificial Intelligence

[27] viXra:1909.0364 [pdf] submitted on 2019-09-17 23:30:47

Exploring Ruby Based Bio-informatics R&D Framework Using NLP/BioNLP/SVM/QRNG/HPC/IoT/Mongo DB/BaseX DB Systems & Related Environments – A Novel Multidisciplinary Approach.

Authors: Nirmal Tej Kumar
Comments: 5 Pages. Short Communication & Technical Notes

Exploring Ruby Based Bio-informatics R&D Framework Using NLP/BioNLP/SVM/QRNG/HPC/IoT/Mongo DB/BaseX DB Systems & Related Environments – A Novel Multidisciplinary Approach. [ Probing Advanced Computational Aspects of Cancer Research With Mathematics ]
Category: Artificial Intelligence

[26] viXra:1909.0347 [pdf] submitted on 2019-09-16 14:38:53

Application of ANN in Pavement Engineering: State-of-Art

Authors: M. Abambres, A. Ferreira
Comments: 61 Pages.

There has been much discussion about the impact and future of artificial intelligence (AI) in our lives and future generations. Many experts even believe that AI will “rule” the world. Artificial Neural Networks (ANN) have provided a convenient and often extremely accurate solution to problems within all fields, and can be seen as advanced general-purpose regression models that try to mimic the behavior of the human brain. The adoption and use of ANN-based methods in the Mechanistic-Empirical Pavement Design Guide is a clear sign of the successful use of neural nets in geomechanical and pavement systems. This work aims to provide an extensive and detailed state-of-the-art of the application of ANN models to pavement management, materials and design problems. Unlike former review articles published before 2014, this work is more descriptive and makes the review much more appealing to the reader by highlighting numerically and/or graphically the effectiveness and possible drawbacks of each ANN application.
Category: Artificial Intelligence

[25] viXra:1909.0346 [pdf] submitted on 2019-09-16 14:41:13

Neural Network-Based Formula for the Buckling Load Prediction of I-Section Cellular Steel Beams

Authors: M. Abambres, K. Rajana, K. Tsavdaridis, T. Ribeiro
Comments: 50 Pages.

Cellular beams are an attractive option for the steel construction industry due to their versatility in terms of strength, size, and weight. Further benefits are the integration of services thereby reducing ceiling-to-floor depth (thus, building’s height), which has a great economic impact. Moreover, the complex localised and global failures characterizing those members have led several scientists to focus their research on the development of more efficient design guidelines. This paper aims to propose an artificial neural network (ANN)-based formula to estimate the critical elastic buckling load of simply supported cellular beams under uniformly distributed vertical loads. The 3645-point dataset used in ANN design was obtained from an extensive parametric finite element analysis performed in ABAQUS. The independent variables adopted as ANN inputs are the following: beam’s length, opening diameter, web-post width, cross-section height, web thickness, flange width, flange thickness, and the distance between the last opening edge and the end support. The proposed model shows a strong potential as an effective design tool. The maximum and average relative errors among the 3645 data points were found to be 3.7% and 0.4%, respectively, whereas the average computing time per data point is smaller than a millisecond for any current personal computer.
Category: Artificial Intelligence

[24] viXra:1909.0345 [pdf] submitted on 2019-09-16 14:50:21

Neural Network-Based Analytical Model to Predict the Shear Strength of Steel Girders with a Trapezoidal Corrugated Web

Authors: M. Abambres, J. He
Comments: 31 Pages.

Corrugated webs are used to increase the shear stability of steel webs of beam-like members and to eliminate the need of transverse stiffeners. Previously developed formulas for predicting the shear strength of trapezoidal corrugated steel webs, along with the corresponding theory, are summarized. An artificial neural network (ANN)-based model is proposed to estimate the shear strength of steel girders with a trapezoidal corrugated web, and under a concentrated load. 210 test results from previous published research were collected into a database according to relevant test specimen parameters in order to feed the simulated ANNs. Seven (geometrical and material) parameters were identified as input variables and the ultimate shear stress at failure was considered the output variable. The proposed ANN-based analytical model yielded maximum and mean relative errors of 0.0% for the 210 points from the database. Moreover, still based on those points, it was illustrated that the ANN-based model clearly outperforms the other existing analytical models, which yield mean errors larger than 13%.
Category: Artificial Intelligence

[23] viXra:1909.0344 [pdf] submitted on 2019-09-16 14:52:25

Shear Capacity of Headed Studs in Steel-Concrete Structures: Analytical Prediction via Soft Computing

Authors: M. Abambres, J. He
Comments: 29 Pages.

