Search

Reliability is of paramount importance for the physical layer of wireless systems due to its decisive impact on end-to-end performance. However, the uncertainty of prevailing deep learning (DL)-based physical layer algorithms is hard to quantify due to the black-box nature of neural networks. This limitation is a major obstacle that hinders their practical deployment. In this paper, we attempt to quantify the uncertainty of an important category of DL-based channel estimators. An efficient statistical method is proposed to make blind predictions for the mean squared error of the DL-estimated channel solely based on received pilots, without knowledge of the ground-truth channel, the prior distribution of the channel, or the noise statistics. The complexity of the blind performance prediction is low and scales only linearly with the number of antennas. Simulation results for ultra-massive multiple-input multiple-output (UM-MIMO) channel estimation with a mixture of far-field and near-field paths are provided to verify the accuracy and efficiency of the proposed method.

Three-dimensional (3D) histopathology involves the microscopic examination of a specimen, which plays a vital role in studying tissue's 3D structures and the signs of diseases. However, acquiring high-quality histological images of a whole organ is extremely time-consuming (e.g., several weeks) and laborious, as the organ has to be sectioned into hundreds or thousands of slices for imaging. Besides, the acquired images are required to undergo a complicated image registration process for 3D reconstruction. Here, by incorporating a recently developed vibratome-assisted block-face imaging technique with deep learning, we developed a pipeline termed HistoTRUST that can rapidly and automatically generate subcellular whole organ's virtual hematoxylin and eosin (H & E) stained histological images, which can be reconstructed into 3D by simple image stacking (i.e., without registration). The performance and robustness of HistoTRUST have been successfully validated by imaging all six organs (e.g., brain, heart, liver, lung, kidney, and spleen). The imaging process for a whole organ takes hours to days, depending on the volume of imaged samples. The generated 3D dataset has the same color tune as the traditional H & E stained histological images. Therefore, the virtual H & E stained images can be directly analyzed by pathologists. HistoTRUST has a high potential to serve as a new standard in providing 3D histology for research or clinical applications.

Terahertz ultra-massive MIMO (THz UM-MIMO) is envisioned as one of the key enablers of 6G wireless networks, for which channel estimation is highly challenging. Traditional analytical estimation methods are no longer effective, as the enlarged array aperture and the small wavelength result in a mixture of far-field and near-field paths, constituting a hybrid-field channel. Deep learning (DL)-based methods, despite the competitive performance, generally lack theoretical guarantees and scale poorly with the size of the array. In this paper, we propose a general DL framework for THz UM-MIMO channel estimation, which leverages existing iterative channel estimators and is with provable guarantees. Each iteration is implemented by a fixed point network (FPN), consisting of a closed-form linear estimator and a DL-based non-linear estimator. The proposed method perfectly matches the THz UM-MIMO channel estimation due to several unique advantages. First, the complexity is low and adaptive. It enjoys provable linear convergence with a low per-iteration cost and monotonically increasing accuracy, which enables an adaptive accuracy-complexity tradeoff. Second, it is robust to practical distribution shifts and can directly generalize to a variety of heavily out-of-distribution scenarios with almost no performance loss, which is suitable for the complicated THz channel conditions. For practical usage, the proposed framework is further extended to wideband THz UM-MIMO systems with beam squint effect. Theoretical analysis and extensive simulation results are provided to illustrate the advantages over the state-of-the-art methods in estimation accuracy, convergence rate, complexity, and robustness.

For the battery management system of electric vehicle, accurate estimation of the State of Charge of Lithium-ion battery can effectively avoid structural damage caused by overcharge or over discharge inside the battery. Considering that the lithium-ion battery is a time-varying nonlinear system, which needs real-time State of Charge estimation, a joint algorithm of forgetting factor recursive least squares and improved adaptive H Infinity Extended Kalman Filter is proposed for online estimation of model parameters and state of charge. Firstly, Thevenin equivalent circuit model is built in Simulink of MATLAB R2021b, and the model parameters are estimated by forgetting factor recursive least square in real time. Secondly, the improved adaptive H Infinity Extended Kalman Filter is used to estimate State of Charge in true time. Finally, the feasibility of the algorithm is verified by two different lithium-ion battery conditions. The experimental results show that improved adaptive H Infinity Extended Kalman Filter has the highest and most stable State of Charge estimation accuracy than the other three comparison methods. The Root Mean Square Error and Mean Absolute Error are 0.6008 % and 0.3578 % under the Dynamic Stress Test condition, and 1.0068 % and 0.8721 % under the Federal Urban Driving Schedule condition respectively, Comment: 6 pages

