Improving the accuracy of semantic segmentation for remote sensing images (RSIs) is crucial for the geoscientific research and applications. However, existing models tend to focus too much on the subject information f...
详细信息
The machine learning and data science community has made significant while dispersive progress in accelerating transformer-based large language models (LLMs), and one promising approach is to replace the original caus...
详细信息
Data overlap is a significant challenge in the task of entity-relation triple extraction. This task includes two research lines, line one first identifies entities and then predicts relations while line two completely...
详细信息
Data overlap is a significant challenge in the task of entity-relation triple extraction. This task includes two research lines, line one first identifies entities and then predicts relations while line two completely shuffles the order. The methods in line two are more conducive to the optimization of the data overlap problem. Recent works have made breakthroughs in dealing with overlapping data, but there are still some defects such as difficulty in convergence and poor performance on datasets with numerous relations. To solve the above problems, we adopt a two-step strategy of first extracting subjects, and then predicting relation- object pairs. Considering the absence of connectivity between the two steps in the conventional method, we adopt the relation sequence as input in both steps and propose the TERS model. The relation sequence can connect two steps and improve the single-step and comprehensive extraction capability of the model. The TERS model consists of two modules. The first module performs information interaction and filters invalid subjects through the Text Relation Attention method. The second module implements multiple iterations of information interaction through the Information Flow method. The combination of these two modules contributes to the strong entity-relation triple extraction capability of our model. We evaluate our method on three public datasets. Extensive experiments show that our TERS model outperforms previous state-of-the-art models in triple extraction and overlapping data processing. Compared with other two-step extraction models, the advantages of our model are more obvious.
API migration is an essential step for code migration between libraries or programming languages, and it is a challenging task as it requires detailed comprehension of both source and target APIs. The existing work ei...
详细信息
In this paper, we study secure computing migration scenarios in uncertain environments with the presence of multiple malicious eavesdroppers (MEs). Specifically, when edge servers (ESs) execute tasks delivered by smar...
详细信息
In this paper, we study secure computing migration scenarios in uncertain environments with the presence of multiple malicious eavesdroppers (MEs). Specifically, when edge servers (ESs) execute tasks delivered by smart devices (SDs), SDs may move beyond the coverage of ESs, and computing migration (CM) of unfinished tasks is required to ensure service continuity. There is a risk of privacy leakage during task migration, and MEs use colluding eavesdropping to eavesdrop on the migrated tasks, and we consider eavesdropping on the associated tasks through data sharing among MEs to improve the eavesdropping efficiency. For eavesdropping in MEs, we achieve eavesdropping strikes using cooperative interference by jammers, which benefit by providing jamming services. In addition, uncertain computational scenarios directly affect the efficiency of task execution, and we consider the uncertainty factor in the malicious eavesdropping environment. To this end, this paper proposes the secure computational migration of associative privacy in uncertain environments (SCMAPUE) model, which transforms uncertainties into interval parameters, and optimizes the five objectives of migration delay, maximum completion time, energy consumption, load balancing and migration reliability to achieve efficient task execution and reliable migration. Aiming at the model characteristics, this paper designs an interval many-objective evolutionary algorithm for reliable migration (IMaOEA-RM), which employs a condition-based interval confidence strategy and a multi-access secure migration selection strategy to improve the convergence of the algorithm, and utilizes a dual-migration crossover strategy in order to adjust the jammer partners and improve the population diversity. Simulation results show that our proposed IMaOEA-RM algorithm can provide a more reliable and efficient migration scheme than existing algorithms.
With the proliferation of voice assistants, microphone-based speech recognition technology usually cannot achieve good performance in the situation of multiple sound sources and ambient noises. In this paper, we propo...
详细信息
Flexible sensors have vast potential applications in human interaction and medical detection. However, achieving sensors with excellent performance, such as sensitivity and sensing range, poses a current challenge due...
详细信息
Flexible sensors have vast potential applications in human interaction and medical detection. However, achieving sensors with excellent performance, such as sensitivity and sensing range, poses a current challenge due to the limitations imposed by sensing principles and material characteristics. This paper proposes a novel method involving a wide-range composite foam sensor comprising foam and structure elastomer. By manipulating the structural parameters of the elastomer, the mechanical properties and inductance characteristics of the composite foam sensor can be tailored. The experimental result indicates the composite foam can achieve a sensitivity of 0.175 kPa-1 within 0-2.8 kPa range and 0.001 kPa-1 within 49.8-164 kPa range. Moreover, the sensor exhibits fast response time of 33 ms and stable cyclic stability (99.62% during 400 cycles). The sensor exhibits outstanding versatility in detecting 9 different types of human movements, including both compression and rotation across various body parts, owing to its remarkable sensing range and sensitivity. This approach provides a fresh design perspective on high-range, composite foam-based flexible sensors.
The grouping protocol in RFID systems is to label tags according to a given partition so that tags in the identical group hold the same group ID, which makes multi-cast transmissions or aggregate queries possible and ...
详细信息
This work focuses on the tasks offloading and resource allocation based on cloud-edge computing. We consider a two-tier multi-user mobile-edge computing (MEC) network, where wireless devices can offload the task data ...
详细信息
Weak-signal detection underlies a variety of ubiquitous computing applications, such as wireless sensing and machinery fault diagnosis. Stochastic resonance (SR) provides a new way for weak-signal detection by boostin...
详细信息
暂无评论