Network embedding task aims at learning low-dimension latent representations of vertices while preserving the structure of a network simultaneously. Most existing network embedding methods mainly ...focus on static networks, which extract and condense the network information without temporal information. However, in the real world, networks keep evolving, where the linkage states between the same vertex pairs at consequential timestamps have very close correlations. In this paper, we propose to study the network embedding problem and focus on modeling the linkage evolution in the dynamic network setting. To address this problem, we propose a deep dynamic network embedding method. More specifically, the method utilizes the historical information obtained from the network snapshots at past timestamps to learn latent representations of the future network. In the proposed embedding method, the objective function is carefully designed to incorporate both the network internal and network dynamic transition structures. Extensive empirical experiments prove the effectiveness of the proposed model on various categories of real-world networks, including a human contact network, a bibliographic network, and e-mail networks. Furthermore, the experimental results also demonstrate the significant advantages of the method compared with both the state-of-the-art embedding techniques and several existing baseline methods.
Compared with the gold standard, polysomnography (PSG), and silver standard, actigraphy, contactless consumer sleep-tracking devices (CCSTDs) are more advantageous for implementing large-sample and ...long-period experiments in the field and out of the laboratory due to their low price, convenience, and unobtrusiveness. This review aimed to examine the effectiveness of CCSTDs application in human experiments. A systematic review and meta-analysis (PRISMA) of their performance in monitoring sleep parameters were conducted (PROSPERO: CRD42022342378). PubMed, EMBASE, Cochrane CENTRALE, and Web of Science were searched, and 26 articles were qualified for systematic review, of which 22 provided quantitative data for meta-analysis. The findings show that CCSTDs had a better accuracy in the experimental group of healthy participants who wore mattress-based devices with piezoelectric sensors. CCSTDs' performance in distinguishing waking from sleeping epochs is as good as that of actigraphy. Moreover, CCSTDs provide data on sleep stages that are not available when actigraphy is used. Therefore, CCSTDs could be an effective alternative tool to PSG and actigraphy in human experiments.
•A constant residual noise power constraint for rank-1 MWF is proposed.•Speech covariance matrix reconstruction to fulfill the rank-1 assumption.•An extensive comparison of the multichannel linear ...filters supported by BLSTM.•A feature variance metric that correlates with the word error rate.
Multichannel linear filters, such as the Multichannel Wiener Filter (MWF) and the Generalized Eigenvalue (GEV) beamformer are popular signal processing techniques which can improve speech recognition performance. In this paper, we present an experimental study on these linear filters in a specific speech recognition task, namely the CHiME-4 challenge, which features real recordings in multiple noisy environments. Specifically, the rank-1 MWF is employed for noise reduction and a new constant residual noise power constraint is derived which enhances the recognition performance. To fulfill the underlying rank-1 assumption, the speech covariance matrix is reconstructed based on eigenvectors or generalized eigenvectors. Then the rank-1 constrained MWF is evaluated with alternative multichannel linear filters under the same framework, which involves a Bidirectional Long Short-Term Memory (BLSTM) network for mask estimation. The proposed filter outperforms alternative ones, leading to a 40% relative Word Error Rate (WER) reduction compared with the baseline Weighted Delay and Sum (WDAS) beamformer on the real test set, and a 15% relative WER reduction compared with the GEV-BAN method. The results also suggest that the speech recognition accuracy correlates more with the Mel-frequency cepstral coefficients (MFCC) feature variance than with the noise reduction or the speech distortion level.
