Search

Time-resolved X-ray photoelectron spectroscopy (TXPS) is a well-established technique to probe coherent nuclear wavepacket dynamics using both table-top and free-electron-based ultrafast X-ray lasers. Energy resolution, however, becomes compromised for a very short pulse duration in the sub-femtosecond range. By resonantly tuning the X-ray pulse to core-excited states undergoing Auger decay, this drawback of TXPS can be mitigated. While resonant Auger-electron spectroscopy (RAS) can recover the vibrational structures not hidden by broadband excitation, the full reconstruction of the wavepacket is a standing challenge. Here, we theoretically demonstrate how the complete information of a nuclear wavepacket, i.e., the populations and relative phases of the vibrational states constituting the wavepacket, can be retrieved from time-resolved RAS (TRAS) measurements. Thus, TRAS offers key insights into coupled nuclear and electronic dynamics in complex systems on ultrashort timescales, providing an alternative to leverage femtosecond and attosecond X-ray probe pulses., QC 20240115

Gamma-ray Transient Monitor (GTM) is an all-sky monitor onboard the Distant Retrograde Orbit-A (DRO-A) satellite with the scientific objective of detecting gamma-ray transients ranging from 20 keV to 1 MeV. GTM is equipped with 5 Gamma-ray Transient Probe (GTP) detector modules, utilizing the NaI(Tl) scintillator coupled with a SiPM array. To reduce the SiPM noise, GTP makes use of a dedicated dual-channel coincident readout design. In this work, we firstly studied the impact of different coincidence times on detection efficiency and ultimately selected the 500 ns time coincidence window for offline data processing. To test the performance of GTPs and validate the Monte Carlo simulated energy response, we conducted comprehensive ground calibration tests using Hard X-ray Calibration Facility (HXCF) and radioactive sources, including energy response, detection efficiency, spatial response, bias-voltage response, and temperature dependence. We extensively presented the ground calibration results, and validated the design and mass model of GTP detector. These work paved the road for the in-flight observation and science data analysis., Comment: 13 pages, 25 figures

Jing-Xian Hu,1,* Dong-Xia Wu,2,* Xuan Wang,3,* Yu-Ling Zhang,4 Hui-Min Guo,1 Jian-Hong Ma,2 Yun Zhang,2 Xiao-Jing Lian,5 Xin Wang,1 Lili Zhang1 1Department of Nursing, Beijing Youan Hospital, Capital Medical University, Beijing, 100069, People’s Republic of China; 2Department of Infection, Beijing Youan Hospital, Capital Medical University, Beijing, 100069, People’s Republic of China; 3Second Department of Hepatology Center for Liver Diseases, Beijing Youan Hospital, Capital Medical University, Beijing, 100069, People’s Republic of China; 4Department of Anesthesiology and Surgery, Beijing Youan Hospital, Capital Medical University, Beijing, 100069, People’s Republic of China; 5Integrated Traditional Chinese and Western Medicine Center, Beijing Youan Hospital, Capital Medical University, Beijing, 100069, People’s Republic of China*These authors contributed equally to this workCorrespondence: Lili Zhang; Xin Wang, Department of Nursing, Beijing Youan Hospital, Capital Medical University, No. 8, Xi Tou Tiao, Youanmen Wai, Fengtai District, Beijing, 100069, People’s Republic of China, Tel/Fax +86 10 8399 7143, Email zhanglyliy@163.com; 13521101275@mail.ccmu.edu.cnObjective: To analyze the relevant research publications on infectious disease nursing in China to understand the current research status of infectious disease in nursing.Methods: Retrieve relevant literature on infectious disease in nursing from the establishment of the Chinese Biomedical Literature Database, China National Knowledge Infrastructure (CNKI), VIP Database, and Wanfang Database until May 10, 2021. Conduct bibliometric analysis using CiteSpace software. Key words were analyzed using cluster analysis.Results: A total of 4693 relevant literature on infectious disease research in nursing care were included in this study. The overall number of publications on infectious disease research in nursing showed an increasing trend, with a peak in 2010. There were 32

Intent is defined for understanding spoken language in existing works. Both textual features and acoustic features involved in medical speech contain intent, which is important for symptomatic diagnosis. In this paper, we propose a medical speech classification model named DRSC that automatically learns to disentangle intent and content representations from textual-acoustic data for classification. The intent representations of the text domain and the Mel-spectrogram domain are extracted via intent encoders, and then the reconstructed text feature and the Mel-spectrogram feature are obtained through two exchanges. After combining the intent from two domains into a joint representation, the integrated intent representation is fed into a decision layer for classification. Experimental results show that our model obtains an average accuracy rate of 95% in detecting 25 different medical symptoms., Comment: Accepted by the 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD 2024)

Dance serves as a powerful medium for expressing human emotions, but the lifelike generation of dance is still a considerable challenge. Recently, diffusion models have showcased remarkable generative abilities across various domains. They hold promise for human motion generation due to their adaptable many-to-many nature. Nonetheless, current diffusion-based motion generation models often create entire motion sequences directly and unidirectionally, lacking focus on the motion with local and bidirectional enhancement. When choreographing high-quality dance movements, people need to take into account not only the musical context but also the nearby music-aligned dance motions. To authentically capture human behavior, we propose a Bidirectional Autoregressive Diffusion Model (BADM) for music-to-dance generation, where a bidirectional encoder is built to enforce that the generated dance is harmonious in both the forward and backward directions. To make the generated dance motion smoother, a local information decoder is built for local motion enhancement. The proposed framework is able to generate new motions based on the input conditions and nearby motions, which foresees individual motion slices iteratively and consolidates all predictions. To further refine the synchronicity between the generated dance and the beat, the beat information is incorporated as an input to generate better music-aligned dance movements. Experimental results demonstrate that the proposed model achieves state-of-the-art performance compared to existing unidirectional approaches on the prominent benchmark for music-to-dance generation.

