High Redundancy Research Articles

Population Distribution Forecasting Based on the Fusion of Spatiotemporal Basic and External Features: A Case Study of Lujiazui Financial District

Predicting the distribution of people in the time window approaching a disaster is crucial for post-disaster assistance activities and can be useful for evacuation route selection and shelter planning. However, two major limitations have not yet been addressed: (1) Most spatiotemporal prediction models incorporate spatiotemporal features either directly or indirectly, which results in high information redundancy in the parameters of the prediction model and low computational efficiency. (2) These models usually incorporate certain basic and external features, and they can neither change spatiotemporal addressed features according to spatiotemporal features nor change them in real-time according to spatiotemporal features. The spatiotemporal feature embedding methods for these models are inflexible and difficult to interpret. To overcome these problems, a lightweight population density distribution prediction framework that considers both basic and external spatiotemporal features is proposed. In the study, an autoencoder is used to extract spatiotemporal coded information to form a spatiotemporal attention mechanism, and basic and external spatiotemporal feature attention is fused by a fusion framework with learnable weights. The fused spatiotemporal attention is fused with Resnet as the prediction backbone network to predict the people distribution. Comparison and ablation experimental results show that the computational efficiency and interpretability of the prediction framework are improved by maximizing the scalability of the spatiotemporal features of the model by unleashing the scalability of the spatiotemporal features of the model while enhancing the interpretability of the spatiotemporal information as compared to the classical and popular spatiotemporal prediction frameworks. This study has a multiplier effect and provides a reference solution for predicting population distributions in similar regions around the globe.

Functional diversity and resilience of bivalves after the Permian-Triassic mass extinction

The Permian-Triassic mass extinction was the largest extinction event in the Phanerozoic eon, with profound taxonomic and ecological effects on the ecosystem function. Functional diversity, a facet of biodiversity, could reflect the ecosystem function and stability. Although previous studies have shown that the functional richness of global marine organisms was decoupled from their taxonomic diversity during the mass extinctions, the evolution of functional diversity during the Permian-Triassic mass extinction and its aftermath is still under debate. The ecologically diverse clade bivalves may be more representative for understanding the evolution of functional diversity. To investigate the evolutionary dynamics of the functional diversity of bivalves, a global bivalve dataset of 8929 occurrences from the latest Permian to the Late Triassic was constructed. Functional richness, functional evenness, and functional redundancy were calculated to reflect the functional diversity in this study. Our results showed that the functional richness of bivalves was slightly affected by the Permian-Triassic mass extinction, decoupled from the significant decrease in taxonomic diversity. Meanwhile, a decrease in functional redundancy and an increase in functional evenness were observed after the mass extinction. In addition, bivalves showed high resilience to the mass extinction by maintaining the ecospace and reducing the functional redundancy. The high taxonomic diversity, high functional richness, high functional redundancy and relatively higher proportion of infaunal bivalves during the Late Triassic indicate that the Mesozoic marine revolution was already underway.

Boosting multi-document summarization with hierarchical graph convolutional networks

The input of the multi-document summarization task is usually long and has high redundancy. Encoding multiple documents is a challenge for the Seq2Seq architecture. The way of concatenating multiple documents into a sequence ignores the relation between documents. Attention-based Seq2Seq architectures have slightly improved the cross-document relation modeling for multi-document summarization. However, these methods ignore the relation between sentences, and there is little improvement that can be achieved through the attention mechanism alone. This paper proposes a hierarchical approach to leveraging the relation between words, sentences, and documents for abstractive multi-document summarization. Our model employs the Graph Convolutional Networks (GCN) for capturing the cross-document and cross-sentence relations. The GCN module can enrich semantic representations by generating high-level hidden features. Our model achieves significant improvement over the attention-based baseline, beating the Hierarchical Transformer by 3.4/1.64, 1.92/1.44 ROUGE-1/2 F1 points on the Multi-News and WikiSum datasets, respectively. Experimental results demonstrate that our delivered method brings substantial improvements over several strong baselines.

