检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Dipayan Dewan Lidia Ghosh Biswadeep Chakraborty Abir Chowdhury Amit Konar Atulya K. Nagar Artificial Intelligence Laboratory ETCE Department Jadavpur University Kolkata India Dept. of Electrical and Computer Engineering Georgia Institute of Technology USA Dept. of Math and Computer Science Liverpool Hope University UK

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

Human behavior is a complex action which has provoked the thoughts of many people for a long time. However, very little about the cognitive aspect of an individual person's personality is known till the date. In order to differentiate people with significant differences in personality from their brain responses, we must at first be able to classify them based on their thought processes. From the viewpoint of classical ethics, people can broadly be classified into two main classes, namely, Categorical and Consequentialist. In this paper, we conduct several experiments where the subjects experience various ethical dilemmas and their ethical values in response to the presented stimuli are investigated through a question-answer session. The brain responses of the subjects are acquired using electroencephalography, which is then fed to an attention based parallel Convolutional Bi-directional Long Short-Term Memory (AConvBi-LSTM-NN) network with an ultimate aim to classify people into two above mentioned categories. Apart from the application point of view, the novelty of the paper lies in representing the EEG time-series into a sequence of multispectral 2D images which contain the spatial information of the acquired signal. The spectral information, along with the EEG time series (temporal information) are then used to train the proposed convolutional Bi-LSTM Network. The experimental results demonstrate promising results in classifying people based on their ethical values from their brain responses, with high classification accuracy. This provides scope for a new direction of research which can be further explored.

关键词： Electroencephalography Convolution Feature extraction Two dimensional displays Electrodes computer architecture Microprocessors

来源：评论

学校读者我要写书评

暂无评论

User Interaction Development for Radiotherapy Virtual Reality Training Application

User Interaction Development for Radiotherapy Virtual Realit...

引用

Computing (ICOCO), IEEE International Conference on

作者： Vei Siang Chan Andrés Iglesias Farhan Mohamed Faezah M. Salleh Habibollah Haron Najwa Ayuni Jamaludin Akemi Gálvez Pedro J. Prada Samuel Ruiz Lihua You Faculty of Computing Universiti Teknologi Malaysia Johor Bahru Malaysia Dept. of Applied Mathematics and Computational Sciences Universidad de Cantabria Santander Spain Faculty of Pharmaceutical Sciences Toho University Funabashi Japan Media and Game Innovation Center of Excellence Universiti Teknologi Malaysia Johor Bahru Malaysia Faculty of Science Universiti Teknologi Malaysia Johor Bahru Malaysia Hospital Universitario Marqués de Valdecilla Santander Spain National Center for Computer Animation Bournemouth University Poole United Kingdom

The advancement of virtual reality (VR) technology can enrich pedagogical approaches and information communication. In the oncology radiotherapy treatment, the medical practitioners revealed two main issues: the lack of training infrastructure and patient comprehension of the treatment process. Virtual simulation can assist in solving these complexities by offering an economical virtual embodiment of the medical facility. This study aims to improve the user interface and experience of VR training applications from previous work by conducting a domain expert intervention methodology. This paper discusses the main challenges and features of user interaction design for effective VR training systems and optimises the system based on feedback from domain experts. The authors anticipate that the key factors and design considerations proposed for this VR training application can benefit the development of related training systems in many other domains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of non-destructive mango assessment using Handheld Spectroscopy and Machine Learning Regression

Development of non-destructive mango assessment using Handhe...

引用

International Conference on Engineering, Technology and Innovative Researches 2019, ICETIR 2019

作者： Abdullah Al-Sanabani, Dheya Galal Solihin, Mahmud Iwan Pui, Liew Phing Astuti, Winda Ang, Chun Kit Hong, Lim Wei Mechatronics Engineering Faculty of Engineering UCSI University Malaysia Food Science Dept. Faculty of Applied Science UCSI University Malaysia Computer Engineering Dept. Faculty of Engineering Bina Nusantara University Indonesia

