检索结果-内蒙古大学图书馆

International Journal of Systematic Innovation 2024年第1期8卷 27-35页

作者： Ma’ady, Mochamad Nizar Palefi Department of Information Systems Institut Teknologi Telkom Surabaya Indonesia

Academic collaboration is tremendously important for higher education. Multidisciplinary academicians may be grouped as a better research collaboration than the previous one. Therefore, such a system is needed, even for a huge number of academicians in an institution. However, existing such recommendation tools are expensive. This paper suggests to develop a system by using machine learning approach in order to search a big academicians data effectively. Hence, with help of the standard of Naïve Bayes creates a flexible text search without depending on what select options including research location or case study instead of only research topic. Furthermore, the output of Naïve Bayes, then, is tranformed to percentage display in order to bring ease of understanding the gap of rec-ommendation. It allows the user to choose a possible partner more than one. Therefore, this approach helps reduce time and effort. © (2023), (Society of Sytematic Innovation). All Rights Reserved.

关键词： Higher Education Naïve Bayes Algorithm Recommendation System Research Partner Collaboration sigmoid activation function

来源：评论

学校读者我要写书评

暂无评论

Implementation of Single Artificial Neuron Using various activation functions and XOR Gate on FPGA chip 2

Implementation of Single Artificial Neuron Using various Act...

引用

2nd IEEE International Conference on Advances in Computing and Communication Engineering (ICACCE)

作者： Abrol, Sahil Mahajan, Rita PEC Univ Technol Dept ECE Chandigarh India

ISBN: (纸本)9781479917341

In this paper, a hardware implementation of an artificial neural network on Field Programmable Gate Arrays (FPGA) is done step by step. First single neurons are implemented using different activation function and then a XOR Gate is implemented. The concurrent structure of a neural network makes it very fast for the computation of certain tasks. This makes ANN well suited for implementation in VLSI technology. Hardware realization of a Neu- ral Network depends on the efficient implementation of Artificial single neuron. FPGA-based reconfigurable computing architectures are suitable for hardware implementation of neural networks. FPGA realization of ANNs with a large number of neurons is still a challenging task. Here design and implementation of a Single neuron with various activation functions is done and then an XOR Gate is implemented using one of these designs. The design of XOR Gate is done by using gradient descent algorithm and taking 3-layers 5-neurons model.

关键词： Artificial neural network VHDL Back propagation Algorithm Xilinx FPGA sigmoid activation function

来源：评论

学校读者我要写书评

暂无评论

Predicting the Risk of Newborns Based on Fuzzy Clustering Method with Prediction Risk Assessment

Predicting the Risk of Newborns Based on Fuzzy Clustering Me...

引用

proc 2014 inter conf contemporary comp informatics (ic3i)

作者： Thomas, Jyothi Kulanthaivel, G. Sathyabama Univ Dept Comp Sci & Engn Madras Tamil Nadu India Natl Inst Tech Teachers Training & Res Madras Tamil Nadu India

ISBN: (纸本)9781479966295

The role of the cervix in the pathogenesis of premature delivery is controversial. In a prospective, multicenter study of pregnant women, we used vaginal ultrasonography to measure the length of the cervix;we also documented the incidence of spontaneous delivery before 35 weeks' gestation. We performed vaginal ultrasonography at approximately 24 and 28 weeks of gestation in women with singleton pregnancies. We then assessed the relation between the length of the cervix and the risk of spontaneous preterm delivery. We examined 2915 women at approximately 24 weeks of gestation and 2531 of these women again at approximately 28 weeks. Spontaneous preterm delivery (at less than 35 weeks) occurred in 126 of the women (4.3 percent) examined at 24 weeks. The length of the cervix was normally distributed at 24 and 28 weeks (mean [SD], 35.28.3 mm and 33.78.5 mm, respectively). The relative risk of preterm delivery increased as the length of the cervix decreased. The paper discusses approximation properties of other possible types of nonlinearities that might be implemented by artificial neural networks. The daily registration has N cases that each of the well-known stimulus-answer couples represents. The objective of this work is to develop a function that allows finding the vector of entrance variables t to the vector of exit variables P. F is any function, in this case the electric power consumption. Their modeling with Artificial Neural Network (ANN) is Multi a Perceptron Layer (PMC). Another form of modeling it is using Interpolation Algorithms (AI). For the lengths measured at 28 weeks, the corresponding relative risks were 2.80, 3.52, 5.39, 9.57, 13.88, and 24.94 (P0.001 for values at or below the 50th percentile;P0.003 for values at the 75th percentile). The risk of spontaneous preterm delivery is increased in women who are found to have a short cervix by vaginal ultrasonography during pregnancy.

