Unsupervised Scheme Research Articles

Unsupervised Dual Transformer Learning for 3-D Textured Surface Segmentation.

Analysis of the 3-D texture is indispensable for various tasks, such as retrieval, segmentation, classification, and inspection of sculptures, knit fabrics, and biological tissues. A 3-D texture represents a locally repeated surface variation (SV) that is independent of the overall shape of the surface and can be determined using the local neighborhood and its characteristics. Existing methods mostly employ computer vision techniques that analyze a 3-D mesh globally, derive features, and then utilize them for classification or retrieval tasks. While several traditional and learning-based methods have been proposed in the literature, only a few have addressed 3-D texture analysis, and none have considered unsupervised schemes so far. This article proposes an original framework for the unsupervised segmentation of 3-D texture on the mesh manifold. The problem is approached as a binary surface segmentation task, where the mesh surface is partitioned into textured and nontextured regions without prior annotation. The proposed method comprises a mutual transformer-based system consisting of a label generator (LG) and a label cleaner (LC). Both models take geometric image representations of the surface mesh facets and label them as texture or nontexture using an iterative mutual learning scheme. Extensive experiments on three publicly available datasets with diverse texture patterns demonstrate that the proposed framework outperforms standard and state-of-the-art unsupervised techniques and performs reasonably well compared to supervised methods.

Unsupervised strategies in detecting log anomalies using AIOps monitoring to amplify performance by PCA and ANN systems

Unsupervised strategies in detecting log anomalies using AIOps monitoring to amplify performance by PCA and ANN systems

Graph alignment exploiting the spatial organization improves the similarity of brain networks.

Every brain is unique, having its structural and functional organization shaped by both genetic and environmental factors over the course of its development. Brain image studies tend to produce results by averaging across a group of subjects, under the common assumption that it is possible to subdivide the cortex into homogeneous areas while maintaining a correspondence across subjects. We investigate this assumption: can the structural properties of a specific region of an atlas be assumed to be the same across subjects? This question is addressed by looking at the network representation of the brain, with nodes corresponding to brain regions and edges to their structural relationships. Using an unsupervised graph matching strategy, we align the structural connectomes of a set of healthy subjects, considering parcellations of different granularity, to understand the connectivity misalignment between regions. First, we compare the obtained permutations with four different algorithm initializations: Spatial Adjacency, Identity, Barycenter, and Random. Our results suggest that applying an alignment strategy improves the similarity across subjects when the number of parcels is above 100 and when using Spatial Adjacency and Identity initialization (the most plausible priors). Second, we characterize the obtained permutations, revealing that the majority of permutations happens between neighbors parcels. Lastly, we study the spatial distribution of the permutations. By visualizing the results on the cortex, we observe no clear spatial patterns on the permutations and all the regions across the context are mostly permuted with first and second order neighbors.

Generating Semantic Adversarial Examples via Feature Manipulation in Latent Space.

The susceptibility of deep neural networks (DNNs) to adversarial intrusions, exemplified by adversarial examples, is well-documented. Conventional attacks implement unstructured, pixel-wise perturbations to mislead classifiers, which often results in a noticeable departure from natural samples and lacks human-perceptible interpretability. In this work, we present an adversarial attack strategy that implements fine-granularity, semantic-meaning-oriented structural perturbations. Our proposed methodology manipulates the semantic attributes of images through the use of disentangled latent codes. We engineer adversarial perturbations by manipulating either a single latent code or a combination thereof. To this end, we propose two unsupervised semantic manipulation strategies: one based on vector-disentangled representation and the other on feature map-disentangled representation, taking into consideration the complexity of the latent codes and the smoothness of the reconstructed images. Our empirical evaluations, conducted extensively on real-world image data, showcase the potency of our attacks, particularly against black-box classifiers. Furthermore, we establish the existence of a universal semantic adversarial example that is agnostic to specific images.

