For predicting the value of the quality variable in fermentation processes, traditional data-driven methods do not use information in large amounts of unlabelled data. To solve this data-rich but information-poor (DRI...
详细信息
For predicting the value of the quality variable in fermentation processes, traditional data-driven methods do not use information in large amounts of unlabelled data. To solve this data-rich but information-poor (DRIP) problem, a teacher student stacked sparse recurrent autoencoder (TS-SSRAE) model is proposed. Compared with traditional data-driven methods, the proposed method has three main advantages. First, an autoencoder is an unsupervised method which can effectively extract rich information in unlabelled data. The proposed stacked recurrent autoencoder (SRAE) with long short-term memory (LSTM) recurrent neural unit is superior to traditional autoencoders when extracting the dynamic correlation information in the fermentation process. Second, sparse constraints can make it much easier for hidden neurons to obtain useful information in a single moment. Finally, the LSTM recurrent neural unit is complex and the inputs of a SRAE must be a sequence, which increases the complexity of the model to a certain extent. So, the knowledge distillation is employed to simplify the model and reduce the computing time. In order to demonstrate its effectiveness, the proposed method is applied to the penicillin fermentation process for a simulation experiment and Escherichia coli production of interleukin-2. The results show that the proposed method based on TS-SSRAE can have better performance than conventional methods.
作者:
Zhang, DonglinWu, Xiao-JunJiangnan Univ
Sch Artificial Intelligence & Comp Sci Wuxi 214122 Jiangsu Peoples R China Jiangnan Univ
Jiangsu Prov Engn Lab Pattern Recognit & Computat Wuxi 214122 Jiangsu Peoples R China
Hashing methods have sparked great attention on multimedia tasks due to their effectiveness and efficiency. However, most existing methods generate binary codes by relaxing the binary constraints, which may cause larg...
详细信息
Hashing methods have sparked great attention on multimedia tasks due to their effectiveness and efficiency. However, most existing methods generate binary codes by relaxing the binary constraints, which may cause large quantization error. In addition, most supervised cross-modal approaches preserve the similarity relationship by constructing an n x n large-size similarity matrix, which requires huge computation, making these methods unscalable. To address the above challenges, this article presents a novel algorithm, called scalable discrete matrix factorization and semantic autoencoder method (SDMSA). SDMSA is a two-stage method. In the first stage, the matrix factorization scheme is utilized to learn the latent semantic information, the label matrix is incorporated into the loss function instead of the similarity matrix. Thereafter, the binary codes can be generated by the latent representations. During optimization, we can avoid manipulating a large nxn similarity matrix, and the hash codes can be generated directly. In the second stage, a novel hash function learning scheme based on the autoencoder is proposed. The encoder-decoder paradigm aims to learn projections, the feature vectors are projected to code vectors by encoder, and the code vectors are projected back to the original feature vectors by the decoder. The encoder-decoder scheme ensures the embedding can well preserve both the semantic and feature information. Specifically, two algorithms SDMSA-lin and SDMSA-ker are developed under the SDMSA framework. Owing to the merit of SDMSA, we can get more semantically meaningful binary hash codes. Extensive experiments on several databases show that SDMSA-lin and SDMSA-ker achieve promising performance.
Detecting defective source code to localize and fix bugs is important to reduce software development efforts. Although deep learning models have made a breakthrough in this field, many issues have not been resolved, s...
详细信息
Detecting defective source code to localize and fix bugs is important to reduce software development efforts. Although deep learning models have made a breakthrough in this field, many issues have not been resolved, such as labeled data shortage and the small size of defective elements. Given two similar programs that differ from each other by an operator or statement, one may be clean while the other may be defective. To address these issues, this study proposes a new deep learning model to facilitate the learning of distinguishing features. The model comprises of three main components: 1) a convolutional neural network-based classifier, 2) an autoencoder, and 3) a k-means cluster. In our model, the autoencoder assists the classifier in generating program latent representations. The k-means cluster provides penalty functions to increase the distinguishability among latent representations. We evaluated the effectiveness of the model according to performance metrics and latent representation quality. The experimental results on the four defect prediction datasets show that the proposed model outperforms the baselines thanks to the generation of sophisticated features.
Recommendation System is one of such solutions to overcome information overload issues and to identify products most relevant to users and provide suggestions to users for items they might be interested in consuming o...
详细信息
Recommendation System is one of such solutions to overcome information overload issues and to identify products most relevant to users and provide suggestions to users for items they might be interested in consuming or elements matching their needs. The significant challenge of several recommendation approaches is that they suggested a huge number of things to the target user. But the exciting items, according to the target user, are seen at the bottom of the recommended list. The proposed approach has improved the quality of recommendations by implementing some of the unique features in the new framework of auto encoder called semi-autoencoder, which contains the rating information as well as some additional information of users. autoencoder is widely used in the recommender system because it gives the best result for feature extraction, dimensionality reduction, regeneration of data, and a better understanding of the user's characteristics. The experimental results are compared with some established popular methods using precision, recall, and F-measure evaluation measures. Users generally don't want to see lots of suggestions. With its six building blocks, the proposed approach gives better performance for the top 10 recommendations compared to other well-known methods.
The accuracy of load forecasting is very important to the safe and economical operation of power system. This paper presents a LSTNet model based on autoencoder feature extraction for load time series prediction. In t...