Using cross-domain knowledge augmentation to explore comorbidity in electronic health records data

Research concentrating on specific diseases or employing single datasets, such as medical histories and thematic data, has garnered considerable attention. However, there has been limited investigation into comorbidities. Although some ad-hoc methods have been utilized in the medical field, there is a scarcity of systematic approaches to address this challenge. The task of expressing patient features using heterogeneous and cross-domain data presents considerable difficulties. Directly mapping this data into a matrix frequently results in issues such as high dimensionality, sparsity, redundancy, and noise. Additionally, given the critical role of supervisory information in medicine, acquiring accurate information is paramount. To address these issues, we propose an enhanced clustering method that capitalizes on cross-domain knowledge augmentation. This method can iteratively learn clustering outcomes and cross-domain knowledge. The cross-domain knowledge matrix produced by our approach can be interpreted as a measure of similarity between instances across domains. We validate our proposed model in real-world electronic health records (EHR) data, and achieve significant performance improvement compared to the baseline method, successfully completing the task of exploring comorbidity. Due to the privacy of EHR data, we also conduct extensive experiments on the publicly available datasets DBLP and UCI. The experimental results show that our algorithm is superior to the baseline algorithm and has strong generality.

Cross-Domain Denoising for Low-Dose Multi-Frame Spiral Computed Tomography.

Computed tomography (CT) has been used worldwide as a non-invasive test to assist in diagnosis. However, the ionizing nature of X-ray exposure raises concerns about potential health risks such as cancer. The desire for lower radiation doses has driven researchers to improve reconstruction quality. Although previous studies on low-dose computed tomography (LDCT) denoising have demonstrated the effectiveness of learning-based methods, most were developed on the simulated data. However, the real-world scenario differs significantly from the simulation domain, especially when using the multi-slice spiral scanner geometry. This paper proposes a two-stage method for the commercially available multi-slice spiral CT scanners that better exploits the complete reconstruction pipeline for LDCT denoising across different domains. Our approach makes good use of the high redundancy of multi-slice projections and the volumetric reconstructions while leveraging the over-smoothing issue in conventional cascaded frameworks caused by aggressive denoising. The dedicated design also provides a more explicit interpretation of the data flow. Extensive experiments on various datasets showed that the proposed method could remove up to 70% of noise without compromised spatial resolution, while subjective evaluations by two experienced radiologists further supported its superior performance against state-of-the-art methods in clinical practice. Code is available at https://github.com/YCL92/TMD-LDCT.

Advancements in Network Attached Storage (NAS) for Mobile Devices: Technological Developments and Performance Assessment

Network-attached storage (NAS) technology has emerged as a vital solution in the evolving landscape of data management and storage. With the exponential growth of data and the increasing demand for efficient, scalable storage solutions, NAS systems offer a centralized, cost-effective, and flexible alternative to traditional storage methods. This paper explores the application and advantages of NAS technology in various scenarios, from home and small business environments to large enterprises. It highlights the key strengths of NAS systems in optimizing data storage, ensuring data security, and facilitating cross-device sharing. The study delves into the architectural components of NAS, including file systems, RAID configurations, and network protocols, to demonstrate how these technologies enhance storage performance and reliability. Technical details on NAS system design, such as the integration of advanced file systems and user-level networking technologies, are discussed to showcase their impact on data transfer efficiency and overall system performance. Experimental results validate the effectiveness of NAS in different environments, illustrating its ability to provide high availability, data redundancy, and low-latency data access. The findings underscore NAS technology’s potential as a versatile and scalable storage solution, with recommendations for future research focused on developing new file systems, optimizing network protocols, and exploring edge computing integrations to further enhance NAS capabilities.

Multimodal In-Sensor Computing System Using Integrated Silicon Photonic Convolutional Processor.

Photonic integrated circuits offer miniaturized solutions for multimodal spectroscopic sensory systems by leveraging the simultaneous interaction of light with temperature, chemicals, and biomolecules, among others. The multimodal spectroscopic sensory data is complex and has huge data volume with high redundancy, thus requiring high communication bandwidth associated with high communication power consumption to transfer the sensory data. To circumvent this high communication cost, the photonic sensor and processor are brought into intimacy and propose a photonic multimodal in-sensor computing system using an integrated silicon photonic convolutional processor. A microring resonator crossbar array is used as the photonic processor to implement convolutional operation with 5-bit accuracy, validated through image edge detection tasks. Further integrating the processor with a photonic spectroscopic sensor, the in situ processing of multimodal spectroscopic sensory data is demonstrated, achieving the classification of protein species of different types and concentrations at various temperatures. A classification accuracy of 97.58% across 45 different classes is achieved. The multimodal in-sensor computing system demonstrates the feasibility of integrating photonic processors and photonic sensors to enhance the data processing capability of photonic devices at the edge.