Deploying neural networks on microcontroller units (MCUs) presents substantial challenges due to their constrained computation and memory resources. Previous researches have explored patch-based inference as a strategy to conserve memory without sacrificing model accuracy. However, this technique suffers from severe redundant computation overhead, leading to a substantial increase in execution latency. A feasible solution to address this issue is mixed-precision quantization, but it faces the challenges of accuracy degradation and a time-consuming search time. In this paper, we propose QuantMCU, a novel patch-based inference method that utilizes value-driven mixed-precision quantization to reduce redundant computation. We first utilize value-driven patch classification (VDPC) to maintain the model accuracy. VDPC classifies patches into two classes based on whether they contain outlier values. For patches containing outlier values, we apply 8-bit quantization to the feature maps on the dataflow branches that follow. In addition, for patches without outlier values, we utilize value-driven quantization search (VDQS) on the feature maps of their following dataflow branches to reduce search time. Specifically, VDQS introduces a novel quantization search metric that takes into account both computation and accuracy, and it employs entropy as an accuracy representation to avoid additional training. VDQS also adopts an iterative approach to determine the bitwidth of each feature map to further accelerate the search process. Experimental results on real-world MCU devices show that QuantMCU can reduce computation by 2.2x on average while maintaining comparable model accuracy compared to the state-of-the-art patch-based inference methods., Comment: Accepted by the 27th Design, Automation and Test in Europe Conference (DATE 2024)

Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive Prompt Decision Transformer (P2DT). This method enhances a transformer-based model by dynamically appending decision tokens during new task training, thus fostering task-specific policies. Our approach mitigates forgetting in continual and offline reinforcement learning scenarios. Moreover, P2DT leverages trajectories collected via traditional reinforcement learning from all tasks and generates new task-specific tokens during training, thereby retaining knowledge from previous studies. Preliminary results demonstrate that our model effectively alleviates catastrophic forgetting and scales well with increasing task environments., Comment: Accepted by the 49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)

This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptive key-learner and task-aware prompts that capture task-relevant information. This unique combination encapsulates general knowledge across tasks and encodes task-specific knowledge. Our comprehensive evaluation across multiple continual learning benchmarks demonstrates INCPrompt's superiority over existing algorithms, showing its effectiveness in mitigating catastrophic forgetting while maintaining high performance. These results highlight the significant impact of task-aware incremental prompting on continual learning performance., Comment: Accepted by the 49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)

Large Language Models (LLMs) have shown significant promise in various applications, including zero-shot and few-shot learning. However, their performance can be hampered by inherent biases. Instead of traditionally sought methods that aim to minimize or correct these biases, this study introduces a novel methodology named ``bias-kNN''. This approach capitalizes on the biased outputs, harnessing them as primary features for kNN and supplementing with gold labels. Our comprehensive evaluations, spanning diverse domain text classification datasets and different GPT-2 model sizes, indicate the adaptability and efficacy of the ``bias-kNN'' method. Remarkably, this approach not only outperforms conventional in-context learning in few-shot scenarios but also demonstrates robustness across a spectrum of samples, templates and verbalizers. This study, therefore, presents a unique perspective on harnessing biases, transforming them into assets for enhanced model performance., Comment: Accepted by the 49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)

Existing emotional speech synthesis methods often utilize an utterance-level style embedding extracted from reference audio, neglecting the inherent multi-scale property of speech prosody. We introduce ED-TTS, a multi-scale emotional speech synthesis model that leverages Speech Emotion Diarization (SED) and Speech Emotion Recognition (SER) to model emotions at different levels. Specifically, our proposed approach integrates the utterance-level emotion embedding extracted by SER with fine-grained frame-level emotion embedding obtained from SED. These embeddings are used to condition the reverse process of the denoising diffusion probabilistic model (DDPM). Additionally, we employ cross-domain SED to accurately predict soft labels, addressing the challenge of a scarcity of fine-grained emotion-annotated datasets for supervising emotional TTS training., Comment: Accepted by 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2024)

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio has the potential ability to well represent content. Besides, the speaker-style modeling with pre-trained models making the process more complex. To tackle these issues, we introduce a new method named "CTVC" which utilizes disentangled speech representations with contrastive learning and time-invariant retrieval. Specifically, a similarity-based compression module is used to facilitate a more intimate connection between the frame-level hidden features and linguistic information at phoneme-level. Additionally, a time-invariant retrieval is proposed for timbre extraction based on multiple segmentations and mutual information. Experimental results demonstrate that "CTVC" outperforms previous studies and improves the sound quality and similarity of converted results., Comment: Accepted by 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2024)

In recent years, the field of talking faces generation has attracted considerable attention, with certain methods adept at generating virtual faces that convincingly imitate human expressions. However, existing methods face challenges related to limited generalization, particularly when dealing with challenging identities. Furthermore, methods for editing expressions are often confined to a singular emotion, failing to adapt to intricate emotions. To overcome these challenges, this paper proposes EmoTalker, an emotionally editable portraits animation approach based on the diffusion model. EmoTalker modifies the denoising process to ensure preservation of the original portrait's identity during inference. To enhance emotion comprehension from text input, Emotion Intensity Block is introduced to analyze fine-grained emotions and strengths derived from prompts. Additionally, a crafted dataset is harnessed to enhance emotion comprehension within prompts. Experiments show the effectiveness of EmoTalker in generating high-quality, emotionally customizable facial expressions., Comment: Accepted by 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2024)

The purpose of emotion recognition in conversation (ERC) is to identify the emotion category of an utterance based on contextual information. Previous ERC methods relied on simple connections for cross-modal fusion and ignored the information differences between modalities, resulting in the model being unable to focus on modality-specific emotional information. At the same time, the shared information between modalities was not processed to generate emotions. Information redundancy problem. To overcome these limitations, we propose a cross-modal fusion emotion prediction network based on vector connections. The network mainly includes two stages: the multi-modal feature fusion stage based on connection vectors and the emotion classification stage based on fused features. Furthermore, we design a supervised inter-class contrastive learning module based on emotion labels. Experimental results confirm the effectiveness of the proposed method, demonstrating excellent performance on the IEMOCAP and MELD datasets., Comment: Accepted by the 20th International Conference on Intelligent Computing (ICIC 2024)