Task-oriented communication is an emerging paradigm for next-generation communication networks, which extracts and transmits task-relevant information, instead of raw data, for downstream applications. Most existing deep learning (DL)-based task-oriented communication systems adopt a closed-world assumption, assuming either the same data distribution for training and testing, or the system could have access to a large out-of-distribution (OoD) dataset for retraining. However, in practical open-world scenarios, task-oriented communication systems will be exposed to unknown OoD data. The powerful approximation ability of learning methods may force the task-oriented communication systems to overfit the training data (i.e., in-distribution data). Therefore, these systems tend to provide overconfident judgments when encountering OoD data. Based on the information bottleneck (IB) framework, we propose a class conditional IB (CCIB) approach to address this problem, supported by information-theoretical insights. The idea is to extract distinguishable features from in-distribution data while keeping their compactness and informativeness. It is achieved by imposing the class conditional latent prior distribution and enforcing the latent of different classes to be far away from each other. Simulation results shall demonstrate that the proposed approach detects OoD data more efficiently than the baselines and state-of-the-art approaches, without compromising the rate-distortion tradeoff.

Holographic MIMO (HMIMO) is being increasingly recognized as a key enabling technology for 6G wireless systems through the deployment of an extremely large number of antennas within a compact space to fully exploit the potentials of the electromagnetic (EM) channel. Nevertheless, the benefits of HMIMO systems cannot be fully unleashed without an efficient means to estimate the high-dimensional channel, whose distribution becomes increasingly complicated due to the accessibility of the near-field region. In this paper, we address the fundamental challenge of designing a low-complexity Bayes-optimal channel estimator in near-field HMIMO systems operating in unknown EM environments. The core idea is to estimate the HMIMO channels solely based on the Stein's score function of the received pilot signals and an estimated noise level, without relying on priors or supervision that is not feasible in practical deployment. A neural network is trained with the unsupervised denoising score matching objective to learn the parameterized score function. Meanwhile, a principal component analysis (PCA)-based algorithm is proposed to estimate the noise level leveraging the low-rank near-field spatial correlation. Building upon these techniques, we develop a Bayes-optimal score-based channel estimator for fully-digital HMIMO transceivers in a closed form. The optimal score-based estimator is also extended to hybrid analog-digital HMIMO systems by incorporating it into a low-complexity message passing algorithm. The (quasi-) Bayes-optimality of the proposed estimators is validated both in theory and by extensive simulation results. In addition to optimality, it is shown that our proposal is robust to various mismatches and can quickly adapt to dynamic EM environments in an online manner thanks to its unsupervised nature, demonstrating its potential in real-world deployment., Comment: 13 pages, 6 figures, 2 tables, submitted to IEEE journal. arXiv admin note: text overlap with arXiv:2311.07908

Holographic MIMO (HMIMO) has recently been recognized as a promising enabler for future 6G systems through the use of an ultra-massive number of antennas in a compact space to exploit the propagation characteristics of the electromagnetic (EM) channel. Nevertheless, the promised gain of HMIMO could not be fully unleashed without an efficient means to estimate the high-dimensional channel. Bayes-optimal estimators typically necessitate either a large volume of supervised training samples or a priori knowledge of the true channel distribution, which could hardly be available in practice due to the enormous system scale and the complicated EM environments. It is thus important to design a Bayes-optimal estimator for the HMIMO channels in arbitrary and unknown EM environments, free of any supervision or priors. This work proposes a self-supervised minimum mean-square-error (MMSE) channel estimation algorithm based on powerful machine learning tools, i.e., score matching and principal component analysis. The training stage requires only the pilot signals, without knowing the spatial correlation, the ground-truth channels, or the received signal-to-noise-ratio. Simulation results will show that, even being totally self-supervised, the proposed algorithm can still approach the performance of the oracle MMSE method with an extremely low complexity, making it a competitive candidate in practice., Comment: 6 pages, 3 figures, 1 table, accepted for presentation at IEEE ICC 2024, Denver, CO, USA

