Early diagnosis and treatment of inherited metabolic diseases (IMDs) is crucial for reducing neonatal mortality rate and improving quality of life in children. The discovery of disease-related biomarkers that can obje...
详细信息
Early diagnosis and treatment of inherited metabolic diseases (IMDs) is crucial for reducing neonatal mortality rate and improving quality of life in children. The discovery of disease-related biomarkers that can objectively measure the potential pathophysiological changes is vital to improve the prognosis of IMDs. In this study, we collected 90 clinic urine samples of newborns, including two types of IMDs and healthy samples, glutaric aciduria type I (GA I) and propionic acidemia (PA). And 132 metabolites were identified using gas chromatography-mass spectrometry (GC-MS). Then we proposed an integrated chemometrics strategy of assembling discrete particle swarm optimization (DPSO) into stacked autoencoder (SAE) to form a framework called DPSO-SAE for the study of GC-MS metabolomics data. SAE was known for its excellent non-linear feature learning ability. The intro-duction of DPSO afforded SAE the possibility of biomarker discovery and improving performance on classifi-cation via enabling synergetic optimization of variable combinations and the parameter of neuron numbers for SAE modeling. We then invoked DPSO-SAE for the data analysis as compared with random forest (RF), partial least squares discriminant analysis (PLSDA) and conventional SAE. Superior performance was obtained by DPSO-SAE with high accuracy and good generalization ability on classification. We further demonstrated the robust-ness of DPSO-SAE in variable selection and proofed the statistical significance of identified marker metabolites that account for IMD classification. Six potential biomarkers were proofed, including 3-methylglutaconic, 3-OH-propionic, Methylcitric, Methylmalonic and Uric for PA and Glutaric for GA I. All results indicated that the proposed strategy of DPSO-SAE was feasible for robust classification and biomarker discovery of IMDs. And it may provide a valuable modeling algorithm for metabolomics studies.
Cumulative studies have shown that many long non -coding RNAs (lncRNAs) are crucial in a number of diseases. Predicting potential IncRNA-disease associations (LDAs) can facilitate disease prevention, diagnosis and tre...
详细信息
Cumulative studies have shown that many long non -coding RNAs (lncRNAs) are crucial in a number of diseases. Predicting potential IncRNA-disease associations (LDAs) can facilitate disease prevention, diagnosis and treatment. Therefore, it is vital to develop practical computational methods for LDA prediction. In this study, we propose a novel predictor named capsule network (CapsNet)-LDA for LDA prediction. CapsNet-LDA first uses a stacked autoencoder for acquiring the informative low -dimensional representations of the IncRNA-disease pairs under multiple views, then the attention mechanism is leveraged to implement an adaptive allocation of importance weights to them, and they are subsequently processed using a CapsNet-based architecture for predicting LDAs. Different from the conventional convolutional neural networks (CNNs) that have some restrictions with the usage of scalar neurons and pooling operations. the CapsNets use vector neurons instead of scalar neurons that have better robustness for the complex combination of features and they use dynamic routing processes for updating parameters. CapsNet-LDA is superior to other five state-of-the-art models on four benchmark datasets, four perturbed datasets and an independent test set in the comparison experiments, demonstrating that CapsNet-LDA has excellent performance and robustness against perturbation, as well as good generalization ability. The ablation studies verify the effectiveness of some modules of CapsNet-LDA. Moreover, the ability of multi -view data to improve performance is proven. Case studies further indicate that CapsNet-LDA can accurately predict novel LDAs for specific diseases.
The evolution of new trends in the automobile industry is creating more comfortable and convenient means of transportation. But still there exist manifold challenges in detecting legal and illegal drivers;therefore, e...
详细信息
The evolution of new trends in the automobile industry is creating more comfortable and convenient means of transportation. But still there exist manifold challenges in detecting legal and illegal drivers;therefore, evaluating the behaviors of drivers needs to be addressed. Taking these into consideration his paper proposes a novel cascade region convolutional neural network-based circulatory system optimization algorithm (CRCNN++ based CSO) to attain optimal multitask framework which includes behavior evaluation, identity authentication of drivers, vehicle diagnosis as well as estimating the fault of the vehicle. In this paper, two diverse naturalistic driving behavior public datasets namely HCRL and UAH drive datasets are collected and pre-processed via normalization as well as scaling process. The preprocessed feature is then extracted and the dimensions are minimized using the stacked autoencoder technique. The CRCNN++-based CSO is employed in determining to multitask which includes identity authentication, behavioral evaluation, vehicle diagnosis, and faults estimation is performed. Finally, the efficiency of the proposed CRCNN++-based CSO method is analyzed by evaluating various metrics namely receiver operating characteristic curve, accuracy, false positive rate, precision, Cohen Kappa score, true positive rate, and F1-Score. The comparative analysis is carried out for various existing techniques and the proposed approach. From the evaluation results, it is revealed that the proposed CRCNN++-based CSO approach delivers better performance in driver identification through driving style behavior.
