Semi-Supervised Informer for the Compound Fault Diagnosis of Industrial Robots.

The increasing deployment of industrial robots in manufacturing requires accurate fault diagnosis. Online monitoring data typically consist of a large volume of unlabeled data and a small quantity of labeled data. Conventional intelligent diagnosis methods heavily rely on supervised learning with abundant labeled data. To address this issue, this paper presents a semi-supervised Informer algorithm for fault diagnosis modeling, leveraging the Informer model's long- and short-term memory capabilities and the benefits of semi-supervised learning to handle the diagnosis of a small amount of labeled data alongside a substantial amount of unlabeled data. An experimental study is conducted using real-world industrial robot monitoring data to assess the proposed algorithm's effectiveness, demonstrating its ability to deliver accurate fault diagnosis despite limited labeled samples.

Highly Sensitive Qualitative and Quantitative Identification of Cashmere and Wool Based on Terahertz Electromagnetically Induced Transparent Metasurface Biosensor.

Cashmere and wool are both natural animal fibers used in the textile industry, but cashmere is of superior quality, is rarer, and more precious. It is therefore important to distinguish the two fibers accurately and effectively. However, challenges due to their similar appearance, morphology, and physical and chemical properties remain. Herein, a terahertz electromagnetic inductive transparency (EIT) metasurface biosensor is introduced for qualitative and quantitative identification of cashmere and wool. The periodic unit structure of the metasurface consists of four rotationally symmetric resonators and two cross-arranged metal secants to form toroidal dipoles and electric dipoles, respectively, so that its effective sensing area can be greatly improved by 1075% compared to the traditional dipole mode, and the sensitivity will be up to 342 GHz/RIU. The amplitude and frequency shift changes of the terahertz transmission spectra caused by the different refractive indices of cashmere/wool can achieve highly sensitive label-free qualitative and quantitative identification of both. The experimental results show that the terahertz metasurface biosensor can work at a concentration of 0.02 mg/mL. It provides a new way to achieve high sensitivity, precision, and trace detection of cashmere/wool, and would be a valuable application for the cashmere industry.

Reliability of MEMS inertial devices in mechanical and thermal environments: A review.

The reliability of MEMS inertial devices applied in complex environments involves interdisciplinary fields, such as structural mechanics, material mechanics and multi-physics field coupling. Nowadays, MEMS inertial devices are widely used in the fields of automotive industry, consumer electronics, aerospace and missile guidance, and a variety of reliability issues induced by complex environments arise subsequently. Hence, reliability analysis and design of MEMS inertial devices are becoming increasingly significant. Since the reliability issues of MEMS inertial devices are mainly caused by complex mechanical and thermal environments with intricate failure mechanisms, there are fewer reviews of related research in this field. Therefore, this paper provides an extensive review of the research on the reliability of typical failure modes and mechanisms in MEMS inertial devices under high temperature, temperature cycling, vibration, shock, and multi-physical field coupling environments in the last five to six years. It is found that though multiple studies exist examining the reliability of MEMS inertial devices under single stress, there is a dearth of research conducted under composite stress and a lack of systematic investigation. Through analyzing and summarizing the current research progress in reliability design, it is concluded that multi-physical field coupling simulation, theoretical modeling, composite stress experiments, and special test standards are important directions for future reliability research on MEMS inertial devices.

Learning From Incorrectness: Active Learning With Negative Pre-Training and Curriculum Querying for Histological Tissue Classification.

Patch-level histological tissue classification is an effective pre-processing method for histological slide analysis. However, the classification of tissue with deep learning requires expensive annotation costs. To alleviate the limitations of annotation budgets, the application of active learning (AL) to histological tissue classification is a promising solution. Nevertheless, there is a large imbalance in performance between categories during application, and the tissue corresponding to the categories with relatively insufficient performance are equally important for cancer diagnosis. In this paper, we propose an active learning framework called ICAL, which contains Incorrectness Negative Pre-training (INP) and Category-wise Curriculum Querying (CCQ) to address the above problem from the perspective of category-to-category and from the perspective of categories themselves, respectively. In particular, INP incorporates the unique mechanism of active learning to treat the incorrect prediction results that obtained from CCQ as complementary labels for negative pre-training, in order to better distinguish similar categories during the training process. CCQ adjusts the query weights based on the learning status on each category by the model trained by INP, and utilizes uncertainty to evaluate and compensate for query bias caused by inadequate category performance. Experimental results on two histological tissue classification datasets demonstrate that ICAL achieves performance approaching that of fully supervised learning with less than 16% of the labeled data. In comparison to the state-of-the-art active learning algorithms, ICAL achieved better and more balanced performance in all categories and maintained robustness with extremely low annotation budgets. The source code will be released at https://github.com/LactorHwt/ICAL.