Headed studs are commonly used as shear connectors to transfer longitudinal shear force at the interface between steel and concrete in composite structures (e.g., bridge decks). Code-based equations for predicting the shear capacity of headed studs are summarized. An artificial neural network (ANN)-based analytical model is proposed to estimate the shear capacity of headed steel studs. 234 push-out test results from previous published research were collected into a database in order to feed the simulated ANNs. Three parameters were identified as input variables for the prediction of the headed stud shear force at failure, namely the steel stud tensile strength and diameter, and the concrete (cylinder) compressive strength. The proposed ANN-based analytical model yielded, for all collected data, maximum and mean relative errors of 3.3 % and 0.6 %, respectively. Moreover, it was illustrated that, for that data, the neural network approach clearly outperforms the existing code-based equations, which yield mean errors greater than 13 %.
Category: Artificial Intelligence

[22] viXra:1909.0341 [pdf] submitted on 2019-09-16 15:57:28

Neural Network-Based Formula for Shear Capacity Prediction of One-Way Slabs Under Concentrated Loads

Authors: M. Abambres, E. Lantsoght
Comments: 33 Pages.

According to the current codes and guidelines, shear assessment of existing reinforced concrete slab bridges sometimes leads to the conclusion that the bridge under consideration has insufficient shear capacity. The calculated shear capacity, however, does not consider the transverse redistribution capacity of slabs, thus leading to overconservative values. This paper proposes an artificial neural network (ANN)-based formula to come up with estimates of the shear capacity of one-way reinforced concrete slabs under a concentrated load, based on 287 test results gathered from the literature. The proposed model yields maximum and mean relative errors of 0.0% for the 287 data points. Moreover, it was illustrated to clearly outperform (mean Vtest / VANN =1.00) the Eurocode 2 provisions (mean VE,EC / VR,c =1.59) for that dataset. A step-by-step assessment scheme for reinforced concrete slab bridges by means of the ANN-based model is also proposed, which results in an improvement of the current assessment procedures.
Category: Artificial Intelligence

[21] viXra:1909.0340 [pdf] submitted on 2019-09-16 16:20:40

Potential of Neural Networks for Maximum Displacement Predictions in Railway Beams on Frictionally Damped Foundations

Authors: M. Abambres, R. Corrêa, A. Pinto da Costa, F. Simões
Comments: 63 Pages.

Since the use of finite element (FE) simulations for the dynamic analysis of railway beams on frictionally damped foundations are (i) very time consuming, and (ii) require advanced know-how and software that go beyond the available resources of typical civil engineering firms, this paper aims to demonstrate the potential of Artificial Neural Networks (ANN) to effectively predict the maximum displacements and the critical velocity in railway beams under moving loads. Four ANN-based models are proposed, one per load velocity range ([50, 175] ∪ [250, 300] m/s; ]175, 250[ m/s) and per displacement type (upward or downward). Each model is function of two independent variables, a frictional parameter and the load velocity. Among all models and the 663 data points used, a maximum error of 5.4 % was obtained when comparing the ANN- and FE-based solutions. Whereas the latter involves an average computing time per data point of thousands of seconds, the former does not even need a millisecond. This study was an important step towards the development of more versatile (i.e., including other types of input variables) ANN-based models for the same type of problem.
Category: Artificial Intelligence

[20] viXra:1909.0322 [pdf] submitted on 2019-09-15 15:35:05

The Complexity of NonSwapClique

Authors: Anisse Ismaili
Comments: 1 Page.

Problem NonSwapClique: Given an undirected graph $G=(V,E)$, does it contain a clique $S\subseteq V$ of size $k$, such that you cannot obtain another clique of the same size by swapping a pair of vertices? In this note, I settle the complexity of this problem as NP-complete, by a reduction from problem \textsc{1-in-3-SAT}.
Category: Artificial Intelligence

[19] viXra:1909.0317 [pdf] submitted on 2019-09-15 20:50:43

Potential of Neural Networks for Structural Damage Localization

Authors: M. Abambres, M. Marcy, G. Doz
Comments: Pages.