High functional vulnerability across the world’s deep-sea hydrothermal vent communities

At the nearly pristine hydrothermal vents of the deep sea, highly endemic animals depend upon bacteria nourished by hydrothermal fluids that emerge as outflows from the seafloor. These animals are remarkable in tolerating extreme conditions, including high heat, toxic reduced sulfide, and low oxygen. Here, we test whether the extreme vent environment has selected for functionally similar species across the world's deep ocean, despite well-established global geographic patterns of high phylogenetic distinctness. High functional redundancy in species pools within regions suggests that the extreme environments select for species with specific traits. Yet, some regions emerge as functional hotspots where species pools with distinct functional trait compositions may represent geological idiosyncrasies of the habitats. Moreover, many species are functionally unique, an outcome of low species richness in a system where the species pool is small at all scales. Given the high proportion of functionally unique species, simulated species extinctions indicate that species losses would rapidly translate to the elimination of functionally irreplaceable species and could tip vent systems to functional collapse. Ocean changes and human-induced threats are expected to significantly impact many vent species as human activities expand in the remote deep sea. The opportunity exists now to take precautionary actions to limit the rates of extinction now ubiquitous in more accessible areas of Earth.

Research on Highly Reliable Self-Powered Vibration Sensors for Geological Drilling

Vibration signals at the bottom of the drill string during geological drilling are crucial for lithological identification and drilling parameter optimization. However, existing downhole vibration sensors suffer from limitations in power supply and reliability. This study proposes a self-powered vibration sensor with high redundancy based on the triboelectric nanogenerator principle, which is capable of measuring both axial and transverse vibrations, thereby reducing the dependence on external power sources. The experimental results show that the sensor can measure axial vibration frequencies ranging from 0 to 11 Hz with an error of less than 4% and transverse vibration frequencies ranging from 0 to 5 Hz with an error of less than 5%. It can operate stably in temperatures from 0 to 180 °C and relative humidities from 0 to 95%. The sensor’s axial vibration measurement features six identical measurement structures, providing high redundancy and effectively enhancing its reliability. Furthermore, the sensor exhibits power generation capabilities. When an external load of 1 MΩ is applied to the axial measurement module and 10 MΩ to the transverse measurement module, the sensor achieves its maximum power output for both axial and transverse measurements, reaching 32.4 × 10−9 W and 2.1 × 10−9 W, respectively. Compared to traditional bottom-of-the-hole vibration sensors, this sensor possesses self-powering capabilities and high reliability, which can improve the operational efficiency and hold significant practical value for future applications.

MD-HIT: Machine learning for material property prediction with dataset redundancy control

Materials datasets usually contain many redundant (highly similar) materials due to the tinkering approach historically used in material design. This redundancy skews the performance evaluation of machine learning (ML) models when using random splitting, leading to overestimated predictive performance and poor performance on out-of-distribution samples. This issue is well-known in bioinformatics for protein function prediction, where tools like CD-HIT are used to reduce redundancy by ensuring sequence similarity among samples greater than a given threshold. In this paper, we survey the overestimated ML performance in materials science for material property prediction and propose MD-HIT, a redundancy reduction algorithm for material datasets. Applying MD-HIT to composition- and structure-based formation energy and band gap prediction problems, we demonstrate that with redundancy control, the prediction performances of the ML models on test sets tend to have relatively lower performance compared to the model with high redundancy, but better reflect models’ true prediction capability.

