scholarly journals A Machine-learning Approach to Integral Field Unit Spectroscopy Observations. III. Disentangling Multiple Components in H ii Regions

2021 ◽  
Vol 923 (2) ◽  
pp. 169
Author(s):  
Carter L. Rhea ◽  
Laurie Rousseau-Nepton ◽  
Simon Prunet ◽  
Julie Hlavacek-Larrondo ◽  
R. Pierre Martin ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Line Of Sight ◽  
H Ii Regions ◽  
Neural Network Approach ◽  
Multiple Components ◽  
Machine Learning Approach ◽  
Central Regions ◽  
Field Unit ◽  
Computational Resources

Abstract In the first two papers of this series, we demonstrated the dynamism of machine learning applied to optical spectral analysis by using neural networks to extract kinematic parameters and emission-line ratios directly from the spectra observed by the SITELLE instrument located at the Canada–France–Hawai’i Telescope. In this third installment, we develop a framework using a convolutional neural network trained on synthetic spectra to determine the number of line-of-sight components present in the SN3 filter (656–683 nm) spectral range of SITELLE. We compare this methodology to standard practice using Bayesian inference. Our results demonstrate that a neural network approach returns more accurate results and uses fewer computational resources over a range of spectral resolutions. Furthermore, we apply the network to SITELLE observations of the merging galaxy system NGC 2207/IC 2163. We find that the closest interacting sector and the central regions of the galaxies are best characterized by two line-of-sight components while the outskirts and spiral arms are well-constrained by a single component. Determining the number of resolvable components is crucial in disentangling different galactic components in merging systems and properly extracting their respective kinematics.

scholarly journals A Novel Method for Intrusion Detection Based on SARSA and Radial Bias Feed Forward Network (RBFFN)

2013 ◽  
Vol 7 (3) ◽  
pp. 646-653
Author(s):  
Anshul Chaturvedi ◽  
Prof. Vineet Richharia
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Intrusion Detection ◽  
Rbf Neural Network ◽  
Neural Network Approach ◽  
Feed Forward Network ◽  
Machine Learning Approach ◽  
Network Process ◽  
Reinforced Learning ◽  
Attack Data

The Internet, computer networks and information are vital resources of current information trend and their protection has increased importance in current existence. Any attempt, successful or unsuccessful to finding the middle ground the discretion, truthfulness and accessibility of any information resource or the information itself is measured a security attack or an intrusion. Intrusion compromised a loose of information credential and trust of security concern. The mechanism of intrusion detection faced a problem of new generated schema and pattern of attack data. Various authors and researchers proposed a method for intrusion detection based on machine learning approach and neural network approach all these compromised with new pattern and schema. Now in this paper a new model of intrusion detection based on SARAS reinforced learning scheme and RBF neural network has proposed. SARAS method imposed a state of attack behaviour and RBF neural network process for training pattern for new schema. Our empirical result shows that the proposed model is better in compression of SARSA and other machine learning technique.

Using artificial neural network condensation to facilitate adaption of machine learning in medical settings by reducing computational burden (Preprint)

2020 ◽  
Author(s):  
Dianbo Liu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Third World ◽  
Mortality Prediction ◽  
Neural Net ◽  
Medical Settings ◽  
Hidden Layer ◽  
Applications Of Machine Learning ◽  
Computational Resources ◽  
Developed Nations

BACKGROUND Applications of machine learning (ML) on health care can have a great impact on people’s lives. At the same time, medical data is usually big, requiring a significant amount of computational resources. Although it might not be a problem for wide-adoption of ML tools in developed nations, availability of computational resource can very well be limited in third-world nations and on mobile devices. This can prevent many people from benefiting of the advancement in ML applications for healthcare. OBJECTIVE In this paper we explored three methods to increase computational efficiency of either recurrent neural net-work(RNN) or feedforward (deep) neural network (DNN) while not compromising its accuracy. We used in-patient mortality prediction as our case analysis upon intensive care dataset. METHODS We reduced the size of RNN and DNN by applying pruning of “unused” neurons. Additionally, we modified the RNN structure by adding a hidden-layer to the RNN cell but reduce the total number of recurrent layers to accomplish a reduction of total parameters in the network. Finally, we implemented quantization on DNN—forcing the weights to be 8-bits instead of 32-bits. RESULTS We found that all methods increased implementation efficiency–including training speed, memory size and inference speed–without reducing the accuracy of mortality prediction. CONCLUSIONS This improvements allow the implementation of sophisticated NN algorithms on devices with lower computational resources.

