Electric power cloud data center becomes more and more widely applied,and yet lacks security protection inside *** most direct solution for this issue is internal network *** paper focuses on the first task of the iso...
详细信息
Electric power cloud data center becomes more and more widely applied,and yet lacks security protection inside *** most direct solution for this issue is internal network *** paper focuses on the first task of the isolation,namely network service identification,and proposes a network service identification framework based on deep *** order to obtain service stream,a network service stream extraction algorithm is proposed based on the flow metric and traffic *** the high dimensionality and complexity of service streams,the denoising and convolutional autoencoders are combined for feature *** then a self-organizing mean maps network is adopted to achieve network service *** results illustrate the effectiveness and superiority of the self-organizing mean maps network with regard to the internal evaluation index of ***,the identification framework proposed seems to provide a foundation for subsequent isolation study.
Identifying drug-target interactions (DTIs) is a major challenge in drug development. Traditionally, similarity-based methods use drug and target similarity matrices to infer the potential drug-target interactions. Bu...
详细信息
ISBN:
(纸本)9781509006212
Identifying drug-target interactions (DTIs) is a major challenge in drug development. Traditionally, similarity-based methods use drug and target similarity matrices to infer the potential drug-target interactions. But these techniques do not handle biochemical data directly. While recent feature-based methods reveal simple patterns of physicochemical properties, efficient method to study large interactive features and precisely predict interactions is still missing. Deep learning has been found to be an appropriate tool for converting high-dimensional features to low-dimensional representations. These deep representations generated from drug-protein pair can serve as training examples for the interaction predictor. In this paper, we propose a promising approach called multi-scale features deep representations inferring interactions (MFDR). We extract the large-scale chemical structure and protein sequence descriptors so as to machine learning model predict if certain human target protein can interact with a specific drug. MFDR use Auto-Encoders as building blocks of deep network for reconstruct drug and protein features to low-dimensional new representations. Then, we make use of support vector machine to infer the potential drug-target interaction from deep representations. The experiment result shows that a deep neural network with Stacked Auto-Encoders exactly output interactive representations for the DTIs prediction task. MFDR is able to predict large-scale drug-target interactions with high accuracy and achieves results better than other feature-based approaches.
Predictive maintenance uses improved Fuzzy Analytic Hierarchy Process(FAHP) model to calculate the weight of equipment failure and the comprehensive index information of equipment failure, to identify its deterioratio...
详细信息
Predictive maintenance uses improved Fuzzy Analytic Hierarchy Process(FAHP) model to calculate the weight of equipment failure and the comprehensive index information of equipment failure, to identify its deterioration trend, and to judge its trend, to calculate the comprehensive maintenance threshold, to generate maintenance decision information and to identify the equipment locations that need to be disposed of.
We seek to better classify canine behavior for guide dog training predictions. Dog temperament is a major factor in success rates and current training also has a blind spot when the puppies are with puppy raisers, who...
详细信息
ISBN:
(纸本)9798400716560
We seek to better classify canine behavior for guide dog training predictions. Dog temperament is a major factor in success rates and current training also has a blind spot when the puppies are with puppy raisers, who are lesser trained volunteers who socialize puppies up to 15 months old. We have used a custom designed smart collar to collect environmental and behavioral data from each puppy individually going through various parts of the guide dog training. We investigate long short-term memory networks (LSTMs), autoencoders (AE), and kernel principal component analysis (KPCA) as methods to identify canine behavior and use multi-sensor data fusion to find the best subset of sensors with the best at classifying temperament. Standard manifold learning experiments take place in controlled environments and translate poorly to real-world applications. This research aims to bridge this gap using guide dog In For Training (IFT) data, which is from a lesser controlled environment and use it to develop a broader data-pattern-to-behavior dictionary for future real-world canine studies.
In this paper, we describe a intrusion detection algorithm based on deep learning for industrial control networks, aiming at the security problem of industrial control network. Deep learning is a kind of intelligent a...
详细信息
ISBN:
(纸本)9781450376228
In this paper, we describe a intrusion detection algorithm based on deep learning for industrial control networks, aiming at the security problem of industrial control network. Deep learning is a kind of intelligent algorithm and has the ability of automatically learning. It use self-learning to enhance the experience and dynamic classification capabilities. The ideology of deep learning is similar to the idea of intrusion detection to improve the detection rate and reduce the rate of false through learning, a sparse auto-encoder-extreme learning machine intrusion detection model is proposed for the problem of intrusion detection accuracy. It uses deep learning autoencoder to combine the coefficient penalty and reconstruction loss of the encode layer to extract the features of high-dimensional data during the training model, and then uses the extreme learning machine to quickly and effectively classify the extracted features. The accuracy of the algorithm is verified by the industrial control intrusion detection standard data set. The experimental results verify that the method can effectively improve the performance of the intrusion detection system and reduce the false alarm rate.
Signal map is of great importance, especially in the dawn of 5G network, for site spectrum monitoring, location-based services (LBS), network construction, and cellular planning. Despite its significance, the traditio...
