Clinical studies have shown that speech pauses can reflect the cognitive function differences between Alzheimer’s Disease (AD) and non-AD patients, while the value of pause information in AD detection has not been fully explored. Herein, we propose a speech pause feature extraction and encoding strategy for only acoustic-signal-based AD detection. First, a voice activity detection (VAD) method was constructed to detect pause/non-pause feature and encode it to binary pause sequences that are easier to calculate. Then, an ensemble machine-learning-based approach was proposed for the classification of AD from the participants’ spontaneous speech, based on the VAD Pause feature sequence and common acoustic feature sets (ComParE and eGeMAPS). The proposed pause feature sequence was verified in five machine-learning models. The validation data included two public challenge datasets (ADReSS and ADReSSo, English voice) and a local dataset (10 audio recordings containing five patients and five controls, Chinese voice). Results showed that the VAD Pause feature was more effective than common feature sets (ComParE: 6373 features and eGeMAPS: 88 features) for AD classification, and that the ensemble method improved the accuracy by more than 5% compared to several baseline methods (8% on the ADReSS dataset; 5.9% on the ADReSSo dataset). Moreover, the pause-sequence-based AD detection method could achieve 80% accuracy on the local dataset. Our study further demonstrated the potential of pause information in speech-based AD detection, and also contributed to a more accessible and general pause feature extraction and encoding method for AD detection.

Purpose: Electrocardiogram (ECG) signals collected from wearable devices are easily corrupted with surrounding noise and artefacts, where the signal-to-noise ratio (SNR) of wearable ECG signals is significantly lower than that from hospital ECG machines. To meet the requirements for monitoring heart disease via wearable devices, eliminating useless or poor-quality ECG signals (e.g., lead-falls and low SNRs) can be solved by signal quality assessment algorithms. Methods: To compensate for the deficiency of the existing ECG quality assessment system, a wearable ECG signal dataset from heart disease patients collected by Lenovo H3 devices was constructed. Then, this paper compares the performance of three machine learning algorithms, i.e., the traditional support vector machine (SVM), least-squares SVM (LS-SVM) and long short-term memory (LSTM) algorithms. Different non-morphological signal quality indices (i.e., the approximate entropy (ApEn), sample entropy (SaEn), fuzzy measure entropy (FMEn), Hurst exponent (HE), kurtosis (K) and power spectral density (PSD) features) extracted from the original ECG signals are fed into the three algorithms as input. Results: The true positive rate, true negative rate, sensitivity and accuracy are used to evaluate the performance of each method, and the LSTM algorithm achieves the best results on these metrics (97.14%, 86.8%, 97.46% and 95.47%, respectively). Conclusions: Among the three algorithms, the LSTM-based quality assessment method is the most suitable for the signals collected by the Lenovo H3 devices. The results also show that the combination of statistical features can effectively evaluate the quality of ECG signals.

Hepatitis B virus (HBV) is a significant public health problem worldwide. Hepatitis B surface antigen (HBsAg) is the principle marker for laboratory testing of HBV, but the rapid identification of HBsAg is challenging in a resource-limited setting. Antibodies to HBsAg (Anti-HBs) levels are measured as markers for an immune response to vaccination as well as for decision making for specific treatment against Hepatitis-B. This research developed a prototype for the rapid detection of HBsAg using immunomagnetic separation, dynamic light scattering, and support vector machine. Magnetic beads coated with polyclonal anti-HBsAg were used to isolate HBsAg from the sample. The performance characteristics of quantitative real-time detection of HBsAg were characterized under optimized conditions. Twelve photodetectors were arranged on four concentric curvatures at different angles. The photodetectors were positioned around the sample flask in forward direction. The prototype acquires the real-time laser scattering light from the sample, and the noise was removed. The power spectral features were extracted from the acquired signal. Support vector machines (SVM) were used for training a classification algorithm by using extracted features. The overall classification accuracy for the identification of HBsAg was 87.7%. The HBsAg detection test was also performed on 20 serum specimens, with 10 serum samples were positive for HBsAg and 10 were healthy control subjects. The test had a dynamic range of 98.86 IU/mL to 3163.5 IU/mL. Results of HBsAg detection agreed completely with those of conventional Chemiluminescence Immunoassay (CLIA). In conclusion, the proposed HBsAg detection method can differentiate the sample that contains HBsAg enriched IM beads and blank IM beads.

