Search

Anomaly detection and state prediction research using multivariate data is being actively conducted in various industrial fields. However, since most dynamically operating industrial machines perform different operating conditions, they contain different types of abnormal conditions, making it difficult to detect anomalies and predict the remaining life. This white paper proposes a condition diagnosis model based on multi-sensor data prediction for estimating the remaining lifespan of equipment while solving two complex problems of detecting four typical abnormal conditions and sensor omissions of industrial machines. First, we use a multi-sensor data generation model to learn relationships between sensors, and second, we use a sensor data prediction model to learn sensor-specific feature information. In order to extract the temporal and spatial characteristics of sensing information and to derive the relationship between the sensors, we propose an attention model with three types of cases. Finally, the state of the device is diagnosed through the difference between the model predicted value and the actual value, and future state information of the device is predicted through the accumulation of error information. In order to prove the robustness of the proposed model, extensive experiments were conducted focusing on the case where sensor omission occurred due to data from equipment with more than 4 types and conditions. Our model produces missing sensor data with about 92% accuracy and detects anomalies with about 88% accuracy, even if parts of the sensor are missing or the operating environments have been changed. The proposed model has improved anomaly detection accuracy compared to the comparative model, and has been proven to be applicable to real industrial problems. [ABSTRACT FROM AUTHOR]

Existing carbon price decomposition methods make effective predictions, promote energy saving and emission reduction, and play an increasingly important role in carbon trading platforms. However, there have been limited studies on reorganization methods and different perspectives for treating decomposition components. In this paper, we introduce a novel component fusion method and develop a hierarchical carbon price prediction model with two levels: a local perspective and an overall perspective. Firstly, the carbon price data are decomposed and the resulting components are subjected to deviation sample entropy fusion, which classifies them into high, medium, and low frequencies according to the physical significance of the entropy values. Next, fine-grained predictions are conducted for the high, medium, and low frequency components, forming the local layer. Subsequently, the decomposition error correction is proposed to obtain the data of the overall layer, and a secondary decomposition of this data is done. Finally, the prediction values from the two levels are summed to obtain the final prediction results. Experimental results from three markets, Guangdong, Tianjin, and Beijing, demonstrate that the proposed fusion method can directly identify the optimal component reorganization scheme, and the model prediction ability is better than the conventional secondary decomposition model. [ABSTRACT FROM AUTHOR]

Dilution effects should be considered in the estimated model of deposit due to its significant impact on feasibility studies, mine planning and scheduling, milling, and stockpiling. This work compares the capacity of two approaches for modelling dilution of intrusive barren dykes into the ore body in a copper deposit. Two approaches were used to generate an undiluted model of copper grade in a copper deposit, which is cross cut by intrusive dykes. The results demonstrated that the second approach is more advantageous in comparison with the first approach, especially when there is hard contact between the ore and barren dykes. [ABSTRACT FROM AUTHOR]

Rockburst is a complex destabilization phenomenon which is a combination of multiple factors, the study of rockburst for classification prediction can help prevent and control engineering geological hazards, reduce casualties and property damage. To achieve efficient and accurate rockburst classification prediction and solve the problem of rockburst propensity assessment, six evaluation factors are selected as the rock explosion prediction and evaluation system: tangential stress $\sigma _{\theta }$ , uniaxial compressive strength $\sigma _{\mathrm {c}}$ , uniaxial tensile strength $\sigma _{\mathrm {t}}$ , tangential stress to uniaxial compressive strength ratio $\sigma _{\mathrm {\theta }}/\sigma _{\mathrm {c}}$ (BCF), uniaxial compressive strength to tensile strength ratio $\mathrm {\sigma }_{\mathrm {c}}/\sigma _{\mathrm {t}}$ (SCF), and elastic deformation energy index $\mathrm {W}_{\mathrm {et}}$ in this study. Widely collected domestic and international groups of rock explosion evaluation data, and 420 sets of valid samples were obtained by data processing. Establish rockburst grading prediction evaluation models based on BP neural networks and support vector machines respectively, then establish BP-SVM prediction models based on arithmetic mean weights and standard deviation weights, analyzing and comparing the prediction rating results of 120 groups of samples among them. Accuracy, Precision, Recall, Specificity, and F1 Score metrics are selected to evaluate the performance of different models, the results show that several models can obtain effective prediction results, among which the standard deviation weight combination BP-SVM model proposed in this paper has the best prediction accuracy and the best effect, which is better than the traditional single machine learning method.