Research on Packaging Reliability and Quality Factor Degradation Model for Wafer-Level Vacuum Sealing MEMS Gyroscopes.

MEMS gyroscopes are widely applied in consumer electronics, aerospace, missile guidance, and other fields. Reliable packaging is the foundation for ensuring the survivability and performance of the sensor in harsh environments, but gas leakage models of wafer-level MEMS gyroscopes are rarely reported. This paper proposes a gas leakage model for evaluating the packaging reliability of wafer-level MEMS gyroscopes. Based on thermodynamics and hydromechanics, the relationships between the quality factor, gas molecule number, and a quality factor degradation model are derived. The mechanism of the effect of gas leakage on the quality factor is explored at wafer-level packaging. The experimental results show that the reciprocal of the quality factor is exponentially related to gas leakage time, which is in accordance with the theoretical analysis. The coefficients of determination (R2) are all greater than 0.95 by fitting the curves in Matlab R2022b. The stable values of the quality factor for drive mode and sense mode are predicted to be 6609.4 and 1205.1, respectively, and the average degradation characteristic time is 435.84 h. The gas leakage time is at least eight times the average characteristic time, namely 3486.72 h, before a stable condition is achieved in the packaging chamber of the MEMS gyroscopes.

Developing a special microwave oven: Assessment of its performance for dough fermentation and nutrient soup elaboration.

Bread and soup are two of the most important foods in daily life, thus dough fermentation and nutrient soup elaboration are more and more popular, but there is a lack of relevant low-cost and high-reliable household appliances on the market. Therefore, this paper proposes automatic control methods for dough fermentation and nutrient soup elaboration based on a special microwave oven. Fermentation theory, run-up microwave fermentation principle, microwave extraction principle, NTC temperature probe design and scalable fuzzy control algorithm are described in detail. Besides, the experimental platform is set up with a temperature chamber, an optical fiber thermometer and a power meter. Experimental results demonstrate that the relationship between the heating time and flour's mass is linear. For different ambient temperature tests, the volume ratios of the fermented dough to unfermented dough of different cases range from 2.2 to 2.62, and the inside of the dough after fermentation is fluffy, with small and dense cavities. Meanwhile, there is no acid taste and skin dryness, and the power consumption of microwave fermentation is less than half of that induced by grill, convection or steam fermentation. The detection error of the NTC temperature probe with microwave shielded is 0.48 °C, and the control error of the closed loop system is less than 0.5 °C. The temperature-rise slope of water is lower than that of ingredient, and the water's temperature is about 1 °C less than that of the ingredient. The soup after microwave elaboration is amber and clear, the ingredients are intact, the water loss is less than 50 g, and the total power consumption is 684 Wh. In short, microwave-based control methods for dough fermentation and nutrient soup elaboration are effective.

Fairness-aware genetic-algorithm-based few-shot classification.

Artificial-intelligence-assisted decision-making is appearing increasingly more frequently in our daily lives; however, it has been shown that biased data can cause unfairness in decision-making. In light of this, computational techniques are needed to limit the inequities in algorithmic decision-making. In this letter, we present a framework to join fair feature selection and fair meta-learning to do few-shot classification, which contains three parts: (1) a pre-processing component acts as an intermediate bridge between fair genetic algorithm (FairGA) and fair few-shot (FairFS) to generate the feature pool; (2) the FairGA module considers the presence or absence of words as gene expression, and filters out key features by a fairness clustering genetic algorithm; (3) the FairFS part carries out the task of representation and fairness constraint classification. Meanwhile, we propose a combinatorial loss function to cope with fairness constraints and hard samples. Experiments show that the proposed method achieves strong competitive performance on three public benchmarks.

A Non-Contact Fall Detection Method for Bathroom Application Based on MEMS Infrared Sensors.

