Search

Abstract Social image data refer to the annotated image with tags in social media, in which the tags are always labeled by users. Integrating the visual and textual information of social image can obtain accurate and comprehensive feature and improve clustering performance. However, the heterogeneous gap between tags and images makes it difficult to reasonably organize the social images. In addition, the tags are often sparse and incomplete due to personal preference and cognition differences of users. To solve these problems, we propose a novel knowledge-aware progressive clustering (KAPC) method, which employs human knowledge to guide the cross-modal clustering of social images. Firstly, we design a dual-similarity semantic expansion strategy to complement the sparse tags with human knowledge, which constructs a more complete semantic similarity matrix for tags through knowledge graphs. Secondly, we define an objective function based on information theory to bridge the heterogeneous gap, which align inter-modal cluster distribution to explore the correlation between visual and textual information. Finally, a progressive iteration method is designed to make the two modalities guide each other and obtain better performance of social image clustering. Extensive experiments on four social image datasets verify the effectiveness of the proposed KAPC method.

Vibration in hot tandem rolling mills has been a problem in the iron and steel industry mainly due to its unpredictability. In this work, vibration data of the second finishing mill (F2) stand of a hot tandem rolling mill are collected and analyzed, and a mathematical model based on the coupling of a non-uniform deformation process, mill structure and hydraulic control system is constructed. The influence of different inlet thickness fluctuation forms, structural parameters and control parameters on the vibration behavior is analyzed. It is concluded that the low-frequency thickness fluctuation with additional skewness can cause the resonance of each subsystem of the rolling mill. The deviation angle of the roll system influences the vibration harmonic output of the rolling mill under a single low-frequency thickness fluctuation excitation. The compensation parameter in the thickness control system affects the natural frequency of the vertical system.

As one of common malignancies, prostate adenocarcinoma (PRAD) has been a growing health problem and a leading cause of cancer-related death. To obtain expression and functional relevant RNAs, we firstly screened candidate hub mRNAs and characterized their associations with cancer. Eight deregulated genes were identified and used to build a risk model (AUC was 0.972 at 10 years) that may be a specific biomarker for cancer prognosis. Then, relevant miRNAs and lncRNAs were screened, and the constructed primarily interaction networks showed the potential cross-talks among diverse RNAs. IsomiR landscapes were surveyed to understand the detailed isomiRs in relevant homologous miRNA loci, which largely enriched RNA interaction network due to diversities of sequence and expression. We finally characterized TK1, miR-222-3p and SNHG3 as crucial RNAs, and the abnormal expression patterns of them were correlated with poor survival outcomes. TK1 was found synthetic lethal interactions with other genes, implicating potential therapeutic target in precision medicine. LncRNA SNHG3 can sponge miR-222-3p to perturb RNA regulatory network and TK1 expression. These results demonstrate that TK1:miR-222-3p:SNHG3 axis may be a potential prognostic biomarker, which will contribute to further understanding cancer pathophysiology and providing potential therapeutic targets in precision medicine.

The Notch signaling has an important role in multiple cellular processes and is related to carcinogenic process. To understand the potential molecular features of the crucial Notch pathway, a comprehensive multi-omics analysis is performed to explore its contributions in cancer, mainly including analysis of somatic mutation landscape, pan-cancer expression, ncRNA regulation and potential prognostic power. The screened 22 Notch core genes are relative stable in DNA variation. Dynamic expression patterns are associated with the Notch activity, which are mainly regulated by multiple ncRNAs via interactions of ncRNA:mRNA and ceRNA networks. The Notch pathway shows a potential prognostic ability through integrating multi-omics features as well as their targets, and it is correlated with immune infiltration and maybe available drug targets, implying the potential role in individualized treatment. Collectively, all of these findings contribute to exploring crucial role of the key pathway in cancer pathophysiology and gaining mechanistic insights into cross-talks among RNAs and biological pathways, which indicates the possible application of the well-conserved Notch signaling pathway in precision medicine.

