Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks35 from public data
- An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series364
A systematic and comprehensive evaluation of unsupervised and semisupervised deep-learning-based methods for anomaly detection and diagnosis on multivariate time series data from cyberphysical systems finds that a simple, channel-wise model—the univariate fully connected auto-encoder, with the dynamic Gaussian scoring function emerges as a winning candidate for both anomaly Detection and diagnosis, beating state-of-the-art algorithms.
- Client Selection for Federated Learning With Non-IID Data in Mobile Edge Computing230
This paper proposes an efficient FL algorithm, named CSFedAvg, in which the clients with lower degree of non-IID data will be chosen to train the models with higher frequency, and conducts simulations using publicly-available datasets to train deep neural networks.
- 206
- Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition163
A template selection approach based on Dynamic Time Warping is proposed, such that complex feature extraction and domain knowledge is avoided and the predictive capability of the algorithm is demonstrated on both simulated and real smartphone data.
- A Survey and Evaluation of Adversarial Attacks in Object Detection32
This article presents a novel taxonomic framework for categorizing adversarial attacks specific to object detection architectures, synthesizes existing robustness metrics, and provides a comprehensive empirical evaluation of state-of-the-art attack methodologies on popular object detection models, including both traditional detectors and modern detectors with vision-language pretraining.
- Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-training30
The Co-learn algorithm is proposed to improve target pseudolabel quality collaboratively through the source model and a pre-trained feature extractor to improve adaptation performance and can be successfully integrated with existing SFDA methods.
- Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation29
This work proposes to integrate the pre-trained network into the target adaptation process as it has diversified features important for generalization and provides an alternate view of features and classification decisions different from the source model.
- Visible-near infrared spectrum-based classification of apple chilling injury on cloud computing platform28
The experimental results showed that, by using the cloud computing platform, an efficient spectrum classification model of apple chilling injury was established; the ANN model had slightly higher accuracy than the SVM model (not including the second-derivative spectra), but the S VM model was more efficient.
- Data Analysis and Forecasting of Tuberculosis Prevalence Rates for Smart Healthcare Based on a Novel Combination Model21
Numerical results show that the developed combination model is not only simple, but is also able to satisfactorily approximate the actual tuberculosis prevalence rate, and can be an effective tool in mining and analyzing big data in the medical field.
- Subject-Independent Wearable P300 Brain–Computer Interface Based on Convolutional Neural Network and Metric Learning18
A calibration-free wearable P300 BCI system is feasible, suggesting significant potential for practical applications of the wearable P300 BCI system.
- 12
- 12
- 11
- Robust Domain-Free Domain Generalization with Class-Aware Alignment9
The proposed DomainFree Domain Generalization (DFDG), a model-agnostic method to achieve better generalization performance on the unseen test domain without the need for source domain labels, is proposed.
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias8
This work introduces Universal Semi-Supervised Do-main Adaptation (UniSSDA), a practical yet challenging setting where the target domain is partially labeled, and the source and target label space may not strictly match.
- 8
- POLA: Online Time Series Prediction by Adaptive Learning Rates7
This work proposes POLA (Predicting Online by Learning rate Adaptation) to automatically regulate the learning rate of recurrent neural network models to adapt to changing time series patterns across time.
- HALO: Learning to Prune Neural Networks with Shrinkage7
A novel penalty called Hierarchical Adaptive Lasso (HALO) which learns to adaptively sparsify weights of a given network via trainable parameters is presented which is able to learn highly sparse network with significant gains in performance over state-of-the-art magnitude pruning methods at the same level of sparsity.
- Performance Evaluation of Machine Learning Approaches for Credit Scoring7
The final experiment results indicate that the XGBoost classifier has a better performance in predictive analytics compared with the other seven models.
- Evidentially Calibrated Source-Free Time-Series Domain Adaptation With Temporal Imputation6
MAsk And imPUte (MAPU), which tackles temporal consistency through a novel imputation task, where randomly masked time series signals are recovered within the learned embedding space, achieving state-of-the-art performance through its uncertainty-aware adaptation strategy.
- Performance analysis of clustering method based on crop pest spectrum6
A scheme to analyze the clustering performance of crop pests spectra with the K-Means and the FCM clustering methods is proposed, and Matlab 2012b was used to realize the two clustering algorithms and analyze these clustering results.
- 5
- 3
- 3
- A Survey and Evaluation of Adversarial Attacks for Object Detection2
A comprehensive taxonomy of adversarial attacks specific to object detection is offered, existing adversarial robustness evaluation metrics are reviewed, and open-source attack methods and model robustness are systematically assessed.
- Domain Generalization via Selective Consistency Regularization for Time Series Classification2
This paper hypothesizes that domains share different class-informative representations, so instead of aligning all domains which can cause negative transfer, they only regularize the discrepancy between closely-related domains.
- 2
- 2
- Analysis of the Key Points of Higher Vocational Digital Film and Television Course Teaching under the Background of Integrated Media1
There are problems in the teaching of digital film and television courses in higher vocational colleges, and solutions are proposed to reform the teaching and make contributions to digital media companies in my country.
- Temporal-Directional Tree-Walk Graph Neural Network for Illicit Transaction Detection–
Results, together with ablation studies, demonstrate that TDTW-GNN effectively captures temporal motifs and directional flows, significantly enhancing illicit transaction detection in dynamic financial networks.
- –
- SS-CTML: Self-Supervised Cross-Task Mutual Learning for CT Image Reconstruction–
Experimental results demonstrate that the SS-CTML framework can obtain promising CT image reconstruction performance in terms of both quantitative and qualitative measurements.
- Potential relation between Covid-19 vaccines and Covid-19 death number–
The statistical research in this paper helps with the evaluation of vaccine efficacy so that safer and more effective vaccines can be selected to reduce mortality.
- Hierarchical Adaptive Lasso: Learning Sparse Neural Networks with Shrinkage via Single Stage Training.–
A novel penalty called Hierarchical Adaptive Lasso (HALO) which learns to adaptively sparsify weights of a given network via trainable parameters without learning a mask is presented.
- Noise management features of the open speech platform–
Noise management features of the Open Speech Platform for hearing aid (HA) research; optimizations to meet time and CPU budgets; and preliminary objective and subjective results of the proposed system are presented.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.