Fabrication technology and structural engineering states-of-art have led to a growing use of slender structures, making them more susceptible to static and dynamic actions that may lead to some sort of damage. In this context, regular inspections and evaluations are necessary to detect and predict structural damage and establish maintenance actions able to guarantee structural safety and durability with minimal cost. However, these procedures are traditionally quite time-consuming and costly, and techniques allowing a more effective damage detection are necessary. This paper assesses the potential of Artificial Neural Network (ANN) models in the prediction of damage localization in structural members, as function of their dynamic properties – the three first natural frequencies are used. Based on 64 numerical examples from damaged (mostly) and undamaged steel channel beams, an ANN-based analytical model is proposed as a highly accurate and efficient damage localization estimator. The proposed model yielded maximum errors of 0.2 and 0.7 % concerning 64 numerical and 3 experimental data points, respectively. Due to the high-quality of results, authors’ next step is the application of similar approaches to entire structures, based on much larger datasets.
Category: Artificial Intelligence

[18] viXra:1909.0316 [pdf] submitted on 2019-09-15 21:46:04

An Interesting Novel Insight into the [ Ocaml+Theorem Prover+AI/ML+Java+Prolog+BaseX-XML DB/ Mongo DB Systems+Imaging Mathematics-Linear Algebra ] to Probe Radiation Oncology Informatics +BIG DATA.

Authors: Nirmal Tej Kumar
Comments: 5 Pages. Short Communication & Technical Notes

An Interesting Novel Insight into the [Ocaml+Theorem Prover+AI/ML+Java+Prolog+BaseX-XML DB/Mongo DB Systems+Imaging Mathematics-Linear Algebra ] to Probe Radiation Oncology Informatics+BIG DATA.
Category: Artificial Intelligence

[17] viXra:1909.0268 [pdf] submitted on 2019-09-12 11:49:08

Machine Learning Rewilding

Authors: George Rajna
Comments: 32 Pages.

There may not be an obvious connection between rewilding and machine learning, but as highlighted today at ESA's ɸ-week, a project in the Netherlands uses satellite data and new digital technology to understand how a nature reserve responds to the pressure of being grazed by herbivores. [22] At the University of South Florida, researchers are integrating machine learning techniques into their work studying proteins. [21] Bioinformatics professors Anthony Gitter and Casey Greene set out in summer 2016 to write a paper about biomedical applications for deep learning, a hot new artificial intelligence field striving to mimic the neural networks of the human brain. [20] A team of researchers from the University of Muenster in Germany has now demonstrated that this combination is extremely well suited to planning chemical syntheses-so-called retrosyntheses-with unprecedented efficiency. [19] Two physicists at ETH Zurich and the Hebrew University of Jerusalem have developed a novel machine-learning algorithm that analyses large data sets describing a physical system and extract from them the essential information needed to understand the underlying physics. [18]
Category: Artificial Intelligence

[16] viXra:1909.0262 [pdf] submitted on 2019-09-13 03:41:15

[ Haxe+mlxo-Haxe ML Library/dlib in C++/clips C Language/cocoalib-C++ ] Based ux Design for the Iot/hpc-High Performance Computing Heterogeneous Medical Informatics R&D Frameworks – an Insight Into the World of Novel ux Designs.

Authors: Nirmal Tej Kumar
Comments: 4 Pages. Short Communication

[ Haxe+MLXO-Haxe ML Library/dlib in C++/CLIPS- C Language/CocoALIB-C++ ]based UX design for the IoT/HPC-High Performance Computing Heterogeneous Medical Informatics R&D Frameworks – An Insight into the World of Novel UX Designs. [ Exploring C/C++/Ocaml/HAXE+ML AI/ML/Grobner Bases based Advanced Medical Informatics + Healthcare ]
Category: Artificial Intelligence

[15] viXra:1909.0236 [pdf] submitted on 2019-09-10 22:00:18

Multimedia Informatics R&D in the Context of [ Haxe+imageai+qrng Lib-Python ] Towards [ Ai/ml/iot/hpc ] Heterogeneous Environment/s

Authors: Nirmal Tej Kumar
Comments: 3 Pages. Short Communication

Multimedia Informatics R&D in the Context of [ HAXE+IMAGEAI+qrng lib-python ] towards [ AI/ML/IoT/HPC ]Heterogeneous Environment/s – An Interesting Insight into [ Imaging Mathematics+Hardware Mathematics ] based Algorithms Using [ Ocaml/Owl/Haxe/Python ] Languages. [ Exploring – Next Generation Radiation Oncology Informatics Framework Using the Above Mentioned Tools ]
Category: Artificial Intelligence

[14] viXra:1909.0170 [pdf] submitted on 2019-09-09 01:48:19

[ Ironruby+.netsdk/linux/mruby Qrng Library/clips .net Expert Systems Software/clips ] Framework for Medical Image Processing

