检索结果-南通市图书馆

维普期刊数据库

Pre-Trained deep neural network-Based Computer-Aided Breast Tumor Diagnosis Using ROI Structures

在线全文

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第1期35卷 63-78页

作者： Venkata Sunil Srikanth S.Krithiga Department of Electronics and Communication Engineering SRM Institute of Science and TechnologyKattankulathurTamilnadu603203India

deep neural network(DNN)based computer-aided breast tumor diagnosis(CABTD)method plays a vital role in the early detection and diagnosis of breast ***,a Brightness mode(B-mode)ultrasound image derives training feature samples that make closer isolation toward the infection ***,it is expensive due to a metaheuristic search of features occupying the global region of interest(ROI)structures of input ***,it may lead to the high computational complexity of the pre-trained DNN-based CABTD *** paper proposes a novel ensemble pretrained DNN-based CABTD method using global-and local-ROI-structures of B-mode ultrasound *** conveys the additional consideration of a local-ROI-structures for further enhan-cing the pretrained DNN-based CABTD method’s breast tumor diagnostic performance without degrading its visual *** features are extracted at various depths(18,50,and 101)from the global and local ROI structures and feed to support vector machine for better *** the experimental results,it has been observed that the combined local and global ROI structure of small depth residual network ResNet18(0.8 in%)has produced significant improve-ment in pixel ratio as compared to ResNet50(0.5 in%)and ResNet101(0.3 in%),***,the pretrained DNN-based CABTD methods have been tested by influencing local and global ROI structures to diagnose two specific breast tumors(Benign and Malignant)and improve the diagnostic accuracy(86%)compared to Dense Net,Alex Net,VGG Net,and Google ***,it reduces the computational complexity due to the small depth residual network ResNet18,respectively.

关键词： Computer-aided diagnosis breast tumor B-mode ultrasound images deep neural network local-ROI-structures feature extraction support vector machine

Research on the Application of the Radiative Transfer Model Based on deep neural network in One-dimensional Variational Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Tropical Meteorology 2022年第3期28卷 326-342页

作者：贺秋瑞张瑞玲李骄阳王振占 School of Information Technology Luoyang Normal UniversityLuoyangHenan 471934 China Key Laboratory of Microwave Remote Sensing National Space Science CenterChinese Academy of SciencesBeijing 100190 China Department of Electrical and Computer Engineering Michigan State UniversityEast LansingMI 48824 USA

As a typical physical retrieval algorithm for retrieving atmospheric parameters,one-dimensional variational(1 DVAR)algorithm is widely used in various climate and meteorological communities and enjoys an important position in the field of microwave remote *** algorithm parameters affecting the performance of the 1 DVAR algorithm,the accuracy of the microwave radiative transfer model for calculating the simulated brightness temperature is the fundamental constraint on the retrieval accuracies of the 1 DVAR algorithm for retrieving atmospheric *** this study,a deep neural network(DNN)is used to describe the nonlinear relationship between atmospheric parameters and satellite-based microwave radiometer observations,and a DNN-based radiative transfer model is developed and applied to the 1 DVAR algorithm to carry out retrieval experiments of the atmospheric temperature and humidity *** retrieval results of the temperature and humidity profiles from the Microwave Humidity and Temperature Sounder(MWHTS)onboard the Feng-Yun-3(FY-3)satellite show that the DNN-based radiative transfer model can obtain higher accuracy for simulating MWHTS observations than that of the operational radiative transfer model RTTOV,and also enables the 1 DVAR algorithm to obtain higher retrieval accuracies of the temperature and humidity *** this study,the DNN-based radiative transfer model applied to the 1 DVAR algorithm can fundamentally improve the retrieval accuracies of atmospheric parameters,which may provide important reference for various applied studies in atmospheric sciences.