scholarly journals Discretization and machine learning approximation of BSDEs with a constraint on the Gains-process

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Idris Kharroubi ◽  
Thomas Lim ◽  
Xavier Warin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Differential Equations ◽  
Numerical Experiments ◽  
Optimization Problem ◽  
Learning Approach ◽  
The Neural Network ◽  
Machine Learning Approach ◽  
Mesh Grid

AbstractWe study the approximation of backward stochastic differential equations (BSDEs for short) with a constraint on the gains process. We first discretize the constraint by applying a so-called facelift operator at times of a grid. We show that this discretely constrained BSDE converges to the continuously constrained one as the mesh grid converges to zero. We then focus on the approximation of the discretely constrained BSDE. For that we adopt a machine learning approach. We show that the facelift can be approximated by an optimization problem over a class of neural networks under constraints on the neural network and its derivative. We then derive an algorithm converging to the discretely constrained BSDE as the number of neurons goes to infinity. We end by numerical experiments.

scholarly journals Encoding Health Records into Pathway Representations for Deep Learning

2021 ◽  
Author(s):  
Marco Luca Sbodio ◽  
Natasha Mulligan ◽  
Stefanie Speichert ◽  
Vanessa Lopez ◽  
Joao Bettencourt-Silva
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Source Code ◽  
Training Dataset ◽  
Health Records ◽  
Learning Tasks ◽  
Patient Pathways ◽  
Computational Resources ◽  
The Impact

There is a growing trend in building deep learning patient representations from health records to obtain a comprehensive view of a patient’s data for machine learning tasks. This paper proposes a reproducible approach to generate patient pathways from health records and to transform them into a machine-processable image-like structure useful for deep learning tasks. Based on this approach, we generated over a million pathways from FAIR synthetic health records and used them to train a convolutional neural network. Our initial experiments show the accuracy of the CNN on a prediction task is comparable or better than other autoencoders trained on the same data, while requiring significantly less computational resources for training. We also assess the impact of the size of the training dataset on autoencoders performances. The source code for generating pathways from health records is provided as open source.

scholarly journals A Machine Learning Approach for Efficient Selection of Enzyme Concentrations and Its Application for Flux Optimization

Catalysts ◽  
2020 ◽  
Vol 10 (3) ◽  
pp. 291 ◽  
Author(s):  
Anamya Ajjolli Nagaraja ◽  
Philippe Charton ◽  
Xavier F. Cadet ◽  
Nicolas Fontaine ◽  
Mathieu Delsaut ◽  
...  
Keyword(s):  
Machine Learning ◽  
Glass Ceiling ◽  
Principal Component ◽  
Enzyme Concentration ◽  
Learning Approach ◽  
Neural Network Approach ◽  
Free System ◽  
Machine Learning Approach ◽  
Selection Of

The metabolic engineering of pathways has been used extensively to produce molecules of interest on an industrial scale. Methods like gene regulation or substrate channeling helped to improve the desired product yield. Cell-free systems are used to overcome the weaknesses of engineered strains. One of the challenges in a cell-free system is selecting the optimized enzyme concentration for optimal yield. Here, a machine learning approach is used to select the enzyme concentration for the upper part of glycolysis. The artificial neural network approach (ANN) is known to be inefficient in extrapolating predictions outside the box: high predicted values will bump into a sort of “glass ceiling”. In order to explore this “glass ceiling” space, we developed a new methodology named glass ceiling ANN (GC-ANN). Principal component analysis (PCA) and data classification methods are used to derive a rule for a high flux, and ANN to predict the flux through the pathway using the input data of 121 balances of four enzymes in the upper part of glycolysis. The outcomes of this study are i. in silico selection of optimum enzyme concentrations for a maximum flux through the pathway and ii. experimental in vitro validation of the “out-of-the-box” fluxes predicted using this new approach. Surprisingly, flux improvements of up to 63% were obtained. Gratifyingly, these improvements are coupled with a cost decrease of up to 25% for the assay.

scholarly journals Generating Interactive Worlds with Text

2020 ◽  
Vol 34 (02) ◽  
pp. 1693-1700 ◽  
Author(s):  
Angela Fan ◽  
Jack Urbanek ◽  
Pratik Ringshia ◽  
Emily Dinan ◽  
Emma Qian ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Common Sense ◽  
Learning Approach ◽  
Adventure Game ◽  
Machine Learning Approach ◽  
Game Environment ◽  
Game Elements ◽  
Construction Algorithms ◽  
Game Environments