Recently, Graph Transformer (GT) models have been widely used in the task of Molecular Property Prediction (MPP) due to their high reliability in characterizing the latent relationship among graph nodes (i.e., the atoms in a molecule). However, most existing GT-based methods usually explore the basic interactions between pairwise atoms, and thus they fail to consider the important interactions among critical motifs (e.g., functional groups consisted of several atoms) of molecules. As motifs in a molecule are significant patterns that are of great importance for determining molecular properties (e.g., toxicity and solubility), overlooking motif interactions inevitably hinders the effectiveness of MPP. To address this issue, we propose a novel Atom-Motif Contrastive Transformer (AMCT), which not only explores the atom-level interactions but also considers the motif-level interactions. Since the representations of atoms and motifs for a given molecule are actually two different views of the same instance, they are naturally aligned to generate the self-supervisory signals for model training. Meanwhile, the same motif can exist in different molecules, and hence we also employ the contrastive loss to maximize the representation agreement of identical motifs across different molecules. Finally, in order to clearly identify the motifs that are critical in deciding the properties of each molecule, we further construct a property-aware attention mechanism into our learning framework. Our proposed AMCT is extensively evaluated on seven popular benchmark datasets, and both quantitative and qualitative results firmly demonstrate its effectiveness when compared with the state-of-the-art methods., Comment: submit to AAAI-24

Scientific laws describing natural systems may be more complex than our intuition can handle, and thus how we discover laws must change. Machine learning (ML) models can analyze large quantities of data, but their structure should match the underlying physical constraints to provide useful insight. Here we demonstrate a ML approach that incorporates such physical intuition to infer force laws in dusty plasma experiments. Trained on 3D particle trajectories, the model accounts for inherent symmetries and non-identical particles, accurately learns the effective non-reciprocal forces between particles, and extracts each particle's mass and charge. The model's accuracy (R^2 > 0.99) points to new physics in dusty plasma beyond the resolution of current theories and demonstrates how ML-powered approaches can guide new routes of scientific discovery in many-body systems., Comment: 25 pages, 4 Figures, 2 Supplemental Figures, 6 Supplemental Videos

Ultra-massive multiple-input multiple-output (UMMIMO) is a cutting-edge technology that promises to revolutionize wireless networks by providing an unprecedentedly high spectral and energy efficiency. The enlarged array aperture of UM-MIMO facilitates the accessibility of the near-field region, thereby offering a novel degree of freedom for communications and sensing. Nevertheless, the transceiver design for such systems is challenging because of the enormous system scale, the complicated channel characteristics, and the uncertainties of the propagation environments. Hence, it is critical to study scalable, low-complexity, and robust algorithms that can efficiently characterize and leverage the properties of the near-field channel. In this article, we advocate two general frameworks from an artificial intelligence (AI)-native perspective to design iterative and noniterative algorithms for the near-field UM-MIMO transceivers, respectively. Near-field beam focusing and channel estimation are presented as two tutorial-style examples to demonstrate the significant advantages of the proposed AI-native frameworks in terms of various key performance indicators., Comment: 7 pages, 3 figures, 2 tables, magazine manuscript, submitted to IEEE for possible publication

Task-oriented communication is an emerging paradigm for next-generation communication networks, which extracts and transmits task-relevant information, instead of raw data, for downstream applications. Most existing deep learning (DL)-based task-oriented communication systems adopt a closed-world scenario, assuming either the same data distribution for training and testing, or the system could have access to a large out-of-distribution (OoD) dataset for retraining. However, in practical open-world scenarios, task-oriented communication systems need to handle unknown OoD data. Under such circumstances, the powerful approximation ability of learning methods may force the task-oriented communication systems to overfit the training data (i.e., in-distribution data) and provide overconfident judgments when encountering OoD data. Based on the information bottleneck (IB) framework, we propose a class conditional IB (CCIB) approach to address this problem in this paper, supported by information-theoretical insights. The idea is to extract distinguishable features from in-distribution data while keeping their compactness and informativeness. This is achieved by imposing the class conditional latent prior distribution and enforcing the latent of different classes to be far away from each other. Simulation results shall demonstrate that the proposed approach detects OoD data more efficiently than the baselines and state-of-the-art approaches, without compromising the rate-distortion tradeoff., Comment: code available in github, accepted by IEEE GLOBECOM2023

We propose a rapid and label-free three-dimensional imaging technique to analyze paraffin-embedded whole organs without tissue staining or clearing. Various anatomical structures are revealed at subcellular resolution, facilitating comprehensive and volumetric cellular histopathological analysis.