Rock burst disasters occurring in underground high-stress rock mass mining and excavation engineering seriously threaten the safety of workers and hinders the progress of engineering construction. Rock burst classification prediction is the basis of reducing and even eliminating rock burst hazards. Currently, most of mainstream discriminant models for rock burst grade prediction are based on small samples. Comprehensive selection according to many pieces of literature, the maximum tangential stress of surrounding rock and rock uniaxial compressive strength ratio coefficient (stress state parameter), rock uniaxial compressive strength and uniaxial tensile strength ratio (brittleness modulus), and the elastic energy index are used as a grading evaluation index of rock burst based on the collection of different construction engineering instances of rock burst in 114 groups of extensive sample data in different regions of the world, which are used to carry out the training study. The representativeness and accuracy of the index selection were verified by the indicator variance analysis and Spearman correlation coefficient hypothesis test. The Intelligent Rock burst Identification System (IRIS) based on an optimizable SVM model was established using data set samples. After extensive data cross-validation training, the accuracy of the SVM discriminant analysis model can reach 95.6%, which is significantly better than the prediction accuracy of the traditional SVM model of 71.9%. The model is used to classify and predict the rock burst intensity of 10 typical projects at home and abroad. The prediction results are consistent with the actual rock burst intensity, which is better than the discriminant model based on small sample data and other existing prediction models. The application of engineering examples shows that the results of the rock burst intensity classification prediction model based on extensive sample data processing analysis and the SVM discriminant method are in good agreement with the actual rock burst intensity, which can effectively provide a reference for the prediction of rock burst intensity grade in a construction area. [ABSTRACT FROM AUTHOR]

With the proliferation of Internet-of-Things and continuous growth in the number of web services at the Internet-scale, the service recommendation is becoming a challenge nowadays. One of the prime aspects influencing the service recommendation is the Quality-of-Service (QoS) parameter, which depicts the performance of a web service. In general, the service provider furnishes the value of the QoS parameters before service deployment. However, in reality, the QoS values of service vary across different users, time, locations, etc. Therefore, estimating the QoS value of service before its execution is an important task, and thus, the QoS prediction has gained significant research attention. Multiple approaches are available in the literature for predicting service QoS. However, these approaches are yet to reach the desired accuracy level. In this article, we study the QoS prediction problem across different users, and propose a novel solution by taking into account the contextual (more specifically, location) information of both services and users. Our proposal includes two key steps: (a) hybrid filtering, and (b) hierarchical prediction mechanism. On the one hand, the hybrid filtering aims to obtain a set of similar users and services, given a target user and a service. On the other hand, the goal of the hierarchical prediction mechanism is to estimate the QoS value accurately by leveraging hierarchical neural-regression. We evaluated our framework on the publicly available WS-DREAM datasets. The experimental results show the outperformance of our framework over the major state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) video contains plentiful multi-domain correlations, including spatial, temporal, and inter-view correlations. In this paper, a deep multi-domain prediction method is proposed for 3D video coding. Different from previous methods, our proposed method utilizes not only spatial and temporal correlations but also inter-view correlation to obtain a more accurate prediction, and adopts deep convolutional neural networks to effectively fuse multi-domain references. More specifically, a hierarchical prediction mechanism, which includes a spatial-temporal prediction network and a multi-domain prediction network, is designed to overcome the fusion difficulty of multi-domain reference information. Furthermore, a progressive spatial-temporal prediction network and a multi-scale multi-domain prediction network are designed to obtain the spatial-temporal prediction result and multi-domain prediction result respectively. Experimental results show that the proposed method achieves considerable bitrate saving compared with 3D-HEVC. [ABSTRACT FROM AUTHOR]