关键词： one-dimensional variational algorithm radiative transfer model deep neural network FY-3 MWHTS temperature and humidity profiles

维普期刊数据库

Adaptive Butterfly Optimization Algorithm(ABOA)Based Feature Selection and deep neural network(DNN)for Detection of Distributed Denial-of-Service(DDoS)Attacks in Cloud

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第10期47卷 1109-1123页

作者： S.Sureshkumar G.K.D.Prasanna Venkatesan R.Santhosh Department of Computer Science and Engineering Karpagam Academy of Higher EducationCoimbatore641021India Dean Engineering Faculty EngineeringKarpagam Academy of Higher EducationCoimbatore641021India Department of Computer Science and Engineering Faculty of EngineeringKarpagam Academy of Higher EducationCoimbatore641021India

Cloud computing technology provides flexible,on-demand,and completely controlled computing resources and services are highly *** this,with its distributed and dynamic nature and shortcomings in virtualization deployment,the cloud environment is exposed to a wide variety of cyber-attacks and security *** Intrusion Detection System(IDS)is a specialized security tool that network professionals use for the safety and security of the networks against attacks launched from various *** attacks are becoming more frequent and powerful,and their attack pathways are continually changing,which requiring the development of new detection *** the purpose of the study is to improve detection *** Selection(FS)is *** the same time,the IDS’s computational problem is limited by focusing on the most relevant elements,and its performance and accuracy *** this research work,the suggested Adaptive butterfly optimization algorithm(ABOA)framework is used to assess the effectiveness of a reduced feature subset during the feature selection phase,that was motivated by this motive *** classification is not compromised by using an ABOA *** design of deep neural networks(DNN)has simplified the categorization of network traffic into normal and DDoS threat ***’s parameters can be finetuned to detect DDoS attacks better using specially built *** reconstruction error,no exploding or vanishing gradients,and reduced network are all benefits of the changes outlined in this *** it comes to performance criteria like accuracy,precision,recall,and F1-Score are the performance measures that show the suggested architecture outperforms the other existing *** the proposed ABOA+DNN is an excellent method for obtaining accurate predictions,with an improved accuracy rate of 99.05%compared to other existing approaches.

关键词： Cloud computing distributed denial of service intrusion detection system adaptive butterfly optimization algorithm deep neural network

Rockburst Intensity Grade Prediction Model Based on Batch Gradient Descent and Multi-Scale Residual deep neural network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第11期47卷 1987-2006页

作者： Yu Zhang Mingkui Zhang Jitao Li Guangshu Chen School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing100044China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and ArchitectureBeijing100044China State Key Laboratory for GeoMechanics and deep Underground Engineering China University of Mining&TechnologyBeijing100083China

Rockburst is a phenomenon in which free surfaces are formed during excavation,which subsequently causes the sudden release of energy in the construction of mines and *** rockburst only peels off rock slices without ejection,while severe rockburst causes casualties and property *** frequency and degree of rockburst damage increases with the excavation ***,rockburst is the leading engineering geological hazard in the excavation process,and thus the prediction of its intensity grade is of great significance to the development of geotechnical ***,the prediction of rockburst intensity grade is one problem that needs to be solved *** comprehensively considering the occurrence mechanism of rockburst,this paper selects the stress index(σθ/σc),brittleness index(σ_(c)/σ_(t)),and rock elastic energy index(Wet)as the rockburst evaluation indexes through the Spearman coefficient *** overcomes the low accuracy problem of a single evaluation index prediction *** this,the BGD-MSR-DNN rockburst intensity grade prediction model based on batch gradient descent and a multi-scale residual deep neural network is *** batch gradient descent(BGD)module is used to replace the gradient descent algorithm,which effectively improves the efficiency of the network and reduces the model training ***,the multi-scale residual(MSR)module solves the problem of network degradation when there are too many hidden layers of the deep neural network(DNN),thus improving the model prediction *** experimental results reveal the BGDMSR-DNN model accuracy to reach 97.1%,outperforming other comparable ***,actual projects such as Qinling Tunnel and Daxiangling Tunnel,reached an accuracy of 100%.The model can be applied in mines and tunnel engineering to realize the accurate and rapid prediction of rockburst intensity grade.