关键词： FPGA Neural Networks sigmoid activation function Schematic Tools

来源：评论

学校读者我要写书评

暂无评论

Low Complexity Artificial Neural Network Unit for Sugar Content Detection in Microwave Sensor System

Low Complexity Artificial Neural Network Unit for Sugar Cont...

引用

Annual Summit and Conference of Asia-Pacific-Signal-and-Information-Processing-Association (APSIPA)

作者： Leekul, Prapan Soontornwong, Parinya Chivapreecha, Sorwat King Mongkuts Inst Technol Ladkrabang Fac Engn Dept Telecommun Engn Bangkok 10520 Thailand Rajamungala Univ Technol Srivijaya Coll Ind Technol Dept Elect Engn Nakhon Sithammarat 80210 Thailand

ISBN: (纸本)9786163618238

This research presents a low complexity artificial neural network (ANN) unit that used for implementation of microwave sensor system in order to detect sugar content in tested solution. Generally, the hardware implementation of ANN suffers from the number of multiplication that used in network and the difficulty of implementing sigmoid activation function. In this paper, distributed arithmetic (DA) will be used to represent the multiplication and make our ANN unit multiplier less computation unit. An efficient digital implementation of sigmoid activation function by using piecewise linear approximation will be used. Therefore, low complexity ANN unit can be achieved and it will be used in a microwave sensor system for sugar content detection.

关键词： approximation theory chemical variables measurement computerised instrumentation distributed arithmetic microwave detectors neural nets piecewise linear techniques sugar transfer functions ANN unit multiplier artificial neural network digital implementation microwave sensor system multiplication piecewise linear approximation sigmoid activation function sugar content detection Abstracts Artificial neural networks Complexity theory Decision support systems Hardware Microwave sensors Sugar

来源：评论

学校读者我要写书评

暂无评论

FPGA Implementation of Neuron Block for Artificial Neural Network 13

FPGA Implementation of Neuron Block for Artificial Neural Ne...

引用

International Conference on Electron Devices and Solid-State Circuits (EDSSC)

作者： Li, ZhaoFang Huang, Yu-Jung Lin, Wei-Cheng I Shou Univ Dept Elect Engn Kaohsiung 84008 Taiwan E DA Hosp Med Engn Dept Kaohsiung 824 Taiwan

ISBN: (纸本)9781538629079

This paper presents the FPGA implementation of neuron block units based on a sigmoid activation function for artificial neural networks (ANNs) applications. The Coordinate Rotation Digital Computer (CORDIC) algorithm has been employed for the approximation of sigmoid activation function. The proposed design was simulated using ModelSim XE II and synthesized using Altera's Quartus II with a Cyclone IV EP4CE115 FPGA device. The functionality of neuron block unit was successfully verified using the trained weight on MNIST dataset.

关键词： sigmoid activation function CORDIC FPGA

来源：评论

学校读者我要写书评

暂无评论

A novel multiscale convolutional neural network based age-related macular degeneration detection using OCT images

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2021年第0期67卷 102538-102538页

作者： Thomas, Anju Harikrishnan, P. M. Krishna, Adithya K. Palanisamy, P. Gopi, Varun P. Natl Inst Technol Tiruchirappalli Dept Elect & Commun Engn Tiruchirappalli 620015 Tamil Nadu India