Exploring neural markers that predict trust behavior may help us to identify the cognitive process underlying trust decisions and to develop a new approach to promote interpersonal trust. It remains unknown how trust behavior may be predicted early in the decision process. We used electrophysiology to sample the brain activity while participants played the role of trustor in an iterative trust game. The results showed that during the trust generation stage, the trust condition led to higher frontocentral beta band activity related to cognitive inhibition compared to the distrust condition (item level). Moreover, individuals with higher frontocentral beta band activity were more likely to perform trust choices at the single-trial level (individual level). Furthermore, after receiving reciprocity feedback on trialn-1, compared to the betrayal feedback and the distrust choice, the frontocentral beta band oscillation had a stronger predictive effect regarding trust choices on trialn. These findings indicate that beta band oscillations during the decision generation stage contribute to subsequent trust choices. [ABSTRACT FROM AUTHOR]

The research field of reconstructing 3D models from 2D images is becoming more and more important. Existing methods typically perform single-view reconstruction or multi-view reconstruction utilizing the properties of recurrent neural networks. Due to the self-occlusion of the model and the special nature of the recurrent neural network, these methods have some problems. We propose a novel three-dimensional fusion hierarchical reconstruction method that utilizes a multi-view feature combination method and a hierarchical prediction strategy to unify the single view and any number of multiple views 3D reconstructions. Experiments show that our method can effectively combine features between different views and obtain better reconstruction results than the baseline, especially in the thin parts of the object. Our source code is available at https://github.com/VIM-Lab/3D-FHNet.

This paper treated the task of social media emoji prediction as a text classification problem, and mapped the input text to the most likely accompanying emojis. Firstly, it proposed an attention mechanism based on hashtags, posting users, posting time, and posting location by studying the relation between emojis and hashtags appearing in the posts. Secondly, it added the emoji position feature. Finally, it discussed the attention mechanism and hierarchical model for the role of emoji prediction task, and trained the various models to compare their prediction effects. The experimental results show that the model has significant improvement on the prediction effect of emojis with different frequency of use. The model is feasible and efficient. [ABSTRACT FROM AUTHOR]

Onboard image processing systems for a hyperspectral sensor have been developed in order to maximize image data transmission efficiency for large volume and high speed data downlink capacity. Since more than 100 channels are required for hyperspectral sensors on Earth observation satellites, fast and small-footprint lossless image compression capability is essential for reducing the size and weight of a sensor system. A fast lossless image compression algorithm has been developed, and is implemented in the onboard correction circuitry of sensitivity and linearity of Complementary Metal Oxide Semiconductor (CMOS) sensors in order to maximize the compression ratio. The employed image compression method is based on Fast, Efficient, Lossless Image compression System (FELICS), which is a hierarchical predictive coding method with resolution scaling. To improve FELICS’s performance of image decorrelation and entropy coding, we apply a two-dimensional interpolation prediction and adaptive Golomb-Rice coding. It supports progressive decompression using resolution scaling while still maintaining superior performance measured as speed and complexity. Coding efficiency and compression speed enlarge the effective capacity of signal transmission channels, which lead to reducing onboard hardware by multiplexing sensor signals into a reduced number of compression circuits. The circuitry is embedded into the data formatter of the sensor system without adding size, weight, power consumption, and fabrication cost.

A recent study decomposed the changes in industrial water use into three hierarchies (output, technology, and structure) using a refined Laspeyres decomposition model, and found monotonous and exclusive trends in the output and technology hierarchies. Based on that research, this study proposes a hierarchical prediction approach to forecast future industrial water demand. Three water demand scenarios (high, medium, and low) were then established based on potential future industrial structural adjustments, and used to predict water demand for the structural hierarchy. The predictive results of this approach were compared with results from a grey prediction model (GPM (1, 1)). The comparison shows that the results of the two approaches were basically identical, differing by less than 10%. Taking Tianjin, China, as a case, and using data from 2003-2012, this study predicts that industrial water demand will continuously increase, reaching 580 million m³, 776.4 million m³, and approximately 1.09 billion m³ by the years 2015, 2020 and 2025 respectively. It is concluded that Tianjin will soon face another water crisis if no immediate measures are taken. This study recommends that Tianjin adjust its industrial structure with water savings as the main objective, and actively seek new sources of water to increase its supply. [ABSTRACT FROM AUTHOR]