详细信息
ISBN:
(纸本)9781728125848
Signal map is of great importance, especially in the dawn of 5G network, for site spectrum monitoring, location-based services (LBS), network construction, and cellular planning. Despite its significance, the traditional signal map construction, e.g., through full site survey, could be time-consuming and labor-intensive as the signal varies frequently over time and the accuracy requirement grows rapidly with the emergence of new applications. Even with crowdsourcing scheme, the participants tend to be unevenly distributed in space while the encouragement budgets for the participants could be far from enough to collect adequate high-quality measurements. Therefore, the signal map constructed by crowdsourcing is often sparse and incomplete. To this end, in this paper, we study how to effectively reconstruct and update the signal map in the case of partially measured signal maps with minimum cost and propose an auto-encoder-based active signal map reconstruction method (AER). Our method is mainly innovative in three parts. Firstly, AER can effectively update the signal map with only a small number of observations while also fully using the incomplete historical signals to effectively update the signal map online. Secondly, AER consists of an active query mechanism which quantitatively evaluates the most valuable measurement site for reconstruction, which further reduces the measurement cost to a large extent. Thirdly, to cope with the measurement dynamics, we give a new signal map model describing not only the signal strength but also the signal dynamics, based on which an advanced AER algorithm is proposed. The simulation results demonstrate the advantages and effectiveness of our approach in both accuracy and cost.
Recent work has shown that it is possible for two wearable devices worn by the same user to generate a common key for secure pairing by exploiting gait as a common secret. A key challenge for such device pairing lies ...
详细信息
ISBN:
(纸本)9781450359528
Recent work has shown that it is possible for two wearable devices worn by the same user to generate a common key for secure pairing by exploiting gait as a common secret. A key challenge for such device pairing lies in matching the bits of the keys generated by two independent devices despite the noisy on-board sensor measurements. We propose a novel machine learning framework that uses an autoencoder to help one device predict the sensor observations at another device and generate the key using the predicted sensor data. We prototype the proposed method and evaluate it using real subjects. Our results show that the proposed method achieves a 10% increase in bit agreement rate between two keys generated independently by two different wearable devices.
This paper focuses on optimizing the Mean Teacher model and validating the improved classification performance on the benchmark CIFAR-10 dataset. The paper optimizes the loss function by constructing a teacher graph, ...
详细信息
ISBN:
(数字)9789887581581
ISBN:
(纸本)9798350366907
This paper focuses on optimizing the Mean Teacher model and validating the improved classification performance on the benchmark CIFAR-10 dataset. The paper optimizes the loss function by constructing a teacher graph, incorporating consistency loss, and introducing smooth neighbors based on the teacher graph. Simultaneously, the student and teacher networks of the original model are replaced with autoencoders to enhance prediction accuracy through the encoder's classification and reconstruction abilities. Ultimately, two ConvLarge structure algorithms, SNTG(Smooth Neighbors on Teacher) and HybridNet, are developed. These three algorithms are compared for recognition performance on the CIFAR-10 dataset, achieving promising results. Both SNTG and HybridNet significantly improve model accuracy compared to the original Mean Teacher algorithm,reducing recognition error rates to around 17% and increasing the accuracy by 3.5%.
Computer vision is a major branch of artificial intelligence algorithm. The algorithm of computer vision mainly consists of the processing of image and video, including image recognition and image detection etc. Pract...
详细信息
ISBN:
(数字)9781728147437
ISBN:
(纸本)9781728147444
Computer vision is a major branch of artificial intelligence algorithm. The algorithm of computer vision mainly consists of the processing of image and video, including image recognition and image detection etc. Practice has proved that computer vision is scientific and practical to a certain extent. In pace with the development of in-depth learning, computer vision has already been put to use well in all walks of life. However, it is still in exploring stage in the medical field, because the medical data is sensitive, which requires high accuracy of the algorithm. In this paper, images of PCam medical electron microscope are put to use for tumor detection, which is an task of image recognition and an automatic encoder is used to lower the dimensions of the data into low-dimensional vectors which are used as features in training. Then the vectors are added as features to the training, and the model is trained together with the original data set as the training features of NASnet. Because detection algorithms in the medical field pay more importance to the true positive rate and false positive rate. When the output is positive, it is necessary to be revalidated by SVM model trained by encoder. As a result, ROC curve is 0.98, which is 0.03 higher than Baseline.
In order to avoid the occurrence of large-scale accidents to the greatest extent,it is necessary to find out the faults in the continuous operation of mechanical equipment and make corresponding *** the development of...
详细信息
In order to avoid the occurrence of large-scale accidents to the greatest extent,it is necessary to find out the faults in the continuous operation of mechanical equipment and make corresponding *** the development of artificial intelligence technology,autoencoder(AE) has been widely used in fault diagnosis,among which class level autoencoder(CLAE)effectively overcome the intra-class variations of detection data under different ***,the CLAE model just uses a single scale method to extract features from the data,and when the data is mixed with noise,the classification performance will *** this work,we proposed a multiscale class level autoencoder model(MSCLAE) which aims at learning robust and discriminative ***,we extract single-scale features from each CLAE model with different input and ouput dimensions respectively and combine these features for fault pattern *** experimental results on a motor bearing dataset have demonstrated that the proposed method can extract more robust features and obtain better anti-noise ability.
暂无评论