The ratio of the elderly to the total population around the world is larger than 10%, and about 30% of the elderly are injured by falls each year. Accidental falls, especially bathroom falls, account for a large proportion. Therefore, fall events detection of the elderly is of great importance. In this article, a non-contact fall detector based on a Micro-electromechanical Systems Pyroelectric Infrared (MEMS PIR) sensor and a thermopile IR array sensor is designed to detect bathroom falls. Besides, image processing algorithms with a low pass filter and double boundary scans are put forward in detail. Then, the statistical features of the area, center, duration and temperature are extracted. Finally, a 3-layer BP neural network is adopted to identify the fall events. Taking into account the key factors of ambient temperature, objective, illumination, fall speed, fall state, fall area and fall scene, 640 tests were performed in total, and 5-fold cross validation is adopted. Experimental results demonstrate that the averages of the precision, recall, detection accuracy and F1-Score are measured to be 94.45%, 90.94%, 92.81% and 92.66%, respectively, which indicates that the novel detection method is feasible. Thereby, this IOT detector can be extensively used for household bathroom fall detection and is low-cost and privacy-security guaranteed.

Weakly supervised semantic segmentation of histological tissue via attention accumulation and pixel-level contrast learning.

Objective. Histopathology image segmentation can assist medical professionals in identifying and diagnosing diseased tissue more efficiently. Although fully supervised segmentation models have excellent performance, the annotation cost is extremely expensive. Weakly supervised models are widely used in medical image segmentation due to their low annotation cost. Nevertheless, these weakly supervised models have difficulty in accurately locating the boundaries between different classes of regions in pathological images, resulting in a high rate of false alarms Our objective is to design a weakly supervised segmentation model to resolve the above problems.Approach. The segmentation model is divided into two main stages, the generation of pseudo labels based on class residual attention accumulation network (CRAANet) and the semantic segmentation based on pixel feature space construction network (PFSCNet). CRAANet provides attention scores for each class through the class residual attention module, while the Attention Accumulation (AA) module overlays the attention feature maps generated in each training epoch. PFSCNet employs a network model containing an inflated convolutional residual neural network and a multi-scale feature-aware module as the segmentation backbone, and proposes dense energy loss and pixel clustering modules are based on contrast learning to solve the pseudo-labeling-inaccuracy problem.Main results. We validate our method using the lung adenocarcinoma (LUAD-HistoSeg) dataset and the breast cancer (BCSS) dataset. The results of the experiments show that our proposed method outperforms other state-of-the-art methods on both datasets in several metrics. This suggests that it is capable of performing well in a wide variety of histopathological image segmentation tasks.Significance. We propose a weakly supervised semantic segmentation network that achieves approximate fully supervised segmentation performance even in the case of incomplete labels. The proposed AA and pixel-level contrast learning also make the edges more accurate and can well assist pathologists in their research.

Experimental Study of Ghost Imaging in Underwater Environment.

Underwater imaging technique is a crucial tool for humans to develop, utilize, and protect the ocean. We comprehensively compare the imaging performance of twenty-four ghost imaging (GI) methods in the underwater environment. The GI methods are divided into two types according to the illumination patterns, the random and orthogonal patterns. Three-group simulations were designed to show the imaging performance of the twenty-four GI methods. Moreover, an experimental system was built, and three-group experiments were implemented. The numerical and experimental results demonstrate that the orthogonal pattern-based compressed sensing GI methods have strong antinoise capability and can restore clear images for underwater objects with a low measurement number. The investigation results are helpful for the practical applications of the underwater GI.

Few-Shot Text Classification with Global-Local Feature Information.

Meta-learning frameworks have been proposed to generalize machine learning models for domain adaptation without sufficient label data in computer vision. However, text classification with meta-learning is less investigated. In this paper, we propose SumFS to find global top-ranked sentences by extractive summary and improve the local vocabulary category features. The SumFS consists of three modules: (1) an unsupervised text summarizer that removes redundant information; (2) a weighting generator that associates feature words with attention scores to weight the lexical representations of words; (3) a regular meta-learning framework that trains with limited labeled data using a ridge regression classifier. In addition, a marine news dataset was established with limited label data. The performance of the algorithm was tested on THUCnews, Fudan, and marine news datasets. Experiments show that the SumFS can maintain or even improve accuracy while reducing input features. Moreover, the training time of each epoch is reduced by more than 50%.

Semisupervised Classification With Novel Graph Construction for High-Dimensional Data.