Authors: Nirmal Tej Kumar
Comments: 3 Pages. Short Communication

[ IronRuby+.NETSDK/Linux/mruby qrng library/CLIPS .NET Expert Systems Software/CLIPS ] Framework in the Context of Designing Next Generation Medical Image Processing Heterogeneous Software and Monitoring Using [ QRNGService/QRNG-Device ] based on Machine Learning Concepts – An Important but Simple R&D Suggestion for [ IoT/HPC ] Image Processing Software Architecture Implementation.
Category: Artificial Intelligence

[13] viXra:1909.0163 [pdf] submitted on 2019-09-07 07:13:12

AI Predict Hybrid Nanoparticle Structure

Authors: George Rajna
Comments: 52 Pages.

Researchers at the Nanoscience Center and Faculty of Information Technology in the University of Jyväskylä, Finland, have achieved a significant step forward in predicting atomic structures of hybrid nanoparticles. [32] Using machine-learning and an integrated photonic chip, researchers from INRS (Canada) and the University of Sussex (UK) can now customize the properties of broadband light sources. [31] A team of EPFL scientists has now written a machine-learning program that can predict, in record time, how atoms will respond to an applied magnetic field. [30] Researchers from the University of Luxembourg, Technische Universität Berlin, and the Fritz Haber Institute of the Max Planck Society have combined machine learning and quantum mechanics to predict the dynamics and atomic interactions in molecules. [29]
Category: Artificial Intelligence

[12] viXra:1909.0156 [pdf] submitted on 2019-09-07 10:56:48

Promoting 3D Printing of Food with Robotic Butlers and Delivery LandBots.

Authors: Bheemaiah, Anil Kumar.
Comments: 4 Pages.

Abstract This paper describes the design of the robotic kitchen of Mutter Gottlich, a non-profit nature spirituality organization. The kitchen is designed as an open space architecture under the Banyan Canopy[1](“Website” n.d.). The use of 3D printers for the production of pancakes, pancake pizzas, Dosas, Dosa Pizzas, vegetable, and vegan meat substrates and chocolate and cakes is described. Robots, namely the Loomo and the R1D2 are mentioned. The detailed design of these robots is mentioned elsewhere. These robots are fully automated to run the facility. The facility along with a spiritual sculpture garden, succulent garden for meditation and a sacred tree for worship and a sacred fireplace, provide for an open-air church/temple. The facility serves as a meeting place for aspirants to meet to compose and sing music and group meditate. It unifies diverse cultures, promotes ecological sustainability and serves as a food pantry for low-income families serving the Freemium business model. Keywords: Robotics, Automation, 3D printing, Food Printers.
Category: Artificial Intelligence

[11] viXra:1909.0140 [pdf] submitted on 2019-09-06 08:58:53

Deep Learning Statistical Physics

Authors: George Rajna
Comments: 46 Pages.

A team of scientists at Freie Universität Berlin has developed an Artificial Intelligence (AI) method that provides a fundamentally new solution of the "sampling problem" in statistical physics. [27] Deep learning, which uses multi-layered artificial neural networks, is a form of machine learning that has demonstrated significant advances in many fields, including natural language processing, image/video labeling and captioning. [26]
Category: Artificial Intelligence

[10] viXra:1909.0133 [pdf] submitted on 2019-09-06 14:16:06

Intentional Economy

Authors: Bheemaiah, Anil Kumar
Comments: 10 Pages.

The Intentional Economy is defined as an alternative lifestyle based economy that is essentially circular axiomatically. It has a coherence defined by sustainability, conservation of natural genome, spirituality and a common philosophy. This paper is on the definition and the status of the Intentional Economy, and a proof that Intentional Living is the way to World Peace. We define a Lean inspired system called Lean A.I derived from the Referendum formulation of e Governance based on the design of the Skynet, an A.I and data mining based network and the Lean inspire ‘Vahi ka Vahi’(VKV) model, that calls for open and pro global designs, and local manufacturing by 3D printing that is sustainable. As an example of the VKV model, we consider the case study of printing 3D printers using 3D printers or the Y lambda operator metaphor. Keywords: Intention Economy, Intentional Economy, Additive Printing, Cloud Computing, Robotics, RPA, DPA, Flex-Rules, Lean Management , Lean Manufacturing, Vahi Ka Vahi,
Category: Artificial Intelligence

