Search

Federated learning (FL) demonstrates significant potential in Industrial Internet of Things (IIoT) settings, as it allows multiple institutions to jointly construct a shared learning model by exchanging model parameters or gradient updates without the need to transmit raw data. However, FL faces risks related to data poisoning and model poisoning. To address these issues, we propose an efficient verifiable federated learning (EVFL) method, which integrates adaptive gradient sparsification (AdaGS), Boneh–Lynn–Shacham (BLS) signatures, and fully homomorphic encryption (FHE). The combination of BLS signatures and the AdaGS algorithm is used to build a secure aggregation protocol. These protocols verify the integrity of parameters uploaded by industrial agents and the consistency of the server's aggregation results. Simulation experiments demonstrate that the AdaGS algorithm significantly reduces verification overhead through parameter sparsification and reuse. Our proposed algorithm achieves better verification efficiency compared to existing solutions. [ABSTRACT FROM AUTHOR]

Intestinal tract is one of the largest organs in human body that is continuously exposed to the external environment, and it plays an important role as a physical and chemical barrier to protect the human body from pathogens. As an important part of the intestinal tract, the integrity of the intestinal mucosal barrier plays a key role in maintaining the intestinal microecological balance. The destruction of the intestinal mucosal barrier can lead to the imbalance and translocation of intestinal flora, which is related to the occurrence and development of various diseases. Intestinal fatty acid binding protein (I-FABP) is one of the fatty acid-binding protein family, which exhibits specificity towards intestinal injury and will be released into the blood circulation rapidly when intestinal injury, ischemia, intestinal mucosal barrier damage and permeability increase occur. The elevated level of I-FABP is an important marker of intestinal injury, and intestinal dysfunction is often associated with many clinical diseases. This article mainly reviews the structural characteristics and function of I-FABP and its relationship with intestinal mucosal barrier related diseases [ABSTRACT FROM AUTHOR]

Recommender systems are fundamental information filtering techniques to recommend content or items that meet users' personalities and potential needs. As a crucial solution to address the difficulty of user identification and unavailability of historical information, session-based recommender systems provide recommendation services that only rely on users' behaviors in the current session. However, most existing studies are not well-designed for modeling heterogeneous user behaviors and capturing the relationships between them in practical scenarios. To fill this gap, in this article, we propose a novel graph-based method, namely Heterogeneous Information Crossing on Graphs (HICG). HICG utilizes multiple types of user behaviors in the sessions to construct heterogeneous graphs, and captures users' current interests with their long-term preferences by effectively crossing the heterogeneous information on the graphs. In addition, we also propose an enhanced version, named HICG-CL, which incorporates the contrastive learning (CL) technique to enhance item representation ability. By utilizing the item co-occurrence relationships across different sessions, HICG-CL improves the recommendation performance of HICG. We conduct extensive experiments on three real-world recommendation datasets, and the results verify that (i) HICG achieves state-of-the-art performance by utilizing multiple types of behaviors on the heterogeneous graph. (ii) HICG-CL further significantly improves the recommendation performance of HICG by the proposed contrastive learning module. [ABSTRACT FROM AUTHOR]