ConcVAE: Conceptual Representation Learning.

Disentangled representation learning aims at obtaining an independent latent representation without supervisory signals. However, the independence of a representation does not guarantee interpretability to match human intuition in the unsupervised settings. In this article, we introduce conceptual representation learning, an unsupervised strategy to learn a representation and its concepts. An antonym pair forms a concept, which determines the semantically meaningful axes in the latent space. Since the connection between signifying words and signified notions is arbitrary in natural languages, the verbalization of data features makes the representation make sense to humans. We thus construct Conceptual VAE (ConcVAE), a variational autoencoder (VAE)-based generative model with an explicit process in which the semantic representation of data is generated via trainable concepts. In visual data, ConcVAE utilizes natural language arbitrariness as an inductive bias of unsupervised learning by using a vision-language pretraining, which can tell an unsupervised model what makes sense to humans. Qualitative and quantitative evaluations show that the conceptual inductive bias in ConcVAE effectively disentangles the latent representation in a sense-making manner without supervision. Code is available at https://github.com/ganmodokix/concvae.

Statistical similarity matching and filtering for clinical image retrieval by machine learning approach

Clinical image retrieval plays a pivotal role in modern healthcare for diagnostics and research, but prior research has grappled with the challenge of achieving high accuracy due to limited filtering techniques. The proposed method includes statistical distance measurements for similarity comparison and a machine learning technique for image filtering. Throughout this framework, the search area for similarity matching is reduced by first filtering away irrelevant images using the probabilistic outcomes of the Support Vector Machine (SVM) classification as class predictions of search and database images. Resizing is done as part of the preprocessing. Then, using Principal Component Analysis (PCA), the preprocessed data’s textural features, visual characteristics, and low-level features are extracted. The study also suggested an adaptive similarity matching method centered on a linear integration of feature-level similarities on the individual-level level. The precision and ranking order details of the most appropriate images retrieved and predicted by SVMs are considered when calculating the feature weights. The system continually alters weights for every distinctive search to generate beneficial outcomes. The supervised and unsupervised learning strategies are studied to link low-level global image features in the generated PCA-based Eigen Space using their high-level semantic and visual classifications to reduce the semantic gap and enhance retrieval effectiveness. The ground-truth database used in experiments has 1594 unique medical images with 3 different databases. Our method significantly improves the precision and recall rates in image retrieval tasks by combining sophisticated feature extraction, data-driven algorithms, and deep learning models. Research obtained an impressive accuracy of 0.99, demonstrating the effectiveness of our approach. This novel methodology addresses the limitations of prior research and provides a robust and reliable solution for clinicians and researchers in the medical field seeking to access and analyze relevant clinical images.

DLUT: Decoupled Learning-Based Unsupervised Tracker.

Unsupervised learning has shown immense potential in object tracking, where accurate classification and regression are crucial for unsupervised trackers. However, the classification and regression branches of most unsupervised trackers calculate object similarities by sharing cross-correlation modules. This leads to high coupling between different branches, thus hindering the network performance. To address the above issue, we propose a Decoupled Learning-based Unsupervised Tracker (DLUT). Specifically, we separate the training pipelines of different branches to unlock their inherent learning potential so that different branches can fully explore the focused feature regions of interest. Furthermore, we design independent adaptive decoupling-correlation modules according to the characteristics of each branch to obtain more discriminative and easily locatable feature response maps. Finally, to suppress the noise interference brought by unsupervised pseudo-label training and highlight the foreground object, we propose a novel suppression-ranking-based unsupervised training strategy. Extensive experiments demonstrate that our DLUT outperforms state-of-the-art unsupervised trackers.

LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation

AbstractThe low‐light environment is integral to everyday activities but poses significant challenges in object detection. Due to the low brightness, noise, and insufficient illumination of the acquired image, the model's object detection performance is reduced. Opposing recent studies mainly developing using supervised learning models, this paper suggests LIDA‐YOLO, an approach for unsupervised adaptation of low‐illumination object detectors. The model improves the YOLOv3 by using normal illumination images as the source domain and low‐illumination images as the target domain and achieves object detection in low‐illumination images through an unsupervised learning strategy. Specifically, a multi‐scale local feature alignment and global feature alignment module are proposed to align the overall attributes of the image and feature biases such as background, scene, and target layout are thus reduced. The experimental results of LIDA‐YOLO on the ExDark dataset achieved the highest performance mAP score of 56.65% compared to several current state‐of‐the‐art unsupervised domain adaptation object detection methods. Compared to I3Net, the performance improvement is 4.04%, and compared to OSHOT, the performance improvement is 6.5%. LIDA‐YOLO achieves a performance improvement of 2.7% compared to the supervised baseline method YOLOv3. Overall, the suggested LIDA‐YOLO model requires fewer samples and presents a stronger generalization ability than previous works.

Abstract C035: Impact of South Florida environmental chemicals on breast cells derived from women of different ancestries

Abstract Breast Cancer (BC) occurrence is due to an interplay of ancestry-based and environmental factors. In order to study BC disparities in South Florida, our group initially focused on 7 Broward County zip codes where the proportion of BC identified at late stage is much higher (55%) than the national average (30-35%), and where there is a high percentage of people of African Ancestry (AA). Thus, we are investigating the interaction of ancestry and the environment in BC. Our hypothesis is that there are unique environmental sensitivities leading to BC that are associated with specific ancestral groups. We expect that some of the carcinogenic chemicals that cause BC may cause more advanced or aggressive BC in AA women. We are studying 2 environmental pollutants, one in water (arsenic) and one in soil (glyphosate) that are prevalent in S. Florida, and these local zip codes, and analyze the specific impact of these pollutants on unique breast reduction mammoplasty cultures derived from women of AA vs. Non-Hispanic White (NHW) ancestry. We have developed a unique tissue engineering system for non-diseased breast that allows us to establish cultures with high success (95%) using a stem cell-based medium and Matrigel. From primary cultures, we have established 38 extended explants (<13 passages) or cell lines (>13 passages). 10 are from AA women and 28 are from women of NHW ancestry, thus far with Hispanic samples in the works. We hypothesize that these groups will show significant differences in their gene expression patterns after exposure to environmental carcinogens. We have previously shown that there is a significantly higher proportion of breast stem cells in AA cultures (N=5) compared with the NHW cultures (N=5) (p= 0.028). This difference in size of the stem cell compartment may help to explain why the age of breast development in these two groups is significantly different and why their subtypes of BC are different based on ancestry. We are using 5 AA and 5 NHW breast reduction mammoplasty cultures, as well as stem cells derived from them, to test arsenic and glyphosate for their ability to alter the transcriptome of these cells using RNA sequencing. Analyses of gene expression using both supervised and unsupervised strategies will be performed (KEGG Pathways and single genes). We expect to see changes that are consistent with pre-invasive malignancy that have been established in endocrine disruptor studies. Because our group is one of the few that has successfully cultured stage 0 BC (Ductal Carcinoma In Situ), we have existing databases of transcriptomic changes from 6 DCIS cell lines as well as from 6 stage I BC cell lines for comparison. Preliminary data from the Nanostring BC360 and RNA sequencing show 8 genes involved in DNA damage and repair that are downregulated in AA breast reduction mammoplasty explants relative to NHW explants. This study will fill an important void in our understanding of how the environment affects pre-cancerous development in specific demographic populations. Citation Format: Jean J. Latimer, Yousef N. Alharbi, Colton R. Simmons, Stephen E. Zimberg, Essie K. Yates. Impact of South Florida environmental chemicals on breast cells derived from women of different ancestries [abstract]. In: Proceedings of the 16th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2023 Sep 29-Oct 2;Orlando, FL. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2023;32(12 Suppl):Abstract nr C035.

