Raw Data Information Research Articles

Stacked isomorphic autoencoder based soft analyzer and its application to sulfur recovery unit

Deep learning is an important and effective tool for process soft sensor modeling in industrial artificial intelligence. Traditional deep learning methods like stacked autoencoder (SAE) usually learn high-level features from their low-level ones progressively by minimizing the reconstruction error for the inputs at each layer. However, the reconstruction cannot be exactly accurate. There is loss cumulation of raw data information from the lowest to the highest levels in SAE. To deal with this problem, a novel deep stacked isomorphic autoencoder (SIAE) is proposed to obtain better feature representation for raw input data in this paper. Different from the original SAE, SIAE aims to extract abstract features at each layer from its previous one by stacking hierarchical isomorphic autoencoders (IAE), in which each IAE reconstructs the same raw input data as well as possible. Thus, SIAE can better describe the complex data patterns and obtain good features for the raw data. Then, SIAE is used to construct soft sensor model for quality prediction. The application on an industrial sulfur recovery unit shows that SIAE can improve the prediction performance for the quality variable.

Bidirectional LSTM Recurrent Neural Network Plus Hidden Markov Model for Wearable Sensor-Based Dynamic State Estimation

Abstract Behavior of animals living in the wild is often studied using visual observations made by trained experts. However, these observations tend to be used to classify behavior during discrete time periods and become more difficult when used to monitor multiple individuals for days or weeks. In this work, we present automatic tools to enable efficient behavior and dynamic state estimation/classification from data collected with animal borne bio-logging tags, without the need for statistical feature engineering. A combined framework of an long short-term memory (LSTM) network and a hidden Markov model (HMM) was developed to exploit sequential temporal information in raw motion data at two levels: within and between windows. Taking a moving window data segmentation approach, LSTM estimates the dynamic state corresponding to each window by parsing the contiguous raw data points within the window. HMM then links all of the individual window estimations and further improves the overall estimation. A case study with bottlenose dolphins was conducted to demonstrate the approach. The combined LSTM–HMM method achieved a 6% improvement over conventional methods such as K-nearest neighbor (KNN) and support vector machine (SVM), pushing the accuracy above 90%. In addition to performance improvements, the proposed method requires a similar amount of training data to traditional machine learning methods, making the method easily adaptable to new tasks.

A Novel Fault Diagnosis Method based on Stacked LSTM

Fault diagnosis is essential to ensure the operation security and economic efficiency of the chemical system. Many fault diagnosis methods have been designed for the chemical process, but most of them ignore the temporal correlation in the sequential observation signals of the chemical process. A novel deep learning method based on Stacked Long Short-Term Memory (LSTM) neural network is proposed, which can effectively model sequential data and detect the abnormal values. The proposed method is also able to fully exploit the long-term dependencies information in raw data and adaptively extract the representative features. The dataset of Tennessee Eastman (TE) process is utilized to verify the practicability and superiority of the proposed method. Extensive experimental results show that the fault detection and diagnosis model we proposed has an excellent performance when compared with several state-of-the-art baseline methods.

Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis

Traditional intelligent fault diagnosis techniques based on artificially selected features fail to make the most of the raw data information, and are short of the capabilities of feature self-learning. Moreover, the most informative and distinguished parts of the different faults signals only account for a small portion in the time domain and frequency domain signals. Therefore, in order to learn the discriminative features from the raw data adaptively, this paper proposes a multiscale local feature learning method based on back-propagation neural network (BPNN) for rolling bearings fault diagnosis. Based on the local characteristics of the fault features in the time domain and the frequency domain, the BPNN is used to locally learn meaningful and dissimilar features from signals of different scales, thus improving the fault diagnosis accuracy. Two sets of rolling bearing datasets are adopted to verify the validity and superiority of the proposed method by comparing with other methods.