Age-related macular degeneration (AMD) is an ocular disorder that affects the elderly. The prevalence of AMD is growing due to the aging population in society;hence early diagnosis is necessary to prevent vision loss in the elderly. Arranging a detailed eye screening system for detecting AMD is a very challenging process. This paper proposes a novel multiscale convolutional neural network (CNN) architecture for accurate diagnosis of AMD. The architecture proposed is a multiscale CNN with seven convolutional layers for classifying AMD or normal images. The multiscale convolution layer enables a large number of local structures to be generated with various filter sizes. In this proposed network, the sigmoid function is used as the classifier. The proposed CNN network is trained on the Mendeley dataset and tested on four datasets, namely Mendeley, OCTID, Duke, SD-OCT Noor dataset and achieved an accuracy of 99.73%, 98.08%, 96.66%, and 97.95% respectively. Comparison with alternative methods yielded results that exhibit the efficiency of the proposed algorithm in AMD detection. Even if the proposed model is trained only on the Mendeley dataset, it achieved good detection accuracy when tested with other datasets. This indicates the proposed model?s ability to classify AMD/Normal images from other datasets. Comparison with other approaches produced results that exhibit the efficiency of the proposed algorithm in detecting AMD. The proposed architecture can be applied in rapid screening of the eye for the early detection of AMD. Due to less complexity and fewer learnable parameters, the proposed CNN can be implemented in real-time.

关键词： Age-related macular degeneration Multiscale CNN sigmoid activation function

来源：评论

学校读者我要写书评

暂无评论

A learning algorithm with activation function manipulation for fault tolerant neural networks

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2001年第7期E84D卷 899-905页

作者： Kamiura, N Taniguchi, Y Hata, Y Matsui, N Himeji Inst Technol Dept Comp Engn Himeji Hyogo 6712201 Japan

In this paper we propose a learning algorithm to enhance the fault tolerance of feedforward neural networks (NNs for short) by manipulating the gradient of sigmoid activation function of the neuron. We assume stuck-at-0 and stuck-at-1 faults of the connection link. For the output layer, we employ the function with the relatively gentle gradient to enhance its fault tolerance. For enhancing the fault tolerance of hidden layer, we steepen the gradient of function after convergence. The experimental results for a character recognition problem show that our NN is superior in fault tolerance, learning cycles and learning time to other NNs trained with the algorithms employing fault injection, forcible weight limit and the calculation of relevance of each weight to the output error. Besides the gradient manipulation incorporated in our algorithm never spoils the generalization ability.

关键词： feedforward neural network backpropagation algorithm stuck-at fault sigmoid activation function

来源：评论

学校读者我要写书评

暂无评论

ProjFE: Prediction of fuzzy entity and relation for knowledge graph completion

引用

APPLIED SOFT COMPUTING 2019年 81卷 105525-000页

作者： Liu, Huajing Bai, Luyi Ma, Xiangnan Yu, Wenting Xu, Changming Northeastern Univ Qinhuangdao Sch Comp & Commun Engn Qinhuangdao 066004 Hebei Peoples R China

A growing number of tasks about knowledge graph completion have been studied and improved recently, but most of them use translation matrices or reflect known entity to other space, always focusing on improving the method of translating known entities and relations. Differing from current works, our paper employs a combination operator instead of the translation matrix to avoid massive calculations, and takes fuzzy membership degree into consideration in the predicting process to enhance accuracy of projection. Hence, we propose a method called ProjFE to predict the missing parts of triplets for knowledge graph completion. This model uses fuzzy combination operators to combine the fuzzy known entities and relations. Score function is employed to access to a descending order of the correct candidates after combination, where the target entity is the top one. What is more, we use sigmoid and ReLU activation functions for evaluations, which could alleviate some undesirable gradient problems in the training process. It is worth noting that our method ProjFE tends to have a relatively smaller parameter size than some existing models. Besides, our model is proved to perform better in terms of Mean Rank. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Fuzzy entities and relations Combination operator Knowledge graph ReLU activation function sigmoid activation function

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection Based on Amended Convolution Neural Network Using MRI Images

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 2023年第10期17卷 2788-2808页

作者： Mohanasundari, M. Chandrasekaran, V Anitha, S. Velalar Coll Engn & Technol Dept Comp Sci & Engn Erode 638012 Tamil Nadu India Velalar Coll Engn & Technol Dept Elect & Commun Engn Erode 638012 Tamil Nadu India Kongu Engn Coll Dept Informat Technol Erode 638060 Tamil Nadu India