详细信息
Network intrusion detection is a constantly evolving field as researchers and practitioners work towards keeping up with novel attacks and growing amounts of network data. To aid in this challenge researchers have bee...
详细信息
ISBN:
(纸本)9781665462839
Network intrusion detection is a constantly evolving field as researchers and practitioners work towards keeping up with novel attacks and growing amounts of network data. To aid in this challenge researchers have been exploring the use of deep learning techniques such as neural networks in order to detect zero-day attacks and reduce the amount of manual analysis required when a network intrusion detection system alert is generated. Herein we use an unsupervised pre-training step in order to take advantage of autoencoder feature residuals. We show that autoencoder feature residuals can be used in place of or in addition to an original feature set as input to a neural network classifier to improve classification performance. Often in such problems, experts perform feature engineering to optimize classification performance. However, such data manipulation is expensive and time consuming. Our novel approach provides a path that can alleviate the need for manual feature extraction while "doing no harm". That is, if the provided features are in some sense optimal, then our methodology will not degrade the classification performance. However, if the provided features are inefficient, then we demonstrate that our methodology can substantially improve classification performance on a broad range of benchmark cybersecurity datasets. Another practical side effect of using autoencoder feature residuals comes to light by analyzing the potential data compression benefits they provide.
Machine learning methods have been widely used in the field of intrusion detection. However, most methods require labeled data sets, and the overhead is very high. Network data is often high-dimensional and has the pr...
详细信息
ISBN:
(纸本)9791188428090
Machine learning methods have been widely used in the field of intrusion detection. However, most methods require labeled data sets, and the overhead is very high. Network data is often high-dimensional and has the problem of data imbalance, which makes many techniques unable to adapt to the real network environment. In this paper, we propose a network intrusion detection model based on autoencoder ensembles. This model uses a recursive feature addition algorithm to select the optimal subset of features, which can significantly reduce the training time of classifiers, and improve the performance of intrusion detection system. After feature selection, the feature subset is grouped, and then each group is mapped to an autoencoder. Multiple such autoencoders ensembles form the detection model. Only normal samples are used for training. The detection model is unsupervised, which improves the efficiency of detecting known and unknown attacks. The experimental results show that feature selection can effectively reduce training and detection time. Our model has high detection accuracy and strong adaptability.
In order to improve the intelligent energy efficiency management of ships, evaluate the fuel utilization efficiency of marine diesel engine. In this paper, a fuel consumption model of marine diesel engine based on aut...
详细信息
ISBN:
(数字)9781665408530
ISBN:
(纸本)9781665408530;9781665408523
In order to improve the intelligent energy efficiency management of ships, evaluate the fuel utilization efficiency of marine diesel engine. In this paper, a fuel consumption model of marine diesel engine based on autoencoder and deep neural network is established, and the autoencoder is used to perform nonlinear dimensionality reduction on the data to obtain more valuable data features, thereby improving the accuracy of the model. The model is verified and compared using the sailing parameters, environmental parameters and fuel consumption of the actual ship during normal sailing. The accuracy rate of the model established in this paper reaches 95.19%, and the results show that the model in this paper can meet the prediction and evaluation analysis of the energy consumption of the marine diesel engine.
Sequential recommendation demonstrates the capability to recommend items by modeling the sequential behavior of users. Traditional methods typically treat users as sequences of items, overlooking the collaborative rel...
详细信息
ISBN:
(纸本)9798400701245
Sequential recommendation demonstrates the capability to recommend items by modeling the sequential behavior of users. Traditional methods typically treat users as sequences of items, overlooking the collaborative relationships among them. Graph-based methods incorporate collaborative information by utilizing the user-item interaction graph. However, these methods sometimes face challenges in terms of time complexity and computational efficiency. To address these limitations, this paper presents AutoSeqRec, an incremental recommendation model specifically designed for sequential recommendation tasks. AutoSeqRec is based on autoencoders and consists of an encoder and three decoders within the autoencoder architecture. These components consider both the user-item interaction matrix and the rows and columns of the item transition matrix. The reconstruction of the user-item interaction matrix captures user long-term preferences through collaborative filtering. In addition, the rows and columns of the item transition matrix represent the item out-degree and in-degree hopping behavior, which allows for modeling the user's short-term interests. When making incremental recommendations, only the input matrices need to be updated, without the need to update parameters, which makes AutoSeqRec very efficient. Comprehensive evaluations demonstrate that AutoSeqRec outperforms existing methods in terms of accuracy, while showcasing its robustness and efficiency.
This paper presents a novel approach to compensate for sensor long-term drift by combining an autoencoder with a long short-term neural network (LSTM). Specifically, an autoencoder is utilized to model the sensor'...
详细信息
ISBN:
(纸本)9798350303872
This paper presents a novel approach to compensate for sensor long-term drift by combining an autoencoder with a long short-term neural network (LSTM). Specifically, an autoencoder is utilized to model the sensor's long-term drift response, and the learned latent space representation is then fed into the input of the subsequent LSTM networks for length estimation. The proposed algorithm is experimentally validated using a single kirigami flexible sensor stretched by a moving platform for length change estimation. The results demonstrate that, compared to a standard LSTM, the proposed algorithm achieves a 76% reduction in root mean square error for length estimation, with a corresponding improvement in the coefficient of determination R2 from -3.09 to 0.77.
暂无评论