Objective This study aimed to investigate the expression of CD73 in colonic tissues in Crohn's disease (CD) and its significance and possible mechanism of action. Methods Thirty male BALB/c mice were randomly divided into normal control group, model group and intervention group. The control group was fed normally, and the model group was treated with TNBS+40% alcohol enema to establish a mouse model of Crohn's disease induced by chronic inflammation. The intervention group was treated with AB-680 intraperitoneally on the second day of each enema based on the model group. Mice body weight, fecal traits and fecal occult blood were recorded for disease activity index (DAI) score of inflammatory bowel disease. The animals were sacrificed at 7th week, their colonic tissues were removed, weighed and measured. The tissue inflammation was observed by standard hematoxylin-eosin (HE) staining. Masson staining was used to measure the area of collagen in colon tissue of mice. CD73 was detected by fluorescence quantitative PCR and immunohistochemistry. The expression levels of TGF-β, TNF-α and IL-6 in colon tissue of mice were determined by ELISA. Results The DAI score was (0.10±0.16) in the control group, (2.80±0.79) in the model group, and (3.07±0.34) in the intervention group. Compared with the control group, the DAI scores of the model and intervention groups were increased significantly (P<0.05). Compared with the model group, the DAI score of the intervention group was significantly increased (P<0.05). HE staining showed that there was no inflammation in the colon of the control group, while the colon of the model group and the intervention group showed typical inflammatory manifestations such as edema and congestion, inflammatory cell infiltration, and mucosal ulcer. The area ratio of collagen in the control group was (4.95±0.82)%, in the model group was (24.62±1.46)%, and in the intervention group was (54.47±2.75)%. Compared with the control group, the area ratio of collagen in the model group and the intervention group was significantly increased (P<0.05). Compared with the model group, the area ratio of collagen in the intervention group was significantly increased (P<0.05). Compared with the control group, the expression of CD73 in colon tissue of the model group and the intervention group was significantly increased (P<0.05). Compared with the model group, the expression of CD73 in colon tissue of the intervention group was decreased (P<0.05). Compared with the control group, the expressions of TGF-β, TNF-α and IL-6 in the model group and the intervention group were significantly increased (P<0.05). Compared with the model group, the expression of TGF-β, TNF-α and IL-6 in the intervention group decreased (P<0.05). Conclusions CD73 is upregulated in colon tissue of CD mice, it can inhibit inflammatory reaction and improve fibrosis by up-regulating TGF-β expression. On the other hand, CD73 can aggravate the inflammatory response in CD intestinal inflammation and fibrosis by upregulating the expression of IL-6 and TNF-α. Therefore, CD73 may play a bidirectional regulatory role in intestinal inflammation and fibrosis of CD. [ABSTRACT FROM AUTHOR]

Considering that no current limiting inductances (CLIs) are installed at the end of the DC line in the flexible DC distribution grid, the protections relying on line boundary are no longer applicable. To overcome this problem, the paper proposes a single‐ended protection method independent of line boundary. Firstly, the Peterson equivalent circuit is applied to analyze the amplitude‐time ratio of initial voltage travelling wave (ARIVTW) under internal and external faults. Secondly, the fault direction criterion based on the fault component current and the fault type criterion based on the pole voltage are built. Subsequently, the fault identification criterion is constructed by using the ARIVTW, and the corresponding protection method is formed. Finally, the flexible DC distribution grid is built in PSCAD to verify the proposed method. The simulation results show that the method is robust to fault resistance and noise. Besides, the method realizes the protection of the whole line, which has good selectivity and engineering applicability. [ABSTRACT FROM AUTHOR]

This study explored the role of T cell subsets and the expression of related microRNAs in patients with recurrent early pregnancy loss (EPL). Fifty patients with EPL loss between May 2018 and May 2021 were randomly selected as the EPL group, and 50 pregnant women with normal pregnancies or normal delivery outcomes were randomly selected as the control group. The expression levels of T cell subset-related markers and T cell subset-related miRNAs, in addition to the frequencies of T cell subsets, in peripheral blood of the two groups were analyzed. In terms of T cell-related markers, the results showed that the expression levels of the transcriptional regulator TBX-21 (T-bet) and interferon regulatory factor 4 (IRF4) were significantly upregulated in peripheral blood of the patients in the EPL group (P < 0.05), whereas the expression levels of GATA binding protein 3 (GATA3) and glucocorticoid-induced tumor necrosis factor receptor (GITR) were significantly downregulated (P < 0.05). In the EPL group, the expression of mir-106b, mir-93, and mir-25 was upregulated (1.51 ± 0.129 , 1.43 ± 0.132 , and 1.73 ± 0.156 , respectively) in regulatory T (Treg) cell-related T cell subsets, whereas the expression of miR-146a and miR-155 was downregulated (P < 0.05). The frequencies of Treg and exhausted T cells in the EPL group were significantly lower than those in the control group (P < 0.05). The cell frequencies of T helper 17 (Th17) cells and exhausted Treg cells in the EPL group were significantly higher than those in the control group (P < 0.05). In conclusion, immune cells and associated miRNA profiles can be used as prognostic biomarkers for the treatment of human reproductive disorders, such as EPL. [ABSTRACT FROM AUTHOR]