关键词： Rockburst prediction rockburst intensity grade deep neural network batch gradient descent multi-scale residual

deep neural network Based Spam Email Classification Using Attention Mechanisms

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Intelligent Learning Systems and Applications 2023年第4期15卷 144-164页

作者： Md. Tofael Ahmed Mariam Akter Md. Saifur Rahman Maqsudur Rahman Pintu Chandra Paul Miss. Nargis Parvin Almas Hossain Antar Department of Information and Communication Technology Comilla University Cumilla Bangladesh Department of Computer Science and Engineering Bangladesh Army International University of Science and Technology Cumilla Bangladesh

Spam emails pose a threat to individuals. The proliferation of spam emails daily has rendered traditional machine learning and deep learning methods for screening them ineffective and inefficient. In our research, we employ deep neural networks like RNN, LSTM, and GRU, incorporating attention mechanisms such as Bahdanua, scaled dot product (SDP), and Luong scaled dot product self-attention for spam email filtering. We evaluate our approach on various datasets, including Trec spam, Enron spam emails, SMS spam collections, and the Ling spam dataset, which constitutes a substantial custom dataset. All these datasets are publicly available. For the Enron dataset, we attain an accuracy of 99.97% using LSTM with SDP self-attention. Our custom dataset exhibits the highest accuracy of 99.01% when employing GRU with SDP self-attention. The SMS spam collection dataset yields a peak accuracy of 99.61% with LSTM and SDP attention. Using the GRU (Gated Recurrent Unit) alongside Luong and SDP (Structured Self-Attention) attention mechanisms, the peak accuracy of 99.89% in the Ling spam dataset. For the Trec spam dataset, the most accurate results are achieved using Luong attention LSTM, with an accuracy rate of 99.01%. Our performance analyses consistently indicate that employing the scaled dot product attention mechanism in conjunction with gated recurrent neural networks (GRU) delivers the most effective results. In summary, our research underscores the efficacy of employing advanced deep learning techniques and attention mechanisms for spam email filtering, with remarkable accuracy across multiple datasets. This approach presents a promising solution to the ever-growing problem of spam emails.

关键词： Spam Email Attention Mechanism deep neural network Bahdanua Attention Scale Dot Product

Predicted Robustness as QoS for deep neural network Models

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2020年第5期35卷 999-1015页

作者： Yue-Huan Wang Ze-Nan Li Jing-Wei Xu Ping Yu Taolue Chen Xiao-Xing Ma State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China Department of Computer Science University of SurreyGuilfordGU27XHU.K.

The adoption of deep neural network(DNN)model as the integral part of real-world software systems necessitates explicit consideration of their quality-of-service(QoS).It is well-known that DNN models are prone to adversarial attacks,and thus it is vitally important to be aware of how robust a modeFs prediction is for a given input instance.A fragile prediction,even with high confidence,is not trustworthy in light of the possibility of adversarial *** propose that DNN models should produce a robustness value as an additional QoS indicator,along with the confidence value,for each prediction they *** approaches for robustness computation are based on adversarial searching,which are usually too expensive to be excised in real *** this paper,we propose to predict,rather than to compute,the robustness measure for each input ***,our approach inspects the output of the neurons of the target model and trains another DNN model to predict the *** focus on convolutional neural network(CNN)models in the current *** show that our approach is accurate,with only 10%-34%additional errors compared with the offline heavy-weight robustness *** also significantly outperforms some alternative *** further validate the effectiveness of the approach when it is applied to detect adversarial attacks and out-of-distribution *** approach demonstrates a better performance than,or at least is comparable to,the state-of-the-art techniques.