Brain tumors are one of the most threatening malignancies for humans. Misdiagnosis of brain tumors can result in false medical intervention, which ultimately reduces a patient's chance of survival. Manual identification and segmentation of brain tumors from Magnetic Resonance Imaging (MRI) scans can be difficult and error-prone because of the great range of tumor tissues that exist in various individuals and the similarity of normal tissues. To overcome this limitation, the Amended Convolutional Neural Network (ACNN) model has been introduced, a unique combination of three techniques that have not been previously explored for brain tumor detection. The three techniques integrated into the ACNN model are image tissue preprocessing using the Kalman Bucy Smoothing Filter to remove noisy pixels from the input, image tissue segmentation using the Isotonic Regressive Image Tissue Segmentation Process, and feature extraction using the Marr Wavelet Transformation. The extracted features are compared with the testing features using a sigmoid activation function in the output layer. The experimental findings show that the suggested model outperforms existing techniques concerning accuracy, precision, sensitivity, dice score, Jaccard index, specificity, Positive Predictive Value, Hausdorff distance, recall, and F1 score. The proposed ACNN model achieved a maximum accuracy of 98.8%, which is higher than other existing models, according to the experimental results.

关键词： Brain tumor CNN Image tissue feature extraction Medical science Magnetic Resonance Imaging Marr Wavelet Transformation sigmoid activation function

来源：评论

学校读者我要写书评

暂无评论

Quantile correlative deep feedforward multilayer perceptron for crop yield prediction

引用

COMPUTERS & ELECTRICAL ENGINEERING 2022年 98卷 107696-107696页

作者： Sivanantham, V Sangeetha, V Alnuaim, Abeer Ali Hatamleh, Wesam Atef Anilkumar, Chunduru Hatamleh, Ashraf Atef Sweidan, Dirar Periyar Univ Constituent Coll Arts & Sci Dept Comp Sci Pappireddipatti Campus Salem 636011 Tamil Nadu India King Saud Univ Coll Appl Studies & Community Serv Dept Comp Sci & Engn POB 22459 Riyadh 11495 Saudi Arabia King Saud Univ Coll Comp & Informat Sci Dept Comp Sci POB 51178 Riyadh 11495 Saudi Arabia GMR Inst Technol Dept Informat Technol Srikakulam 532127 Andhra Pradesh India King Saud Univ Coll Sci Dept Bot & Microbiol Riyadh 11451 Saudi Arabia Univ Skovde Sch Informat Hogskolevagen 1 S-54128 Skovde Sweden

Crop yield prediction is an essential one in agriculture. Crop yield protection is the science and practice of handling plant diseases, weeds, and other pests. Accurate information regarding the crop yield history is essential for making decisions regarding agricultural risk management. Many research studies have been undertaken for identifying crop productivity using various data mining techniques. However, the prediction accuracy of crop yields was not improved with minimum time consumption. To overcome the issues, a novel Quantile Regressive Empirical correlative functioned Deep Feed Forward Multilayer Perceptron Classification (QRECF-DFFMPC) Method is proposed for crop yield prediction. QRECF-DFFMPC Method comprises three layers such as input and output layer with one or more hidden layers. The input layer of deep neural learning receives several features and data from the dataset and then sent it to the hidden layer 1. In that layer, Empirical Orthogonal function is used to select the relevant features with the help of orthogonal basis functions. After that, Quantile regression is used in the hidden layer 2 to analyze the features and produce the regression value for every data point. Then, the regression value of data points is sent to the output layer for improving the prediction accuracy and reducing the time complexity. Experimental evaluation is carried out on factors such as prediction accuracy, precision, and prediction time for several data points and the number of features. The result shows that the proposed technique enhanced the prediction accuracy and precision by 6% and 9% and reduces the prediction time by 32%, as compared to existing works.

关键词： Crop yield prediction Deep feedforward multi-layer perceptron Empirical orthogonal function Quantile regression sigmoid activation function

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：