Quality determines the shelf-life and selling prices of fresh mango, and therefore quality observation and control of fresh mango are of utmost significance in the processing and management of its supply chain. Mango fruit (mangifera indica) quality methods are mostly destructive in nature. Different mechanical, electromagnetic and non-destructive methods are increasingly important nowadays because of the ease of operation, speed, and reliability of the process. This project aims to develop a non-destructive assessment of mango quality using handheld micro NIR (near-infrared) spectroscopic device. NIR spectra data and Brix levels, which indicate the sugar content of the plant, i.e. indicating the sweetness of the mango, were collected from three different types of Mango (Chokanan, Rainbow, and Kai Te), resulting 80 samples (i.e. 60 samples for training and 20 samples for testing) in this project. NIR spectra can be converted mathematically to obtain quantitative information of chemical and physical nature by multivariate calibration. The spectra data is pre-processed using Gaussian smoothing and extended multiplicative signal correction (EMSC) for the elimination of uncontrollable path length or scattering effects. These samples were then used to develop a predictive model using both Support Vector Machine (SVM) regression and Partial Least Squares regression (PLS) methods. The coefficient of determination (R2) obtained from SVM for training/calibration and testing dataset are 0.96 and 0.95 respectively. Meanwhile, the coefficient of determination (R2) obtained from PLS for calibration/training and testing dataset are 0.89 and 0.86 respectively. The results obtained from this project indicate that the handheld NIR has potential use for non-destructive assessment of mango fruits quality. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Geometric Aggregation Operator for MCDM Method Based on AIFS Information: Application to Renewable-Energy-Source-Selection Problems

Geometric Aggregation Operator for MCDM Method Based on AIFS...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Bhagawati Prasad Joshi Arvind Bhatt Mehul Manu Anuj Kumar Sangeeta Pant Shailendra Giri Department of Mathematics Graphic Era Hill University Bhimtal India Department of Mathematics Uttarakhand Open University Haldwani Uttrakhand India Department of Allied Sciences Graphic Era Hill University Bhimtal India School of Computer Science Engg. & Applications D. Y. Patil International University (DYPIU) Pune Maharashtra Department of Applied Sciences Symbiosis International (Deemed University) (SIU) Pune Maharashtra Department of Mathematics Education Dept. Govt of Uttarakhand Pauri Garhwal India

Ambiguous intuitionistic fuzzy set (AIFS) theory is more suitable tool to deal with uncertainties as compared to fuzzy set (FS) and intuitionistic FS. In this paper, a method for the classification of renewable energy sources (RES) under the AIFS environment is proposed. Firstly, we propose new aggregation operators, namely the ambiguous-intuitionistic weighted-geometric (AI-WG) and the ambiguous-intuitionistic ordered-weighted-geometric (AI-OWG) are proposed, to fuse AIFNs input information. Then, based on these defined operators, we develop an approach for RES-selection problem and successfully applied it for a RES classification. The obtained results are compared with some considered methods to verify its effectiveness and efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mango Leaf Disease Classification using Deep Learning: A Comprehensive Survey

Research Square

引用

Research Square 2025年

作者： Rai, Rebika Das, Arunita Dhal, Krishna Gopal Sasmal, Buddhadev Galvez, Jorge Dept. of Computer Applications Sikkim University Sikkim India West Bengal Paschim Medinipur India Dept. of Pure and Applied Science Midnapore City College West Bengal Paschim Medinipur India Information and Knowledge based Innovation Department Universidad de Guadalajara Av. Revolución 1500 C.P. 44430 Mexico

Mango cultivation plays a pivotal role in the development and growth of a country, contributing significantly to its economy and agricultural sector. The cultivation of mangoes not only provides a valuable source of income for farmers but also boosts export opportunities, fostering economic stability. However, the impact of mango leaf diseases poses a serious threat to global mango production. Diseases like anthracnose, powdery mildew, sooty mould, and gall midge can lead to reduced yields, diminished fruit quality, and economic losses for farmers. The timely detection and management of these diseases are crucial for mitigating their adverse effects. Fortunately, advanced technology, especially deep learning, has shown up as an effective ally in the early detection of these diseases. Therefore, the aim of this study is to present an updated survey report on this topic. © 2025, CC BY.