Procedurally generating cohesive and interesting game environments is challenging and time-consuming. In order for the relationships between the game elements to be natural, common-sense has to be encoded into arrangement of the elements. In this work, we investigate a machine learning approach for world creation using content from the multi-player text adventure game environment LIGHT (Urbanek et al. 2019). We introduce neural network based models to compositionally arrange locations, characters, and objects into a coherent whole. In addition to creating worlds based on existing elements, our models can generate new game content. Humans can also leverage our models to interactively aid in worldbuilding. We show that the game environments created with our approach are cohesive, diverse, and preferred by human evaluators compared to other machine learning based world construction algorithms.

scholarly journals Ecg Heartbeat Classification: Conceptual Understanding through Cnn & Rnn – A Machine Learning Approach

2020 ◽  
Vol 10 (2) ◽  
pp. 143-147
Author(s):  
P. Rama Santosh Naidu ◽  
K.Venkata Ramana ◽  
G. Lavanya Devi
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Dominant Role ◽  
Machine Learning Techniques ◽  
Heartbeat Classification ◽  
Ecg Signals ◽  
The Past ◽  
Learning Techniques ◽  
Machine Learning Approach

In recent days Machine Learning has become major study aspect in various applications that includes medical care where convenient discovery of anomalies in ECG signals plays an important role in monitoring patient's condition regularly. This study concentrates on various MachineLearning techniques applied for classification of ECG signals which include CNN and RNN. In the past few years, it is being observed that CNN is playing a dominant role in feature extraction from which we can infer that machine learning techniques have been showing accuracy and progress in classification of ECG signals. Therefore, this paper includes Convolutional Neural Network and Recurrent Neural Network which is being classified into two types for better results from considerably increased depth.

scholarly journals An Evaluation Study on Investment Efficiency: A Predictive Machine Learning Approach

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Weiwei Hao ◽  
Hongyan Gao ◽  
Zongqing Liu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Structural Equation ◽  
Evaluation Index System ◽  
Corporate Debt ◽  
Investment Efficiency ◽  
Neural Network Approach ◽  
Ownership Reform ◽  
Nonlinear Autoregressive ◽  
Autoregressive Neural Network

This paper proposes a nonlinear autoregressive neural network (NARNET) method for the investment performance evaluation of state-owned enterprises (SOE). It is different from the traditional method based on machine learning, such as linear regression, structural equation, clustering, and principal component analysis; this paper uses a regression prediction method to analyze investment efficiency. In this paper, we firstly analyze the relationship between diversified ownership reform, corporate debt leverage, and the investment efficiency of state-owned enterprises (SOE). Secondly, a set of investment efficiency evaluation index system for SOE was constructed, and a nonlinear autoregressive neural network approach was used for verification. The data of A-share state-owned listed companies in Shanghai and Shenzhen stock exchanges from 2009 to 2018 are taken as a sample. The experimental results show that the output value from the NARNET is highly fitted to the actual data. Based on the neural network model regression analysis, this paper conducts a descriptive statistical analysis of the main variables and control variables of the evaluation indicators. It verifies the direct impact of diversified ownership reform on the investment efficiency of SOE and the indirect impact on the investment efficiency of SOE through corporate debt leverage.

Detection of Abnormal Activity to Alert the Nearby Persons via M-DNN Based Surveillance System

2021 ◽  
Vol 16 ◽  
pp. 668-685
Author(s):  
Shankargoud Patil ◽  
Kappargaon S. Prabhushetty
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Support Vector ◽  
Learning Approach ◽  
Normal Behavior ◽  
Machine Learning Approach ◽  
Artificial Neural Network Ann ◽  
Static Conditions ◽  
Advanced System

In today's environment, video surveillance is critical. When artificial intelligence, machine learning, and deep learning were introduced into the system, the technology had progressed much too far. Different methods are in place using the above combinations to help distinguish various wary activities from the live tracking of footages. Human behavior is the most unpredictable, and determining whether it is suspicious or normal is quite tough. In a theoretical setting, a deep learning approach is utilized to detect suspicious or normal behavior and sends an alarm to the nearby people if suspicious activity is predicted. In this paper, data fusion technique is used for feature extraction which gives an accurate outcome. Moreover, the classes are classified by the well effective machine learning approach of modified deep neural network (M-DNN), that predicts the classes very well. The proposed method gains 95% accuracy, as well the advanced system is contrast with previous methods like artificial neural network (ANN), random forest (RF) and support vector machine (SVM). This approach is well fitted for dynamic and static conditions.

Sign in / Sign up

Export Citation Format

Share Document