A novel unsupervised dynamic feature domain adaptation strategy for cross-individual myoelectric gesture recognition

Objective. Surface electromyography pattern recognition (sEMG-PR) is considered as a promising control method for human-machine interaction systems. However, the performance of a trained classifier would greatly degrade for novel users since sEMG signals are user-dependent and largely affected by a number of individual factors such as the quantity of subcutaneous fat and the skin impedance. Approach. To solve this issue, we proposed a novel unsupervised cross-individual motion recognition method that aligned sEMG features from different individuals by self-adaptive dimensional dynamic distribution adaptation (SD-DDA) in this study. In the method, both the distances of marginal and conditional distributions between source and target features were minimized through automatically selecting the optimal feature domain dimension by using a small amount of unlabeled target data. Main results. The effectiveness of the proposed method was tested on four different feature sets, and results showed that the average classification accuracy was improved by above 10% on our collected dataset with the best accuracy reached 90.4%. Compared to six kinds of classic transfer learning methods, the proposed method showed an outstanding performance with improvements of 3.2%-13.8%. Additionally, the proposed method achieved an approximate 9% improvement on a publicly available dataset. Significance. These results suggested that the proposed SD-DDA method is feasible for cross-individual motion intention recognition, which would provide help for the application of sEMG-PR based system.

Autostereoscopic 3D Measurement Based on Adaptive Focus Volume Aggregation

Autostereoscopic three-dimensional measuring systems are a kind of portable and fast precision metrology instrument. The systems are based on integral imaging that makes use of a micro-lens array before an image sensor to observe measured parts from multiple perspectives. Since autostereoscopic measuring systems can obtain longitudinal and lateral information within single snapshots rapidly, the three-dimensional profiles of the measured parts can be reconstructed by shape from focus. In general, the reconstruction process consists of data acquisition, pre-processing, digital refocusing, focus measures, and depth estimation. The accuracy of depth estimation is determined by the focus volume generated by focus measure operators which could be sensitive to the noise during digital refocusing. Without prior knowledge and surface information, directly estimated depth maps usually contain severe noise and incorrect representation of continuous surfaces. To eliminate the effects of refocusing noise and take advantage of traditional focus measure methods with robustness, an adaptive focus volume aggregation method based on convolutional neural networks is presented to optimize the focus volume for more accurate depth estimation. Since a large amount of data and ground truth are costly to acquire for model convergence, backpropagation is performed for every sample under an unsupervised strategy. The training strategy makes use of a smoothness constraint and an identical distribution constraint that restricts the difference between the distribution of the network output and the distribution of ideal depth estimation. Experimental results show that the proposed adaptive aggregation method significantly reduces the noise during depth estimation and retains more accurate surface profiles. As a result, the autostereoscopic measuring system can directly recover surface profiles from raw data without any prior information.

Learning a target-dependent classifier for cross-domain semantic segmentation: Fine-tuning versus meta-learning

Recently proposed domain adaptation arts have dominated the field of cross-domain semantic segmentation by operating domain manifolds alignment and learning an optimal joint hypothesis (joint-domain classifier) for both source and target domains. However, a joint-domain classifier can still violate the cluster assumption in the target domain in case domain manifolds are not fully aligned after domain adaptation. In this work, we raise the intractability of perfect domain alignment and turn to exploit a novel hypothesis: a target-dependent classifier, to efficiently adapt to the target domain clusters even given a certain degree of domain misalignment. Specifically, we first propose an unsupervised fine-tuning strategy, which optimizes the joint hypothesis of vanilla domain adaptation into a target-dependent hypothesis to better fit with the target domain clusters. Second, we connect the “learning to learn” concept of meta-learning with pixel-wise domain adaptation, which serves as a reliable hypothesis initialization, providing an alternative solution to learning a more generalized target-dependent classifier. The proposed learning method is general to conventional domain adaptation models. In experiments, we recycle the pre-trained conventional DA models and learn target-dependent classifiers with the proposed method. Experimental results on synthetic-to-real adaptation and cross-city adaptation benchmarks demonstrate that the target-dependent classifier leads over state-of-the-art performance.