关键词： Cultivation

来源：评论

学校读者我要写书评

暂无评论

Two approaches to machine learning classification of time series based on recurrence plots 3

Two approaches to machine learning classification of time se...

引用

3rd IEEE International Conference on Data Stream Mining and Processing, DSMP 2020

作者： Kirichenko, Lyudmyla Radivilova, Tamara Bulakh, Vitalii Zinchenko, Petro Saif Alghawli, Abed Kharkiv National University of Radio Electronics Department of Applied Mathematics Kharkiv Ukraine Kharkiv National University of Radio Electronics V.V. Popovskyy Dept. of Infocommunication Engineering Kharkiv Ukraine Prince Sattam Bin Abdulaziz University Department of Computer Science Aflaj Saudi Arabia

ISBN: (数字)9781728132143

ISBN: (纸本)9781728132143

The article considers the task of classifying fractal time series based on the construction of their recurrence plots. Short realizations of EEG signals were used as input data. Two classification machine learning methods were considered: in the first case, quantitative fractal and recurrent characteristics of the time series were classification features, in the second case, image recognition of recurrence plots was carried out. The results showed fairly high classification quality for both methods, and relative advantage of the image classification method. © 2020 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Plant Stem Tissue Modeling and Parameter Identification using Meta-heuristic Optimization Algorithms

Research Square

引用

Research Square 2021年

作者： Ghoneim, Mohamed S. Ismail, Samar I. Said, Lobna A. Eltawil, Ahmed M. Radwan, Ahmed G. Madian, Ahmed H. Nile University Giza Egypt Electrical Engineering and Computer Science Dept. University of California-Irvine Irvine United States King Abdullah Univ. of Science and Technology Thuwal Saudi Arabia Engineering Mathematics and Physics Department Cairo University Egypt School of Engineering and Applied Sciences Nile University Giza Egypt Radiation Engineering Dept. NCRRT Egyptian Atomic Energy Authority Cairo Egypt

Bio-impedance non-invasive measurement techniques usage is rapidly increasing in the agriculture industry. These measured impedance variations reflect tacit biochemical and biophysical changes of living and non-living tissues. Bio-impedance circuit modeling is an effective solution used in biology and medicine to fit the measured impedance. This paper proposes two new fractional-order bio-impedance plant stem models. These new models are compared among three commonly used bio-impedance fractional-order circuit models in plant modeling (Cole, Double Cole, FO Double-shell). The two proposed models represent the characterization of the biological cellular morphology of the plant stem through a non-invasive method. Experiments are conducted on two samples of three different medical plant species under the family Lamiaceae, and each sample is measured at two inter-electrode spacing distances. Bio-impedance measurements are done using an electrochemical station (SP150) in the frequency range from 100 Hz to 100 kHz. All employed models are compared by fitting the measured data to find the most suitable circuit model that models the plant stem. The proposed models give the best results in all inter-electrode spacing distances. Four different meta-heuristic optimization algorithms are used in the fitting process to extract all models parameter and find the best optimization algorithm in the bio-impedance problems. © 2021, CC BY.

关键词： Circuit simulation

来源：评论

学校读者我要写书评

暂无评论

Stability of automata neural networks I 4

Stability of automata neural networks I

引用

Nonlinear Image Processing IV 1993

作者： Liu, Ying Dept. of Math. and Computer Science School of Sciences and Technology Savannah State College SavannahGA31404 United States

In an earlier paper[7], the authors have introduced binary automata neural networks, which can be considered a further development of the Hopfield model and BAM. Hopfield model is a one-state automata neural network with only one synaptic connection matrix in the alphabet. BAM is a special two-state automata neural network. In general, there can be any number of states and there can be any number of synaptic connection matrices in the alphabet. In this paper, we will first systematically introduce the automata network. The original automata network is called union network in this paper. Several new types of automata networks are developed in this paper. Then we will study the stability problem of the automata networks for several cases. © 1993 SPIE. All rights reserved.

