检索结果-内蒙古大学图书馆

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shoeibi, Afshin Sadeghi, Delaram Moridian, Parisa Ghassemi, Navid Heras, Jonathan Alizadehsani, Roohallah Khadem, Ali Kong, Yinan Nahavandi, Saeid Zhang, Yu-Dong Gorriz, Juan M. The Faculty of Electrical Engineering K. N. Toosi University of Technology Tehran Iran The Dept. of Medical Engineering Mashhad Branch Islamic Azad University Mashhad Iran The Faculty of Engineering Science and Research Branch Islamic Azad University Tehran Iran The Department of Mathematics and Computer Science University of la Rioja La Rioja Spain Deakin University VIC3217 Australia The School of Engineering Macquarie University Sydney2109 Australia The Harvard Paulson School of Engineering and Applied Sciences Harvard University AllstonMA02134 United States The Department of Informatics University of Leicester Leicester United Kingdom The Department of Signal Theory Networking and Communications Universidad de Granada Spain The Department of Psychiatry. University of Cambridge United Kingdom

Schizophrenia (SZ) is a mental disorder whereby due to the secretion of specific chemicals in the brain, the function of some brain regions is out of balance, leading to the lack of coordination between thoughts, actions, and emotions. This study provides various intelligent deep learning (DL)-based methods for automated SZ diagnosis via electroencephalography (EEG) signals. The obtained results are compared with those of conventional intelligent methods. To implement the proposed methods, the dataset of the Institute of Psychiatry and Neurology in Warsaw, Poland, has been used. First, EEG signals were divided into 25 s time frames and then were normalized by z-score or norm L2. In the classification step, two different approaches were considered for SZ diagnosis via EEG signals. In this step, the classification of EEG signals was first carried out by conventional machine learning methods, e.g., support vector machine, k-nearest neighbors, decision tree, naïve Bayes, random forest, extremely randomized trees, and bagging. Various proposed DL models, namely, long short-term memories (LSTMs), one-dimensional convolutional networks (1D-CNNs), and 1DCNN-LSTMs, were used in the following. In this step, the DL models were implemented and compared with different activation functions. Among the proposed DL models, the CNN-LSTM architecture has had the best performance. In this architecture, the ReLU activation function with the z-score and L2-combined normalization was used. The proposed CNN-LSTM model has achieved an accuracy percentage of 99.25. © 2021, CC BY-NC-ND.

关键词： Diseases

State of the Art of Audio- and Video-Based Solutions for AAL

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Aleksic, Slavisa Atanasov, Michael Agius, Jean Calleja Camilleri, Kenneth Čartolovni, Anto Climent-Pérez, Pau Colantonio, Sara Cristina, Stefania Despotovic, Vladimir Ekenel, Hazım Kemal Erakin, Ekrem Florez-Revuelta, Francisco Germanese, Danila Grech, Nicole Sigurðardóttir, Steinunn Gróa Emirzeoğlu, Murat Iliev, Ivo Jovanovic, Mladjan Kampel, Martin Kearns, William Klimczuk, Andrzej Lambrinos, Lambros Lumetzberger, Jennifer Mucha, Wiktor Noiret, Sophie Pajalic, Zada Pérez, Rodrigo Rodriguez Petrova, Galidiya Petrovica, Sintija Pocta, Peter Poli, Angelica Pudane, Mara Spinsante, Susanna Salah, Albert Ali Santofimia, Maria Jose Islind, Anna Sigríður Stoicu-Tivadar, Lacramioara Tellioğlu, Hilda Zgank, Andrej Leipzig University of Applied Sciences Germany TU Wien Austria Department of Anatomy University of Malta Malta Centre for Biomedical Cybernetics Faculty of Engineering Department of Systems and Control Engineering Malta Catholic University of Croatia Croatia Universidad de Alicante Spain Institute of Information Science and Technologies The National Research Council of Italy Italy Department of Systems and Control Engineering University of Malta Malta University of Luxembourg Luxembourg Dept. of Computer Engineering Istanbul Technical University Turkey Reykjavik University School of Computer Science Iceland Sağlık Bilimleri Fakültesi Fizyoterapi ve Rehabilitasyon Karadeniz Technical University Research Information System Turkey TU Sofia Bulgaria Singidunum University Belgrade Serbia University of South Florida United States SGH Warsaw School of Economics Poland Department of Communication and Internet Studies Cyprus University of Technologies Cyprus Technical University of Vienna Austria VID Specialized University Oslo Norway Getafe University Hospital Spain Riga Technical University Latvia University of Zilina Slovakia Università Politecnica Marche Italy Utrecht University Netherlands Universidad de Castilla-La Mancha Spain Reykjavik University Iceland University Politehnica Timisoara Romania University of Maribor Slovenia