Choosing appropriate scenarios is critical for autonomous vehicles (AVs) safety testing. Real-world crash scenarios can be used as critical scenarios to test the safety performance of AVs. As one of the dominant types...
详细信息
Choosing appropriate scenarios is critical for autonomous vehicles (AVs) safety testing. Real-world crash scenarios can be used as critical scenarios to test the safety performance of AVs. As one of the dominant types of traffic crashes, the car to powered-two-wheelers (PTWs) crash results in a higher possibility of fatality than ordinary car-to-car crashes. Generally, typical testing scenarios are chosen according to the subjective understanding of the safety experts with limited static features of crashes (e.g., geometric features, weather). This study introduced a novel method to identify typical car-to-PTWs crash scenarios based on real-world crashes with dynamic pre-crash features investigated from the China In-depth Mobility Safety Study-Traffic Accident (CIMSSTA) database. First, we present crash data collection and construction methods of the CIMSS-TA database to construct testing scenarios. Second, the stacked autoencoder methods are used to learn and obtain embedded features from the high-dimensional data. Third, the extracted features are clustered using k-means clustering algorithm, and then the clustering results are interpreted. Six typical car-to-PTWs scenarios are obtained with the proposed processes. This study introduces a typical high-risk scenario construction method based on deep embedded clustering. Unlike existing researches, the proposed method eliminates the negative impacts of manually selecting clustering variables and provides a more detailed scenario description. As a result, the typical scenarios obtained from AV testing are more robust.
This study explores the important problem of urban traffic congestion, focusing on the challenges that emergency vehicles encounter. Existing traffic management systems frequently fail to efficiently prioritize emerge...
详细信息
Accurate micro-crack detections on the whole surface of civil structures have great significance. Distributed optical fiber sensor based on Brillouin optical time-domain analysis technology exhibits great facility to ...
详细信息
Accurate micro-crack detections on the whole surface of civil structures have great significance. Distributed optical fiber sensor based on Brillouin optical time-domain analysis technology exhibits great facility to measure strain distributions along the whole surface of structures with a high spatial resolution, thus providing a potential and competitive solution to the detection problem. However, mainly due to low signal-to-noise ratio in measurements, such sensor system is still limited in crack detection-based structural health monitoring applications. How to extract high-quality micro-crack feature representations from the low signal-to-noise ratio-distributed strain measurements is crucial to solve the problem. It has been demonstrated in field of pattern recognition that deep learning can automatically extract high-quality noise-robust feature representations from mass chaos data. Therefore, a micro-crack detection method is proposed herein based on deep learning to analyze the full-scale strain measurements. Each measurement is normalized and segmented into a set of equal-length subsequences. autoencoders, a typical kind of building block of deep neural network, are stacked layer-wise into a deep network and then exploited to automatically extract feature representations from the subsequences. Each extracted feature representation is labeled as one of the two categories by a Softmax regression. One category originates in the subsequences acquired from structure sections with crack defects and another from sections without any cracks. The micro-crack detections are achieved by solving such a crack/non-crack binary classification problem. A 15-m-long steel I-beam with artifact crack defects is built up in laboratory to verify the proposed method. Experimental results demonstrate that the minimum size of detectable crack opening width reaches to 23 mu m, and besides, the proposed method is significantly better than traditional Fisher linear discriminant analys
The unmanned combat aerial vehicle(UCAV)is a research hot issue in the world,and the situation assessment is an important part of *** overcome shortcomings of the existing situation assessment methods,such as low accu...