Abstract Simultaneous localization and mapping (SLAM) addresses the problem of constructing the map from noisy sensor data and tracking the robot's path within the built map. After decades of development, a lot of mature systems achieve competent results in feature‐based implementations. However, there are still problems when migrating the technology to practical applications. One typical example is the accuracy and robustness of SLAM in environment with illuminance and texture variations. To this end, two modules in the existing systems are improved here namely tracking and camera relocalization. In tracking module, image pyramid is processed with Laplacian of Gaussian (LoG) operator in feature extraction for enhanced edges and details. A majority voting mechanism is proposed to dynamically evaluate and redetermine the zero‐mean sum of square difference threshold according to the matching error estimation in patch search. In camera relocalization module, full convolutional neural network which focuses on certain parts of the input data is utilized in guiding for accurate output predictions. The authors implement the two modules into OpenvSLAM and propose a neural guided visual SLAM system named LoG‐SLAM. Experiments on publicly available datasets show that the accuracy and efficiency increase with LoG‐SLAM when compared with other feature‐based methods, and relocalization accuracy also improves compared with the recently proposed deep learning pipelines.

Recently, the cross-modal analysis has drawn much attention due to the rapid growth and widespread emergence of multimodal data. It integrates multiple modalities to improve learning and generalization performance. However, most previous methods just focus on learning a common shared feature space for all modalities and ignore the private information hidden in each individual modality. To address this problem, we propose a novel shared-private information bottleneck (SPIB) method for cross-modal clustering. First, we devise a hybrid words model and a consensus clustering model to construct the shared information of multiple modalities, which capture the statistical correlation of low-level features and the semantic relations of the high-level clustering partitions, respectively. Second, the shared information of multiple modalities and the private information of individual modalities are maximally preserved through a unified information maximization function. Finally, the optimization of SPIB function is performed by a sequential “draw-and-merge” procedure, which guarantees the function converges to a local maximum. Besides, to solve the lack of tags in cross-modal social images, we also investigate the use of structured prior knowledge in the form of knowledge graph to enrich the information in semantic modality and design a novel semantic similarity measurement for social images. The experimental results on four types of cross-modal datasets demonstrate that our method outperforms the state-of-the-art approaches.

An image can be described in terms of appearance frequency of visual words. This representation is implemented in bag-of-visual-words (BoVW)-based loop closure detection for its efficiency and effectiveness. However, traditional BoVW-based approaches are strongly affected by false positive loops due to scene ambiguity caused by redundant words in the vocabulary and fail to detect bidirectional loops in monocular mode. Aiming at overcoming these problems, we propose a novel vocabulary construction algorithm named hierarchical sequential information bottleneck (HsIB) by leveraging the maximization of mutual information (MMI) mechanism. First, feature descriptors are extracted from training images for visual vocabulary construction. Second, HsIB extracts discriminative yet informative visual words through the MMI mechanism in vocabulary construction, which treats feature descriptors clustering as a process of data compression. Finally, the clustering process reaches a tradeoff between compactness and discrimination and improves the performance of traditional BoVW-based loop closure detection. The proposed method is compared with state-of-the-art methods on publicly available datasets. We also create a challenging dataset to further evaluate the performance of HsIB on bidirectional loops. To the best of our knowledge, we are the first to implement information bottleneck (IB) method in visual-SLAM (vSLAM) loop closure detection, and we obtain impressive results.

Three-dimensional reconstruction of abdominal aortic aneurysm is the key technology to improve the success rate of surgical and reduce complications. However, the outer contour of abdominal aortic aneurysm(AAA)is fuzzy, which make it difficult for recent existing method to obtain its accurate segmentation performance and high reconstruction accuracy. In this paper, an improved compressive sensing reconstruction algorithm is proposed, which defines a differentiable and convex total variation (TV) function as an optimization goal function and further reduces the number of projections and improve the quality of reconstructed images. Our proposed algorithm improves the speed and stability of the reconstruction algorithm in three-dimensional reconstruction of abdominal aortic aneurysm. The experimental results show that the proposed model can be used for 3D modeling in 3-D printing to improve the accuracy of endovascular repair and the adaptability of the stent, which is suitable for the application of bioengineering medicine.