Hidden Markov random field models for cell-type assignment of spatially resolved transcriptomics.

The recent development of spatially resolved transcriptomics (SRT)technologies has facilitated research on gene expression in the spatial context. Annotating cell types is one crucial step for downstream analysis. However, many existing algorithms use an unsupervised strategy to assign cell types for SRT data. They first conduct clustering analysis and then aggregate cluster-level expression based on the clustering results. This workflow fails to leverage the marker gene information efficiently. On the other hand, other cell annotation methods designed for single-cell RNA-seq data utilize the cell-type marker genes information but fail to use spatial information in SRT data. We introduce a statistical spatial transcriptomics cell assignment model, SPAN, to annotate clusters of cells or spots into known types in SRT data with prior knowledge of predefined marker genes and spatial information. The SPAN model annotates cells or spots from SRT data using predefined overexpressed marker genes and combines a mixture model with a hidden Markov random field to model the spatial dependency between neighboring spots. We demonstrate the effectiveness of SPAN against spatial and nonspatial clustering algorithms through extensive simulation and real data experiments. https://github.com/ChengZ352/SPAN.

Usage of model combination in computational toxicology

New Approach Methodologies (NAMs) have ushered in a new era in the field of toxicology, aiming to replace animal testing. However, despite these advancements, they are not exempt from the inherent complexities associated with the study's endpoint. In this review, we have identified three major groups of complexities: mechanistic, chemical space, and methodological. The mechanistic complexity arises from interconnected biological processes within a network that are challenging to model in a single step. In the second group, chemical space complexity exhibits significant dissimilarity between compounds in the training and test series. The third group encompasses algorithmic and molecular descriptor limitations and typical class imbalance problems. To address these complexities, this work provides a guide to the usage of a combination of predictive Quantitative Structure-Activity Relationship (QSAR) models, known as metamodels. This combination of low-level models (LLMs) enables a more precise approach to the problem by focusing on different sub-mechanisms or sub-processes. For mechanistic complexity, multiple Molecular Initiating Events (MIEs) or levels of information are combined to form a mechanistic-based metamodel. Regarding the complexity arising from chemical space, two types of approaches were reviewed to construct a fragment-based chemical space metamodel: those with and without structure sharing. Metamodels with structure sharing utilize unsupervised strategies to identify data patterns and build low-level models for each cluster, which are then combined. For situations without structure sharing due to pharmaceutical industry intellectual property, the use of prediction sharing, and federated learning approaches have been reviewed. Lastly, to tackle methodological complexity, various algorithms are combined to overcome their limitations, diverse descriptors are employed to enhance problem definition and balanced dataset combinations are used to address class imbalance issues (methodological-based metamodels). Remarkably, metamodels consistently outperformed classical QSAR models across all cases, highlighting the importance of alternatives to classical QSAR models when faced with such complexities.

Fast inverse lithography approach based on a model-driven graph convolutional network.

Inverse lithography technique (ILT) is a leading-edge method to improve the image fidelity of an advanced optical lithography system by performing pixel-wise optimization on the transmission function of photomask. However, traditional ILTs are computationally intensive, which limits their application in high volume manufacturing of integrated circuits. This paper proposes a model-driven graph convolutional network (MGCN) framework combined with the dense concentric circular sampling (DCCS) method to effectively improve computational efficiency and imaging fidelity of current ILTs. Firstly, the DCCS template is used to extract the geometric features from the layout pattern of integrated circuits, which are then input into a GCN-based encoder to predict the optimized mask pattern of the ILT. Then, a model-driven decoder based on the lithography imaging process is developed to retrieve the print image of the predicted ILT mask. By means of the cooperation between the encoder and decoder, an unsupervised training strategy is proposed to avoid the time-consuming labelling process of the training samples. With the help of the parallel computing under GPU framework, the well-trained encoder can make a fast prediction of ILT mask with high-fidelity image results. The results demonstrate the state-of-the-art performance of the proposed MGCN approach compared to some other comparative ILT methods.

