On the Trade-Off between Multi-level Security Classification Accuracy and Training Time

2015 ◽  
Author(s):  
Paal Engelstad
Keyword(s):  
Classification Accuracy ◽  
Trade Off ◽  
Training Time ◽  
Multi Level ◽  
And Training

scholarly journals Remote Sensing Scene Image Classification Based on Dense Fusion of Multi-Level Features

2021 ◽  
Vol 13 (21) ◽  
pp. 4379
Author(s):  
Cuiping Shi ◽  
Xinlei Zhang ◽  
Jingwei Sun ◽  
Liguo Wang
Keyword(s):  
Remote Sensing ◽  
Image Classification ◽  
Classification Accuracy ◽  
Model Complexity ◽  
Current Layer ◽  
Model Accuracy ◽  
Running Speed ◽  
Trade Off ◽  
Scene Image ◽  
Multi Level

For remote sensing scene image classification, many convolution neural networks improve the classification accuracy at the cost of the time and space complexity of the models. This leads to a slow running speed for the model and cannot realize a trade-off between the model accuracy and the model running speed. As the network deepens, it is difficult to extract the key features with a sample double branched structure, and it also leads to the loss of shallow features, which is unfavorable to the classification of remote sensing scene images. To solve this problem, we propose a dual branch multi-level feature dense fusion-based lightweight convolutional neural network (BMDF-LCNN). The network structure can fully extract the information of the current layer through 3 × 3 depthwise separable convolution and 1 × 1 standard convolution, identity branches, and fuse with the features extracted from the previous layer 1 × 1 standard convolution, thus avoiding the loss of shallow information due to network deepening. In addition, we propose a downsampling structure that is more suitable for extracting the shallow features of the network by using the pooled branch to downsample and the convolution branch to compensate for the pooled features. Experiments were carried out on four open and challenging remote sensing image scene data sets. The experimental results show that the proposed method has higher classification accuracy and lower model complexity than some state-of-the-art classification methods and realizes the trade-off between model accuracy and model running speed.

scholarly journals An Improved Convolutional Neural Network for Text Classification

2021 ◽  
Vol 2066 (1) ◽  
pp. 012091
Author(s):  
Xiaojing Fan ◽  
A Runa ◽  
Zhili Pei ◽  
Mingyang Jiang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Text Classification ◽  
Classification Accuracy ◽  
Classification Performance ◽  
Classification Model ◽  
Classification Problems ◽  
Training Time ◽  
Accuracy And Precision ◽  
And Training

Abstract This paper studies the text classification based on deep learning. Aiming at the problem of over fitting and training time consuming of CNN text classification model, a SDCNN model is constructed based on sparse dropout convolutional neural network. Experimental results show that, compared with CNN, SDCNN further improves the classification performance of the model, and its classification accuracy and precision can reach 98.96% and 85.61%, respectively, indicating that SDCNN has more advantages in text classification problems.

Automatic accounting of Baikal diatomic algae: approaches and prospects

2019 ◽  
pp. 295-299
Author(s):  
Кonstantin А. Elshin ◽  
Еlena I. Molchanova ◽  
Мarina V. Usoltseva ◽  
Yelena V. Likhoshway
Keyword(s):  
Object Detection ◽  
Loss Function ◽  
Classification Accuracy ◽  
Diatom Species ◽  
Bounding Box ◽  
Synedra Acus ◽  
And Training

Using the TensorFlow Object Detection API, an approach to identifying and registering Baikal diatom species Synedra acus subsp. radians has been tested. As a result, a set of images was formed and training was conducted. It is shown that аfter 15000 training iterations, the total value of the loss function was obtained equal to 0,04. At the same time, the classification accuracy is equal to 95%, and the accuracy of construction of the bounding box is also equal to 95%.

scholarly journals Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models

2021 ◽  
pp. 109434202110109
Author(s):  
Sam Ade Jacobs ◽  
Tim Moon ◽  
Kevin McLoughlin ◽  
Derek Jones ◽  
David Hysom ◽  
...  
Keyword(s):  
Small Molecule ◽  
Molecular Design ◽  
Turnaround Time ◽  
Generative Models ◽  
Quality Model ◽  
Training Time ◽  
Small Molecule Drug ◽  
Training Approach ◽  
Previous State ◽  
Multi Level

We improved the quality and reduced the time to produce machine learned models for use in small molecule antiviral design. Our globally asynchronous multi-level parallel training approach strong scales to all of Sierra with up to 97.7% efficiency. We trained a novel, character-based Wasserstein autoencoder that produces a higher quality model trained on 1.613 billion compounds in 23 minutes while the previous state of the art takes a day on 1 million compounds. Reducing training time from a day to minutes shifts the model creation bottleneck from computer job turnaround time to human innovation time. Our implementation achieves 318 PFLOPs for 17.1% of half-precision peak. We will incorporate this model into our molecular design loop enabling the generation of more diverse compounds; searching for novel, candidate antiviral drugs improves and reduces the time to synthesize compounds to be tested in the lab.