Copyright of Frontiers of Information Technology & Electronic Engineering is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Purpose: We evaluated the differences between patients with SARS-CoV-2 Omicron variant infections and Fever outpatients, so that prevention and control measures can be taken in time. Patients and Methods: This study retrospectively analyzed 65 patients with SARS-CoV-2 Omicron variant. Sixty-nine age- and sex-matched Fever outpatients were enrolled during the same period of time. We also reanalyzed data from 81 SARS-CoV-2 Wild-Type-infected patients. We compared the clinical characteristics and initial indexes of routine tests among the 3 groups. Results: A total of 93.8% of the patients with Omicron infections had clinical symptoms, and the major symptoms were cough, fever and pharyngalgia. Pharyngalgia was a specific manifestation in Omicron group compared to Wild-Type group. The white blood cell of the Omicron group was lower than that of the Fever group [5.0 (3.6– 6.1) vs 10.1 (7.6– 12.9) × 109/L, P < 0.001]. The neutrophil count in Omicron group was lower than that in Fever and Wild-Type group [2.6 (1.8– 3.9) vs 8.1 (5.9– 10.9), P < 0.001; 2.6 (1.8– 3.9) vs 3.4 (2.5– 4.7) × 109/L, P < 0.001]. The white blood cell and neutrophil counts were lower in Omicron group than in the Fever group. The top 5 major symptoms were fever, cough, pharyngalgia, headache and expectoration. Conclusion: There are differences between the patients with Omicron infections and Fever outpatients, both in clinical manifestations and initial routine hematology indicators. We hope to provide some clues for early identification combined with a history of living in the epidemic area. [ABSTRACT FROM AUTHOR]

Recently, Factorization Machine (FM) has become more and more popular for recommendation systems due to its effectiveness in finding informative interactions between features. Usually, the weights for the interactions are learned as a low rank weight matrix, which is formulated as an inner product of two low rank matrices. This low rank matrix can help improve the generalization ability of Factorization Machine. However, to choose the rank properly, it usually needs to run the algorithm for many times using different ranks, which clearly is inefficient for some large-scale datasets. To alleviate this issue, we propose an Adaptive Boosting framework of Factorization Machine (AdaFM), which can adaptively search for proper ranks for different datasets without re-training. Instead of using a fixed rank for FM, the proposed algorithm will gradually increase its rank according to its performance until the performance does not grow. Extensive experiments are conducted to validate the proposed method on multiple large-scale datasets. The experimental results demonstrate that the proposed method can be more effective than the state-of-the-art Factorization Machines. [ABSTRACT FROM AUTHOR]

Point-of-Interest (POI) recommendation has been extensively studied and successfully applied in industry recently. However, most existing approaches build centralized models on the basis of collecting users' data. Both private data and models are held by the recommender, which causes serious privacy concerns. In this article, we propose a novel Privacy preserving POI Recommendation (PriRec) framework. First, to protect data privacy, users' private data (features and actions) are kept on their own side, e.g., Cellphone or Pad. Meanwhile, the public data that need to be accessed by all the users are kept by the recommender to reduce the storage costs of users' devices. Those public data include: (1) static data only related to the status of POI, such as POI categories, and (2) dynamic data dependent on user-POI actions such as visited counts. The dynamic data could be sensitive, and we develop local differential privacy techniques to release such data to the public with privacy guarantees. Second, PriRec follows the representations of Factorization Machine (FM) that consists of a linear model and the feature interaction model. To protect the model privacy, the linear models are saved on the users' side, and we propose a secure decentralized gradient descent protocol for users to learn it collaboratively. The feature interaction model is kept by the recommender since there is no privacy risk, and we adopt a secure aggregation strategy in a federated learning paradigm to learn it. To this end, PriRec keeps users' private raw data and models in users' own hands, and protects user privacy to a large extent. We apply PriRec in real-world datasets, and comprehensive experiments demonstrate that, compared with FM, PriRec achieves comparable or even better recommendation accuracy. [ABSTRACT FROM AUTHOR]