Implementation of Artificial Intelligence for Classification of Frogs in Bioacoustics

This research presents the implementation of artificial intelligence (AI) for classification of frogs in symmetry of the bioacoustics spectral by using the feedforward neural network approach (FNNA) and support vector machine (SVM). Recently, the symmetry concept has been applied in physics, and in mathematics to help make mathematical models tractable to achieve the best learning performance. Owing to the symmetry of the bioacoustics spectral, feature extraction can be achieved by integrating the techniques of Mel-scale frequency cepstral coefficient (MFCC) and mentioned machine learning algorithms, such as SVM, neural network, and so on. At the beginning, the raw data information for our experiment is taken from a website which collects many kinds of frog sounds. This in fact saves us collecting the raw data by using a digital signal processing technique. The generally proposed system detects bioacoustic features by using the microphone sensor to record the sounds of different frogs. The data acquisition system uses an embedded controller and a dynamic signal module for making high-accuracy measurements. With regard to bioacoustic features, they are filtered through the MFCC algorithm. As the filtering process is finished, all values from ceptrum signals are collected to form the datasets. For classification and identification of frogs, we adopt the multi-layer FNNA algorithm in machine learning and the results are compared with those obtained by the SVM method at the same time. Additionally, two optimizer functions in neural network include: scaled conjugate gradient (SCG) and gradient descent adaptive learning rate (GDA). Both optimization methods are used to evaluate the classification results from the feature datasets in model training. Also, calculation results from the general central processing unit (CPU) and Nvidia graphics processing unit (GPU) processors are evaluated and discussed. The effectiveness of the experimental system on the filtered feature datasets is classified by using the FNNA and the SVM scheme. The expected experimental results of the identification with respect to different symmetry bioacoustic features of fifteen frogs are obtained and finally distinguished.

Rolling element bearing diagnosis based on probability box theory

Feature extraction leads to the loss of statistical information of raw data and ignores the sampling uncertainty and the fluctuations in the signal over time in mechanical fault diagnosis. In this paper, novel modeling methods for mechanical signals based on probability box theory were proposed to solve the above problem. First, the type of random distribution of the bearing signals were analyzed. Then, a Dempster-Shafer structure was obtained to establish a probability box model. To address the identification difficulty of the type of random distribution for the bearing signals, a second probability box model was established based on a vector consisting of features from the bearing signals. If the data are not found to follow a random distribution, a third modeling method based on the definition of probability boxes was proposed. The effectiveness and applicability of the three proposed models were compared with experimental data from rolling element bearings. The combination of probability box theory and mechanical fault diagnosis theory can open up a new research direction for mechanical fault diagnosis.

Recent Technological Advances in the Mass Spectrometry-based Nanomedicine Studies: An Insight from Nanoproteomics

Nanoscience becomes one of the most cutting-edge research directions in recent years since it is gradually matured from basic to applied science. Nanoparticles (NPs) and nanomaterials (NMs) play important roles in various aspects of biomedicine science, and their influences on the environment have caused a whole range of uncertainties which require extensive attention. Due to the quantitative and dynamic information provided for human proteome, mass spectrometry (MS)-based quantitative proteomic technique has been a powerful tool for nanomedicine study. In this article, recent trends of progress and development in the nanomedicine of proteomics were discussed from quantification techniques and publicly available resources or tools. First, a variety of popular protein quantification techniques including labeling and label-free strategies applied to nanomedicine studies are overviewed and systematically discussed. Then, numerous protein profiling tools for data processing and postbiological statistical analysis and publicly available data repositories for providing enrichment MS raw data information sources are also discussed.

Multimodal GAN for Energy Efficiency and Cloud Classification in Internet of Things

Efficient processing of large-scale multimodal sensor data is a key issue for applying the Internet of Things (IoT). Accurate cloud classification is critical for weather and climate monitoring, which are parts of IoT applications. In this paper, we propose a novel generative deep model named multimodal generative adversarial network (Multimodal GAN) to improve both the energy efficiency and the cloud classification accuracy in IoT. The proposed Multimodal GAN is composed of a discriminator and a generator, each of which is devised to a two-stream network. The branches of two-stream structure correspond to the cloud visual information and the cloud scalar information, respectively. Therefore, the Multimodal GAN is capable of generating the cloud visual information and cloud scalar information simultaneously. Afterward, the training set is extended by the generated multimodal cloud samples, and the deep multimodal cloud classification model is trained by the extended training set. As a result, the classification model possesses high generalization ability and is less prone to be over-fitting. Moreover, the feature representations extracted from the classification model reflect the salient information of raw multimodal cloud data, and therefore they can be stored and transmitted in IoT. The effectiveness of the proposed method in energy efficiency and cloud classification is validated on the multimodal cloud dataset.