Parallel Channel Feature Weighted Seizure Prediction Based on Multi-Scale Spatial and Temporal Factorization

Epileptic seizure prediction based on electroencephalography (EEG) plays an important role in the field. However, the existing epilepsy prediction methods have little modeling ability to capture the interaction between features, and the high redundancy of features leads to the limitations of model performance. In addition, the feature information guided by the multi-channel spatial location of the brain region is ignored. To solve these problems, this paper proposes a parallel channel feature-weighted seizure prediction network based on multi-scale temporal and spatial factorization (MS-STFM-PCFWNet). Specifically, the feature information of time domain and multi-channel spatial domain of brain region can be extracted by using feature matrix to fully learn the correlation between channels. Secondly, the multi-scale spatiotemporal Factorizer (MS-STFM) is utilized to combine and interact the features, and the correlation information between the features is captured. Finally, by combining the multi-scale Inception module with an efficient channel attention mechanism, a parallel channel feature weighted network (PCFWNet) is constructed to effectively learn multi-domain features and map the discriminant representation of epilepsy prediction. The proposed MS-STFM-PCFWNet is evaluated on public CHB-MIT and BONN datasets. The experimental results show that compared with the most advanced methods, the proposed method achieves excellent predictive performance, which can be used for early warning of epileptic seizures in specific patients.

Quantitative phase imaging with two in-line holograms.

Quantitative phase imaging (QPI) has emerged as a practical technique for acquiring structural information from phase objects. Digital holography can realize phase detection, but it is limited by a spatial bandwidth product or affected by the overlap of conjugate images. The phase retrieval algorithm serves as an effective tool for QPI dealing with intensity patterns. Traditional phase retrieval algorithms heavily rely on strong support constraints or high data redundancy to accurately reconstruct the sample image. However, in single-frame phase retrieval algorithms, the precise acquisition of support constraints is notably challenging. The multiple-measurement spends much time on data acquisition and is unsuitable for dynamic sample observation. In this paper, we propose a novel, to the best of our knowledge, quantitative phase imaging method that utilizes only two in-line holograms. We have developed a phase retrieval algorithm based on ptychography, which eliminates twin-image and separates illumination background. The proposed method achieves high data utilization efficiency and can be employed for dynamic imaging.

Ultra-short term wind power prediction method based on LightGBM and transformer

Abstract Accurate ultra-short-term wind power prediction is very important for the safe and stable operation of the power system. At present, most wind power forecasting systems use numerical weather forecast data and the data collected by the Supervisory Control And Data Acquisition (SCADA) system. However, these data have the characteristics of high data dimension, feature redundancy, and feature correlation. Therefore, in the process of ultra-short power prediction, it is necessary to select features with high power correlation and low cross-correlation between features. In this paper, a feature selection method for wind power prediction based on LightGBM is proposed to calculate the importance of all features and determine the preliminary selected features. Then, the maximum information coefficient is used to construct the correlation discriminant matrix, according to which the features with similar importance in a single screening are evaluated, and the input features with high similarity are discarded. In addition, in order to improve the accuracy of the system’s wind power prediction, this paper uses the effective features extracted by LightGBM to design an ultra-short-term power prediction method based on Transformer. The results show that the RMSE of ultra-short-term wind power prediction is 7.3%.

Research on the inverse kinematics of heavy-load manipulator and end-effector for fusion reactor

The environment in Tokamak fusion reactor is hostile to remote handling (RH) equipment that maintains in-vessel components. Many maintenance tasks include transferring components, pipe cutting, and welding in the vacuum vessel (VV). To fulfill these maintenance works, a 7- degree-of-freedom (DOF) heavy load manipulator and a 3-DOF end-effector are designed and connected together to form a 10-DOF redundant robot. The inverse kinematics for such a high redundancy robot, considering obstacle avoidance in the complex space of VV, is a challenge. To solve this problem, the Jacobian method is adopted, and a method specially designed for obstacle avoidance of redundant robots working in the VV is integrated to simplify algorithm calculation and improve inverse solution efficiency. The algorithm is applied to solve the inverse kinematics of the redundant robot for the maintenance of the divertor plasma facing components (PFC) in VV. The results show that the inverse kinematics of the redundant robot can be solved quickly with high positioning accuracy. The method can also be used for other fusion reactor maintenance robots with some adjustments. The maintenance efficiency of redundant robot can be improved with the method which can be valuable for the whole remote handling process.