In a multi-resolution image encoding system, the image is encoded into a single file as a layer of bit streams, and then it is transmitted layer by layer progressively to reduce the transmission time across a low bandwidth connection. This encoding scheme is also suitable for multiple decoders, each with different capabilities ranging from a handheld device to a PC. In our previous work, we proposed an edge adaptive hierarchical interpolation algorithm for multi-resolution image coding system. In this paper, we enhanced its compression efficiency by adding three major components. First, its prediction accuracy is improved using context adaptive error modeling as a feedback. Second, the conditional probability of prediction errors is sharpened by removing the sign redundancy among local prediction errors by applying sign flipping. Third, the conditional probability is sharpened further by reducing the number of distinct error symbols using error remapping function. Experimental results on benchmark data sets reveal that the enhanced algorithm achieves a better compression bit rate than our previous algorithm and other algorithms. It is shown that compression bit rate is much better for images that are rich in directional edges and textures. The enhanced algorithm also shows better rate-distortion performance and visual quality at the intermediate stages of progressive image transmission. [ABSTRACT FROM AUTHOR]

[Display omitted] • Geological domains often control the grade distribution in ore deposits. • Diagnosing the nature of geological boundaries is essential to predict grades. • Three approaches to predict grades in the presence of soft boundaries are compared. • An application to a porphyry copper deposit is presented. • Simulated grade models allow accurately assessing in-situ and recoverable resources. The incorporation of geological controls is essential for an accurate assessment of the in-situ and recoverable resources in an ore deposit, directly impacting the downstream stages of mining projects. Commonly, the mineral resources evaluation is carried out hierarchically, considering the definition of geological domains first and then predicting or simulating the metal grades within each domain. Nevertheless, this approach assumes a weak correlation between the metal grades across the domain boundaries, which could not be suitable when gradual variations of the grades are observed across these boundaries. To account for the latter scenario known as soft boundaries, we compare three approaches: (i) a hierarchical prediction of the geological domain indicators and the grade within each domain, (ii) a direct prediction of partial grades, defined as the product of the grade and a geological domain indicator, and (iii) a joint simulation of the grade and geological domain indicators. A porphyry copper deposit in which the copper grade is controlled by mineralogical and rock type domains is used as a case study. When compared with production data, the proposed approaches generate more precise predictions than the traditional approach consisting in accounting for the hard boundaries between mineralogical domains but ignoring the soft boundaries between rock types. The joint simulation approach provides more realistic grade variations across the rock type boundaries, allows for an unbiased prediction of the recoverable resources, and quantifies the uncertainty on these resources based on multiple grade outcomes. Ultimately, we emphasize that identifying the geological controls and the nature (hard or soft) of the geological boundaries, and then defining the proper approaches to account for them is necessary to accurately assess the in-situ and recoverable resources. [ABSTRACT FROM AUTHOR]

Abstract: Multimedia design such as video decoders are typically composed of several communicating tasks. Each task is characterized by its workload variation. The target device of this kind of application contains several processing unit. This calls for a dynamic management of hardware units to improve the QOS of the application and to optimally allocate resources. In this paper, we propose a new architecture based on hierarchical multilevel neural network to model workload variation of each task. The hierarchical structure of this neural network perfectly describes the multilevel decomposition of each hardware unit. The aim of this investigation is to build a design with a control unit that manages the architecture and resource allocation according to the neural network workload prediction. [Copyright &y& Elsevier]

We propose a new hierarchical approach to resolution scalable lossless and near-lossless (NLS) compression. It combines the adaptability of DPCM schemes with new hierarchical oriented predictors to provide resolution scalability with better compression performances than the usual hierarchical interpolation predictor or the wavelet transform. Because the proposed hierarchical oriented prediction (HOP) is not really efficient on smooth images, we also introduce new predictors, which are dynamically optimized using a least-square criterion. Lossless compression results, which are obtained on a large-scale medical image database, are more than 4% better on CTs and 9% better on MRIs than resolution scalable JPEG-2000 (J2K) and close to nonscalable CALIC. The HOP algorithm is also well suited for NLS compression, providing an interesting rate–distortion tradeoff compared with JPEG-LS and equivalent or a better PSNR than J2K for a high bit rate on noisy (native) medical images. [ABSTRACT FROM PUBLISHER]