Generating Parametric BRDFs from Natural Language Descriptions

AbstractArtistic authoring of 3D environments is a laborious enterprise that also requires skilled content creators. There have been impressive improvements in using machine learning to address different aspects of generating 3D content, such as generating meshes, arranging geometry, synthesizing textures, etc. In this paper we develop a model to generate Bidirectional Reflectance Distribution Functions (BRDFs) from descriptive textual prompts. BRDFs are four dimensional probability distributions that characterize the interaction of light with surface materials. They are either represented parametrically, or by tabulating the probability density associated with every pair of incident and outgoing angles. The former lends itself to artistic editing while the latter is used when measuring the appearance of real materials. Numerous works have focused on hypothesizing BRDF models from images of materials. We learn a mapping from textual descriptions of materials to parametric BRDFs. Our model is first trained using a semi‐supervised approach before being tuned via an unsupervised scheme. Although our model is general, in this paper we specifically generate parameters for MDL materials, conditioned on natural language descriptions, within NVIDIA's Omniverse platform. This enables use cases such as real‐time text prompts to change materials of objects in 3D environments such as “dull plastic” or “shiny iron”. Since the output of our model is a parametric BRDF, rather than an image of the material, it may be used to render materials using any shape under arbitrarily specified viewing and lighting conditions.

CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather With a High-Quality Real Snow Dataset

Snow is one of the toughest adverse weather conditions for object detection (OD). Currently, not only there is a lack of snowy OD datasets to train cutting-edge detectors, but also these detectors have difficulties of learning latent information beneficial for detection in snow. To alleviate the two above problems, we first establish a real-world snowy OD dataset, named RSOD. Besides, we develop an unsupervised training strategy with a distinctive activation function, called <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Peak \ Act$</tex-math> </inline-formula> , to quantitatively evaluate the effect of snow on each object. Peak Act helps grade the images in RSOD into four-difficulty levels. To our knowledge, RSOD is the first quantitatively evaluated and graded real-world snowy OD dataset. Then, we propose a novel Cross Fusion (CF) block to construct a lightweight OD network based on YOLOv5s (called CF-YOLO). CF is a plug-and-play feature aggregation module, which integrates the advantages of Feature Pyramid Network and Path Aggregation Network in a simpler yet more flexible form. Both RSOD and CF lead our CF-YOLO to possess an optimization ability for OD in real-world snow. That is, CF-YOLO can handle unfavorable detection problems of vagueness, distortion and covering of snow. Experiments show that our CF-YOLO achieves better detection results on RSOD, compared to SOTAs. The code and dataset are available at https://github.com/qqding77/CF-YOLO-and-RSOD.

Deep-learning for automated markerless tracking of infants general movements

The presence of abnormal infant General Movements (GMs) is a strong predictor of progressive neurodevelopmental disorders, including cerebral palsy (CP). Automation of the assessment will overcome scalability barriers that limit its delivery to at-risk individuals. Here, we report a robust markerless pose-estimation scheme, based on advanced deep-learning technology, to track infant movements in consumer mobile device video recordings. Two deep neural network models, namely Efficientnet-b6 and resnet-152, were trained on manually annotated data across twelve anatomical locations (3 per limb) in 12 videos from 6 full-term infants (mean age = 17.33 (SD 2.9) wks, 4 male, 2 female), using the DeepLabCut™ framework. K-fold cross-validation indicates the generalization capability of the deep-nets for GM tracking on out-of-domain data with an overall performance of 95.52% (SD 2.43) from the best performing model (Efficientnet-b6) across all infants (performance range: 84.32–99.24% across all anatomical locations). The paper further introduces an automatic, unsupervised strategy for performance evaluation on extensive out-of-domain recordings through a fusion of likelihoods from a Kalman filter and the deep-net. Findings indicate the possibility of establishing an automated GM tracking platform, as a suitable alternative to, or support for, the current observational protocols for early diagnosis of neurodevelopmental disorders in early infancy.