Known for efficient computation and easy storage, hashing has been extensively explored in cross-modal retrieval. The majority of current hashing models are predicated on the premise of a direct one-to-one mapping between data points. However, in real practice, data correspondence across modalities may be partially provided. In this research, we introduce an innovative unsupervised hashing technique designed for semi-paired cross-modal retrieval tasks, named Reconstruction Relations Embedded Hashing (RREH). RREH assumes that multi-modal data share a common subspace. For paired data, RREH explores the latent consistent information of heterogeneous modalities by seeking a shared representation. For unpaired data, to effectively capture the latent discriminative features, the high-order relationships between unpaired data and anchors are embedded into the latent subspace, which are computed by efficient linear reconstruction. The anchors are sampled from paired data, which improves the efficiency of hash learning. The RREH trains the underlying features and the binary encodings in a unified framework with high-order reconstruction relations preserved. With the well devised objective function and discrete optimization algorithm, RREH is designed to be scalable, making it suitable for large-scale datasets and facilitating efficient cross-modal retrieval. In the evaluation process, the proposed is tested with partially paired data to establish its superiority over several existing methods., Comment: Accepted by the 20th International Conference on Intelligent Computing (ICIC 2024)

Although current Text-To-Speech (TTS) models are able to generate high-quality speech samples, there are still challenges in developing emotion intensity controllable TTS. Most existing TTS models achieve emotion intensity control by extracting intensity information from reference speeches. Unfortunately, limited by the lack of modeling for intra-class emotion intensity and the model's information decoupling capability, the generated speech cannot achieve fine-grained emotion intensity control and suffers from information leakage issues. In this paper, we propose an emotion transfer TTS model, which defines a remapping-based sorting method to model intra-class relative intensity information, combined with Mutual Information (MI) to decouple speaker and emotion information, and synthesizes expressive speeches with perceptible intensity differences. Experiments show that our model achieves fine-grained emotion control while preserving speaker information., Comment: Accepted by the 8th APWeb-WAIM International Joint Conference on Web and Big Data

With the rapid advancements in artificial intelligence, the development of knowledgeable and personalized agents has become increasingly prevalent. However, the inherent variability in state variables and action spaces among personalized agents poses significant aggregation challenges for traditional federated learning algorithms. To tackle these challenges, we introduce the Federated Split Decision Transformer (FSDT), an innovative framework designed explicitly for AI agent decision tasks. The FSDT framework excels at navigating the intricacies of personalized agents by harnessing distributed data for training while preserving data privacy. It employs a two-stage training process, with local embedding and prediction models on client agents and a global transformer decoder model on the server. Our comprehensive evaluation using the benchmark D4RL dataset highlights the superior performance of our algorithm in federated split learning for personalized agents, coupled with significant reductions in communication and computational overhead compared to traditional centralized training approaches. The FSDT framework demonstrates strong potential for enabling efficient and privacy-preserving collaborative learning in applications such as autonomous driving decision systems. Our findings underscore the efficacy of the FSDT framework in effectively leveraging distributed offline reinforcement learning data to enable powerful multi-type agent decision systems., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Knowledge Graph Completion (KGC) has emerged as a promising solution to address the issue of incompleteness within Knowledge Graphs (KGs). Traditional KGC research primarily centers on triple classification and link prediction. Nevertheless, we contend that these tasks do not align well with real-world scenarios and merely serve as surrogate benchmarks. In this paper, we investigate three crucial processes relevant to real-world construction scenarios: (a) the verification process, which arises from the necessity and limitations of human verifiers; (b) the mining process, which identifies the most promising candidates for verification; and (c) the training process, which harnesses verified data for subsequent utilization; in order to achieve a transition toward more realistic challenges. By integrating these three processes, we introduce the Progressive Knowledge Graph Completion (PKGC) task, which simulates the gradual completion of KGs in real-world scenarios. Furthermore, to expedite PKGC processing, we propose two acceleration modules: Optimized Top-$k$ algorithm and Semantic Validity Filter. These modules significantly enhance the efficiency of the mining procedure. Our experiments demonstrate that performance in link prediction does not accurately reflect performance in PKGC. A more in-depth analysis reveals the key factors influencing the results and provides potential directions for future research., Comment: 14 pages, 10 figures

Most earlier investigations on talking face generation have focused on the synchronization of lip motion and speech content. However, human head pose and facial emotions are equally important characteristics of natural human faces. While audio-driven talking face generation has seen notable advancements, existing methods either overlook facial emotions or are limited to specific individuals and cannot be applied to arbitrary subjects. In this paper, we propose a one-shot Talking Head Generation framework (SPEAK) that distinguishes itself from general Talking Face Generation by enabling emotional and postural control. Specifically, we introduce the Inter-Reconstructed Feature Disentanglement (IRFD) method to decouple human facial features into three latent spaces. We then design a face editing module that modifies speech content and facial latent codes into a single latent space. Subsequently, we present a novel generator that employs modified latent codes derived from the editing module to regulate emotional expression, head poses, and speech content in synthesizing facial animations. Extensive trials demonstrate that our method can generate realistic talking head with coordinated lip motions, authentic facial emotions, and smooth head movements. The demo video is available at the anonymous link: https://anonymous.4open.science/r/SPEAK-F56E

One-shot voice conversion aims to change the timbre of any source speech to match that of the unseen target speaker with only one speech sample. Existing methods face difficulties in satisfactory speech representation disentanglement and suffer from sizable networks as some of them leverage numerous complex modules for disentanglement. In this paper, we propose a model named MAIN-VC to effectively disentangle via a concise neural network. The proposed model utilizes Siamese encoders to learn clean representations, further enhanced by the designed mutual information estimator. The Siamese structure and the newly designed convolution module contribute to the lightweight of our model while ensuring performance in diverse voice conversion tasks. The experimental results show that the proposed model achieves comparable subjective scores and exhibits improvements in objective metrics compared to existing methods in a one-shot voice conversion scenario., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