Recently, there has been increasing progress in end-to-end automatic speech recognition (ASR) architecture, which transcribes speech to text without any pre-trained alignments. One popular end-to-end ...approach is the hybrid Connectionist Temporal Classification (CTC) and attention (CTC/attention) based ASR architecture, which utilizes the advantages of both CTC and attention. The hybrid CTC/attention ASR systems exhibit performance comparable to that of the conventional deep neural network (DNN)/ hidden Markov model (HMM) ASR systems. However, how to deploy hybrid CTC/attention systems for online speech recognition is still a non-trivial problem. This article describes our proposed online hybrid CTC/attention end-to-end ASR architecture, which replaces all the offline components of conventional CTC/attention ASR architecture with their corresponding streaming components. Firstly, we propose stable monotonic chunk-wise attention (sMoChA) to stream the conventional global attention, and further propose monotonic truncated attention (MTA) to simplify sMoChA and solve the training-and-decoding mismatch problem of sMoChA. Secondly, we propose truncated CTC (T-CTC) prefix score to stream CTC prefix score calculation. Thirdly, we design dynamic waiting joint decoding (DWJD) algorithm to dynamically collect the predictions of CTC and attention in an online manner. Finally, we use latency-controlled bidirectional long short-term memory (LC-BLSTM) to stream the widely-used offline bidirectional encoder network. Experiments with LibriSpeech English and HKUST Mandarin tasks demonstrate that, compared with the offline CTC/attention model, our proposed online CTC/attention model improves the real time factor in human-computer interaction services and maintains its performance with moderate degradation. To the best of our knowledge, this is the first work to provide the full-stack online solution for CTC/attention end-to-end ASR architecture.
Anabolic androgenic steroids (AASs) are usually illegally added to animal feed because they can significantly promote animal growth and increase carcasses' leanness, which threatens the safety of ...animal-derived foods and indirectly hazards human health. This study aimed to establish an ultra-high performance liquid chromatography-tandem mass spectrometry (UHPLC-MS/MS) method for the simultaneous detection of twelve AAS residues in livestock and poultry meat. The homogenized samples were extracted with acetonitrile containing 1% acetic acid (
/
) and purified using the one-step extraction column. After concentration using nitrogen, the residues were redissolved in acetonitrile and then quantified with an external standard method using UHPLC-MS/MS. The results showed that the above-mentioned method had a satisfactory linear correlation (
≥ 0.9903) with a concentration range of 1-100 μg/L, and the limits of detection (LODs) and quantification (LOQs) were 0.03-0.33 μg/kg and 0.09-0.90 μg/kg, respectively. With the intraday and interday precision less than 15%, the average recoveries of pork, beef, lamb, and chicken, at different spiked levels, ranged from 68.3 to 93.3%, 68.0 to 99.4%, 71.6 to 109.8%, and 70.5 to 97.7%, respectively. Overall, the established method is validated, precise, and capable of the high-throughput determination of the residues of twelve AASs in livestock and poultry meat.
Deep neural networks (DNNs) have been shown to be effective for single sound source localization in shallow water environments. However, multiple source localization is a more challenging task ...because of the interactions among multiple acoustic signals. This paper proposes a framework for multiple source localization on underwater horizontal arrays using deep neural networks. The two-stage DNNs are adopted to determine both the directions and ranges of multiple sources successively. A feed-forward neural network is trained for direction finding, while the long short term memory recurrent neural network is used for source ranging. Particularly, in the source ranging stage, we perform subarray beamforming to extract features of sources that are detected by the direction finding stage, because subarray beamforming can enhance the mixed signal to the desired direction while preserving the horizontal-longitudinal correlations of the acoustic field. In this way, a universal model trained in the single-source scenario can be applied to multi-source scenarios with arbitrary numbers of sources. Both simulations and experiments in a range-independent shallow water environment of SWellEx-96 Event S5 are given to demonstrate the effectiveness of the proposed method.
In recent years, the role of video games in enhancing brain plasticity and learning ability has been verified, and this learning transfer is known as the "learning to learn" effect of video game ...training. At the same time, against the background of healthy lighting, the influence of non-visual effects of light environment on the human rhythmic system has been gradually confirmed. As a special operation form of Visual Display Terminal (VDT) operation, video game training has a high dependence on VDT equipment and the VDT screen, and the background usually has a huge difference in brightness. Compared with the light environment of ordinary operation space, the light environment of VDT operation space is more complex. This complex light environment's non-visual effects cause human emotions, alertness, fatigue, cognitive ability, and other changes, which may affect the efficiency of the "learning to learn" effect of video game training. This article focuses on the impact of the light environment in the VDT workspace on the "learning to learn" effect of video game training. It first traces the factors that trigger the "learning to learn" effect of video game training, that is, the improvement of people's attention, perception, and cognitive ability. Then, the influencing mechanism and the evaluation method of the VDT workspace space light environment on the human rhythm system are discussed based on the basic theory of photobiological effect. In addition, the VDT display lighting light time pattern, photophysical properties, regulation, and protection mechanism on the human rhythm system are studied to demonstrate the VDT workspace light environment's special characteristics. Finally, combined with the progress of artificial lighting technology and the research results of health lighting, given the "learning to learn" effect of video game training, some thoughts on the design of the light environment of the workplace and future research directions are presented.