scholarly journals P38 COVID-19 impact on Surgical Training And Recovery Planning (COVID-STAR) Survey

BJS Open ◽  
2021 ◽  
Vol 5 (Supplement_1) ◽  
Author(s):  
◽  
Joshua Clements
Keyword(s):  
Surgical Training ◽  
Negative Impact ◽  
Healthcare Delivery ◽  
Cross Sectional Study ◽  
Surgical Trainee ◽  
Surgical Specialty ◽  
Cross Sectional ◽  
Training Time ◽  
Surgical Trainees ◽  
And Training

Abstract Background The COVID-19 pandemic has resulted in dynamic changes to healthcare delivery. Surgery as a specialty has been significantly affected and with that the delivery of surgical training. Method This national, collaborative, cross sectional study comprising 13 surgical trainee associations distributed a pan surgical specialty survey on the COVID-19 impact on surgical training over a 4-week period (11th May - 8th June 2020). The survey was voluntary and open to medical students and surgical trainees of all specialties and training grades. All aspects of training were qualitatively assessed. This study was reported according to STROBE guidelines. Results 810 completed responses were analysed. (M401: F 390) with representation from all deaneries and training grades. 41% of respondents (n = 301) were redeployed with 74% (n = 223) redeployed > 4 weeks. Complete loss of training was reported in elective operating (69.5% n = 474), outpatient activity (67.3%, n = 457), Elective endoscopy (69.5% n = 246) with > 50% reduction in training time reported in emergency operating (48%, n = 326) and completion of work-based assessments (WBA) (46%, n = 309). 81% (n = 551) reported course cancellations and departmental and regional teaching programmes were cancelled without rescheduling in 58% and 60% of cases respectively. A perceived lack of Elective operative exposure and completions of WBA’s were the primary reported factor affecting potential training progression. Overall, > 50% of trainees (n = 377) felt they would not meet the competencies required for that training period. Conclusion This study has demonstrated a perceived negative impact on numerous aspects of surgical training affecting all training specialties and grades.

Optimal Packet Camouflage Against Traffic Analysis

2021 ◽  
Vol 24 (3) ◽  
pp. 1-23
Author(s):  
Louma Chaddad ◽  
Ali Chehab ◽  
Imad H. Elhajj ◽  
Ayman Kayssi
Keyword(s):  
Classification Accuracy ◽  
Traffic Analysis ◽  
Sensitive Data ◽  
Privacy And Security ◽  
Trade Off ◽  
Network Applications ◽  
Extensive Evaluation ◽  
Flow Features ◽  
Data Content ◽  
Packet Length

Research has proved that supposedly secure encrypted network traffic is actually threatened by privacy and security violations from many aspects. This is mainly due to flow features leaking evidence about user activity and data content. Currently, adversaries can use statistical traffic analysis to create classifiers for network applications and infer users’ sensitive data. In this article, we propose a system that optimally prevents traffic feature leaks. In our first algorithm, we model the packet length probability distribution of the source app to be protected and that of the target app that the source app will resemble. We define a model that mutates the packet lengths of a source app to those lengths from the target app having similar bin probability. This would confuse a classifier by identifying a mutated source app as the target app. In our second obfuscation algorithm, we present an optimized scheme resulting in a trade-off between privacy and complexity overhead. For this reason, we propose a mathematical model for network obfuscation. We formulate analytically the problem of selecting the target app and the length from the target app to mutate to. Then, we propose an algorithm to solve it dynamically. Extensive evaluation of the proposed models, on real app traffic traces, shows significant obfuscation efficiency with relatively acceptable overhead. We were able to reduce a classification accuracy from 91.1% to 0.22% using the first algorithm, with 11.86% padding overhead. The same classification accuracy was reduced to 1.76% with only 0.73% overhead using the second algorithm.

scholarly journals Training Tips for the Transformer Model

2018 ◽  
Vol 110 (1) ◽  
pp. 43-70 ◽  
Author(s):  
Martin Popel ◽  
Ondřej Bojar
Keyword(s):  
Sentence Length ◽  
Batch Size ◽  
Critical Parameters ◽  
Neural Machine Translation ◽  
Training Time ◽  
Multiple Gpus ◽  
Translation Quality ◽  
Transformer Model ◽  
Data Constraints ◽  
And Training