In recent years, Transformer networks have shown remarkable performance in speech recognition tasks. However, their deployment poses challenges due to high computational and storage resource requirements. To address this issue, a lightweight model called EfficientASR is proposed in this paper, aiming to enhance the versatility of Transformer models. EfficientASR employs two primary modules: Shared Residual Multi-Head Attention (SRMHA) and Chunk-Level Feedforward Networks (CFFN). The SRMHA module effectively reduces redundant computations in the network, while the CFFN module captures spatial knowledge and reduces the number of parameters. The effectiveness of the EfficientASR model is validated on two public datasets, namely Aishell-1 and HKUST. Experimental results demonstrate a 36% reduction in parameters compared to the baseline Transformer network, along with improvements of 0.3% and 0.2% in Character Error Rate (CER) on the Aishell-1 and HKUST datasets, respectively., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Using unsupervised learning to disentangle speech into content, rhythm, pitch, and timbre for voice conversion has become a hot research topic. Existing works generally take into account disentangling speech components through human-crafted bottleneck features which can not achieve sufficient information disentangling, while pitch and rhythm may still be mixed together. There is a risk of information overlap in the disentangling process which results in less speech naturalness. To overcome such limits, we propose a two-stage model to disentangle speech representations in a self-supervised manner without a human-crafted bottleneck design, which uses the Mutual Information (MI) with the designed upper bound estimator (IFUB) to separate overlapping information between speech components. Moreover, we design a Joint Text-Guided Consistent (TGC) module to guide the extraction of speech content and eliminate timbre leakage issues. Experiments show that our model can achieve a better performance than the baseline, regarding disentanglement effectiveness, speech naturalness, and similarity. Audio samples can be found at https://largeaudiomodel.com/eadvc., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Voice conversion is the task to transform voice characteristics of source speech while preserving content information. Nowadays, self-supervised representation learning models are increasingly utilized in content extraction. However, in these representations, a lot of hidden speaker information leads to timbre leakage while the prosodic information of hidden units lacks use. To address these issues, we propose a novel framework for expressive voice conversion called "SAVC" based on soft speech units from HuBert-soft. Taking soft speech units as input, we design an attribute encoder to extract content and prosody features respectively. Specifically, we first introduce statistic perturbation imposed by adversarial style augmentation to eliminate speaker information. Then the prosody is implicitly modeled on soft speech units with knowledge distillation. Experiment results show that the intelligibility and naturalness of converted speech outperform previous work., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Extractive Question Answering (EQA) in Machine Reading Comprehension (MRC) often faces the challenge of dealing with semantically identical but format-variant inputs. Our work introduces a novel approach, called the ``Query Latent Semantic Calibrator (QLSC)'', designed as an auxiliary module for existing MRC models. We propose a unique scaling strategy to capture latent semantic center features of queries. These features are then seamlessly integrated into traditional query and passage embeddings using an attention mechanism. By deepening the comprehension of the semantic queries-passage relationship, our approach diminishes sensitivity to variations in text format and boosts the model's capability in pinpointing accurate answers. Experimental results on robust Question-Answer datasets confirm that our approach effectively handles format-variant but semantically identical queries, highlighting the effectiveness and adaptability of our proposed method., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Singing voice beautifying is a novel task that has application value in people's daily life, aiming to correct the pitch of the singing voice and improve the expressiveness without changing the original timbre and content. Existing methods rely on paired data or only concentrate on the correction of pitch. However, professional songs and amateur songs from the same person are hard to obtain, and singing voice beautifying doesn't only contain pitch correction but other aspects like emotion and rhythm. Since we propose a fast and high-fidelity singing voice beautifying system called ConTuner, a diffusion model combined with the modified condition to generate the beautified Mel-spectrogram, where the modified condition is composed of optimized pitch and expressiveness. For pitch correction, we establish a mapping relationship from MIDI, spectrum envelope to pitch. To make amateur singing more expressive, we propose the expressiveness enhancer in the latent space to convert amateur vocal tone to professional. ConTuner achieves a satisfactory beautification effect on both Mandarin and English songs. Ablation study demonstrates that the expressiveness enhancer and generator-based accelerate method in ConTuner are effective., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

With recent advances in speech synthesis including text-to-speech (TTS) and voice conversion (VC) systems enabling the generation of ultra-realistic audio deepfakes, there is growing concern about their potential misuse. However, most deepfake (DF) detection methods rely solely on the fuzzy knowledge learned by a single model, resulting in performance bottlenecks and transparency issues. Inspired by retrieval-augmented generation (RAG), we propose a retrieval-augmented detection (RAD) framework that augments test samples with similar retrieved samples for enhanced detection. We also extend the multi-fusion attentive classifier to integrate it with our proposed RAD framework. Extensive experiments show the superior performance of the proposed RAD framework over baseline methods, achieving state-of-the-art results on the ASVspoof 2021 DF set and competitive results on the 2019 and 2021 LA sets. Further sample analysis indicates that the retriever consistently retrieves samples mostly from the same speaker with acoustic characteristics highly consistent with the query audio, thereby improving detection performance., Comment: Accepted by the 2024 International Conference on Multimedia Retrieval (ICMR 2024)

Single-model systems often suffer from deficiencies in tasks such as speaker verification (SV) and image classification, relying heavily on partial prior knowledge during decision-making, resulting in suboptimal performance. Although multi-model fusion (MMF) can mitigate some of these issues, redundancy in learned representations may limits improvements. To this end, we propose an adversarial complementary representation learning (ACoRL) framework that enables newly trained models to avoid previously acquired knowledge, allowing each individual component model to learn maximally distinct, complementary representations. We make three detailed explanations of why this works and experimental results demonstrate that our method more efficiently improves performance compared to traditional MMF. Furthermore, attribution analysis validates the model trained under ACoRL acquires more complementary knowledge, highlighting the efficacy of our approach in enhancing efficiency and robustness across tasks., Comment: Accepted by the 2024 International Joint Conference on Neural Networks (IJCNN 2024)