Terahertz ultra-massive MIMO (THz UM-MIMO) is envisioned as one of the key enablers of 6G wireless networks, for which channel estimation is highly challenging. Traditional analytical estimation methods are no longer effective, as the enlarged array aperture and the small wavelength result in a mixture of far-field and near-field paths, constituting a hybrid-field channel. Deep learning (DL)-based methods, despite the competitive performance, generally lack theoretical guarantees and scale poorly with the size of the array. In this paper, we propose a general DL framework for THz UM-MIMO channel estimation, which leverages existing iterative channel estimators and is with provable guarantees. Each iteration is implemented by a fixed point network (FPN), consisting of a closed-form linear estimator and a DL-based non-linear estimator. The proposed method perfectly matches the THz UM-MIMO channel estimation due to several unique advantages. First, the complexity is low and adaptive. It enjoys provable linear convergence with a low per-iteration cost and monotonically increasing accuracy, which enables an adaptive accuracy-complexity tradeoff. Second, it is robust to practical distribution shifts and can directly generalize to a variety of heavily out-of-distribution scenarios with almost no performance loss, which is suitable for the complicated THz channel conditions. For practical usage, the proposed framework is further extended to wideband THz UM-MIMO systems with beam squint effect. Theoretical analysis and extensive simulation results are provided to illustrate the advantages over the state-of-the-art methods in estimation accuracy, convergence rate, complexity, and robustness., Comment: 15 pages, 11 figures, 5 tables, accepted by IEEE Journal of Selected Topics in Signal Processing (JSTSP)

In frequency-division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems, downlink channel state information (CSI) needs to be sent back to the base station (BS) by the users, which causes prohibitive feedback overhead. In this paper, we propose a lightweight and flexible deep learning-based CSI feedback approach by capitalizing on deep equilibrium models. Different from existing deep learning-based methods that stack multiple explicit layers, we propose an implicit equilibrium block to mimic the behavior of an infinite-depth neural network. In particular, the implicit equilibrium block is defined by a fixed-point iteration and the trainable parameters in different iterations are shared, which results in a lightweight model. Furthermore, the number of forward iterations can be adjusted according to users' computation capability, enabling a flexible accuracy-efficiency trade-off. Simulation results will show that the proposed design obtains a comparable performance as the benchmarks but with much-reduced complexity and permits an accuracy-efficiency trade-off at runtime., Comment: submitted to IEEE for possible publication

Reliability is of paramount importance for the physical layer of wireless systems due to its decisive impact on end-to-end performance. However, the uncertainty of prevailing deep learning (DL)-based physical layer algorithms is hard to quantify due to the black-box nature of neural networks. This limitation is a major obstacle that hinders their practical deployment. In this paper, we attempt to quantify the uncertainty of an important category of DL-based channel estimators. An efficient statistical method is proposed to make blind predictions for the mean squared error of the DL-estimated channel solely based on received pilots, without knowledge of the ground-truth channel, the prior distribution of the channel, or the noise statistics. The complexity of the blind performance prediction is low and scales only linearly with the number of antennas. Simulation results for ultra-massive multiple-input multiple-output (UM-MIMO) channel estimation with a mixture of far-field and near-field paths are provided to verify the accuracy and efficiency of the proposed method., Comment: 6 pages, 3 figures, 1 table, accepted by IEEE ICC 2023

Terahertz ultra-massive multiple-input multiple-output (THz UM-MIMO) is envisioned as one of the key enablers of 6G wireless systems. Due to the joint effect of its large array aperture and small wavelength, the near-field region of THz UM-MIMO is greatly enlarged. The high-dimensional channel of such systems thus consists of a stochastic mixture of far and near fields, which renders channel estimation extremely challenging. Previous works based on uni-field assumptions cannot capture the hybrid far- and near-field features, thus suffering significant performance loss. This motivates us to consider hybrid-field channel estimation. We draw inspirations from fixed point theory to develop an efficient deep learning based channel estimator with adaptive complexity and linear convergence guarantee. Built upon classic orthogonal approximate message passing, we transform each iteration into a contractive mapping, comprising a closed-form linear estimator and a neural network based non-linear estimator. A major algorithmic innovation involves applying fixed point iteration to compute the channel estimate while modeling neural networks with arbitrary depth and adapting to the hybrid-field channel conditions. Simulation results verify our theoretical analysis and show significant performance gains over state-of-the-art approaches in the estimation accuracy and convergence rate. © 2022 IEEE.

Recently, Graph Convolutional Network (GCN) has been widely used in Hyperspectral Image (HSI) classification due to its satisfactory performance. However, the number of labeled pixels is very limited in HSI, and thus the available supervision information is usually insufficient, which will inevitably degrade the representation ability of most existing GCN-based methods. To enhance the feature representation ability, in this paper, a GCN model with contrastive learning is proposed to explore the supervision signals contained in both spectral information and spatial relations, which is termed Contrastive Graph Convolutional Network (ConGCN), for HSI classification. First, in order to mine sufficient supervision signals from spectral information, a semi-supervised contrastive loss function is utilized to maximize the agreement between different views of the same node or the nodes from the same land cover category. Second, to extract the precious yet implicit spatial relations in HSI, a graph generative loss function is leveraged to explore supplementary supervision signals contained in the graph topology. In addition, an adaptive graph augmentation technique is designed to flexibly incorporate the spectral-spatial priors of HSI, which helps facilitate the subsequent contrastive representation learning. The extensive experimental results on four typical benchmark datasets firmly demonstrate the effectiveness of the proposed ConGCN in both qualitative and quantitative aspects.