[9] viXra:1909.0119 [pdf] submitted on 2019-09-07 05:37:02

An Interesting+promising Suggestion Based on [clips/psyclone ] Related ai Frameworks & Their [ Extension + Interfacing ] with Ruby-LLVM Software in the Context of Iot/hpc Heterogeneous Image Processing Environment/s Let us Happily Explore Ruby Language

Authors: Nirmal Tej Kumar
Comments: 2 Pages. Short Communication

An Interesting+Promising Suggestion based on [CLIPS/Psyclone ] related AI Frameworks & their [ Extension +Interfacing ] with Ruby-LLVM Software in the Context of IoT/HPC Heterogeneous Image Processing Environment/s - Let us Happily Explore Ruby Language towards Designing Advanced Expert Systems for Multi-disciplinary R&D involving Next Generation Smart Devices [ Hardware/Software/Firmware ]. [ C/C++/Ruby/LLVM based AI Revolution Advanced Medical Image Processing ]
Category: Artificial Intelligence

[8] viXra:1909.0104 [pdf] submitted on 2019-09-05 17:17:15

The Algorithmic Audit: Working with Vendors to Validate Radiology-AI Algorithms - How We Do It

Authors: Vidur Mahajan, Vasanthakumar Venugopal, Saumya Gaur, Salil Gupta, Murali Murugavel, Harsh Mahajan
Comments: 7 Pages.

There is a plethora of Artificial Intelligence (AI) tools that are being developed around the world aiming at either speeding up or improving the accuracy of radiologists. It is essential for radiologists to work with the developers of such algorithms to determine true clinical utility and risks associated with these algorithms. We present a framework, called an Algorithmic Audit, for working with the developers of such algorithms to test and improve the performance of the algorithms. The framework includes concepts of true independent validation on data that the algorithm has not seen before, curating datasets for such testing, deep examination of false positives and false negatives (to examine implications of such errors) and real-world deployment and testing of algorithms.
Category: Artificial Intelligence

[7] viXra:1909.0102 [pdf] submitted on 2019-09-05 23:03:28

[ ImageJ/Fiji/Java/JikesRVM-Research Virtual Machine/HoloJ/Jython/Python/Z3Py-Theorem Prover/QRNG Device/qrng-pylib/Machine Learning] as Holography based Image Processing & Informatics Platform in the Context of Medical Image Processing

Authors: Nirmal Tej Kumar
Comments: 2 Pages. Short Communication

[ ImageJ/Fiji/Java/JikesRVM-Research Virtual Machine/HoloJ/Jython/Python/Z3Py-Theorem Prover/QRNG Device/qrng-pylib/Machine Learning] as Holography based Image Processing & Informatics Platform in the Context of Medical Image Processing/cryo-EM Image Processing R&D. An Interesting Short Communication & Simple Technical Point of View by Prototyping Some Image Processing Algorithms.
Category: Artificial Intelligence

[6] viXra:1909.0100 [pdf] submitted on 2019-09-06 00:09:05

Multi-Dimensional Asset Allocation Strategy with DA-RNN

Authors: Tae Young Lee
Comments: 7 Pages. Draft Paper

Most RoboAdvisors reflect the perspective of investment banks, which differs from commercial banks in Korea. Most customers who use commercial banks have a conservative approach. In customer-focused thinking, the more you design your Robo Advisor, the more important it is to minimize customer losses. It was designed with the belief that the guarantee of principal through defense of the bear market would be a solid foundation to be returned to profits from the bear market. The traditional asset allocation model is dedicated to simple predictions that take risk as a parameter of volatility and draw the expected return to calculate the optimal share of the asset. This is not a big problem when the market is good, but it's going to cause a loss of the customer's principal in a booming market. This is not in line with the bank's robovisor idea, and we have created deep learning algorithms to defend against the bear market.
Category: Artificial Intelligence

[5] viXra:1909.0088 [pdf] replaced on 2019-09-19 04:09:56

Trimming Neural Networks

Authors: Mastane Achab, Massil Achab
Comments: 3 Pages.

We introduce a new type of artificial neural network (ANN): the trimming neural network (TNN) model. As most ANNs, a TNN is an alternating sequence of linear and nonlinear vectorial operators. Recall that in usual ANN models, nonlinear functions are independently applied on each entry of each layer. In contrast, we design TNNs' nonlinearities as functions of the whole layer: indeed, they are based on sorting all the layer's entries. In particular, we focus on the trimming operation which consists in summing all entries but a certain fraction of the smallest/largest ones. We show that TNNs enjoy convexity properties useful in various statistical learning contexts.
Category: Artificial Intelligence

[4] viXra:1909.0074 [pdf] submitted on 2019-09-03 07:24:43

Deep Reinforcement Learning for Visual Question Answering

Authors: Ayoub Abraich
Comments: 131 Pages.

