Anaerobic fermentation is the most important link to gas production, this paper solves the current problem with the help of the current complete machine learning technology, combining perception and intelligent proces...
详细信息
ISBN:
(数字)9798350376258
ISBN:
(纸本)9798350376265
Anaerobic fermentation is the most important link to gas production, this paper solves the current problem with the help of the current complete machine learning technology, combining perception and intelligent processing, intelligent processing of information, and derive a decision-making basis for its control or management [1]. Aiming at the current problems of the anaerobic fermentation process in biogas engineering, the system design was carried out, and the anaerobic fermentation process of biogas and its main influencing factors were investigated, and the monitoring parameters of the system were selected to be temperature, PH value, liquid level and redox potential [2]. Previous studies are mainly based on a single prediction model, which leads to poor generalization ability of the model. In this study, unbalanced samples are handled by Borderline-SMOTE algorithm. Based on the Stacking integrated learning approach, a common single prediction model is used to construct a combined prediction model. The accuracy, precision, recall, F1 score and area under the ROC curve are used to evaluate the advantages and disadvantages of the combined prediction model over the single prediction model.
Audio-visual target speaker extraction (AV-TSE) aims to extract the specific person’s speech from the audio mixture given auxiliary visual cues. Previous methods usually search for the target voice through speech-lip...
详细信息
Graph random walk is widely used in the graph processing as it is a fundamental component in graph analysis, ranging from vertices ranking to the graph embedding. Different from traditional graph processing workload, ...
详细信息
Graph random walk is widely used in the graph processing as it is a fundamental component in graph analysis, ranging from vertices ranking to the graph embedding. Different from traditional graph processing workload, random walk features massive processing parallelisms and poor graph data reuse, being limited by low I/O efficiency. Prior designs for random walk mitigate slow I/O operations. However, the state-of-the-art random walk processing systems are bounded by slow disk I/O bandwidth, which is confirmed by our experiments with real-world graphs. To address this issue, we propose FlashWalker, an in-storage accelerator for random walk that moves walk updating close to graph data stored in flash memory, by exploiting significant parallelisms inside SSD. Featuring a heterogeneous and parallel processing system, FlashWalker includes a board-level accelerator, channel-level accelerators, and chip-level accelerators. To address challenges posed by the tight resource constraints for processing large-scale graphs, we propose novel designs: storing a few popular subgraphs in accelerators, the pre-walking for dense walks, two optimizations to search the subgraph mapping table, and a subgraph scheduling algorithm. We implement FlashWalker in RTL, showing small circuit area overhead. Our evaluation shows FlashWalker reduces the execution time of random walk algorithms by up to 660.50×, compared with GraphWalker, which is the state-of-the-art system for random walk algorithms.
作者：
Xiong, QiTang, KaiMa, MinboZhang, JiXu, JieLi, TianruiSchool of Computing and Artificial Intelligence
Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education National Engineering Laboratory of Integrated Transportation Big Data Application Technology Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China School of Computing
The University of Leeds LeedsLS2 9JT United Kingdom
Long-term time series forecasting (LTSF) is a critical task across diverse domains. Despite significant advancements in LTSF research, we identify a performance bottleneck in existing LTSF methods caused by the inadeq...
详细信息
In practical clinical applications, vascular intervention surgical robots have developed sophisticated human-machine interaction systems, enabling assistance to physicians in performing remote surgeries and providing ...
详细信息
ISBN:
(数字)9798350388077
ISBN:
(纸本)9798350388084
In practical clinical applications, vascular intervention surgical robots have developed sophisticated human-machine interaction systems, enabling assistance to physicians in performing remote surgeries and providing intelligent visual feedback. However, regarding surgical safety, current research predominantly focuses on force feedback and robot control logic, with clamping mechanisms targeting the locking of catheters and guide wires. Excessive clamping force may lead to surface damage to intervention instruments, while insufficient force delivery may result from slippery surfaces. Therefore, addressing these issues, this study proposed a passive, compliant safety strategy for an adaptive clamping device based on a vascular intervention surgical robot platform. This device can accommodate different diameter catheters and maintain a constant delivery force during the intervention process. Finally, through experimentation, the effectiveness, safety, and stability of the device were demonstrated.
Federated Learning enables collaboratively model training among a number of distributed devices with the coordination of a centralized server, where each device alternatively performs local gradient computation and co...
Federated Learning enables collaboratively model training among a number of distributed devices with the coordination of a centralized server, where each device alternatively performs local gradient computation and communication to the server. FL suffers from significant performance degradation due to the excessive communication delay between the server and devices, especially when the network bandwidth of these devices is limited, which is common in edge environments. Existing methods overlap the gradient computation and communication to hide the communication latency to accelerate the FL training. However, the overlapping can also lead to an inevitable gap between the local model in each device and the global model in the server that seriously restricts the convergence rate of learning process. To address this problem, we propose a new overlapping method for FL, AOCC-FL, which aligns the local model with the global model via calibrated compensation such that the communication delay can be hidden without deteriorating the convergence performance. Theoretically, we prove that AOCC-FL admits the same convergence rate as the non-overlapping method. On both simulated and testbed experiments, we show that AOCC-FL achieves a comparable convergence rate relative to the non-overlapping method while outperforming the state-of-the-art overlapping methods.
Since deep learning (DL) can automatically learn features from source code, it has been widely used to detect source code vulnerability. To achieve scalable vulnerability scanning, some prior studies intend to process...
详细信息
ISBN:
(纸本)9781665495899
Since deep learning (DL) can automatically learn features from source code, it has been widely used to detect source code vulnerability. To achieve scalable vulnerability scanning, some prior studies intend to process the source code directly by treating them as text. To achieve accurate vulnerability detection, other approaches consider distilling the program semantics into graph representations and using them to detect vulnerability. In practice, text-based techniques are scalable but not accurate due to the lack of program semantics. Graph-based methods are accurate but not scalable since graph analysis is typically time-consuming. In this paper, we aim to achieve both scalability and accuracy on scanning large-scale source code vulnerabilities. Inspired by existing DL-based image classification which has the ability to analyze millions of images accurately, we prefer to use these techniques to accomplish our purpose. Specifically, we propose a novel idea that can efficiently convert the source code of a function into an image while preserving the program details. We implement Vul-CNN and evaluate it on a dataset of 13,687 vulnerable functions and 26,970 non-vulnerable functions. Experimental results report that VulCNN can achieve better accuracy than eight state-of-the-art vul-nerability detectors (i.e., Checkmarx, FlawFinder, RATS, TokenCNN, VulDeePecker, SySeVR, VulDeeLocator, and Devign). As for scalability, VulCNN is about four times faster than VulDeePecker and SySeVR, about 15 times faster than VulDeeLocator, and about six times faster than Devign. Furthermore, we conduct a case study on more than 25 million lines of code and the result indicates that VulCNN can detect large-scale vulnerability. Through the scanning reports, we finally discover 73 vulnerabilities that are not reported in NVD.
We propose Mocha, a non-hierarchical caching architecture that organizes DRAM and NVM in a flat address space physically, but manages DRAM/NVM in a cache/memory hierarchy in this paper. Since the commercial NVM device...
详细信息
Though the collection of metro smart card data could help improve the operations of the metro system, the release of such data might lead to privacy issues. Few studies have quantified the probability to re-identify a...
详细信息
Multi-instance learning (MIL) is a celebrated learning framework where each example is represented as a bag of instances. An example is negative if it has no positive instances, and vice versa if at least one positive...
详细信息
暂无评论