Internet companies are facing the need for handling large-scale machine learning applications on a daily basis and distributed implementation of machine learning algorithms which can handle extra-large-scale tasks with great performance is widely needed. Deep forest is a recently proposed deep learning framework which uses tree ensembles as its building blocks and it has achieved highly competitive results on various domains of tasks. However, it has not been tested on extremely large-scale tasks. In this work, based on our parameter server system, we developed the distributed version of deep forest. To meet the need for real-world tasks, many improvements are introduced to the original deep forest model, including MART (Multiple Additive Regression Tree) as base learners for efficiency and effectiveness consideration, the cost-based method for handling prevalent class-imbalanced data, MART based feature selection for high dimension data, and different evaluation metrics for automatically determining the cascade level. We tested the deep forest model on an extra-large-scale task, i.e., automatic detection of cash-out fraud, with more than 100 million training samples. Experimental results showed that the deep forest model has the best performance according to the evaluation metrics from different perspectives even with very little effort for parameter tuning. This model can block fraud transactions in a large amount of money each day. Even compared with the best-deployed model, the deep forest model can additionally bring a significant decrease in economic loss each day. [ABSTRACT FROM AUTHOR]

Relative radiometric calibration, or flat fielding, is indispensable for obtaining high-quality optical satellite imagery for sensors that have more than one detector per band. High-resolution optical push-broom sensors with thousands of detectors per band are now common. Multiple techniques have been employed for relative radiometric calibration. One technique, often called side-slither, where the sensor axis is rotated 90° in yaw relative to normal acquisitions, has been gaining popularity, being applied to Landsat 8, QuickBird, RapidEye, and other satellites. Side-slither can be more time efficient than some of the traditional methods, as only one acquisition may be required. In addition, the side-slither does not require any onboard calibration hardware, only a satellite capability to yaw and maintain a stable yawed attitude. A relative radiometric calibration method based on histograms of side-slither data is developed. This method has three steps: pre-processing, extraction of key points, and calculation of coefficients. Histogram matching and Otsu's method are used to extract key points. Three datasets from the Chinese GaoFen-9 satellite were used: one to obtain the relative radiometric coefficients, and the others to verify the coefficients. Root-mean-square deviations of the corrected imagery were better than 0.1%. The maximum streaking metrics was less than 1. This method produced significantly better relative radiometric calibration than the traditional method used for GaoFen-9. [ABSTRACT FROM AUTHOR]

Incorporating social network information and contexts to improve recommendation performance has been drawing considerable attention recently. However, a majority of existing social recommendation approaches suffer from the following problems: (1) They only employ individual trust among users to optimize prediction solutions in user latent feature space or in user-item rating space; thus, they exhibit low recommendation accuracy. (2) They use decision trees to perform context-based user-item subgrouping; thus, they can only handle categorical contexts. (3) They have difficulty coping with the data sparsity problem. To solve these problems, and accurately and realistically model recommender systems, we propose a social matrix factorization method to optimize the prediction solution in both user latent feature space and user-item rating space using the individual trust among users. To further improve the recommendation performance and alleviate the data sparsity problem, we propose a context-aware enhanced model based on Gaussian mixture model (GMM). Two real datasets (one sparse dataset and one dense dataset) based experiments show that our proposed method outperforms the state-of-the-art social matrix factorization and context-aware recommendation methods in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]

Recommender system (RS) has become an active research area driven by the enormous industrial demands. Meanwhile, with the rapid development of microblogging system, various kinds of social data are available, which provide opportunities as well as challenges for traditional RSs. In this paper, we introduce the social recommendation (SR) problem utilizing microblogging data. We study this problem via multi-view user preference learning. Specifically, we first model user preference by learning a low-dimensional common representation of multi-view information including rating information, social relations, item side information, tagging information, and then recommend items based on the learnt user preference. We also develop an efficient alternating direction method of multipliers (ADMM) scheme to solve the proposed model. We empirically evaluate our approach using two real world datasets to demonstrate the significant improvement of our proposed approach against the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Today’s decreasing product development cycle time requires rapid and cost-effective reliability analysis and testing. Qualification is the process of demonstrating that a product is capable of meeting or exceeding specified requirements. Light-emitting diode (LED) qualification tests are often as long as 6000 h, but this length of time does not guarantee the typically required lifetime of 10 years or more. This paper presents a prognostics-based technique that reduces the LED qualification time. An anomaly detection technique called the similarity-based metric test is developed to identify anomalies without utilizing historical libraries of healthy and unhealthy data. The similarity-based metric test extracts features from the spectral power distributions (SPDs) using peak analysis, reduces the dimensionality of the features using principal component analysis, and partitions the data set of principal components into groups using a k-nearest neighbor (KNN)-kernel density-based clustering technique. A detection algorithm then evaluates the distances from the centroid of each cluster to each test point and detects anomalies when the distance is greater than the threshold. From this, the dominant degradation processes associated with the LED die and phosphors in the LED package can be identified. In our case study, anomalies were detected at less than 1200 h using the similarity-based metric test. Thus, our method could decrease the amount of LED qualification testing time by providing users with an earlier time to begin remaining useful life prediction without waiting 6000 h as required by industrial standards. [ABSTRACT FROM PUBLISHER]