The 12-lead electrocardiogram (ECG) is crucial in assessing patient decisions. However, portable ECG devices capable of acquiring a complete 12-lead ECG are scarce. For the first time, a deep learning-based method is proposed to reconstruct the 12-lead ECG from Frank leads (V_X, V_Y, and V_Z) or EASI leads (V_ES, V_AS, and V_AI). The innovative ECG reconstruction network called M2Eformer is composed of a 2D-ECGblock and a ProbDecoder module. The 2D-ECGblock module adaptively segments EASI leads into multi-periods based on frequency energy, transforming the 1D time series into a 2D tensor representing within-cycle and between-cycle variations. The ProbDecoder module aims to extract Probsparse self-attention and achieve one-step output for the target leads. Experimental results from comparing recorded and reconstructed 12-lead ECG using Frank leads indicate that M2Eformer outperforms traditional ECG reconstruction methods on a public database. In this study, a self-constructed database (10 healthy individuals + 15 patients) was utilized for the clinical diagnostic validation of ECG reconstructed from EASI leads. Subsequently, both the ECG reconstructed using EASI and the recorded 12-lead ECG were subjected to a double-blind diagnostic experiment conducted by three cardiologists. The overall diagnostic consensus among three cardiology experts, reaching a rate of 96%, indicates the significant utility of EASI-reconstructed 12-lead ECG in facilitating the diagnosis of cardiac conditions.

The recognition of animal behavior can enhance the accuracy and repeatability of animal experiments, provide reliable data and conclusions for scientific research, which has significant theoretical research implications and practical application value. Compared with human behavior analysis, animal behavior analysis develops slowly due to the limitation of labeled datasets, and research is often restricted to target detection. However, in recent years, the research of skeleton modeling based on deep learning can provide skeleton information and motion characteristics for animal behavior analysis, which has become an important method in the field of animal behavior research. This article integrates the latest research findings on animal behavior recognition using deep learning algorithms, with a focus on typical algorithms for pose estimation and skeleton modeling. Then, the typical algorithms and general evaluation indicators are sorted out, and their performance is compared on common datasets. Finally, the challenging and pressing issues in this field are summarized, and the future development trend is prospected.

Text-to-speech (TTS) synthesizers have been widely used as a vital assistive tool in various fields. Traditional sequence-to-sequence (seq2seq) TTS such as Tacotron2 uses a single soft attention mechanism for encoder and decoder alignment tasks, which is the biggest shortcoming that incorrectly or repeatedly generates words when dealing with long sentences. It may also generate sentences with run-on and wrong breaks regardless of punctuation marks, which causes the synthesized waveform to lack emotion and sound unnatural. In this paper, we propose an end-to-end neural generative TTS model that is based on the deep-inherited attention (DIA) mechanism along with an adjustable local-sensitive factor (LSF). The inheritance mechanism allows multiple iterations of the DIA by sharing the same training parameter, which tightens the token–frame correlation, as well as fastens the alignment process. In addition, LSF is adopted to enhance the context connection by expanding the DIA concentration region. In addition, a multi-RNN block is used in the decoder for better acoustic feature extraction and generation. Hidden-state information driven from the multi-RNN layers is utilized for attention alignment. The collaborative work of the DIA and multi-RNN layers contributes to outperformance in the high-quality prediction of the phrase breaks of the synthesized speech. We used WaveGlow as a vocoder for real-time, human-like audio synthesis. Human subjective experiments show that the DIA-TTS achieved a mean opinion score (MOS) of 4.48 in terms of naturalness. Ablation studies further prove the superiority of the DIA mechanism for the enhancement of phrase breaks and attention robustness.