Depressurization strategy of China's advanced pressurized water reactor under typical accidents

Advanced pressurized water reactor was simulated using system analysis program. The depressurization strategy for the automatic depressurization system (ADS) under typical ADS-triggering accidents (2-inch/10-inch cold leg break, inadvertent opening of the ADS, DVI pipeline break) was investigated. The results show that after these accidents, ADS can ensure the operation of the three types of safe injection tanks, with high redundancy and inherent safety. The multi-stage design of ADS aids the sparger in maintaining a stable critical jet state. In 10-inch cold leg break accident, the sparger cannot reached the critical jet state under all of pipeline fault conditions. From a system point of view, adjusting the pipeline design of ADS is necessary to avoid long-term condensation oscillation of the sparger in some accidents. From a design perspective of the local equipment, the nozzle structure of the sparger should attenuate the dynamic load caused by the condensation oscillation and back-attack phenomenon.

Prompt-supervised dynamic attention graph convolutional network for skeleton-based action recognition

Skeleton-based action recognition is a core task in the field of video understanding. Skeleton sequences are characterized by high information density, low redundancy, and clear structural information, thereby facilitating the analysis of complex relationships among human behaviors more readily than other modalities. Although existing studies have encoded skeleton data and achieved positive outcomes, they have often overlooked the precise high-level semantic information inherent in the action descriptions. To address this issue, this paper proposes a prompt-supervised dynamic attention graph convolutional network (PDA-GCN). Specifically, the PDA-GCN incorporates a prompt supervision (PS) module that leverages a pre-trained large-scale language model (LLM) as a knowledge engine and retains the generated text features as prompts to provide additional supervision during model training, enhancing the model’s ability to discern analogous actions with negligible computational cost. In addition, for the purpose of bolstering the learning of discriminative features, a dynamic attention graph convolution (DA-GC) module is presented. This module utilizes self-attention mechanism to adaptively infer intrinsic relationships between joints and integrates dynamic convolution to strengthen the emphasis on local information. This dual focus on both global context and local details further amplifies the efficiency and effectiveness of the model. Extensive experiments, conducted on the widely-used skeleton-based action recognition datasets NTU RGB+D 60 and NTU RGB+D 120, demonstrate that the PDA-GCN surpasses known state-of-the-art methods, achieving accuracies of 93.4% on the NTU RGB+D 60 cross-subject split and 90.7% on the NTU RGB+D 120 cross-subject split.

GCP: A multi-strategy improved wireless sensor network model for environmental monitoring

Nowadays, smart environmental monitoring devices are widely used in various fields, and one of the most representative tools is the wireless sensor network (WSN). WSNs are easy to deploy and provide real-time information feedback, which is very suitable for environmental monitoring. As we all know, the environmental monitoring network because of the special nature of its work requirements, the need for uninterrupted and real-time transmission of monitoring data, which leads to energy consumption is extremely large, and this cannot meet the needs of its long-term work. Existing traditional routing has problems such as unscientific cluster head election and high redundancy in data transmission, which usually lead to a large amount of energy consumption, which is not conducive to the long-term stable operation of sensor networks. In this paper, we improve the traditional routing protocol and design a cluster head election method based on the genetic algorithm, which proposes a new fitness function in terms of energy, distance, and the number of nodes in the cluster, and performs the selection of cluster head nodes based on this method. In addition, we propose a new grey prediction model, which can realize the real-time update of data queues, and optimize the data transmission process of traditional WSNs based on this prediction model to reduce the amount of intra-cluster data transmission. Combining these improvements, a grey cluster prediction (GCP) model is proposed, and the performance of the model is tested based on real mine and soil data sets. The simulation results show that the model significantly reduces energy loss and extends the network life cycle while ensuring the integrity of data transmission. It can also meet the requirements of long-term stable operation of environmental monitoring equipment.