•Adenoviral delivery of CRISPR/Cas9 produces efficient gene editing in cultured cells.•Effective gene knockout in the adult mouse liver via adenoviral delivery of CRISPR/Cas9.•The gene editing in the ...liver is stable over long term and after extensive liver tissue regeneration.
We developed an adenovirus-based CRISPR/Cas9 system for gene editing in vivo. In the liver, we demonstrated that the system could reach the level of tissue-specific gene knockout, resulting in phenotypic changes. Given the wide spectrum of cell types susceptible to adenoviral infection, and the fact that adenoviral genome rarely integrates into its host cell genome, we believe the adenovirus-based CRISPR/Cas9 system will find applications in a variety of experimental settings.
Internal mildewed nutmeg is difficult to perceive without cutting the nutmeg open and examining it carefully, which poses a significant risk to public health. At present, macroscopic identification ...and chromatographic analysis are applied to determine whether nutmeg is moldy or not. However, the former relies on a human panel, with the disadvantages of subjectivity and empirical dependence, whilst the latter is generally time-consuming and requires organic solvents. Therefore, it is urgent to develop a rapid and feasible approach for evaluating the quality and predicting mildew in nutmeg. In this study, the quality and odor characteristics of five groups of nutmeg samples with different degrees of mildew were analyzed by using the responses of an electronic nose combined with chemical profiling. The main physicochemical indicators, such as the levels of α-pinene, β-pinene, elemicin, and dehydro-di-isoeugenol, were determined. The results revealed that the contents of α-pinene, β-pinene, and elemicin changed significantly with the extension of storage time. Through the use of an electronic nose and HS–GC–MS technology to assess the overall odor characteristics of nutmeg samples, it was found that the production of volatile organic compounds (VOCs) such as ammonia/organic amines, carbon monoxide, ethanol, and hydrogen sulfide, as well as changes in the terpene and phenylpropene components of the nutmeg itself, may be the material basis for the changes in odor. The accuracy of the qualitative classification model for the degree of mildew in nutmeg was higher than 90% according to the electronic nose data combined with different machine learning algorithms. Quantitative models were established for predicting the contents of the chemical components, and models based on a BP neural network (BPNN), the support vector machine (SVM), and the random forest algorithm (RF) all showed good performance in predicting the concentrations of these chemical components, except for dehydro-di-isoeugenol. The BPNN performed effectively in predicting the storage time of nutmeg on the basis of the E-nose’s responses, with an RMSE and R2 of 0.268 and 0.996 for the training set, and 0.317 and 0.993 for the testing set, respectively. The results demonstrated that the responses of the electronic nose (E-nose) had a high correlation with the internal quality of nutmeg. This work proposes a quick and non-destructive evaluation method for the quality of nutmeg, which has high accuracy in discriminating between different degrees of mold in nutmeg and is conducive to early detection and warning of moldy phenomena.
The transformation and reconstruction of traditional villages into "post-rural" tourism communities constitute a primary pathway for achieving modernization in rural areas on the outskirts of large ...metropolitan areas and advancing countryside revitalization. The evolutionary process of this transition also serves as an important perspective for understanding the socio-economic development of rural areas in China. We selected Chengdu Bamboo Craft Village as a case study, employing a comprehensive rural spatial framework based on the "rural locality-representations of the rural-everyday lives of the rural." Grounded in a multi-dimensional analysis perspective of "capital-power-individual," it dissects the multi-dimensional spatial reproduction process of "post-rural" tourism communities, aiming to provide support for exploring the spatial evolution, relational changes, and governance practices of rural tourism destinations under the backdrop of capital invest in rural areas. The main conclusions drawn are as fo
PDF