It is a matter of fact that Europe is facing more and more crucial challenges regarding health and social care due to the demographic change and the current economic context. The recent COVID-19 pandemic has stressed this situation even further, thus highlighting the need for taking action. Active and Assisted Living (AAL) technologies come as a viable approach to help facing these challenges, thanks to the high potential they have in enabling remote care and support. Broadly speaking, AAL can be referred to as the use of innovative and advanced Information and Communication Technologies to create supportive, inclusive and empowering applications and environments that enable older, impaired or frail people to live independently and stay active longer in society. AAL capitalizes on the growing pervasiveness and effectiveness of sensing and computing facilities to supply the persons in need with smart assistance, by responding to their necessities of autonomy, independence, comfort, security and safety. The application scenarios addressed by AAL are complex, due to the inherent heterogeneity of the end-user population, their living arrangements, and their physical conditions or impairment. Despite aiming at diverse goals, AAL systems should share some common characteristics. They are designed to provide support in daily life in an invisible, unobtrusive and user-friendly manner. Moreover, they are conceived to be intelligent, to be able to learn and adapt to the requirements and requests of the assisted people, and to synchronise with their specific needs. Nevertheless, to ensure the uptake of AAL in society, potential users must be willing to use AAL applications and to integrate them in their daily environments and lives. In this respect, video- and audio-based AAL applications have several advantages, in terms of unobtrusiveness and information richness. Indeed, cameras and microphones are far less obtrusive with respect to the hindrance other wearable sensors may

关键词： computer vision

Towards Translation of Semantics of Automotive Interface Description Models from Franca to AUTOSAR Frameworks : An Approach using Semantic Synergies

学校读者我要写书评

暂无评论

Towards Translation of Semantics of Automotive Interface Des...

International Conference on applied Electronics, AE

作者： Sangita De Michael Niklas Brian Rooney Juergen Mottok Premek Brada Corporate System and Technology SW Continental Automotive GmbH Regensburg Germany Dept. of Electrical Engineering and Information Technology OstBayerische Technical University (OTH) Regensburg Germany Dept. of Computer Science and Engineering Faculty of Applied Sciences University of West Bohemia Pilsen Czech Republic

The automotive industry is eventually evolving into a complex network of services. The heterogeneous and distributed nature of automotive software systems demands flexible software components which can operate in different environments. Because of heterogeneous automotive development environments, the domain experts, must cope with too many diversities, adaption layers, and incompatibilities to design applications for the current generation of autonomous driving vehicles. In this context, interface adaptation is a promising approach to achieve flexibility without directly changing the respective components. AUTOSAR, which is the de-facto standard for describing automotive system architecture and is a hugely comprehensive standard allowing designers full control from abstract system description to bare metal level deployment. However, the vehicle subsystems have still evolved to include multifarious high-level domains not covered by AUTOSAR e.g. Infotainment, Telematics etc. Therefore, it seems beneficial to bridge the semantic gaps between AUTOSAR applications and other standards of automotive application domains. The goal of this paper is to investigate interface semantic mapping and achieve transparent integration of domain-specific applications using the translation of semantics among the AUTOSAR platform software component models and other software components models of open source development platforms e.g. GENIVI. A key goal of such a modelling approach is the reuse of existing interface description languages and respective code generators. This will enhance future interoperability and decrease in incompatibility among these platforms.

关键词： Semantics Automotive engineering Adaptation models Standards Connectors Receivers Software

Realization of a Low Energy State of an Electron Beam in Uniform Channel 20

学校读者我要写书评

暂无评论

Realization of a Low Energy State of an Electron Beam in Uni...