Abstract This article describes our experiments in neural machine translation using the recent Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et al., 2017). We examine some of the critical parameters that affect the final translation quality, memory usage, training stability and training time, concluding each experiment with a set of recommendations for fellow researchers. In addition to confirming the general mantra “more data and larger models”, we address scaling to multiple GPUs and provide practical tips for improved training regarding batch size, learning rate, warmup steps, maximum sentence length and checkpoint averaging. We hope that our observations will allow others to get better results given their particular hardware and data constraints.

scholarly journals A New Subject-Specific Discriminative and Multi-Scale Filter Bank Tangent Space Mapping Method for Recognition of Multiclass Motor Imagery

2021 ◽  
Vol 15 ◽  
Author(s):  
Fan Wu ◽  
Anmin Gong ◽  
Hongyun Li ◽  
Lei Zhao ◽  
Wei Zhang ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Tangent Space ◽  
Filter Bank ◽  
Space Mapping ◽  
Training Time ◽  
Frequency Bands ◽  
Multi Scale ◽  
Average Accuracy ◽  
Subject Specific ◽  
The Subject

Objective: Tangent Space Mapping (TSM) using the geometric structure of the covariance matrices is an effective method to recognize multiclass motor imagery (MI). Compared with the traditional CSP method, the Riemann geometric method based on TSM takes into account the nonlinear information contained in the covariance matrix, and can extract more abundant and effective features. Moreover, the method is an unsupervised operation, which can reduce the time of feature extraction. However, EEG features induced by MI mental activities of different subjects are not the same, so selection of subject-specific discriminative EEG frequency components play a vital role in the recognition of multiclass MI. In order to solve the problem, a discriminative and multi-scale filter bank tangent space mapping (DMFBTSM) algorithm is proposed in this article to design the subject-specific Filter Bank (FB) so as to effectively recognize multiclass MI tasks.Methods: On the 4-class BCI competition IV-2a dataset, first, a non-parametric method of multivariate analysis of variance (MANOVA) based on the sum of squared distances is used to select discriminative frequency bands for a subject; next, a multi-scale FB is generated according to the range of these frequency bands, and then decompose multi-channel EEG of the subject into multiple sub-bands combined with several time windows. Then TSM algorithm is used to estimate Riemannian tangent space features in each sub-band and finally a liner Support Vector Machines (SVM) is used for classification.Main Results: The analysis results show that the proposed discriminative FB enhances the multi-scale TSM algorithm, improves the classification accuracy and reduces the execution time during training and testing. On the 4-class BCI competition IV-2a dataset, the average session to session classification accuracy of nine subjects reached 77.33 ± 12.3%. When the training time and the test time are similar, the average classification accuracy is 2.56% higher than the latest TSM method based on multi-scale filter bank analysis technology. When the classification accuracy is similar, the training speed is increased by more than three times, and the test speed is increased two times more. Compared with Supervised Fisher Geodesic Minimum Distance to the Mean (Supervised FGMDRM), another new variant based on Riemann geometry classifier, the average accuracy is 3.36% higher, we also compared with the latest Deep Learning method, and the average accuracy of 10-fold cross validation improved by 2.58%.Conclusion: Research shows that the proposed DMFBTSM algorithm can improve the classification accuracy of MI tasks.Significance: Compared with the MFBTSM algorithm, the algorithm proposed in this article is expected to select frequency bands with good separability for specific subject to improve the classification accuracy of multiclass MI tasks and reduce the feature dimension to reduce training time and testing time.

scholarly journals Mosquito Larvae Detection using Deep Learning

2019 ◽  
Vol 8 (12) ◽  
pp. 804-809
Keyword(s):  
Deep Learning ◽  
Mobile Application ◽  
Web Application ◽  
Individual Performance ◽  
Mosquito Larvae ◽  
Accuracy Score ◽  
Performance Category ◽  
Training Time ◽  
The Cost ◽  
And Training

Dengue cases has become endemic in Malaysia. The cost of operation to exterminate mosquito habitats are also high. To do effective operation, information from community are crucial. But, without knowing the characteristic of Aedes larvae it is hard to recognize the larvae without guide from the expert. The use of deep learning in image classification and recognition is crucial to tackle this problem. The purpose of this project is to conduct a study of characteristics of Aedes larvae and determine the best convolutional neural network model in classifying the mosquito larvae. 3 performance evaluation vector which is accuracy, log-loss and AUC-ROC will be used to measure the model’s individual performance. Then performance category which consist of Accuracy Score, Loss Score, File Size Score and Training Time Score will be used to evaluate which model is the best to be implemented into web application or mobile application. From the score collected for each model, ResNet50 has proved to be the best model in classifying the mosquito larvae species.

Sign in / Sign up

Export Citation Format

Share Document