Bidirectional consistency with temporal-aware for semi-supervised time series classification.

Semi-supervised learning (SSL) has achieved significant success due to its capacity to alleviate annotation dependencies. Most existing SSL methods utilize pseudo-labeling to propagate useful supervised information for training unlabeled data. However, these methods ignore learning temporal representations, making it challenging to obtain a well-separable feature space for modeling explicit class boundaries. In this work, we propose a semi-supervised Time Series classification framework via Bidirectional Consistency with Temporal-aware (TS-BCT), which regularizes the feature space distribution by learning temporal representations through pseudo-label-guided contrastive learning. Specifically, TS-BCT utilizes time-specific augmentation to transform the entire raw time series into two distinct views, avoiding sampling bias. The pseudo-labels for each view, generated through confidence estimation in the feature space, are then employed to propagate class-related information into unlabeled samples. Subsequently, we introduce a temporal-aware contrastive learning module that learns discriminative temporal-invariant representations. Finally, we design a bidirectional consistency strategy by incorporating pseudo-labels from two distinct views into temporal-aware contrastive learning to construct a class-related contrastive pattern. This strategy enables the model to learn well-separated feature spaces, making class boundaries more discriminative. Extensive experimental results on real-world datasets demonstrate the effectiveness of TS-BCT compared to baselines.

Pseudo anomalies enhanced deep support vector data description for electrocardiogram quality assessment.

Electrocardiogram (ECG) recordings obtained from wearable devices are susceptible to noise interference that degrades the signal quality. Traditional methods for assessing the quality of electrocardiogram signals (SQA) are mostly supervised and typically rely on limited types of noise in the training data, which imposes limitations in detecting unknown anomalies. The high variability of both ECG signals and noise presents a greater challenge to the generalization of traditional methods. In this paper, we propose a simple and effective unsupervised SQA method by modeling the SQA of ECG as a problem of anomaly detection, in which, a model of pseudo anomalies enhanced deep support vector data description is introduced to learn a more discriminative and generalized hypersphere of the high-quality ECG in a self-supervised manner. Specifically, we propose a series of ECG noise-generation methods to simulate the noise of real scenarios and use the generated noise samples as the pseudo anomalies to correct the hypersphere learned solely by the high-quality ECG samples. Finally, the quality of ECG can be measured based on the distance to the center of the hypersphere. Extensive experimental results on multiple public datasets and our constructed real-world 12-lead dataset demonstrate the effectiveness of the proposed method.

The Antitumour Activity of a Curcumin and Piperine Loaded iRGD-Modified Liposome: In Vitro and In Vivo Evaluation.

Lung cancer is one of the most common cancers around the world, with a high mortality rate. Despite substantial advancements in diagnoses and therapies, the outlook and survival of patients with lung cancer remains dismal due to drug tolerance and malignant reactions. New interventional treatments urgently need to be explored if natural compounds are to be used to reduce toxicity and adverse effects to meet the needs of lung cancer clinical treatment. An internalizing arginine-glycine-aspartic acid (iRGD) modified by a tumour-piercing peptide liposome (iRGD-LP-CUR-PIP) was developed via co-delivery of curcumin (CUR) and piperine (PIP). Its antitumour efficacy was evaluated and validated via in vivo and in vitro experiments. iRGD-LP-CUR-PIP enhanced tumour targeting and cellular internalisation effectively. In vitro, iRGD-LP-CUR-PIP exhibited enhanced cellular uptake, suppression of tumour cell multiplication and invasion and energy-independent cellular uptake. In vivo, iRGD-LP-CUR-PIP showed high antitumour efficacy, mainly in terms of significant tumour volume reduction and increased weight and spleen index. Data showed that iRGD peptide has active tumour targeting and it significantly improves the penetration and cellular internalisation of tumours in the liposomal system. The use of CUR in combination with PIP can exert synergistic antitumour activity. This study provides a targeted therapeutic system based on natural components to improve antitumour efficacy in lung cancer.

Synthesizing the complex orbital-angular-momentum spectrum of hybrid modes existed in a few-mode fiber.

In this study, a simple and reliable method enabling to well synthesize the complex orbit-angular-momentum (OAM) spectrum of hybrid mode in a few-mode fiber is proposed and numerically demonstrated, which is realized by using the so-called inverse scattering method based on the genetic algorithm (GA), where the main Fourier components of a specially-selected ring in intensity distribution of the hybrid mode is used as the optimization objective. As a proof-of-concept example, power spectrum of a hybrid mode consisted of the first- and second-order OAM modes was successfully reconstructed with an accuracy higher than 0.99. This is the first time, to the best of our knowledge, that the complex OAM spectrum of a fiber hybrid mode consisted of more than two kinds of OAM modes is synthesized directly from the intensity distribution of the hybrid mode itself.