La conception de bout en bout des systèmes de dialogue est récemment devenue un sujet de recherche populaire grâce à des outils puissants tels que des architectures codeur-décodeur pour l'apprentissage séquence à séquence. Pourtant, la plupart des approches actuelles considèrent la gestion du dialogue homme-machine comme un problème d’apprentissage supervisé, visant à prédire la prochaine déclaration d’un participant, compte tenu de l’historique complet du dialogue. Cette vision est aussi simpliste pour rendre le problème de planification intrinsèque inhérent au dialogue ainsi que sa nature enracinée, rendant le contexte d'un dialogue plus vaste que seulement l'historique. C’est la raison pour laquelle seules les tâches de bavardage et de réponse aux questions ont été traitées jusqu’à présent en utilisant des architectures de bout en bout. Dans ce rapport, nous présentons une méthode d’apprentissage par renforcement profond permettant d’optimiser les dialogues axés sur les tâches, basés sur l’algorithme policy gradient. Cette approche est testée sur un ensemble de données de 120 000 dialogues collectés via Mechanical Turk et fournit des résultats encourageants pour résoudre à la fois le problème de la génération de dialogues naturels et la tâche de découvrir un objet spécifique dans une image complexe.
Category: Artificial Intelligence

[3] viXra:1909.0061 [pdf] replaced on 2019-11-19 21:46:23

Acl-Gan: Multi-Domain Image-to-Image Translation Gan Using New Losses to Reduce the Time for Hyperparameter Optimization and Training

Authors: JeongIk Cho
Comments: 13 Pages.

StarGAN, which has impressive performance in image-to-image translation, is based on the determination of three important hyperparameters: adversarial weight, classification weight, and reconstruction weight, which have a significant impact on the performance of the model. In this study, by proposing an attribute loss that can replace conditional GAN losses: adversarial loss and classification loss, the time required for the optimization of attribute weight replaced the time required for the optimization of adversarial weight and classification weight, which can drastically reduce the time required for hyperparameter optimization. Proposed attribute loss is the sum of the losses of each GAN when creating a GAN for each attribute, and since each GAN shares a hidden layer, it does not increase the amount of computation much. Also, propose simplified content loss, which reduces computation by simplifying reconstruction loss. Reconstruction loss of StarGAN goes through the generator twice, while simplified content loss goes through only once, reduce the amount of computation. Also, propose an architecture that prevents background distortion through image framing and improves training speed through a bidirectional progressive growing generator.
Category: Artificial Intelligence

[2] viXra:1909.0034 [pdf] submitted on 2019-09-02 23:07:02

A Short Communication & Technical Notes on - Developing Novel Image Processing Algorithms Using - [ MarvinJ+JSON+IMAGEAI+Z3 API in Python(Theorem Prover)] in the Context of Next Generation Medical Image Processing Software/Cryo-EM Image Processing

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

A Short Communication & Technical Notes on - Developing Novel Image Processing Algorithms Using - [ MarvinJ+JSON+IMAGEAI+Z3 API in Python(Theorem Prover)] in the Context of Next Generation Medical Image Processing Software/Cryo-EM Image Processing Software Architecture R&D for [ AI/IoT/HPC/Mobile Systems ] Heterogeneous Environment/s
Category: Artificial Intelligence

[1] viXra:1909.0009 [pdf] submitted on 2019-09-01 03:15:45

Interesting R&D Investigations Using Java Script(js) Language & Its Related Software/ai & ML Libraries in the Context of Advanced Medical Image Processing/electron Microscopy Image Processing Informatics Frameworks Based on Ai/ml/dl/iot/hpc

Authors: Nirmal Tej Kumar
Comments: 6 Pages. Short Technical Notes & Simple Suggestion

Interesting R&D Investigations Using Java Script(JS) Language & its related Software/AI & ML Libraries in the Context of Advanced Medical Image Processing/Electron Microscopy Image Processing Informatics Frameworks based on AI/ML/DL/IoT/HPC Heterogeneous Environment/s – A Simple R&D Introduction. [ Exploring – C/C++/Ruby/LLVM/GCCS/Emscripten/SWIProlog/WASM/MarvinJ/OpenCVJS – for Image Processing ]
Category: Artificial Intelligence