Partial Multi-View Clustering Based on Sparse Embedding Framework

In this paper, we propose a novel partial multi-view clustering method based on the sparse embedding framework, which can handle incomplete view data well and obtain good clustering performance. Most real-world datasets are often comprised of different views, which provide complementary information for each other for clustering or classification tasks. Existing multi-view clustering methods assume that each example appears in all views or all examples contained at least one view. But each view of real data is often subject to various degrees of damage resulting in partial examples. There are some works on partial view clustering, in which almost all are based on standard non-negative matrix factorization (NMF) to solve the problem that did not consider the sparseness degree of coefficient and unsatisfactory basic matrices learned by NMF. Besides, most existing clustering methods only carry out dimensionality reduction before learning the models, which is unable to make full use of the discriminative information in raw data. Thus, partial multi-view clustering based on sparse embedding framework is proposed, in which dimensionality reduction and dictionary learning are taken into consideration simultaneously to learn better sparse coefficients and dictionaries. The proposed method preserves as much useful information as possible in original space by constraining projection matrix to be orthogonal and imposes Fisher discrimination analysis on dictionaries rather than sparse coefficients, which makes the learned dictionaries more discriminating and promotes sparsity of coefficients. Finally, the synthetic dataset, the extended Yale B dataset, the MNISIT Handwritten Digit dataset and the large dataset-Caltech101 are employed to perform clustering tasks, and the experimental results show that the proposed method achieved a better clustering performance than the other state-of-the-art clustering methods.

Network Intrusion Detection: Based on Deep Hierarchical Network and Original Flow Data

Network intrusion detection plays a very important role in protecting computer network security. The abnormal traffic detection and analysis by extracting the statistical features of flow is the main analysis method in the field of network intrusion detection. However, these features need to be designed and extracted manually, which often loses the original information of the flow and leads to poor detection efficiency. In this paper, we do not manually design the features of the flow but directly extract the raw data information of the flow for analysis. In addition, we first proposed a new network intrusion detection model named the deep hierarchical network, which integrates the improved LeNet-5 and LSTM neural network structures, while learning the spatial and temporal features of flow. By designing a reasonable network cascading method, we can train our proposed hierarchical network at the same time instead of training two networks separately. In this paper, we use the CICIDS2017 dataset and the CTU dataset. The number and types of flow in these two datasets are large, and the attack types are relatively new. The experimental results show that the performance of the proposed hierarchical network model is significantly better than other network intrusion detection models, which can achieve the best detection accuracy. Finally, we also present an analysis method for traffic features which has an important contribution to abnormal traffic detection and gives the actual meanings of these important features.

Text analytics to analyze and monitor construction project contract and correspondence

Abstract Text mining is a fast-growing area of research, due to its ability to discover valuable information and getting insights hidden in plain texts. The aim of this paper is to apply text mining in order to analyze construction project contracts and visually analyze project correspondence. Analyzing construction contract helps project parties to figure out their obligations and reduce time and effort needed for contract analysis. Additionally, performing text mining to the contract helps in extracting critical keywords that should be monitored closely in the correspondence. On the other hand, applying text mining for project correspondence helps in gaining an understanding regarding the communication nature and sentiment between project parties. Thus, the paper develops a Dynamic Text Analytical model for Contract and Correspondence “DTA-CC” through utilizing BIM. The DTA-CC model assists project parties to explore texts and get insights regarding the project performance. The specific objectives of this study are to 1-perform a text analytics of the construction project contract, 2- integrate project correspondence within the BIM model and 3- develop a text analytical model based on project's correspondence to monitor the project performance. The DTA-CC model is validated by applying a case study for a construction project located in Cairo, Egypt. The case study found that there is a lot of hidden information in the project's raw data. Moreover, it is crucial to monitor raw data in order to achieve a successful project. This study extends the existing knowledge by proposing a novel methodology to extract meaningful patterns from construction projects data.

Accurate filtering of privacy-sensitive information in raw genomic data

Sequencing thousands of human genomes has enabled breakthroughs in many areas, among them precision medicine, the study of rare diseases, and forensics. However, mass collection of such sensitive data entails enormous risks if not protected to the highest standards. In this article, we follow the position and argue that post-alignment privacy is not enough and that data should be automatically protected as early as possible in the genomics workflow, ideally immediately after the data is produced. We show that a previous approach for filtering short reads cannot extend to long reads and present a novel filtering approach that classifies raw genomic data (i.e., whose location and content is not yet determined) into privacy-sensitive (i.e., more affected by a successful privacy attack) and non-privacy-sensitive information. Such a classification allows the fine-grained and automated adjustment of protective measures to mitigate the possible consequences of exposure, in particular when relying on public clouds. We present the first filter that can be indistinctly applied to reads of any length, i.e., making it usable with any recent or future sequencing technologies. The filter is accurate, in the sense that it detects all known sensitive nucleotides except those located in highly variable regions (less than 10 nucleotides remain undetected per genome instead of 100,000 in previous works). It has far less false positives than previously known methods (10% instead of 60%) and can detect sensitive nucleotides despite sequencing errors (86% detected instead of 56% with 2% of mutations). Finally, practical experiments demonstrate high performance, both in terms of throughput and memory consumption.