Terahertz ultra-massive multiple-input multiple-output (THz UM-MIMO) is envisioned as one of the key enablers of 6G wireless systems. Due to the joint effect of its array aperture and small wavelength, the near-field region of THz UM-MIMO is greatly enlarged. The high-dimensional channel of such systems thus consists of a stochastic mixture of far and near fields, which renders channel estimation extremely challenging. Previous works based on uni-field assumptions cannot capture the hybrid far- and near-field features, thus suffering significant performance loss. This motivates us to consider hybrid-field channel estimation. We draw inspirations from fixed point theory to develop an efficient deep learning based channel estimator with adaptive complexity and linear convergence guarantee. Built upon classic orthogonal approximate message passing, we transform each iteration into a contractive mapping, comprising a closed-form linear estimator and a neural network based non-linear estimator. A major algorithmic innovation involves applying fixed point iteration to compute the channel estimate while modeling neural networks with arbitrary depth and adapting to the hybrid-field channel conditions. Simulation results verify our theoretical analysis and show significant performance gains over state-of-the-art approaches in the estimation accuracy and convergence rate., Comment: 6 pages, 3 figures, accepted by IEEE Globecom 2022. Source code is publicly available at https://github.com/wyuaq/FPN-OAMP-THz-Channel-Estimation

This work presents an ensemble system based on various uni-modal and bi-modal model architectures developed for the SemEval 2022 Task 5: MAMI-Multimedia Automatic Misogyny Identification. The challenge organizers provide an English meme dataset to develop and train systems for identifying and classifying misogynous memes. More precisely, the competition is separated into two sub-tasks: sub-task A asks for a binary decision as to whether a meme expresses misogyny, while sub-task B is to classify misogynous memes into the potentially overlapping sub-categories of stereotype, shaming, objectification, and violence. For our submission, we implement a new model fusion network and employ an ensemble learning approach for better performance. With this structure, we achieve a 0.755 macroaverage F1-score (11th) in sub-task A and a 0.709 weighted-average F1-score (10th) in sub-task B., Comment: 10 pages

Rapid multicolor three-dimensional (3D) imaging for centimeter-scale specimens with subcellular resolution remains a challenging but captivating scientific pursuit. Here, we present a fast, cost-effective, and robust multicolor whole-organ 3D imaging method assisted with ultraviolet (UV) surface excitation and vibratomy-assisted sectioning, termed translational rapid ultraviolet-excited sectioning tomography (TRUST). With an inexpensive UV light-emitting diode (UV-LED) and a color camera, TRUST achieves widefield exogenous molecular-specific fluorescence and endogenous content-rich autofluorescence imaging simultaneously while preserving low system complexity and system cost. Formalin-fixed specimens are stained layer by layer along with serial mechanical sectioning to achieve automated 3D imaging with high staining uniformity and time efficiency. 3D models of all vital organs in wild-type C57BL/6 mice with the 3D structure of their internal components (e.g., vessel network, glomeruli, and nerve tracts) can be reconstructed after imaging with TRUST to demonstrate its fast, robust, and high-content multicolor 3D imaging capability. Moreover, its potential for developmental biology has also been validated by imaging entire mouse embryos (similar to 2 days for the embryo at the embryonic day of 15). TRUST offers a fast and cost-effective approach for high-resolution whole-organ multicolor 3D imaging while relieving researchers from the heavy sample preparation workload.

We propose a rapid and label-free three-dimensional imaging technique to analyze paraffin-embedded whole organs without tissue staining or clearing. Various anatomical structures are revealed at subcellular resolution, facilitating comprehensive and volumetric cellular histopathological analysis.

With the growing availability of smart devices and cloud services, personal speech assistance systems are increasingly used on a daily basis. Most devices redirect the voice recordings to a central server, which uses them for upgrading the recognizer model. This leads to major privacy concerns, since private data could be misused by the server or third parties. Federated learning is a decentralized optimization strategy that has been proposed to address such concerns. Utilizing this approach, private data is used for on-device training. Afterwards, updated model parameters are sent to the server to improve the global model, which is redistributed to the clients. In this work, we implement federated learning for speech recognition in a hybrid and an end-to-end model. We discuss the outcomes of these systems, which both show great similarities and only small improvements, pointing to a need for a deeper understanding of federated learning for speech recognition.