Intravenous (IV) access is an important daily clinical procedure that delivers fluids or medication into a patient’s vein. However, IV insertion is very challenging where clinicians are suffering in locating the subcutaneous vein due to patients’ physiological factors such as hairy forearm and thick dermis fat, and also medical staff’s level of fatigue. To resolve this issue, researchers have proposed autonomous machines to be used for IV access, but such equipment are lacking capability in detecting the vein accurately. Therefore, this project proposes an automatic vein detection algorithm using deep learning for IV access purpose. U-Net, a fully connected network (FCN) architecture is employed in this project due to its capability in detecting the near-infrared (NIR) subcutaneous vein. Data augmentation is applied to increase the dataset size and reduce the bias from overfitting. The original U-Net architecture is optimized by replacing up-sampling with transpose convolution as well as the additional implementation of batch normalization besides reducing the number of layers to diminish the risk of overfitting. After fine-tuning and retraining the hypermodel, an unsupervised dataset is used to evaluate the hypermodel by selecting 10 checkpoints for each forearm image and comparing the checkpoints on predicted outputs to determine true positive vein pixels. The proposed lightweight U-Net has achieved slightly lower accuracy (0.8871) than the original U-Net architecture. Even so, the sensitivity, specificity, and precision are greatly improved by achieving 0.7806, 0.9935, and 0.9918 respectively. This result indicates that the proposed algorithm can be applied into the venipuncture machine to accurately locate the subcutaneous vein for intravenous (IV) procedures.

Insight into fundamental light-matter interaction as well as underlying photo-physical processes is crucial for the development of novel optoelectronic devices. Palladium diselenide (PdSe2), an important representative of emerging 2D noble metal dichalcogenides, has gain considerable attention owing to its unique optical, physical, and chemical properties. In this study, 2D PdSe2 nanosheets (NSs) are prepared using the liquid-phase exfoliation method. A broadband carrier relaxation dynamics from visible to near-infrared bands are revealed using a time-resolved transient absorption spectrometer, giving results that indicate band filling and bandgap renormalization (BGR) effects in the 2D PdSe2 NSs. The observed blue-shift of the transient absorption spectra at the primary stage and the subsequent red-shift can be ascribed to this BGR effect. These findings reveal the many-body character of the 2D TMDs material and may hold keys for applications in the field of optoelectronics and ultrafast photonics.

Resonant Auger scattering (RAS) provides information on the core-valence electronic transition and impresses a rich fingerprint of the electronic structure and nuclear configuration at the time-initiating RAS process. Here, we suggest using a femtosecond X-ray pulse to trigger RAS in a distorted molecule, which is generated from the nuclear evolution on a valence excited state pumped by a femtosecond ultraviolet pulse. With the time delay varied, the amount of molecular distortion can be controlled and the RAS measurements imprint both their electronic structures and changing geometries. This strategy is showcased in H2O prepared in an O-H dissociative valence state, where molecular and fragment lines appear in RAS spectra as signatures of ultrafast dissociation. Given the generality of this approach for a broad class of molecules, this work opens a new alternative pump-probe technique for mapping the core and valence dynamics with ultrashort X-ray probe pulses., QC 20230829

Dan Luo,1,2,* Bo-Yi Yang,3,* Kai Qin,4 Chong-Yu Shi,3 Nian-Sa Wei,4 Hai Li,1 Yi-Xiang Qin,1 Gang Liu,1 Xiao-Ling Qin,1 Shi-Yi Chen,1 Xiao-Jing Guo,1 Li Gan,1 Ruo-Lan Xu,1 Bai-Qing Dong,1 Jing Li5 1Department of Biostatistics, School of Public Health and Management of Guangxi University of Chinese Medicine, Nanning, Guangxi, People’s Republic of China; 2Guangxi Key Laboratory of Translational Medicine for Treating High-Incidence Infectious Diseases with Integrative Medicine, Guangxi University of Chinese Medicine, Nanning, Guangxi, People’s Republic of China; 3The First Affiliated Hospital, Guangxi Medical University, Nanning, Guangxi, People’s Republic of China; 4The Second Affiliated Hospital, Guangxi Medical University, Nanning, Guangxi, People’s Republic of China; 5Deparment of Physiology, School of Basic Medical Sciences of Guangxi Medical University, Nanning, Guangxi, People’s Republic of China*These authors contributed equally to this workCorrespondence: Bai-Qing Dong, Guangxi University of Chinese Medicine, 13 Wuhe Road, Nanning, Guangxi, 530200, People’s Republic of China, Tel/Fax +86-771-4928360, Email 764937318@qq.com Jing Li, Guangxi Medical University, 22 Shuangyong Road, Nanning, Guangxi, 530021, People’s Republic of China, Tel/Fax +86-771-5358212, Email lijing@gxmu.edu.cnPurpose: Distinguishing latent tuberculosis infection (LTBI) from active tuberculosis (ATB) is important to control the prevalence of tuberculosis; however, there is currently no effective method. The aim of this study was to discover specific metabolites through fecal untargeted metabolomics to discriminate ATB, individuals with LTBI, and healthy controls (HC) and to probe the metabolic perturbation associated with the progression of tuberculosis.Patients and Methods: Liquid chromatography-tandem mass spectrometry (LC-MS/MS) was performed to comprehensively detect compounds in fecal samples from HC, LTBI, and ATB patients. Differential metabolites

Phosphorus (P) is a finite natural resource and is increasingly considered to be a challenge for global sustainability. Agriculture in China plays a key role in global sustainable P management. Rhizosphere and soil-based P management are necessary for improving P-use efficiency and crop productivity in intensive agriculture in China. A previous study has shown that the future demand for phosphate fertilizer by China estimated by the LePA model (legacy phosphorus assessment model) can be greatly reduced by soil-based P management (the building-up and maintenance approach). The present study used the LePA model to predict the phosphate demand by China through combined rhizosphere and soil-based P management at county scale under four P fertilizer scenarios: (1) same P application rate as in 2012; (2) rate maintained same as 2012 in low-P counties or no P fertilizer applied in high-P counties until targeted soil Olsen-P (TPOlsen) level is reached, and then rate was the same as P-removed at harvest; (3) rate in each county decreased to 1–7 kg ha–1 yr–1 after TPOlsen is reached in low-P counties, then increased by 0.1–9 kg ha–1 yr–1 until equal to P-removal; (4) rate maintained same as 2012 in low-P counties until TPOlsen is reached and then equaled to P-removal, while the rate in high-P counties is decreased to 1–7 kg ha–1 yr–1 until TPOlsen is reached and then increased by 0.1–9 kg ha–1 yr–1 until equal to P-removal. Our predictions showed that the total demand for P fertilizer by whole China was 693 Mt P2O5 and according to scenario 4, P fertilizer could be reduced by 57.5% compared with farmer current practice, during the period 2013–2080. The model showed that rhizosphere P management led to a further 8.0% decrease in P fertilizer use compared with soil-based P management. The average soil Olsen-P level in China only needs to be maintained at 17 mg kg–1 to achieve high crop yields. Our results provide a firm basis for government to issue-relevant policies for sustai