UDATNN: A modeling scheme integrating unsupervised domain adversarial learning and tri-training strategy for variety recognition of maize seeds with domain shift

Constructing an accurate classification model is the key to realizing maize seed varieties identification based on optical sensing techniques. However, the optical information (features) of seeds collected by optical sensing technology is easily affected by the planting environment (e.g., origin, year), which makes the training samples used to construct the model (source domain, SD) and the samples to be recognized (target domain, TD) subject to domain shift (DS), and ultimately undermines the recognition performance of the model. In this study, a modeling scheme, called unsupervised domain adversarial tri-training of neural networks (UDATNN), is proposed for maize variety recognition in the presence of DS. Firstly, an unsupervised domain adversarial learning approach is used to map the raw features of the SD and TD into a low-dimensional feature space in order to achieve feature alignment of the SD and TD, and to improve the feature discriminability of different varieties of seeds. Subsequently, the aligned low-dimensional features are used as inputs of classifiers (random forest) and part of the target domain samples are iteratively selected and given pseudo-labels according to the tri-training strategy. Finally, these samples assigned with pseudo-labels (called updating samples) together with the training samples in SD are used to re-train the classification model constructed based on the unsupervised domain adversarial strategy, for improving recognition accuracy of seed varieties with DS scenario. Hyperspectral images of a total of 4584 maize seeds, including 7 varieties (each variety produced from two or three years) were collected to verify the performance of the proposed scheme. The recognition accuracy of the target domain reaches 91.5%, 94.1%, and 92.6% under 3 different domain shifts, which improves the recognition performance nearly by 8%–22% compared with the no-transfer model and the traditional transfer model. The model performance was further discussed by calculating precision, recall, and F1 score to achieve satisfactory results. The robustness of the model was also verified by discussing the randomness of the update samples and the effect of the number of samples in the source domain on the model performance through 100 random experiments and multiple experimental comparisons. The proposed UDATNN scheme can be used as a new framework to address the nondestructive identification of seed varieties under domain shift conditions.

Rolling Bearing Fault Diagnosis across Operating Conditions Based on Unsupervised Domain Adaptation

In practical industrial scenarios, mechanical equipment frequently operates within dynamic working conditions. To address the challenge posed by the incongruent data distribution between source and target domains amidst varying operational contexts, particularly in the absence of labels within the target domain, this study presents a solution involving deep feature construction and an unsupervised domain adaptation strategy for rolling bearing fault diagnosis across varying working conditions. The proposed methodology commences by subjecting the original vibration signal of the bearing to a fast Fourier transform (FFT) to extract spectral information. Subsequently, an innovative amalgamation of a one-dimensional convolutional layer and an auto-encoder were introduced to construct a convolutional auto-encoder (CAE) dedicated to acquiring depth features from the spectrum. In a subsequent step, leveraging the depth features gleaned from the convolutional auto-encoder, a balanced distribution adaptation (BDA) mechanism was introduced to facilitate the domain adaptation of features from both the source and target domains. The culminating stage entails the classification of adapted features using the K-nearest neighbor (KNN) algorithm to attain cross-domain diagnosis. Empirical evaluations are conducted on two extensively used datasets. The findings substantiate that the proposed approach is capable of accomplishing the cross-domain fault diagnosis task even without labeled data within the target domain. Furthermore, the diagnostic accuracy and stability of the proposed method surpass those of various other migration and deep learning approaches.