Audio-visual speech recognition (AVSR) can effectively and significantly improve the recognition rates of small-vocabulary systems, compared to their audio-only counterparts. For large-vocabulary systems, however, there are still many difficulties, such as unsatisfactory video recognition accuracies, that make it hard to improve over audio-only baselines. In this paper, we specifically consider such scenarios, focusing on the large-vocabulary task of the LRS2 database, where audio-only performance is far superior to video-only accuracies, making this an interesting and challenging setup for multi-modal integration. To address the inherent difficulties, we propose a new fusion strategy: a recurrent integration network is trained to fuse the state posteriors of multiple single-modality models, guided by a set of model-based and signal-based stream reliability measures. During decoding, this network is used for stream integration within a hybrid recognizer, where it can thus cope with the time-variant reliability and information content of its multiple feature inputs. We compare the results with end-to-end AVSR systems as well as with competitive hybrid baseline models, finding that the new fusion strategy shows superior results, on average even outperforming oracle dynamic stream weighting, which has so far marked the -- realistically unachievable -- upper bound for standard stream weighting. Even though the pure lipreading performance is low, audio-visual integration is helpful under all -- clean, noisy, and reverberant -- conditions. On average, the new system achieves a relative word error rate reduction of 42.18\% compared to the audio-only model, pointing at a high effectiveness of the proposed integration approach.

In this paper, we focus on the multi-object tracking (MOT) problem of automatic driving and robot navigation. Most existing MOT methods track multiple objects using a singular RGB camera, which are prone to camera field-of-view and suffer tracking failures in complex scenarios due to background clutters and poor light conditions. To meet these challenges, we propose a MultiModality PAnoramic multi-object Tracking framework (MMPAT), which takes both 2D panorama images and 3D point clouds as input and then infers target trajectories using the multimodality data. The proposed method contains four major modules, a panorama image detection module, a multimodality data fusion module, a data association module and a trajectory inference model. We evaluate the proposed method on the JRDB dataset, where the MMPAT achieves the top performance in both the detection and tracking tasks and significantly outperforms state-of-the-art methods by a large margin (15.7 and 8.5 improvement in terms of AP and MOTA, respectively).

End-to-end acoustic speech recognition has quickly gained widespread popularity and shows promising results in many studies. Specifically the joint transformer/CTC model provides very good performance in many tasks. However, under noisy and distorted conditions, the performance still degrades notably. While audio-visual speech recognition can significantly improve the recognition rate of end-to-end models in such poor conditions, it is not obvious how to best utilize any available information on acoustic and visual signal quality and reliability in these models. We thus consider the question of how to optimally inform the transformer/CTC model of any time-variant reliability of the acoustic and visual information streams. We propose a new fusion strategy, incorporating reliability information in a decision fusion net that considers the temporal effects of the attention mechanism. This approach yields significant improvements compared to a state-of-the-art baseline model on the Lip Reading Sentences 2 and 3 (LRS2 and LRS3) corpus. On average, the new system achieves a relative word error rate reduction of 43% compared to the audio-only setup and 31% compared to the audiovisual end-to-end baseline., Comment: 5 pages

The development of aggregation-induced emission (AIE) building block and deciphering its luminescence mechanism are of great significance. Here a feasible strategy for the construction of AIE unit based on E-Z isomerization (EZI) of exocyclic C=N double bond is proposed. Taking [1,2,4]thiadiazole[4,3-a]pyridine (TZP) derivative as an example, its aryl-substituted derivative (TZPP) shows obvious AIE character. The analysis of spectral data and theoretical calculations indicates that fast structural relaxation of TZPP in the emissive state plays a key role in a low fluorescence quantum yield in dilute solution, which should be caused by the small energy gap between locally excited (LE) state and twisted intramolecular charge transfer state. When in solid state, the bright emission with LE state characteristic reappears due to the large shift barrier of geometry transformation. As a potential building block for AIEgens with special heterocyclic structure, these findings would open up opportunities for developing various functional materials.

The development of aggregation-induced emission (AIE) building block and deciphering its luminescence mechanism are of great significance. Here a feasible strategy for the construction of AIE unit based on E-Z isomerization (EZI) of exocyclic C=N double bond is proposed. Taking [1,2,4]thiadiazole[4,3-a]pyridine (TZP) derivative as an example, its aryl-substituted derivative (TZPP) shows obvious AIE character. The analysis of spectral data and theoretical calculations indicates that fast structural relaxation of TZPP in the emissive state plays a key role in a low fluorescence quantum yield in dilute solution, which should be caused by the small energy gap between locally excited (LE) state and twisted intramolecular charge transfer state. When in solid state, the bright emission with LE state characteristic reappears due to the large shift barrier of geometry transformation. As a potential building block for AIEgens with special heterocyclic structure, these findings would open up opportunities for developing various functional materials.