As a new member of the Gravitational wave high-energy Electromagnetic Counterpart All-sky Monitor (GECAM) after GECAM-A and GECAM-B, GECAM-C (originally called HEBS), which was launched on board the SATech-01 satellite on July 27, 2022, aims to monitor and localize X-ray and gamma-ray transients from $\sim$ 6 keV to 6 MeV. GECAM-C utilizes a similar design to GECAM but operates in a more complex orbital environment. In this work, we utilize the secondary particles simultaneously produced by the cosmic-ray events on orbit and recorded by multiple detectors, to calibrate the relative timing accuracy between all detectors of GECAM-C. We find the result is 0.1 $\mu \rm s$, which is the highest time resolution among all GRB detectors ever flown and very helpful in timing analyses such as minimum variable timescale and spectral lags, as well as in time delay localization. Besides, we calibrate the absolute time accuracy using the one-year Crab pulsar data observed by GECAM-C and Fermi/GBM, as well as GECAM-C and GECAM-B. The results are $2.02\pm 2.26\ \mu \rm s$ and $5.82\pm 3.59\ \mu \rm s$, respectively. Finally, we investigate the spectral lag between the different energy bands of Crab pulsar observed by GECAM and GBM, which is $\sim -0.2\ {\rm \mu s\ keV^{-1}}$., Comment: submitted

Diabetic cardiomyopathy (DCM) is a cardiovascular disease which has been reported as a major cause of mortality worldwide for several years. Berberine (BBR) is a natural compound extracted from a Chinese herb, with a clinically reported anti-DCM effect; however, its molecular mechanisms have not yet been fully elucidated. The present study indicated that BBR markedly alleviated DCM by inhibiting IL-1 beta secretion and the expression of gasdermin D (Gsdmd) at the post-transcriptional level. Considering the importance of microRNAs (miRNAs/miRs) in the regulation of the post-transcriptional process of specific genes, the ability of BBR to upregulate the expression levels of miR-18a-3p by activating its promoter (-1,000/-500) was examined. Notably, miR-18a-3p targeted Gsdmd and abated pyroptosis in high glucose-treated H9C2 cells. Moreover, miR-18a-3p overexpression inhibited Gsdmd expression and improved biomarkers of cardiac function in a rat model of DCM. On the whole, the findings of the present study indicate that BBR alleviates DCM by inhibiting miR-18a-3p-mediated Gsdmd activation; thus, BBR may be considered a potential therapeutic agent for the treatment of DCM.

The gamma-ray detectors (GRDs) of GECAM-C onborad SATech-01 satellite is designed to monitor gamma-ray transients all over the sky from 6 keV to 6 MeV. The energy response matrix is the key to do spectral measurements of bursts, which is usually generated from GEANT4 simulation and partially verified by the ground calibration. In this work, energy response matrix of GECAM-C GRD is cross-calibrated with Fermi/GBM and Swift/BAT using a sample of Gamma-Ray Bursts (GRBs) and Soft Gamma-Ray Repeaters (SGRs). The calibration results show there is a good agreement between GECAM-C and other reasonably well calibrated instrument (i.e. Fermi/GBM and Swift/BAT). We also find that different GRD detectors of GECAM-C also show consistency with each other. All these results indicate that GECAM-C GRD can provide reliable spectral measurements., Comment: preliminary version, will be updated soon

GRB 221009A is the brightest gamma-ray burst ever detected since the discovery of this kind of energetic explosions. However, an accurate measurement of the prompt emission properties of this burst is very challenging due to its exceptional brightness. With joint observations of \textit{Insight}-HXMT and GECAM-C, we made an unprecedentedly accurate measurement of the emission during the first $\sim$1800 s of GRB 221009A, including its precursor, main emission (ME, which dominates the burst in flux), flaring emission and early afterglow, in the hard X-ray to soft gamma-ray band from $\sim$ 10 keV to $\sim$ 6 MeV. Based on the GECAM-C unsaturated data of the ME, we measure a record-breaking isotropic equivalent energy ($E_{\rm iso}$) of $\bf \sim 1.5 \times 10^{55}$ erg, which is about eight times the total rest-mass energy of the Sun. The early afterglow data require a significant jet break between 650 s and 1100 s, most likely at $\sim950$ s from the afterglow starting time $T_{AG}$, which corresponds to a jet opening angle of $\sim {0.7^\circ} \ (\eta_\gamma n)^{1/8}$, where $n$ is the ambient medium density in units of $\rm cm^{-3}$ and $\eta_\gamma$ is the ratio between $\gamma$-ray energy and afterglow kinetic energy. The beaming-corrected total $\gamma$-ray energy $E_{\gamma}$ is $\sim 1.15 \times10^{51} \ (\eta_\gamma n)^{1/4}$ erg, which is typical for long GRBs. These results suggest that this GRB may have a special central engine, which could launch and collimate a very narrowly beamed jet with an ordinary energy budget, leading to exceptionally luminous gamma-ray radiation per unit solid angle. Alternatively, more GRBs might have such a narrow and bright beam, which are missed by an unfavorable viewing angle or have been detected without distance measurement., Comment: Submitted to National Science Review. This paper is under press embargo, contact the corresponding author for details

As a new member of GECAM mission, GECAM-C (also named High Energy Burst Searcher, HEBS) was launched onboard the SATech-01 satellite on July 27th, 2022, which is capable to monitor gamma-ray transients from $\sim$ 6 keV to 6 MeV. As the main detector, there are 12 gamma-ray detectors (GRDs) equipped for GECAM-C. In order to verify the GECAM-C GRD detector performance and to validate the Monte Carlo simulations of detector response, comprehensive on-ground calibration experiments have been performed using X-ray beam and radioactive sources, including Energy-Channel relation, energy resolution, detection efficiency, SiPM voltage-gain relation and the non-uniformity of positional response. In this paper, the detailed calibration campaigns and data analysis results for GECAM-C GRDs are presented, demonstrating the excellent performance of GECAM-C GRD detectors., Comment: third version