详细信息
The unmanned combat aerial vehicle(UCAV)is a research hot issue in the world,and the situation assessment is an important part of *** overcome shortcomings of the existing situation assessment methods,such as low accuracy and strong dependence on prior knowledge,a datadriven situation assessment method is *** clustering and classification are combined,the former is used to mine situational knowledge,and the latter is used to realize rapid *** evaluation factor and distance evaluation factor are proposed to transform multi-dimensional air combat information into two-dimensional features.A convolution success-history based adaptive differential evolution with linear population size reduc-tion-means(C-LSHADE-Means)algorithm is *** convolutional pooling layer is used to compress the size of data and preserve the distribution *** LSHADE algorithm is used to initialize the center of the mean clustering,which over-comes the defect of initialization *** experi-ment with the seven clustering algorithms is done on the UCI data set,through four clustering indexes,and it proves that the method proposed in this paper has better clustering performance.A situation assessment model based on stacked autoen-coder and learning vector quantization(SAE-LVQ)network is constructed,and it uses SAE to reconstruct air combat data fea-tures,and uses the self-competition layer of the LVQ to achieve efficient *** with the five kinds of assess-ments models,the SAE-LVQ model has the highest ***,three kinds of confrontation processes from air combat maneuvering instrumentation(ACMI)are selected,and the model in this paper is used for situation *** assessment results are in line with the actual situation.
anomaly detection of gateway electrical energy metering device is important for maintenance and operations in the power systems. Traditionally, anomaly detection was typically performed manually through the analysis o...
详细信息
anomaly detection of gateway electrical energy metering device is important for maintenance and operations in the power systems. Traditionally, anomaly detection was typically performed manually through the analysis of the collected energy information. However, the manual process is time-consuming and labor-intensive. In this condition, this paper proposes a hybrid deep-learning model, which integrates stacked intelligently detecting the abnormal events of gateway electrical energy metering device. The proposed model named SAE-LSTM model, first uses SAE to extract deep latent features of threephase voltage data collected from the gateway electrical energy metering device, and then adopts LSTM for separating the abnormal events based on the extracted deep latent features. The SAE-LSTM model, can effectively highlight the temporal information of the electrical data, thereby enhancing the accuracy of anomaly detection. The simulation experiments verify the advantages of the SAE-LSTM model in anomaly detection under different signal-to-noise ratios. The experimental results of real datasets demonstrate that it is suitable for anomaly detection of gateway electrical energy metering devices in practical scenarios.
In the era of Big data,learning discriminant feature representation from network traffic is identified has as an invariably essential task for improving the detection ability of an intrusion detection system(IDS).Owin...
详细信息
In the era of Big data,learning discriminant feature representation from network traffic is identified has as an invariably essential task for improving the detection ability of an intrusion detection system(IDS).Owing to the lack of accurately labeled network traffic data,many unsupervised feature representation learning models have been proposed with state-of-theart ***,these models fail to consider the classification error while learning the feature ***,the learnt feature representation may degrade the performance of the classification *** the first time in the field of intrusion detection,this paper proposes an unsupervised IDS model leveraging the benefits of deep autoencoder(DAE)for learning the robust feature representation and one-class support vector machine(OCSVM)for finding the more compact decision hyperplane for intrusion ***,the proposed model defines a new unified objective function to minimize the reconstruction and classification error *** unique contribution not only enables the model to support joint learning for feature representation and classifier training but also guides to learn the robust feature representation which can improve the discrimination ability of the classifier for intrusion *** set of evaluation experiments are conducted to demonstrate the potential of the proposed ***,the ablation evaluation on benchmark dataset,NSL-KDD validates the design decision of the proposed ***,the performance evaluation on recent intrusion dataset,UNSW-NB15 signifies the stable performance of the proposed ***,the comparative evaluation verifies the efficacy of the proposed model against recently published state-of-the-art methods.
In process monitoring based on stacked autoencoders (SAEs), the performance of monitoring models is directly decided by the validity of the structure and parameters, which are primarily determined by time-consuming ma...
详细信息
In process monitoring based on stacked autoencoders (SAEs), the performance of monitoring models is directly decided by the validity of the structure and parameters, which are primarily determined by time-consuming manual adjustments. This paper presents a novel method that can adaptively select parameters rather than tuning them manually. The proposed method is called adaptive parameter tuning SAE (APT-SAE). Basic SAEs aim to compress the original input data and extract simple and abstract features. Thus, the redundant information of each hidden layer output should be as small as possible. The next layer of nodes can be remarkably reduced if the amount of redundant information is large. During the pre-training stage of APT-SAE, an adaptive parameter tuning strategy is used for rapidly determining the number of layers and nodes in the paper. The cross-covariance of each AE's input data is used to determine the node number of succeeding AE. The pre-training stage ends when the correlation is weak, which is decided by the average value of cross-variance matrix. The proposed method is applied to a benchmark problem, and it outperforms several state-of-the-art methods.
暂无评论