关键词： deep neural network quality of service robustness prediction

Hybrid deep neural network based prediction method for unsteady flows with moving boundary

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mechanica Sinica 2021年第10期37卷 1557-1566,I0003页

作者： Ren-Kun Han Zhong Zhang Yi-Xing Wang Zi-Yang Liu Yang Zhang Gang Chen State Key Laboratory for Strength and Vibration of Mechanical Structures Shannxi Key Laboratory for Environment and Control of Flight VehicleSchool of Aerospace EngineeringXi’an Jiaotong UniversityXi’an710049China Science and Technology on Reliability and Environment Engineering Laboratory Beijing Institute of Structure and Environment EngineeringBeijing100076China

Any motion, forced or free, of boundary affects the flow field around this boundary. A new kind of reduced order model (ROM) based on hybrid deep neural network is proposed to model flow field evolution process of unsteady flow around moving boundary. This hybrid deep neural network can map the relationship between the flow field at the next time step and the flow field and boundary positions at the previous time steps. Based on the learned information, the hybrid deep neural network can quickly and accurately predict the flow field. Unsteady flows around forced oscillation cylinder with various amplitudes, frequencies, and Reynolds numbers are simulated to establish the training and testing datasets. The prediction results of the hybrid deep neural network and the computational fluid dynamics (CFD) simulation results are consistent with high accuracy. The forces on the moving boundary can be integrated through the predicted flow field data. Good performance makes this new ROM method can be used in many fluid dynamics research fields, which needs fast and accurate simulation.

关键词： deep neural network Flow fields prediction Moving boundary

AI based on frequency slicing deep neural network for underwater visible light communication

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第6期63卷 47-54页

作者： Nan CHI Fangchen HU Guoqiang LI Chaofan WANG Wenqing NIU Key Laboratory for Information Science of Electromagnetic Waves (MoE) Fudan University

In this paper, we propose a low-complexity frequency slicing deep neural network(FSDNN) for wide-band signal post-equalization in a 1.2 m underwater visible light communication system. FSDNN and deep neural network(DNN) outperform the least mean square equalizer. Then, by splitting the received signal into two parallel signals using a digital low-pass filter and a high-pass filter, we demonstrate that the FSDNN significantly reduces the complexity of the traditional DNN post-equalizer. Moreover, the complexity of the FSDNN decreases considerably to 11.15% compared with the conventional DNN for a 2.7 Gbit/s wide-band transmitted signal with a similar bit error ratio performance.

关键词： deep neural network frequency slicing underwater visible light communication visible light communication

Iterative learning-based many-objective history matching using deep neural network with stacked autoencoder

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Petroleum Science 2021年第5期18卷 1465-1482页

作者： Jaejun Kim Changhyup Park Seongin Ahn Byeongcheol Kang Hyungsik Jung Ilsik Jang Department of Energy Systems Engineering Seoul National UniversitySeoul08826Republic of Korea Department of Energy and Resources Engineering Kangwon National UniversityChuncheonKangwon24341Republic of Korea Geo-ICT Convergence Research Team Korea Institute of Geoscience and Mineral ResourcesDaejeon34132Republic of Korea Department of Energy and Resources Engineering Chosun UniversityGwangju61452Republic of Korea

This paper presents an innovative data-integration that uses an iterative-learning method,a deep neural network(DNN)coupled with a stacked autoencoder(SAE)to solve issues encountered with many-objective history *** proposed method consists of a DNN-based inverse model with SAE-encoded static data and iterative updates of supervised-learning data are based on distance-based clustering *** functions as an inverse model and results in encoded flattened data,while SAE,as a pre-trained neural network,successfully reduces dimensionality and reliably reconstructs *** iterative-learning method can improve the training data for DNN by showing the error reduction achieved with each iteration *** proposed workflow shows the small mean absolute percentage error below 4%for all objective functions,while a typical multi-objective evolutionary algorithm fails to significantly reduce the initial population *** learning-based manyobjective history matching estimates the trends in water cuts that are not reliably included in dynamicdata *** confirms the proposed workflow constructs more plausible *** workflow would be a reliable alternative to overcome the less-convergent Pareto-based multi-objective evolutionary algorithm in the presence of geological uncertainty and varying objective functions.

关键词： deep neural network Stacked autoencoder History matching Iterative learning Clustering Many-objective

维普期刊数据库