20th International Symposium on High-Current Electronics, ISHCE 2018

作者： Fuks, Mikhail Kovalev, Nikolav Schamiloglu, Edl Dept. of Electrical and Computer Engineering University of New Mexico AlbuquerqueNM87131-1356 United States Russian Academy of Science Nizhny Institute of Applied Physics Novgorod Russia

ISBN: (纸本)9781538668900

Earlier it was shown that between two virtual cathodes in a channel consisting of 3 uniform tubes with different radii a low energy state of electrons with the potential close to the cathode potential appears. In the present paper we show that the low energy state also appears in uniform tube but between a real tubular cathode and a magnetic mirror. © 2018 IEEE.

关键词： Electron beams

Structural, Morphological, and Optical Properties of CuO thin films treated by Gamma ray

学校读者我要写书评

暂无评论

Structural, Morphological, and Optical Properties of CuO thi...

2018 International Conference on computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018

作者： Saha, S.M.K. Ali, M.H. Hossen, Moha. Feroz Firoz Pervez, M. Mia, M.N.H. Khalid Hossain, M. Sayid Haque, M.A. Dept. of Computer Science and Engineering Southeast University Bangladesh Dept. of Electronics and Telecommunication Engineering Begum Rokeya University Bangladesh Dept. of Applied Physics and Electronic Engineering University of Rajshahi Bangladesh Institute of Electronics Atomic Energy Research Establishment Bangladesh Atomic Energy Commission Dhaka Bangladesh

ISBN: (纸本)9781538647752

Semiconductor electronic and optical devices are used in space, nuclear reactor, particle accelerator for data acquisition, processing, and power control systems. Gamma ray is inherent in these types of environment. Thus, the semiconductor materials used in the installed device interacts with gamma ray altering properties of semiconductors significantly. Therefore, the effect of gamma ray needs to be explored before applying a material in a radiation-exposed environment. In this work, CuO thin film, a p-type potential compound semiconductor for optoelectronics and photonics device, was fabricated by Doctor-blade method on a glass substrate and irradiated with Cobalt-60 gamma radiation source. For the first time, the effects of absorbed dose on morphological, structural, and optical properties on CuO thin film were investigated by SEM, XRD, and UV-vis-NIR spectroscopic analyses. Significant variations in optical bandgap, transmittance, absorbance, crystallite size, lattice strain, and dislocation density were observed. © 2018 IEEE.

关键词： Copper oxides

Sirona: Sustainable integration of regenerative outer-space nature and agriculture. Part 2 - Design development and projected performance 70

学校读者我要写书评

暂无评论

Sirona: Sustainable integration of regenerative outer-space ...

70th International Astronautical Congress, IAC 2019

作者： Hava, Heather Larissa Zhou, H. King, Abby Mehlenbeck, Chad Lombardi, Elizabeth M. Kaufman, Andy Correll, Nikolaus Ann and H. J. Smead Aerospace Engineering Sciences University of Colorado Boulder 1111 Engineering Drive BoulderCO80309 United States John A. Paulson School of Engineering and Applied Sciences Harvard University 29 Oxford St CambridgeMA02138 United States Dept. of Chemical and Biological Engineering 1111 Engineering Drive BoulderCO80309 United States Golden CO80403 United States Dept. of Ecology and Evolutionary Biology Cornell University E145 Corson Hall IthacaNY14853 United States Dept. of Tropical Plants and Soil Sciences 3190 Maile Way HonoluluHI96822 United States Dept. of Computer Science 1111 Engineering Drive BoulderCO80309 United States

A comprehensive Bioregenerative Life Support System (BLiSS) for long-duration human space exploration missions (LDEM) requires an innovative design philosophy and novel technical solutions. SIRONA: Sustainable Integration of Regenerative Outer-space Nature and Agriculture is a greenhouse design that produces a wide variety of food sources and provides life support functions including access to nature to improve astronaut restoration, relaxation, and recreation. Whereas Hava et al. 2019 outlined the primary technologies and system architecture of SIRONA, this paper describes the foundational design principles that informed the development of the greenhouse. Analyses on projected performance are also carried out to validate design assumptions and constraints. Copyright © 2019 by the International Astronautical Federation (IAF). All rights reserved.