Abstract: Machine prognosis can be considered as the generation of long-term predictions that describe the evolution in time of a fault indicator, with the purpose of estimating the remaining useful life (RUL) of a failing component/subsystem so that timely maintenance can be performed to avoid catastrophic failures. This paper proposes an integrated RUL prediction method using adaptive neuro-fuzzy inference systems (ANFIS) and high-order particle filtering, which forecasts the time evolution of the fault indicator and estimates the probability density function (pdf) of RUL. The ANFIS is trained and integrated in a high-order particle filter as a model describing the fault progression. The high-order particle filter is used to estimate the current state and carry out p-step-ahead predictions via a set of particles. These predictions are used to estimate the RUL pdf. The performance of the proposed method is evaluated via the real-world data from a seeded fault test for a UH-60 helicopter planetary gear plate. The results demonstrate that it outperforms both the conventional ANFIS predictor and the particle-filter-based predictor where the fault growth model is a first-order model that is trained via the ANFIS. [Copyright &y& Elsevier]

This paper presents a dynamic recurrent neuro-fuzzy system (DRNFS) with short memory for obstacle avoidance of mobile robots in unknown environments. The DRNFS is developed to avoid obstacles through supervised learning from a set of obstacle-avoidance trajectories provided by a human driver. The feedback connections added in the second layer of the DRNFS make the system cope with temporal problems, which allows the robot to memorize the previous environment information. The parameters and structure of the DRNFS can be automatically optimized through the learning process. The parameter optimization is realized by the ordered derivative algorithm, and the structure simplification is completed by the fuzzy rules similarity measure. Simulation results are presented to verify the feasibility of the proposed system. [ABSTRACT FROM AUTHOR]

This paper proposes a novel approach for machine health condition prognosis based on neuro-fuzzy systems (NFSs) and Bayesian algorithms. The NFS, after training with machine condition data, is employed as a prognostic model to forecast the evolution of the machine fault state with time. An online model update scheme is developed on the basis of the probability density function (PDF) of the NFS residuals between the actual and predicted condition data. Bayesian estimation algorithms adopt the model's predicted data as prior information in combination with online measurements to update the degree of belief in the forecasting estimations. In order to simplify the implementation of the proposed approach, a recursive Bayesian algorithm called particle filtering is utilized to calculate in real time a posterior PDF by a set of random samples (or particles) with associated weights. When new data become available, the weights of all particles are updated, and then, predictions are carried out, which form the PDF of the predicted estimations. The developed method is evaluated via two experimental cases—a cracked carrier plate and a faulty bearing. The prediction performance is compared with three prevalent machine condition predictors—recurrent neural networks, NFSs, and recurrent NFSs. The results demonstrate that the proposed approach can predict machine conditions more accurately. [ABSTRACT FROM PUBLISHER]

Machine prognosis is a significant part of condition-based maintenance and intends to monitor and track the time evolution of a fault so that maintenance can be performed or the task can be terminated to avoid a catastrophic failure. A new prognostic method is developed in this paper using adaptive neuro–fuzzy inference systems (ANFISs) and high-order particle filtering. The ANFIS is trained via machine historical failure data. The trained ANFIS and its modeling noise constitute an mth-order hidden Markov model to describe the fault propagation process. The high-order particle filter uses this Markov model to predict the time evolution of the fault indicator in the form of a probability density function. An online update scheme is developed to adapt the Markov model to various machine dynamics quickly. The performance of the proposed method is evaluated by using the testing data from a cracked carrier plate and a faulty bearing. Results show that it outperforms classical condition predictors. [ABSTRACT FROM AUTHOR]