scholarly journals Improving the Performance of Deep Learning Model-Based Classification by the Analysis of Local Probability

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Guanghao Jin ◽  
Yixin Hu ◽  
Yuming Jiao ◽  
Junfang Wen ◽  
Qingzeng Song
Keyword(s):  
Deep Learning ◽  
Local Environment ◽  
Learning Model ◽  
Human Beings ◽  
Training Samples ◽  
Local Probability ◽  
Validation Set ◽  
Deep Learning Model ◽  
New Framework ◽  
Better Than

Generally, the performance of deep learning-based classification models is highly related to the captured features of training samples. When a sample is not clear or contains a similar number of features of many objects, we cannot easily classify what it is. Actually, human beings classify objects by not only the features but also some information such as the probability of these objects in an environment. For example, when we know further information such as one object has a higher probability in the environment than the others, we can easily give the answer about what is in the sample. We call this kind of probability as local probability as this is related to the local environment. In this paper, we carried out a new framework that is named L-PDL to improve the performance of deep learning based on the analysis of this kind of local probability. Firstly, our method trains the deep learning model on the training set. Then, we can get the probability of objects on each sample by this trained model. Secondly, we get the posterior local probability of objects on the validation set. Finally, this probability conditionally cooperates with the probability of objects on testing samples. We select three popular deep learning models on three real datasets for the evaluation. The experimental results show that our method can obviously improve the performance on the real datasets, which is better than the state-of-the-art methods.

Deep Learning Model for Spatial Interpolation of Real-Time Seismic Intensity

2020 ◽  
Vol 91 (6) ◽  
pp. 3433-3443
Author(s):  
Ryota Otake ◽  
Jun Kurima ◽  
Hiroyuki Goto ◽  
Sumio Sawada
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Weighted Average ◽  
Learning Model ◽  
Seismic Intensity ◽  
Validation Data ◽  
Seismic Stations ◽  
Geological Information ◽  
Deep Learning Model ◽  
Better Than

Abstract Spatial distribution of seismic intensity plays an important role in emergency response during and immediately after an earthquake. In this study, we propose a deep learning model to predict the seismic intensity based on only the observation records at the seismic stations in a surrounding area. The deep learning model is trained using the observation records at both the input and target stations, and no geological information is used. Once the model is developed, for example, using the data from a temporal seismic array, the model can spatially interpolate the seismic intensity from the sparse layout of the seismic stations. The model consists of long short-term memory cells, which are well-established neural network components for time series analysis. We used observed seismograms in 1996 through 2019 at the Kyoshin Network (K-NET) and Kiban–Kyoshin Network (KiK-net) stations located in the northeastern part of Japan. In our deep learning model, approximately 85% of validation data is successfully classified into seismic intensity scales, which is better than adopting either the maximum or weighted average of the input data. We also apply the deep learning model to earthquake early warning (EEW). The model can predict the seismic intensity accurately and provides a long warning time. We concluded that our approach is a possible future solution for increasing the accuracy of EEW.

scholarly journals Packet Preprocessing in CNN-Based Network Intrusion Detection System

Electronics ◽  
2020 ◽  
Vol 9 (7) ◽  
pp. 1151 ◽  
Author(s):  
Wooyeon Jo ◽  
Sungjin Kim ◽  
Changhoon Lee ◽  
Taeshik Shon
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Learning Model ◽  
Learning Models ◽  
Packet Data ◽  
Deep Learning Model ◽  
Better Than