Xiao-Yan Wang,1 Xiao-Jing Zhang,2 Xiao Xia,3 Shu-Zhen Chang,4 An-Zhao Wu4 1Infectious Diseases Department II, Shandong Public Health Clinical Center, Jinan, 250000, People’s Republic of China; 2Public Health Department, Shandong Public Health Clinical Center, Jinan, 250000, People’s Republic of China; 3Medical Insurance Office, Shandong Public Health Clinical Center, Jinan, 250000, People’s Republic of China; 4TCM & Western Medicine Department, Shandong Public Health Clinical Center, Jinan, 250000, People’s Republic of ChinaCorrespondence: An-Zhao Wu, TCM & Western Medicine Department, Shandong Public Health Clinical Center, 2999 Gangxing West Road, High Tech District, Jinan, 250000, People’s Republic of China, Tel +86 531-86568184, Email anzhaowu564@outlook.comObjective: This study aimed to analyze the epidemiological and clinical characteristics of measles in Jinan, Shandong, China, over a 32-year stage to facilitate measles prevention in the future.Methods: Data on measles cases from 1991 to 2022 were obtained from the public health department and medical records of patients at Shandong Public Health Clinical Center. Retrospective analysis was conducted on the distribution of measles cases in different years, months, and age groups, and observation of the differences in clinical manifestations and complications among different age groups.Results: From January 1991 to December 2022, 7531 measles cases were recorded at Shandong Public Health Clinical Center. During the 32-year period, there were two outbreaks of measles in 2008 and 2016, respectively. During the COVID-19 pandemic period from 2020 to 2022, the number of cases reached the lowest point in the past 30 years. The number and percentage of cases in the 0– 1y groups was significantly higher than in other age groups, and 97.75% patients in this group did not receive measles vaccine. Complications such as pneumonia and myocarditis appeared more frequent in patients under 12 years of age

Out-of-distribution (OOD) detection aims at enhancing standard deep neural networks to distinguish anomalous inputs from original training data. Previous progress has introduced various approaches where the in-distribution training data and even several OOD examples are prerequisites. However, due to privacy and security, auxiliary data tends to be impractical in a real-world scenario. In this paper, we propose a data-free method without training on natural data, called Class-Conditional Impressions Reappearing (C2IR), which utilizes image impressions from the fixed model to recover class-conditional feature statistics. Based on that, we introduce Integral Probability Metrics to estimate layer-wise class-conditional deviations and obtain layer weights by Measuring Gradient-based Importance (MGI). The experiments verify the effectiveness of our method and indicate that C2IR outperforms other post-hoc methods and reaches comparable performance to the full access (ID and OOD) detection method, especially in the far-OOD dataset (SVHN)., Comment: Accepted by ICASSP 2023

Value-decomposition methods, which reduce the difficulty of a multi-agent system by decomposing the joint state-action space into local observation-action spaces, have become popular in cooperative multi-agent reinforcement learning (MARL). However, value-decomposition methods still have the problems of tremendous sample consumption for training and lack of active exploration. In this paper, we propose a scalable value-decomposition exploration (SVDE) method, which includes a scalable training mechanism, intrinsic reward design, and explorative experience replay. The scalable training mechanism asynchronously decouples strategy learning with environmental interaction, so as to accelerate sample generation in a MapReduce manner. For the problem of lack of exploration, an intrinsic reward design and explorative experience replay are proposed, so as to enhance exploration to produce diverse samples and filter non-novel samples, respectively. Empirically, our method achieves the best performance on almost all maps compared to other popular algorithms in a set of StarCraft II micromanagement games. A data-efficiency experiment also shows the acceleration of SVDE for sample collection and policy convergence, and we demonstrate the effectiveness of factors in SVDE through a set of ablation experiments., Comment: 13 pages, 9 figures

Deep neural retrieval models have amply demonstrated their power but estimating the reliability of their predictions remains challenging. Most dialog response retrieval models output a single score for a response on how relevant it is to a given question. However, the bad calibration of deep neural network results in various uncertainty for the single score such that the unreliable predictions always misinform user decisions. To investigate these issues, we present an efficient calibration and uncertainty estimation framework PG-DRR for dialog response retrieval models which adds a Gaussian Process layer to a deterministic deep neural network and recovers conjugacy for tractable posterior inference by P\'{o}lya-Gamma augmentation. Finally, PG-DRR achieves the lowest empirical calibration error (ECE) in the in-domain datasets and the distributional shift task while keeping $R_{10}@1$ and MAP performance., Comment: Accepted by AAAI 2023

Music genre classification has been widely studied in past few years for its various applications in music information retrieval. Previous works tend to perform unsatisfactorily, since those methods only use audio content or jointly use audio content and lyrics content inefficiently. In addition, as genres normally co-occur in a music track, it is desirable to capture and model the genre correlations to improve the performance of multi-label music genre classification. To solve these issues, we present a novel multi-modal method leveraging audio-lyrics contrastive loss and two symmetric cross-modal attention, to align and fuse features from audio and lyrics. Furthermore, based on the nature of the multi-label classification, a genre correlations extraction module is presented to capture and model potential genre correlations. Extensive experiments demonstrate that our proposed method significantly surpasses other multi-label music genre classification methods and achieves state-of-the-art result on Music4All dataset., Comment: Accepted by ICASSP 2023

Deep neural networks have achieved remarkable performance in retrieval-based dialogue systems, but they are shown to be ill calibrated. Though basic calibration methods like Monte Carlo Dropout and Ensemble can calibrate well, these methods are time-consuming in the training or inference stages. To tackle these challenges, we propose an efficient uncertainty calibration framework GPF-BERT for BERT-based conversational search, which employs a Gaussian Process layer and the focal loss on top of the BERT architecture to achieve a high-quality neural ranker. Extensive experiments are conducted to verify the effectiveness of our method. In comparison with basic calibration methods, GPF-BERT achieves the lowest empirical calibration error (ECE) in three in-domain datasets and the distributional shift tasks, while yielding the highest $R_{10}@1$ and MAP performance on most cases. In terms of time consumption, our GPF-BERT has an 8$\times$ speedup., Comment: Accepted by ICASSP 2023

