Filters








381 Hits in 8.2 sec

Comparing Kurtosis Score to Traditional Statistical Metrics for Characterizing the Structure in Neural Ensemble Activity [chapter]

Peter Stratton, Janet Wiles
2008 Lecture Notes in Computer Science  
We therefore propose that kurtosis is a useful addition to the statistical toolbox for identifying interesting structure in neuron ensemble activity.  ...  This study investigates the range of behaviors possible in ensembles of spiking neurons and the effect of their connectivity on ensemble dynamics utilizing a novel application of statistical measures and  ...  The authors thank Markus Diesmann and Tom Tetzlaff for insightful discussions. This work was supported by an ARC Thinking Systems grant and a COSNet Overseas Travel grant (COSNet Proposal number 92).  ... 
doi:10.1007/978-3-540-88853-6_9 fatcat:rilau7hlenas7j3vdnrbxcy4ca

An Advanced CNN-LSTM Model for Cryptocurrency Forecasting

Ioannis E. Livieris, Niki Kiriakidou, Stavros Stavroyiannis, Panagiotis Pintelas
2021 Electronics  
In this research, we propose a multiple-input deep neural network model for the prediction of cryptocurrency price and movement.  ...  with traditional fully-connected deep neural networks.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/electronics10030287 fatcat:hx53erpc4fg55ppslorz5kl4ji

A Spatio-Temporal Ensemble Deep Learning Architecture for Real-Time Defect Detection during Laser Welding on Low Power Embedded Computing Boards

Christian Knaak, Jakob von Eßen, Moritz Kröger, Frederic Schulze, Peter Abels, Arnold Gillner
2021 Sensors  
Ultimately, the ensemble deep neural network is implemented and optimized to operate on low-power embedded computing devices with low latency (1.1 ms), demonstrating sufficient performance for real-time  ...  In addition, the ability to recognize the current state of product quality in real-time is an important prerequisite for autonomous and self-improving manufacturing systems.  ...  The ensemble deep learning architecture is also compared to state-of-the-art CNNs for image processing.  ... 
doi:10.3390/s21124205 fatcat:ro2gpcb5p5gxnl57yzhibw6pzu

Automated Spleen Injury Detection Using 3D Active Contours and Machine Learning

Julie Wang, Alexander Wood, Chao Gao, Kayvan Najarian, Jonathan Gryak
2021 Entropy  
While computer-assisted diagnosis systems exist for other conditions assessed using CT scans, the current method to detect spleen injuries involves the manual review of scans by radiologists, which is  ...  The spleen is one of the most frequently injured organs in blunt abdominal trauma.  ...  Fractal features have been widely applied in texture and shape analyses of images, including medical images [9, 21] to characterize the irregularity of physical structures.  ... 
doi:10.3390/e23040382 pmid:33804831 fatcat:lol7wa6m4jhplp5lccdsiz72zm

Fault Detection and Identification Methodology Under an Incremental Learning Framework Applied to Industrial Machinery

Jesus A. Carino, Miguel Delgado-Prieto, Jose Antonio Iglesias, Araceli Sanchis, Daniel Zurita, Marta Millan, Juan Antonio Ortega Redondo, Rene Romero-Troncoso
2018 IEEE Access  
This work is also supported in part by the Spanish Ministry of Economy and Competitiveness under the TRA2016-80472-R Research Project.  ...  The authors would like to thank the support and the access to the friction test machine database provided by MAPRO Sistemas de ensayo S.A. especially to Álvaro Istúriz and Alberto Saéz.  ...  First, a set of statistical time-based features are estimated in order to characterize the available physical magnitudes.  ... 
doi:10.1109/access.2018.2868430 fatcat:lj3drth4ardfnj6irvnra3nxdq

Bankruptcy Prediction: The Case of the Greek Market

Angeliki Papana, Anastasia Spyridou
2020 Forecasting  
The research on bankruptcy prediction is of the utmost importance as it aims to build statistical models that can distinguish healthy firms from financially distressed ones.  ...  A comparison of linear discriminant analysis, logit, decision trees and neural networks is performed. The results show that discriminant analysis is slightly superior to the other methods.  ...  All authors have read and agreed to the published version of the manuscript. Funding: This research received no external funding. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/forecast2040027 fatcat:we5op3ofpba3hnsuntqduw3t3a

A Machine Learning Approach for Micro-Credit Scoring

Apostolos Ampountolas, Titus Nyarko Nde, Paresh Date, Corina Constantinescu
2021 Risks  
This presents inexpensive and reliable means to micro-lending institutions around the developing world with which to assess creditworthiness in the absence of credit history or central credit databases  ...  This research compares various machine learning algorithms on real micro-lending data to test their efficacy at classifying borrowers into various credit categories.  ...  The tree flow display is comparable to a progress diagram, with a tree structure in which cases are arranged based on their feature values (Szczerbicki 2001) .  ... 
doi:10.3390/risks9030050 fatcat:osqzqypywjhlbdv7xfrz6ewfum

A Review of the Recent Developments in Integrating Machine Learning Models with Sensor Devices in the Smart Buildings Sector with a View to Attaining Enhanced Sensing, Energy Efficiency, and Optimal Building Management