The proliferation of various connected platforms, including Internet of things, industrial control systems (ICSs), connected cars, and in-vehicle networks, has resulted in the simultaneous use of multiple protocols and devices. Chaotic situations caused by the usage of different protocols and various types of devices, such as heterogeneous networks, implemented differently by vendors renders the adoption of a flexible security solution difficult, such as recent deep learning-based intrusion detection system (IDS) studies. These studies optimized the deep learning model for their environment to improve performance, but the basic principle of the deep learning model used was not changed, so this can be called a next-generation IDS with a model that has little or no requirements. Some studies proposed IDS based on unsupervised learning technology that does not require labeled data. However, not using available assets, such as network packet data, is a waste of resources. If the security solution considers the role and importance of the devices constituting the network and the security area of the protocol standard by experts, the assets can be well used, but it will no longer be flexible. Most deep learning model-based IDS studies used recurrent neural network (RNN), which is a supervised learning model, because the characteristics of the RNN model, especially when the long-short term memory (LSTM) is incorporated, are better configured to reflect the flow of the packet data stream over time, and thus perform better than other supervised learning models such as convolutional neural network (CNN). However, if the input data induce the CNN’s kernel to sufficiently reflect the network characteristics through proper preprocessing, it could perform better than other deep learning models in the network IDS. Hence, we propose the first preprocessing method, called “direct”, for network IDS that can use the characteristics of the kernel by using the minimum protocol information, field size, and offset. In addition to direct, we propose two more preprocessing techniques called “weighted” and “compressed”. Each requires additional network information; therefore, direct conversion was compared with related studies. Including direct, the proposed preprocessing methods are based on field-to-pixel philosophy, which can reflect the advantages of CNN by extracting the convolutional features of each pixel. Direct is the most intuitive method of applying field-to-pixel conversion to reflect an image’s convolutional characteristics in the CNN. Weighted and compressed are conversion methods used to evaluate the direct method. Consequently, the IDS constructed using a CNN with the proposed direct preprocessing method demonstrated meaningful performance in the NSL-KDD dataset.

scholarly journals Mapping Rice Paddy Distribution Using Remote Sensing by Coupling Deep Learning with Phenological Characteristics

2021 ◽  
Vol 13 (7) ◽  
pp. 1360
Author(s):  
A-Xing Zhu ◽  
Fang-He Zhao ◽  
Hao-Bo Pan ◽  
Jun-Zhi Liu
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Rice Paddy ◽  
Learning Model ◽  
Field Sampling ◽  
Learning Methods ◽  
Training Samples ◽  
Field Samples ◽  
Deep Learning Model

Two main approaches are used in mapping rice paddy distribution from remote sensing images: phenological methods or machine learning methods. The phenological methods can map rice paddy distribution in a simple way but with limited accuracy. Machine learning, particularly deep learning, methods that learn the spectral signatures can achieve higher accuracy yet require a large number of field samples. This paper proposed a pheno-deep method to couple the simplicity of the phenological methods and the learning ability of the deep learning methods for mapping rice paddy at high accuracy without the need of field samples. The phenological method was first used to initially delineate the rice paddy for the purpose of creating training samples. These samples were then used to train the deep learning model. The trained deep learning model was applied to map the spatial distribution of rice paddy. The effectiveness of the pheno-deep method was evaluated in Jin’an District, Lu’an City, Anhui Province, China. Results show that the pheno-deep method achieved a high performance with the overall accuracy, the precision, the recall, and AUC (area under curve) being 88.8%, 87.2%, 91.1%, and 94.4%, respectively. The pheno-deep method achieved a much better performance than the phenological alone method and can overcome the noises in the training samples from the phenological method. The overall accuracy of the pheno-deep method is only 2.4% lower than that of the deep learning alone method trained with field samples and this difference is not statistically significant. In addition, the pheno-deep method requires no field sampling, which would be a noteworthy advantage for situations when large training samples are difficult to obtain. This study shows that by combining knowledge-based methods with data-driven methods, it is possible to achieve high mapping accuracy of geographic variables using remote sensing even with little field sampling efforts.

scholarly journals Underwater Topography Inversion in Liaodong Shoal Based on GRU Deep Learning Model

2020 ◽  
Vol 12 (24) ◽  
pp. 4068
Author(s):  
Zihao Leng ◽  
Jie Zhang ◽  
Yi Ma ◽  
Jingyu Zhang
Keyword(s):  
Deep Learning ◽  
Water Depth ◽  
Learning Model ◽  
Water Area ◽  
Accuracy Evaluation ◽  
Underwater Topography ◽  
Wide Range ◽  
Log Linear ◽  
Deep Learning Model ◽  
New Framework