Sequential Fault Diagnosis Based on LSTM Neural Network

Fault diagnosis of chemical process data becomes one of the most important directions in research and practice. Conventional fault diagnosis and classification methods first extract features from the raw process data. Then certain classifiers are adopted to make diagnosis. However, these conventional methods suffer from the expertise of feature extraction and classifier design. They also lack the adaptive processing of the dynamic information in raw data. This paper proposes a fault diagnosis method based on long short-term memory (LSTM) neural network. The novel method can directly classify the raw process data without specific feature extraction and classifier design. It is also able to adaptively learn the dynamic information in raw data. First, raw process data are used to train the LSTM neural network until the cost function of LSTM converges below certain predefined small positive value. In this step, the dynamic information of raw process data is adaptively learned by LSTM. Then testing data are used to obtain the diagnosis results of the trained LSTM neural network. The application of LSTM to fault identification and analysis is evaluated in the Tennessee Eastman benchmark process. Extensive experimental results show LSTM can better separate different faults and provide more promising fault diagnosis performance.

Normalized Cheeger Cut With Neighborhood Rough Approximation

A graph-based collecting study recently attracted significant attention from the scientific research community. Normalized Cheeger cut is a balanced graph partition criterion and a generalized version of normalized graph cut. A stress-free resolution of the normalized Cheeger cut can be obtained by employing the eigenvectors of curve p-Laplacian. However, it is highly sensitive for the original Cheeger cut to collect the interference of noise and disrelated properties. Thus, the performance of the Cheeger cut decreases when high-dimensional data are grouped. To decrease the negative influence of outliers and superfluous properties of collecting, we design an efficient attribute decrease method which is based on neighborhood rough approximation. This design aims to improve the collection of the Cheeger cut. The suggested algorithm introduces information entropy to the neighborhood rough sets in order to measure the importance of attributes. This algorithm reserves the most valuable features and removes the redundant features while retaining the maximum category information of raw data. We then build the p-Laplacian array with the optimized attribute sets and obtain the collecting consequences via the eigen-subspace decomposition of graph p-Laplacian. The cogency of the proposed algorithm is established in various standard data collections. Experimentations demonstrated that our method enjoys sturdy robustness to noise or disrelated feature information in high-dimensional figures.

A Computational-Based Method for Predicting Drug-Target Interactions by Using Stacked Autoencoder Deep Neural Network.

Identifying the interaction between drugs and target proteins is an important area of drug research, which provides a broad prospect for low-risk and faster drug development. However, due to the limitations of traditional experiments when revealing drug-protein interactions (DTIs), the screening of targets not only takes a lot of time and money but also has high false-positive and false-negative rates. Therefore, it is imperative to develop effective automatic computational methods to accurately predict DTIs in the postgenome era. In this article, we propose a new computational method for predicting DTIs from drug molecular structure and protein sequence by using the stacked autoencoder of deep learning, which can adequately extract the raw data information. The proposed method has the advantage that it can automatically mine the hidden information from protein sequences and generate highly representative features through iterations of multiple layers. The feature descriptors are then constructed by combining the molecular substructure fingerprint information, and fed into the rotation forest for accurate prediction. The experimental results of fivefold cross-validation indicate that the proposed method achieves superior performance on gold standard data sets (enzymes, ion channels, GPCRs [G-protein-coupled receptors], and nuclear receptors) with accuracy of 0.9414, 0.9116, 0.8669, and 0.8056, respectively. We further comprehensively explore the performance of the proposed method by comparing it with other feature extraction algorithms, state-of-the-art classifiers, and other excellent methods on the same data set. The excellent comparison results demonstrate that the proposed method is highly competitive when predicting drug-target interactions.