Because of predicting all the target tokens in parallel, the non-autoregressive models greatly improve the decoding efficiency of speech recognition compared with traditional autoregressive models. In this work, we present dynamic alignment Mask CTC, introducing two methods: (1) Aligned Cross Entropy (AXE), finding the monotonic alignment that minimizes the cross-entropy loss through dynamic programming, (2) Dynamic Rectification, creating new training samples by replacing some masks with model predicted tokens. The AXE ignores the absolute position alignment between prediction and ground truth sentence and focuses on tokens matching in relative order. The dynamic rectification method makes the model capable of simulating the non-mask but possible wrong tokens, even if they have high confidence. Our experiments on WSJ dataset demonstrated that not only AXE loss but also the rectification method could improve the WER performance of Mask CTC., Comment: Accepted by ICASSP 2023

Recent expressive text to speech (TTS) models focus on synthesizing emotional speech, but some fine-grained styles such as intonation are neglected. In this paper, we propose QI-TTS which aims to better transfer and control intonation to further deliver the speaker's questioning intention while transferring emotion from reference speech. We propose a multi-style extractor to extract style embedding from two different levels. While the sentence level represents emotion, the final syllable level represents intonation. For fine-grained intonation control, we use relative attributes to represent intonation intensity at the syllable level.Experiments have validated the effectiveness of QI-TTS for improving intonation expressiveness in emotional speech synthesis., Comment: Accepted by ICASSP 2023

Data-Free Knowledge Distillation (DFKD) has recently attracted growing attention in the academic community, especially with major breakthroughs in computer vision. Despite promising results, the technique has not been well applied to audio and signal processing. Due to the variable duration of audio signals, it has its own unique way of modeling. In this work, we propose feature-rich audio model inversion (FRAMI), a data-free knowledge distillation framework for general sound classification tasks. It first generates high-quality and feature-rich Mel-spectrograms through a feature-invariant contrastive loss. Then, the hidden states before and after the statistics pooling layer are reused when knowledge distillation is performed on these feature-rich samples. Experimental results on the Urbansound8k, ESC-50, and audioMNIST datasets demonstrate that FRAMI can generate feature-rich samples. Meanwhile, the accuracy of the student model is further improved by reusing the hidden state and significantly outperforms the baseline method., Comment: Accepted by ICASSP 2023. International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023)

This paper presents an innovative method for humanoid robots to acquire a comprehensive set of motor skills through reinforcement learning. The approach utilizes an achievement-triggered multi-path reward function rooted in developmental robotics principles, facilitating the robot to learn gross motor skills typically mastered by human infants within a single training phase. The proposed method outperforms standard reinforcement learning techniques in success rates and learning speed within a simulation environment. By leveraging the principles of self-discovery and exploration integral to infant learning, this method holds the potential to significantly advance humanoid robot motor skill acquisition., Comment: 8 pages, 9 figures. Submitted to IEEE Robotics and Automation Letters. Video available at https://youtu.be/d0RqrW1EzjQ

This paper addresses the problem of enabling a robot to search for a semantic object, i.e., an object with a semantic label, in an unknown and GPS-denied environment. For the robot in the unknown environment to detect and find the target semantic object, it must perform simultaneous localization and mapping (SLAM) at both geometric and semantic levels using its onboard sensors while planning and executing its motion based on the ever-updated SLAM results. In other words, the robot must be able to conduct simultaneous localization, semantic mapping, motion planning, and execution in real-time in the presence of sensing and motion uncertainty. This is an open problem as it combines semantic SLAM based on perception and real-time motion planning and execution under uncertainty. Moreover, the goals of the robot motion change on the fly depending on whether and how the robot can detect the target object. We propose a novel approach to tackle the problem, leveraging semantic SLAM, Bayesian Networks, Markov Decision Process, and Real-Time Dynamic Programming. The results in simulation and real experiments demonstrate the effectiveness and efficiency of our approach.

Histopathological tissue classification is a fundamental task in computational pathology. Deep learning-based models have achieved superior performance but centralized training with data centralization suffers from the privacy leakage problem. Federated learning (FL) can safeguard privacy by keeping training samples locally, but existing FL-based frameworks require a large number of well-annotated training samples and numerous rounds of communication which hinder their practicability in the real-world clinical scenario. In this paper, we propose a universal and lightweight federated learning framework, named Federated Deep-Broad Learning (FedDBL), to achieve superior classification performance with limited training samples and only one-round communication. By simply associating a pre-trained deep learning feature extractor, a fast and lightweight broad learning inference system and a classical federated aggregation approach, FedDBL can dramatically reduce data dependency and improve communication efficiency. Five-fold cross-validation demonstrates that FedDBL greatly outperforms the competitors with only one-round communication and limited training samples, while it even achieves comparable performance with the ones under multiple-round communications. Furthermore, due to the lightweight design and one-round communication, FedDBL reduces the communication burden from 4.6GB to only 276.5KB per client using the ResNet-50 backbone at 50-round training. Since no data or deep model sharing across different clients, the privacy issue is well-solved and the model security is guaranteed with no model inversion attack risk. Code is available at https://github.com/tianpeng-deng/FedDBL.

This paper introduces a novel and general method to address the problem of using a general-purpose robot manipulator with a parallel gripper to wrap a deformable linear object (DLO), called a rope, around a rigid object, called a rod, autonomously. Such a robotic wrapping task has broad potential applications in automotive, electromechanical industries construction manufacturing, etc., but has hardly been studied. Our method does not require prior knowledge of the physical and geometrical properties of the objects but enables the robot to use real-time RGB-D perception to determine the wrapping state and feedback control to achieve high-quality results. As such, it provides the robot manipulator with the general capabilities to handle wrapping tasks of different rods or ropes. We tested our method on 6 combinations of 3 different ropes and 2 rods. The result shows that the wrapping quality improved and converged within 5 wraps for all test cases.