Rolling mills vibration is a key factor that hinders the production of thin-strip steel. Currently, vibration is mainly suppressed by adjusting rolling mill parameters which is not a common approach. Due to special working conditions, the information of work roll, such as displacement and velocity, cannot be directly measured. Therefore, based on extended state observer, new resonance ratio control method, which is a common approach, is proposed to suppress the rolling mill vibration. First, the equivalent mass of the back roll is identified. Then, the interaction force between the work roll and the back roll and the velocity of the back roll are estimated using the extended state observer. Finally, these values are introduced into the input of the servo valve to compensate. The simulation results indicate that vibrations of both the work roll and the back roll are suppressed, and this method has a great tolerance for the identification error of the back-roll equivalent mass, and extended state observer compensation possesses a more superior vibration suppression than disturbance observer compensation.

The torque of the main drive system is one of the most important force and energy parameters of the rolling mill, and the strain type torque online telemetry system is a practical method for measuring torque parameters. The strain gauges and transmitters on the rotating shaft are driven by a high-frequency induction power system. Their installation, debugging, and maintenance are cumbersome, and their very low power transmission efficiency (PTE) has become a challenging problem for online telemetry systems. In this paper, a magnetic coupling resonant wireless power supply method is utilized to replace the high-frequency induction power supply. Through theoretical and experimental research, it is concluded that the magnetically coupled resonant wireless power supply method can realize long-distance power supply, overcoming many shortcomings of the high-frequency induction power supply system. In the laboratory, a maximum PTE of 83.7% is obtained for a transmission distance of 50 mm. Under the influence of environmental factors common for the transmission shaft of a rolling mill, the PTE decreases by 34%, but normal operation of the system can be achieved by adjusting the compensation capacitance. The proposed system provides a guarantee for a long-term stable power supply on the measured axis of a rolling mill torque online telemetry system.

In this paper, a new tuning method is proposed, based on the desired dynamics equation (DDE) and the generalized frequency method (GFM), for a two-degree-of-freedom proportional-integral-derivative (PID) controller. The DDE method builds a quantitative relationship between the performance and the two-degree-of-freedom PID controller parameters and guarantees the desired dynamic, but it cannot guarantee the stability margin. So, we have developed the proposed tuning method, which guarantees not only the desired dynamic but also the stability margin. Based on the DDE and the GFM, several simple formulas are deduced to calculate directly the controller parameters. In addition, it performs almost no overshooting setpoint response. Compared with Panagopoulos’ method, the proposed methodology is proven to be effective.

Interleukin 22 (IL-22) is a T-cell secreted cytokine that modulates inflammatory response in nonhematopoietic tissues such as epithelium and liver. The function of IL-22 in adipose tissue is currently unknown. We generated a transgenic mouse model with overexpression of IL-22 specifically in adipose tissue. The IL-22 transgenic mice had no apparent changes in obesity and insulin resistance after feeding with high fat diet (HFD). Unexpectedly, all the IL-22 transgenic mice fed with HFD for four months developed spontaneous tumors in epididymal adipose tissue. Histological analysis indicated that the tumors were well-differentiated liposarcomas with infiltration of inflammatory cells. IL-22 overexpression promotes production of inflammatory cytokines such as IL-1β and IL-10 and stimulates ERK phosphorylation in adipose tissue. Furthermore, IL-22 treatment in differentiated 3T3-L1 adipocytes could induce IL-1β and IL-10 expression, together with stimulation of ERK phosphorylation. Taken together, our study not only established a novel mouse model with spontaneous liposarcoma, but also revealed that IL-22 overexpression may collaborate with diet-induced obesity to impact on tumor development in mouse.