关键词： Hopfield neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring the Geometry and Topology of Neural Network Loss Landscapes

arXiv

引用

arXiv 2021年

作者： Horoi, Stefan Huang, Jessie Rieck, Bastian Lajoie, Guillaume Wolf, Guy Krishnaswamy, Smita Dept. of Math. and Stat. Université de Montréal MontréalQC Canada Mila - Quebec Artificial Intelligence Institute MontréalQC Canada Dept. of Computer Science Yale University New HavenCT United States Dept. of Genetics Yale University New HavenCT United States Inst. of AI for Health Helmholtz Centre Munich Munich Germany

Recent work has established clear links between the generalization performance of trained neural networks and the geometry of their loss landscape near the local minima to which they converge. This suggests that qualitative and quantitative examination of the loss landscape geometry could yield insights about neural network generalization performance during training. To this end, researchers have proposed visualizing the loss landscape through the use of simple dimensionality reduction techniques. However, such visualization methods have been limited by their linear nature and only capture features in one or two dimensions, thus restricting sampling of the loss landscape to lines or planes. Here, we expand and improve upon these in three ways. First, we present a novel "jump and retrain" procedure for sampling relevant portions of the loss landscape. We show that the resulting sampled data holds more meaningful information about the network’s ability to generalize. Next, we show that non-linear dimensionality reduction of the jump and retrain trajectories via PHATE, a trajectory and manifold-preserving method, allows us to visualize differences between networks that are generalizing well vs poorly. Finally, we combine PHATE trajectories with a computational homology characterization to quantify trajectory differences. Copyright © 2021, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

A DNA Based Colour Image Encryption Scheme Using A Convolutional Autoencoder

arXiv

引用

arXiv 2022年

作者： Ahmed, Fawad Rehman, Muneeb Ur Ahmad, Jawad Khan, Muhammad Shahbaz Boulila, Wadii Srivastava, Gautam Lin, Jerry Chun-Wei Buchanan, William J. Department of Cyber Security Pakistan Navy Engineering College NUST Karachi75350 Pakistan Department of Electrical Engineering HITEC University Taxila Pakistan School of Computing Edinburgh Napier University Edinburgh United Kingdom Department of Electrical Engineering HITEC University Taxila47080 Pakistan Robotics and Internet-of-Things Laboratory Prince Sultan University Riyadh Saudi Arabia RIADI Laboratory University of Manouba Manouba Tunisia Math and Computer Science Brandon University Brandon Canada Research Centre for Interneural Computing China Medical University Taichung Taiwan Dept of Computer Science and Math Lebanese American University Beirut Lebanon Western Norway University of Applied Sciences Bergen Norway

With the advancement in technology, digital images can easily be transmitted and stored over the Internet. Encryption is used to avoid illegal interception of digital images. Encrypting large-sized colour images in their original dimension generally results in low encryption/decryption speed along with exerting a burden on the limited bandwidth of the transmission channel. To address the aforementioned issues, a new encryption scheme for colour images employing convolutional autoencoder, DNA and chaos is presented in this paper. The proposed scheme has two main modules, the dimensionality conversion module using the proposed convolutional autoencoder, and the encryption/decryption module using DNA and chaos. The dimension of the input colour image is first reduced from N × M × 3 toP × Q gray-scale image using the encoder. Encryption and decryption are then performed in the reduced dimension space. The decrypted gray-scale image is upsampled to obtain the original colour image having dimension N × M × 3. The training and validation accuracy of the proposed autoencoder is 97% and 95%, respectively. Once the autoencoder is trained, it can be used to reduce and subsequently increase the dimension of any arbitrary input colour image. The efficacy of the designed autoencoder has been demonstrated by the successful reconstruction of the compressed image into the original colour image with negligible perceptual distortion. The second major contribution presented in this paper is an image encryption scheme using DNA along with multiple chaotic sequences and substitution boxes. The security of the proposed image encryption algorithm has been gauged using several evaluation parameters, such as histogram of the cipher image, entropy, NPCR, UACI, key sensitivity, contrast, etc. The experimental results of the proposed scheme demonstrate its effectiveness to perform colour image encryption. © 2022, CC BY.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：