Dana-Mihaela Petroșanu, George Căruțașu, Nicoleta Luminița Căruțașu, Alexandru Pîrjan
2019 Energies  
Moreover, the conducted review creates the premises for identifying in the scientific literature the main purposes for integrating Machine Learning techniques with sensing devices in smart environments  ...  To this end, we have used reliable sources of scientific information, namely the Elsevier Scopus and the Clarivate Analytics Web of Science international databases, in order to assess the interest regarding  ...  In [25] , the authors made use of Convolutional Neural Networks (CNNs) for detecting abnormal behavior related to dementia, the results were compared with methods such as Naïve Bayes (NB), Hidden Markov  ... 
doi:10.3390/en12244745 fatcat:eix222pupjcmddolute2qh4wia

HIFA: Promising Heterogeneous Solar Irradiance Forecasting Approach Based on Kernel Mapping

Mohamed Abdel-Nasser, Karar Mahmoud, Matti Lehtonen
2021 IEEE Access  
The results reveal that HIFA substantially improves the accuracy of solar irradiance forecasting when compared to ensemble-based approaches, thanks to the generalization capability of the proposed aggregation  ...  HIFA utilizes efficient deep recurrent neural networks, which can exploit long-term information from previous computations to model the fluctuated solar irradiance, for building the IFMs.  ...  To demonstrate such diversity of datasets, we compare solar irradiance at the three sites in terms of statistical metrics, namely the mean (µ), standard deviation (σ 2 ), kurtosis, and skewness.  ... 
doi:10.1109/access.2021.3122826 fatcat:jpxxqowgtrhidnijjxrd3sfyiq

An ensemble of deep learning-based multi-model for ECG heartbeats arrhythmia classification

Ehab Essa, Xianghua Xie
2021 IEEE Access  
RNN varies in the learning structure from feedforward neural networks by connecting the outputs of the current time step to the inputs of the next time step.  ...  traditional machine learning methods or deep neural networks.  ... 
doi:10.1109/access.2021.3098986 fatcat:fusxrz66qfhcrdduj2sedtsmn4

Smoothing and stationarity enforcement framework for deep learning time-series forecasting

Ioannis E Livieris, Stavros Stavroyiannis, Lazaros Iliadis, Panagiotis Pintelas
2021 Neural computing & applications (Print)  
These transformations are performed in two successive stages: The first stage is based on the smoothing technique for the development of a new de-noised version of the original series in which every value  ...  The second stage of transformations is performed on the smoothed series and it is based on differencing the series in order to be stationary and be considerably easier fitted and analyzed by a deep learning  ...  accuracy and AUC scores, in case trained with Smoothed FD series compared to that trained with the traditional first-differenced series.  ... 
doi:10.1007/s00521-021-06043-1 pmid:33967398 pmcid:PMC8096631 fatcat:pbyemgutlbcr5ar7kpxzazmtxq

A New Distributed Anomaly Detection Approach for Log IDS Management Based on Deep Learning

2021 Turkish Journal of Electrical Engineering and Computer Sciences  
The results obtained in these experiments appear to provide a 16 promising gain in performance evaluation metrics compared to the other available methods. 17  ...  We conducted 14 comparative experiments with the approach we propose to detect cyberattack anomalies in log data management with 15 the classification methods used in machine learning.  ...  In the next stage after 7 balancing the data, we use a deep neural network structure to detect outliers.  ... 
doi:10.3906/elk-2102-89 fatcat:uuvpnnwclvfpzmppfda5a3iqse

Computer-Aided Grading of Gliomas Combining Automatic Segmentation and Radiomics

Wei Chen, Boqiang Liu, Suting Peng, Jiawei Sun, Xu Qiao
2018 International Journal of Biomedical Imaging  
The MRI data containing 220 high-grade gliomas and 54 low-grade gliomas are used to evaluate our system. A multiscale 3D convolutional neural network is trained to segment whole tumor regions.  ...  Our CAD system is highly effective for the grading of gliomas with an accuracy of 91.27%, a weighted macroprecision of 91.27%, a weighted macrorecall of 91.27%, and a weighted macro-F1 score of 90.64%.  ...  Conflicts of Interest The authors declare that there are no conflicts of interest regarding the publication of this paper.  ... 
doi:10.1155/2018/2512037 pmid:29853828 pmcid:PMC5964423 fatcat:fsrvakaddzh6fdwghip3h5aqqe

Perceptual image quality assessment: a survey

Guangtao Zhai, Xiongkuo Min
2020 Science China Information Sciences  
Third, the performances of the state-of-the-art quality measures for visual signals are compared with an introduction of the evaluation protocols.  ...  Perceptual quality assessment plays a vital role in the visual communication systems owing to the existence of quality degradations introduced in various stages of visual signal acquisition, compression  ...  Then quality score prediction model is built for each feature, and an ensemble method is utilized to combine all quality scores. Freitas et al.  ... 
doi:10.1007/s11432-019-2757-1 fatcat:kizmju2lbbbcxjb42y6stct5sq

Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks

M.N. Utah, J.C. Jung
2020 Nuclear Engineering and Technology  
Also, a deep neural network (DNN) was developed for the prediction of RUL based on the failure modes of the SOV.  ...  Jung, Fault state detection and remaining useful life prediction in AC powered solenoid operated valves based on traditional machine learning and deep neural networks, Nuclear Engineering and Technology  ...  Acknowledgement This research was supported by the 2019 Research Fund of the KEPCO international Nuclear Graduate School (KINGS), the Republic of Korea.  ... 
doi:10.1016/j.net.2020.02.001 fatcat:ceepsl7ypjhe5i4lj5ybvucig4
« Previous Showing results 1 — 15 out of 381 results