The Liaodong Shoal in the east of the Bohai Sea has obvious water depth variation. The clear shallow water area and deep turbid area coexist, which is characterized by complex submarine topography. The traditional semi-theoretical and semi-empirical models are often difficult to provide optimal inversion results. In this paper, based on the traditional principle of water depth inversion in shallow areas, a new framework is proposed in combination with the deep turbid sea area. This new framework extends the application of traditional optical water depth inversion methods, can meet the needs of the depth inversion work in the composite sea environment. Moreover, the gate recurrent unit (GRU) deep-learning model is introduced to approximate the unified inversion model by numerical calculation. In this paper, based on the above-mentioned inversion framework, the water depth inversion work is processed by using the wide range images of GF-1 satellite, then the relevant analysis and accuracy evaluation are carried out. The results show that: (1) for the overall water depth inversion, the determination coefficient R2 is higher than 0.9 and the MRE is lower than 20% are obtained, and the evaluation index shows that the GRU model can better retrieve the underwater topography of this region. (2) Compared with the traditional log-linear model, Stumpf model, and multi-layer feedforward neural network, the GRU model was significantly improved in various evaluation indices. (3) The model has the best inversion performance in the 24–32 m-depth section, with a MRE of about 4% and a MAE of about 1.42 m, which is more suitable for the inversion work in the comparative section area. (4) The inversion diagram indicates that this model can well reflect the regional seabed characteristics of multiple radial sand ridges, and the overall inversion result is excellent and practical.

A deep learning survival model for triple-negative breast cancer patients.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e12594-e12594
Author(s):  
Yiyue Xu ◽  
Bing Zou ◽  
Bingjie Fan ◽  
Wanlong Li ◽  
Shijiang Wang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Regression Analysis ◽  
Deep Learning ◽  
Random Forest ◽  
Cox Regression ◽  
Learning Model ◽  
Survival Model ◽  
Cox Regression Analysis ◽  
Validation Set ◽  
Deep Learning Model

e12594 Background: Triple-negative breast cancer (TNBC) is the subtype of breast cancer with the worst prognosis. There is no reliable model for survival prediction of TNBC patients. The traditional Cox regression analysis with poor prediction power cannot satisfy the clinical needs. The purpose was to establish a deep learning model and develop a new prognostic system for TNBC patients. Methods: This study collected data of TNBC patients from the Surveillance, Epidemiology, and End Results (SEER) program between 2010 and 2016. 70% were used to develop the deep learning model, 15% were used as the validation set, and 15% as the independent testing set. Then the concordance-index (c-index) and Brier score (IBS) were calculated and compared with the Cox regression analysis and random forest. Finally, according to the classification of the deep survival model, an individualized prognosis system was established. Results: A total of 37,818 patients were enrolled in this study. In the validation set, the c-index of the deep learning was 0.799, which was better than the traditional Cox regression model (0.774) and random forest (0.763). The independent testing set further proved the robustness of the deep survival model (c-index 0.788). The new prognosis system based on the deep survival model reached an area under the curve (AUC) of 0.805, which was better than the Tumor, Node, Metastases (TNM) staging system (0.771). Conclusions: Deep learning model had better prediction power than the Cox regression analysis and the random forest. The established prognosis system can better predict prognosis and aid individual risk stratification for TNBC patients patients.

Improving Sentiment Analysis using Hybrid Deep Learning Model

2020 ◽  
Vol 13 (4) ◽  
pp. 627-640 ◽  
Author(s):  
Avinash Chandra Pandey ◽  
Dharmveer Singh Rajpoot
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Classification Accuracy ◽  
Short Term Memory ◽  
Computational Cost ◽  
Extraction Process ◽  
Learning Model ◽  
Sentiment Classification ◽  
Deep Learning Model

Background: Sentiment analysis is a contextual mining of text which determines viewpoint of users with respect to some sentimental topics commonly present at social networking websites. Twitter is one of the social sites where people express their opinion about any topic in the form of tweets. These tweets can be examined using various sentiment classification methods to find the opinion of users. Traditional sentiment analysis methods use manually extracted features for opinion classification. The manual feature extraction process is a complicated task since it requires predefined sentiment lexicons. On the other hand, deep learning methods automatically extract relevant features from data hence; they provide better performance and richer representation competency than the traditional methods. Objective: The main aim of this paper is to enhance the sentiment classification accuracy and to reduce the computational cost. Method: To achieve the objective, a hybrid deep learning model, based on convolution neural network and bi-directional long-short term memory neural network has been introduced. Results: The proposed sentiment classification method achieves the highest accuracy for the most of the datasets. Further, from the statistical analysis efficacy of the proposed method has been validated. Conclusion: Sentiment classification accuracy can be improved by creating veracious hybrid models. Moreover, performance can also be enhanced by tuning the hyper parameters of deep leaning models.

Sign in / Sign up

Export Citation Format

Share Document