关键词： Greenhouses

Rich dynamics and anticontrol of extinction in a prey-predator system

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Danca, Marius-F Fečkan, Michal Kuznetsov, Nikolay Cheng, Guanrong Dept. of Mathematics and Computer Science Avram Iancu University of Cluj- Napoca Romania Romanian Institute of Science and Technology Cluj-Napoca Romania Dept. of Mathematical Analysis and Numerical Mathematics Faculty of Mathematics Physics and Informatics Comenius University in Bratislava Mathematical Institute Slovak Academy of Sciences Dept. of Applied Cybernetics Saint-Petersburg State University Russia Dept. of Mathematical Information Technology University of Jyväskylä Finland Dept. of Electronic Engineering City University of Hong Kong Hong Kong

This paper reveals some new and rich dynamics of a two-dimensional prey-predator system and to anticontrol the extinction of one of the species. For a particular value of the bifurcation parameter, one of the system variable dynamics is going to extinct, while another remains chaotic. To prevent the extinction, a simple anticontrol algorithm is applied so that the system orbits can escape from the vanishing trap. As the bifurcation parameter increases, the system presents quasiperiodic, stable, chaotic and also hyperchaotic orbits. Some of the chaotic attractors are Kaplan-Yorke type, in the sense that the sum of its Lyapunov exponents is positive. Also, atypically for undriven discrete systems, it is numerically found that, for some small parameter ranges, the system seemingly presents strange nonchaotic attractors. It is shown both analytically and by numerical simulations that the original system and the anticontrolled system undergo several Neimark-Sacker bifurcations. Beside the classical numerical tools for analyzing chaotic systems, such as phase portraits, time series and power spectral density, the’0-1’ test is used to differentiate regular attractors from chaotic attractors. Copyright © 2019, The Authors. All rights reserved.

关键词： Spectral density

A Lipschitz-constrained anomaly discriminator framework

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Tong, Alexander Wolf, Guy Krishnaswamy, Smita Dept. of Computer Science Yale University New HavenCT United States Dept. of Math. and Stat Université de Montréal MontrealQC Canada Depts. of Genetics & Comp. Sci Yale University New HavenCT United States

Anomaly detection is a problem of great interest in medicine, finance, and other fields where error and fraud need to be detected and corrected. Most deep anomaly detection methods rely on autoencoder reconstruction error. However, we show that this approach has limited value. First, this approach starts to perform poorly when either noise or anomalies contaminate training data, even to a small extent. Second, this approach cannot detect anomalous but simple to reconstruct points. This can be seen even in relatively simple examples, such as feeding a black image to detectors trained on MNIST digits. Here, we introduce a new discriminatorbased unsupervised Lipschitz anomaly detector (LAD). We train a Wasserstein discriminator, similar to the ones used in GANs, to detect the difference between the training data and corruptions of the training data. We show that this procedure successfully detects unseen anomalies with guarantees on those that have a certain Wasserstein distance from the data or corrupted training set. Finally, we show results of this system in an electronic medical record dataset of HIV-positive veterans from the veterans aging cohort study (VACS) to establish usability in a medical setting. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

Confidence from invariance to image transformations

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Bahat, Yuval Shakhnarovich, Gregory Dept. of Computer Science and Applied Math Weizmann Institute of Science Rehovot Israel Toyota Technological Institute at Chicago ChicagoIL United States

We develop a technique for automatically detecting the classification errors of a pre-trained visual classifier. Our method is agnostic to the form of the classifier, requiring access only to classifier responses to a set of inputs. We train a parametric binary classifier (error/correct) on a representation derived from a set of classifier responses generated from multiple copies of the same input, each subject to a different natural image transformation. Thus, we establish a measure of confidence in classifier's decision by analyzing the invariance of its decision under various transformations. In experiments with multiple data sets (STL- 10,CIFAR-100,ImageNet) and classifiers, we demonstrate new state of the art for the error detection task. In addition, we apply our technique to novelty detection scenarios, where we also demonstrate state of the art results. Copyright © 2018, The Authors. All rights reserved.

关键词： Classification (of information)