Emotion recognition in conversation (ERC), the task of discerning human emotions for each utterance within a conversation, has garnered significant attention in human-computer interaction systems. Previous ERC studies...
详细信息
Predicting RNA binding protein(RBP) binding sites on circular RNAs(circ RNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but th...
详细信息
Predicting RNA binding protein(RBP) binding sites on circular RNAs(circ RNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but they cannot fully learn the features. Therefore, we propose circ-CNNED, a convolutional neural network(CNN)-based encoding and decoding framework. We first adopt two encoding methods to obtain two original matrices. We preprocess them using CNN before fusion. To capture the feature dependencies, we utilize temporal convolutional network(TCN) and CNN to construct encoding and decoding blocks, respectively. Then we introduce global expectation pooling to learn latent information and enhance the robustness of circ-CNNED. We perform circ-CNNED across 37 datasets to evaluate its effect. The comparison and ablation experiments demonstrate that our method is superior. In addition, motif enrichment analysis on four datasets helps us to explore the reason for performance improvement of circ-CNNED.
The popular constitutive models used in the field of hot forming of magnesium alloys can be divided into phenomenological models, machine learning models, and internal state variables (ISV) models based on physical me...
详细信息
Cloud detection (CD) in remote sensing images is commonly used in satellite imaging and laser communication. UNet-based methods with multi-level feature caching and interaction learning, are popular for superior CD pe...
详细信息
Most of current semantic communication (SemCom) frameworks focus on the image transmission, which, however, do not address the problem on how to deliver digital signals without any semantic features. This paper propos...
详细信息
Fifth-generation communication technology enables advanced indoor positioning with its high bandwidth and frequency capabilities. However, indoor environment variability causes signal propagation fluctuations, making ...
详细信息
Improving the yield strength（YS） and work hardening of FeNiCoCr-based high entropy alloys（HEAs） at high-strainrates（HSR） can meet the needs of applications such as automotive, bridge, and marine. In the present ...
详细信息
Improving the yield strength（YS） and work hardening of FeNiCoCr-based high entropy alloys（HEAs） at high-strainrates（HSR） can meet the needs of applications such as automotive, bridge, and marine. In the present work, a new Fe20Ni30Co20Cr20Al5V5nanoprecipitate-strengthened HEAs was developed, and the quasi-static compressive, dynamiccompressive properties, as well as its dynamic-deformation mechanism, were systematically investigated. The results show that nanoprecipitate-strengthened HEAs exhibit excellent dynamic mechanical properties. When the strain rate is 3750 s-1, the YS of the HEAs with nanoprecipitates is 1383 MPa, which is 3 times that of the counterpart without nanoprecipitates, possessing an excellent strain rate strengthening effect. The grain size of the HEAs with nanoprecipitates is twice of that without nanoprecipitates after HSR deformation. The presence of nanoprecipitates suppresses the intragranular slip of dislocations, preventing the accumulation of dislocations to form subgrain boundaries and hindering grain refinement. The interaction between nanoprecipitates and stacking faults inhibits the expansion and rearrangement of stacking faults and delays the appearance of deformation twins（DTs） until the strain rate of 3750 s-1, at which the twin width in HEA with nanoprecipitates is significantly narrower than that without nanoprecipitates. Narrower DTs can better hinder dislocation movement, reduce dislocation slip paths, enhance the dynamic Hall–Petch effect, and improve the work-hardening ability of HEAs at HSR.
Faced with an escalating number of fingerprint images, most existing retrieval approachs suffer from a common problem: diminishing computational efficiency. This paper presents a hierarchical retrieval system tailored...
详细信息
High-throughput computing(HTC) is a computing paradigm that aims to accomplish jobs by easily breaking them into smaller,independent ***,it requires a large amount of computing power for a long *** existing HTC framew...
详细信息
High-throughput computing(HTC) is a computing paradigm that aims to accomplish jobs by easily breaking them into smaller,independent ***,it requires a large amount of computing power for a long *** existing HTC frameworks are job-oriented without support for coscheduling with hardware architecture and task-level ***,most of the frameworks reach a limited scale,and their usability needs further ***,we present HTDcr,a job execution framework for the HTC on *** study aims to improve the throughput,task dispatching,and usability of the *** detail,the throughput optimizations include a sophisticated designed task management system,a hierarchical scheduler,and the co-optimization of the task-scheduling strategy with the application and hardware *** optimizations for usability include a programable execution workflow,mechanisms for more robust and reliable service qualities,and a fine-grained resource allocation system for the colocation of multiple *** to our evaluations,HTDcr can achieve outstanding scalability and high throughput on large-scale clusters for the HTC *** evaluate HTDcr with several microbenchmarks and real-world applications on Tianhe-2 and Sunway TaihuLight to demonstrate its effects on existing design *** instance,the task scheduling for two real-world applications integrated with the application and hardware characteristics achieves 1.7× and 1.9× speedups over the basic task-scheduling strategy.
The influence of the blending ratio of pyrolyzed semi-char(SC)on the ignition,NO emission and burnout characteristics of lignite co-fired with SC was investigated in a 350 kW fuel-rich/lean combustion *** flame temper...
详细信息
The influence of the blending ratio of pyrolyzed semi-char(SC)on the ignition,NO emission and burnout characteristics of lignite co-fired with SC was investigated in a 350 kW fuel-rich/lean combustion *** flame temperature and concentrations of gaseous species including O_(2),CO,and NO,were measured in *** results indicated that the ignition characteristics of the blended fuel worsened with increasing SC blending ratio,such as an elongated ignition standoff *** addition of SC to lignite delayed the appearance of a stable flame boundary,and the stable combustion zone moved down,but the final combustion stability was gradually strengthened in the later combustion *** emission concentration at the primary combustion zone(PCZ)outlet was the lowest at 472.6 mg/m^(3)@6%O_(2)when the SC blending ratio was 25%.The combustion zone and reducing zone areas in PCZ were defined to evaluate the NO reduction characteristics,and quantitative analysis using a multiple linear regression model showed that heterogeneous reduction was more important than homogeneous reduction in lowering NO *** Raman spectrum of the char sample indicated that the addition of lignite promoted the formation of small aromatic rings in the early ignition stage,corresponding to a higher char *** burnout ratio of pure lignite was maximal and was decreased by increasing the SC blending ***,considering the ignition standoff distance,NO emission,and burnout ratio,the optimum SC blending ratio was estimated to be 25%.
暂无评论