The development of aggregation-induced emission (AIE) building block and deciphering its luminescence mechanism are of great significance. Here a feasible strategy for the construction of AIE unit based on E-Z isomerization (EZI) of exocyclic C=N double bond is proposed. Taking [1,2,4]thiadiazole[4,3-a]pyridine (TZP) derivative as an example, its aryl-substituted derivative (TZPP) shows obvious AIE character. The analysis of spectral data and theoretical calculations indicates that fast structural relaxation of TZPP in the emissive state plays a key role in a low fluorescence quantum yield in dilute solution, which should be caused by the small energy gap between locally excited (LE) state and twisted intramolecular charge transfer state. When in solid state, the bright emission with LE state characteristic reappears due to the large shift barrier of geometry transformation. As a potential building block for AIEgens with special heterocyclic structure, these findings would open up opportunities for developing various functional materials.

For many small- and medium-vocabulary tasks, audio-visual speech recognition can significantly improve the recognition rates compared to audio-only systems. However, there is still an ongoing debate regarding the best combination strategy for multi-modal information, which should allow for the translation of these gains to large-vocabulary recognition. While an integration at the level of state-posterior probabilities, using dynamic stream weighting, is almost universally helpful for small-vocabulary systems, in large-vocabulary speech recognition, the recognition accuracy remains difficult to improve. In the following, we specifically consider the large-vocabulary task of the LRS2 database, and we investigate a broad range of integration strategies, comparing early integration and end-to-end learning with many versions of hybrid recognition and dynamic stream weighting. One aspect, which is shown to provide much benefit here, is the use of dynamic stream reliability indicators, which allow for hybrid architectures to strongly profit from the inclusion of visual information whenever the audio channel is distorted even slightly., Comment: 5 pages

This paper aims at analyzing risks management of genetically modified (GM) crop technology in China, including risk classification, risk generating mechanisms and its governance. Firstly, we seek to create a three-dimensional model capable of assessing the risks of GM crop technologies. Based on this model, the risks of GM crop technologies can be divided into eight types, depending on the high or low risks levels associated with social hazard, technology uncertainty and economic harm. China’s GM technology is currently located in the high risk zone of this model, particularly in the market of GM soybean. In order to tackle this risk, the article introduces the Actor-Network Theory (ANT) as a useful tool to explore its risk assessment and governance. Lastly, we suggest the Chinese government needs to construct an efficient governance mechanism which should be able to balance actors’ interests and reduce or avoid risks induced by GM crop technologies.

We search for evidence of a relation between properties of young stellar objects (YSOs) and their parent molecular clouds to understand the initial conditions of high-mass star formation. A sample of 135 sources was selected from the Infrared Astronomical Satellite (IRAS) Point Source Catalog, on the basis of their red color to enhance the possibility of discovering young sources. Using the Kolner Observatorium fur SubMillimeter Astronomie (KOSMA) 3-m telescope, a single-point survey in 13CO(2-1) was carried out for the entire sample, and 14 sources were mapped further. Archival mid-infrared (MIR) data were compared with the 13CO emissions to identify evolutionary stages of the sources. A 13CO observed sample was assembled to investigate the correlation between 13CO line width of the clouds and the luminosity of the associated YSOs. We identified 98 sources suitable for star formation analyses for which relevant parameters were calculated. We detected 18 cores from 14 mapped sources, which were identified with eight pre-UC HII regions and one UC HII region, two high-mass cores earlier than pre-UC HII phase, four possible star forming clusters, and three sourceless cores. By compiling a large (360 sources) 13CO observed sample, a good correlation was found between the 13CO line width of the clouds and the bolometric luminosity of the associated YSOs, which can be fitted as a power law: lg(dV13/km/s)=-0.023+0.135lg(Lbol/Lsolar). Results show that luminous (>10^3Lsolar) YSOs tend to be associated with both more massive and more turbulent (dV13>2km/s) molecular cloud structures., Comment: Accepted by Astronomy and Astrophysics; this version: sent to publisher; 13 pages, 4 figures, 2 tables, 1 online appendix