Graph-based methods have achieved impressive performance on semisupervised classification (SSC). Traditional graph-based methods have two main drawbacks. First, the graph is predefined before training a classifier, which does not leverage the interactions between the classifier training and similarity matrix learning. Second, when handling high-dimensional data with noisy or redundant features, the graph constructed in the original input space is actually unsuitable and may lead to poor performance. In this article, we propose an SSC method with novel graph construction (SSC-NGC), in which the similarity matrix is optimized in both label space and an additional subspace to get a better and more robust result than in original data space. Furthermore, to obtain a high-quality subspace, we learn the projection matrix of the additional subspace by preserving the local and global structure of the data. Finally, we intergrade the classifier training, the graph construction, and the subspace learning into a unified framework. With this framework, the classifier parameters, similarity matrix, and projection matrix of subspace are adaptively learned in an iterative scheme to obtain an optimal joint result. We conduct extensive comparative experiments against state-of-the-art methods over multiple real-world data sets. Experimental results demonstrate the superiority of the proposed method over other state-of-the-art algorithms.

Underwater compressive computational ghost imaging with wavelet enhancement.

We propose a compressive Hadamard computational ghost imaging (CGI) method to restore clear images of objects in the underwater environment. We construct an underwater CGI system model and develop a total variation regularization prior-based compressed-sensing algorithm for the CGI image reconstruction. We design a wavelet enhancement algorithm to further denoise and enhance the quality of the CGI image. We build an experimental setup and implement a series of experiments. The effectiveness and advantages of the proposed method are experimentally investigated. The results show that the proposed method can achieve clear imaging for underwater objects with a sub-Nyquist sampling ratio. The proposed method is helpful for improving the image quality of the underwater CGI.

Towards fine-scale population stratification modeling based on kernel principal component analysis and random forest.

BACKGROUND: Population stratification modeling is essential in Genome-Wide Association Studies. OBJECTIVE: In this paper, we aim to build a fine-scale population stratification model to efficiently infer individual genetic ancestry. METHODS: Kernel Principal Component Analysis (PCA) and random forest are adopted to build the population stratification model, together with parameter optimization. We explore different PCA methods, including standard PCA and kernel PCA to extract relevant features from the genotype data that is transformed by vcf2geno, a pipeline from LASER software. These extracted features are fed into a random forest for ensemble learning. Parameter tuning is performed to jointly find the optimal number of principal components, kernel function for PCA and parameters of the random forest. RESULTS: Experiments based on HGDP dataset show that kernel PCA with Sigmoid function and Gaussian function can achieve higher prediction accuracy than the standard PCA. Compared to standard PCA with the two principal components, the accuracy by using KPCA-Sigmoid with the optimal number of principal components can achieve around 100% and 200% improvement for East Asian and European populations, respectively. CONCLUSION: With the optimal parameter configuration on both PCA and random forest, our proposed method can infer the individual genetic ancestry more accurately, given their variants.

Sub-Nyquist computational ghost imaging with deep learning.

We propose a deep learning computational ghost imaging (CGI) scheme to achieve sub-Nyquist and high-quality image reconstruction. Unlike the second-order-correlation CGI and compressive-sensing CGI, which use lots of illumination patterns and a one-dimensional (1-D) light intensity sequence (LIS) for image reconstruction, a deep neural network (DAttNet) is proposed to restore the target image only using the 1-D LIS. The DAttNet is trained with simulation data and retrieves the target image from experimental data. The experimental results indicate that the proposed scheme can provide high-quality images with a sub-Nyquist sampling ratio and performs better than the conventional and compressive-sensing CGI methods in sub-Nyquist sampling ratio conditions (e.g., 5.45%). The proposed scheme has potential practical applications in underwater, real-time and dynamic CGI.

Order Statistics Concordance Coefficient With Applications to Multichannel Biosignal Analysis.

In this paper, we propose a novel concordance coefficient, called order statistics concordance coefficient (OSCOC), to quantify the association among multichannel biosignals. To uncover its properties, we compare OSCOC with three other similar indexes, i.e., average Pearson's product moment correlation coefficient (APPMCC), Kendall's concordance coefficients (KCC), and average Kendall's tau (AKT), under a multivariate normal model (MNM), linear model (LM), and nonlinear model. To further demonstrate its usefulness, we present an example on atrial arrhythmia analysis based on real-world multichannel cardiac signals. Theoretical derivations as well as numerical results suggest that 1) under MNM and LM, OSCOC performs equally well with APPMCC, and outperforms the other two methods, 2) in nonlinear case, OSCOC even has better performance than KCC and AKT, which are well known to be robust under increasing nonlinear transformations, and 3) OSCOC performs the best in the case study of arrhythmia analysis in terms of the volume under the surface.