Patterns and drivers in the functional diversity decomposition of invaded stream fish communities

AbstractAimThe assembly of real‐world ecological communities in human‐modified landscapes is influenced by a complex interplay of spatial, temporal, environmental and invasion gradients. However, understanding the relative importance of these drivers and their interactions in shaping functional assembly remains elusive. Our study aimed to investigate the relative influence of these drivers on the functional assembly of a stream fish metacommunity.LocationStreams of the Lake Balaton catchment, Hungary.MethodsWe analysed a long‐term (18‐year) dataset of the stream fish metacommunity, focusing on changes in functional diversity (Q), redundancy (R) and species dominance (D). Ternary diagrams were utilized to decompose functional diversity into Q, R and D components and to visualize diversity patterns. Linear mixed‐effect regression and separate structural equation models were employed to identify significant drivers of Q, R and D.ResultsNative fish communities exhibited low functional diversity (Q) but high redundancy (R) and dominance (D), indicating functional convergence and dominance. Stream habitat size, network position and associated spatial, physical and chemical gradients emerged as consistently significant drivers of D and R. Changes in Q were additionally linked to non‐native community properties and subtle shifts in land use and within‐stream habitat characteristics.Main ConclusionsOur findings suggest that both environmental filtering and interspecies interactions, particularly trait similarity between invaders and natives shape functional assembly of stream fish metacommunities. Despite minimal temporal directional changes, environmental drivers predominantly influence long‐term diversity patterns of native fish communities, overshadowing invasion effects. Our findings underscore the importance of considering both environmental filtering mechanisms and interspecies interactions in understanding functional assembly. Additionally, the joint application of diversity decomposition frameworks with predictive modelling provides comprehensive insight into patterns of functional diversity and assembly across ecological communities.

Rapid identification of moxa wool storage period based on hyperspectral imaging technology and machine learning

Moxa wool (MW), derived from the dried leaves of Artemisiaargyi, plays a significant role in traditional Chinese medicine. However, the quality of MW varies with its storage period, impacting its therapeutic efficacy. Traditional methods for quality detection are limited and destructive. To address this, we propose a non-destructive detection method using hyperspectral imaging technology and machine learning algorithms to accurately identify the storage period of MW. Nevertheless, hyperspectral data poses challenges due to its high dimensionality and redundancy, leading to increased computational complexity. To overcome this, we employed principal component analysis (PCA), competitive adaptive reweighted sampling (CARS), and successive projection algorithm (SPA) for data dimensionality reduction and wavelength selection. The results demonstrate that these techniques significantly enhance the accuracy of MW storage year identification. For Nanyang MW, the CARS+SVM model achieved the highest accuracy rates of 99.8% in the visible-near-infrared (VNIR) range and 99.55% in the shortwave infrared (SWIR) range. Similarly, for Qichun MW, the SPA+SVM model achieved identification accuracies of 99.78% and 99.47% in the VNIR and SWIR ranges, respectively. This research provides valuable insights into the rapid detection of MW quality by indication of storage years and presents a novel approach for quality control of MW in the field of traditional Chinese medicine. The combination of hyperspectral imaging and machine learning offers a promising solution for efficient and accurate MW identification, contributing to the advancement of traditional medicine practices.

Ecological function maintained despite mesomammal declines

Mid-sized mammals (i.e., mesomammals) fulfill important ecological roles, serving as essential scavengers, predators, pollinators, and seed dispersers in the ecosystems they inhabit. Consequently, declines in mesomammal populations have the potential to alter ecological processes and fundamentally change ecosystems. However, ecosystems characterized by high functional redundancy, where multiple species can fulfil similar ecological roles, may be less impacted by the loss of mesomammals and other vertebrates. The Greater Everglades Ecosystem in southern Florida is a historically biodiverse region that has recently been impacted by multiple anthropogenic threats, most notably the introduction of the Burmese python (Python molurus bivittatus). Since pythons became established, mesomammal populations have become greatly reduced. To assess whether these declines in mesomammals have affected two critical ecosystem functions—scavenging and frugivory—we conducted experiments in areas where mesomammals were present and absent. We did not observe significant differences in scavenging or frugivory efficiency in areas with and without mesomammals, but we did observe significant differences in the communities responsible for scavenging and frugivory. Despite the observed evidence of redundancy, the changes in community composition could potentially lead to indirect consequences on processes like seed dispersal and disease dynamics within this ecosystem, emphasizing the need for further study.