We search for evidence of a relation between properties of young stellar objects (YSOs) and their parent molecular clouds to understand the initial conditions of high-mass star formation. A sample of 135 sources was selected from the Infrared Astronomical Satellite (IRAS) Point Source Catalog, on the basis of their red color to enhance the possibility of discovering young sources. Using the Kolner Observatorium fur SubMillimeter Astronomie (KOSMA) 3-m telescope, a single-point survey in 13CO(2-1) was carried out for the entire sample, and 14 sources were mapped further. Archival mid-infrared (MIR) data were compared with the 13CO emissions to identify evolutionary stages of the sources. A 13CO observed sample was assembled to investigate the correlation between 13CO line width of the clouds and the luminosity of the associated YSOs. We identified 98 sources suitable for star formation analyses for which relevant parameters were calculated. We detected 18 cores from 14 mapped sources, which were identified with eight pre-UC HII regions and one UC HII region, two high-mass cores earlier than pre-UC HII phase, four possible star forming clusters, and three sourceless cores. By compiling a large (360 sources) 13CO observed sample, a good correlation was found between the 13CO line width of the clouds and the bolometric luminosity of the associated YSOs, which can be fitted as a power law: lg(dV13/km/s)=-0.023+0.135lg(Lbol/Lsolar). Results show that luminous (>10^3Lsolar) YSOs tend to be associated with both more massive and more turbulent (dV13>2km/s) molecular cloud structures., Comment: Accepted by Astronomy and Astrophysics; this version: sent to publisher; 13 pages, 4 figures, 2 tables, 1 online appendix

A statistical study of the properties of molecular outflows is performed based on an up-to-date sample. 391 outflows were identified in published articles or preprints before February 28, 2003. The parameters of position, morphology, mass, energy, outflow dynamics and central source luminosity are presented for each outflow source. Outflow lobe polarity is known for all the sources, and 84% are found to be bipolar. The sources are divided into low mass and high mass groups according to either the available bolometric luminosity of the central source or the outflow mass.Energetic mass ejection may be a common aspect of the formation of high mass as well as low mass stars. Outflow masses are correlated strongly with bolometric luminosity of the center sources, which was obtained for the first time. There are also correlations between the central source luminosity and the parameters of mechanical luminosity and the thrust or force necessary to drive the outflow. The results show that flow mass, momentum and energy depend on the nature of the central source. Despite their similarity, there are differences between the high mass and low mass outflows on collimation, flow masses, mass-dynamical time relation and associated objects such as HH objects and water masers.Sources with characteristics of collapse or infall comprise 12% of the entire outflow sample. The spatial distribution of the outflow sources in the Galaxy is presented and the local occurrence rate is compared with the stellar birth rate., Comment: 16 pages, 9 figures

A statistical study of the properties of molecular outflows is performed based on an up-to-date sample. 391 outflows were identified in published articles or preprints before February 28, 2003. The parameters of position, morphology, mass, energy, outflow dynamics and central source luminosity are presented for each outflow source. Outflow lobe polarity is known for all the sources, and 84% are found to be bipolar. The sources are divided into low mass and high mass groups according to either the available bolometric luminosity of the central source or the outflow mass.Energetic mass ejection may be a common aspect of the formation of high mass as well as low mass stars. Outflow masses are correlated strongly with bolometric luminosity of the center sources, which was obtained for the first time. There are also correlations between the central source luminosity and the parameters of mechanical luminosity and the thrust or force necessary to drive the outflow. The results show that flow mass, momentum and energy depend on the nature of the central source. Despite their similarity, there are differences between the high mass and low mass outflows on collimation, flow masses, mass-dynamical time relation and associated objects such as HH objects and water masers.Sources with characteristics of collapse or infall comprise 12% of the entire outflow sample. The spatial distribution of the outflow sources in the Galaxy is presented and the local occurrence rate is compared with the stellar birth rate., Comment: 16 pages, 9 figures

A novel supermolecule [HgBr2(ptz)]2 · HgBr2 (ptz=phenothiazine) with uncoordinated inorganic salt HgBr2 presented in a 1D chain was prepared. The bulky ligand phenothiazine has unusual coordination mode with large steric inhibition perpendicular to the chain direction. The uncoordinated HgBr2 molecule was stabilized by multiple weak Hg⋯Br interactions and the whole structure was also stabilized by strong π–π interactions and N–H⋯Br hydrogen bonds to form 2D network.

A novel supramolecule [HgCl2(ptz)]2·HgCl2 (ptz = phenothiazine) with uncoordinated inorganic salt HgCl2 presented in a 1D chain was first prepared and then successfully applied as a new precursor in the preparation of submicrometer Hg2Cl2 rods. Single crystal X-ray analysis showed that the 1D chain structure is stabilized by hydrogen bonds between adjacent chains and the coordination mode of the ligand phenothiazine is unusual with large steric inhibition other than the chain directions. The results revealed that the particular chain structure plays a significant role in the formation of the Hg2Cl2 rods.