The Virtual IELab – an exercise in replicating part of the EXIOBASE V.2 production pipeline in a virtual laboratory

ABSTRACTWe explore options to replicate the EXIOBASE2 multi-region input–output (MRIO) database in the Virtual IELab cloud-computing laboratory environment. Whereas EXIOBASE2 is constructed using a multi-process reconciliation procedure, we present an alternative compilation technique that uses EXIOBASE2's pre-processed data and final tables in reconciling the IELab MRIO with conflicting raw data information. This approach skips the labour-intensive step of detailing and harmonising country tables. Adherence metrics reveal the EXIOBASE2-based IELab table to be considerably less balanced than the original but with stronger adherence to other constraints data. However, these metrics are not comparable to the original EXIOBASE2 statistics due to the distinctive implementation of constraint sets in the two platforms. IELab's main value-added is its flexibility in tailoring EXIOBASE2-based MRIOs beyond the original recipe. Finally, IELab's global carbon, water and material footprints are shown to be comparable with previously reported resource footprints. In contrast, deviations in land footprints warrant further investigation.

Multilinear Spatial Discriminant Analysis for Dimensionality Reduction

In the last few years, great efforts have been made to extend the linear projection technique (LPT) for multidimensional data (i.e., tensor), generally referred to as the multilinear projection technique (MPT). The vectorized nature of LPT requires high-dimensional data to be converted into vector, and hence may lose spatial neighborhood information of raw data. MPT well addresses this problem by encoding multidimensional data as general tensors of a second or even higher order. In this paper, we propose a novel multilinear projection technique, called multilinear spatial discriminant analysis (MSDA), to identify the underlying manifold of high-order tensor data. MSDA considers both the nonlocal structure and the local structure of data in the transform domain, seeking to learn the projection matrices from all directions of tensor data that simultaneously maximize the nonlocal structure and minimize the local structure. Different from multilinear principal component analysis (MPCA) that aims to preserve the global structure and tensor locality preserving projection (TLPP) that is in favor of preserving the local structure, MSDA seeks a tradeoff between the nonlocal (global) and local structures so as to drive its discriminant information from the range of the non-local structure and the range of the local structure. This spatial discriminant characteristic makes MSDA have more powerful manifold preserving ability than TLPP and MPCA. Theoretical analysis shows that traditional MPTs, such as multilinear linear discriminant analysis, TLPP, MPCA, and tensor maximum margin criterion, could be derived from the MSDA model by setting different graphs and constraints. Extensive experiments on face databases (ORL, CMU PIE, and the extended Yale-B) and the Weizmann action database demonstrate the effectiveness of the proposed MSDA method.

빅데이터의 효과적인 처리 및 활용을 위한 클라이언트-서버 모델 설계

빅데이터의 효과적인 처리 및 활용을 위한 클라이언트-서버 모델 설계

Multi-patch embedding canonical correlation analysis for multi-view feature learning

Locality-based feature learning for multi-view data has received intensive attention recently. As a result of only considering single-category local neighbor relationships, most of such the learning methods are difficult to well reveal intrinsic geometric structure information of raw high-dimensional data. To solve the problem, we propose a novel supervised multi-view correlation feature learning algorithm based on multi-category local neighbor relationships, called multi-patch embedding canonical correlation analysis (MPECCA). Our algorithm not only employs multiple local patches of each raw data to better capture the intrinsic geometric structure information, but also makes intraclass correlation features as close as possible by minimizing intraclass scatter of each view. Extensive experimental results on several real-world image datasets have demonstrated the effectiveness of our algorithm.

Keystone indices probabilistic species sensitivity distribution in the case of the derivation of water quality criteria for copper in Tai Lake.

An alternative method for species sensitivity distribution (SSD) that considers the interaction between species and the community importance is illustrated in this article. First, a food web based on the relationship between predator and prey was constructed, and the keystone indices of species were obtained based on the food web. Then, the probability density distribution of the sensitivity for each species was derived from all of the available endpoints of each species. Finally, the species sensitivity distribution for ecosystem was constructed by sampling a specific number of values from the probability density distribution of the sensitivity for each species. Data of copper toxicity to the aquatic organisms in Tai Lake were selected to derived site-specific water quality criteria (WQC). Ninety-seven endpoints of acute toxicity for 47 species and 188 endpoints of chronic toxicity for 29 species were included, and the acute and chronic WQC developed by keystone indices probabilistic species sensitivity distribution (K-PSSD) were 4.982μg/L and 0.965μg/L, respectively. Results showed that the aquatic organisms of Tai Lake might be underprotected. Compared with the SSD, the K-PSSD coped with the interactions between species, the community importance, and the intraspecies and interspecies variation more effectively and was better at depicting the tendency and information of raw data. The K-PSSD was especially applicable to site-specific WQC and provided an alternative or supplement to the SSD.