In the field of computer vision, image feature extraction is the bridge connecting low-level image data with high-level visual tasks such as image matching and object recognition. The SIFT algorithm occupies an import...
详细信息
Community coding algorithms had been demonstrated to have capability to improve the performance of wireless networks. This paper offers a research, assessment, and implementation of community coding algorithms for Wi-...
详细信息
Visual object tracking is a traditional task in computer vision, which has developed with several decades. With the development of machine learning, correlation filter (CF) has been proposed with satisfying performanc...
详细信息
Over the past few years, Graph Convolutional Networks (GCN) have emerged as a promising tool in the field of recommendation. They have the ability to effectively learn user and item embeddings by leveraging collaborat...
详细信息
Ensuring the reliability and user satisfaction of cloud services necessitates prompt anomaly detection followed by diagnosis. Existing techniques for anomaly detection focus solely on real-time detection, meaning that...
详细信息
ISBN:
(纸本)9798350329964
Ensuring the reliability and user satisfaction of cloud services necessitates prompt anomaly detection followed by diagnosis. Existing techniques for anomaly detection focus solely on real-time detection, meaning that anomaly alerts are issued as soon as anomalies occur. However, anomalies can propagate and escalate into failures, making faster-than-real-time anomaly detection highly desirable for expediting downstream analysis and intervention. This paper proposes Maat, the first work to address anomaly anticipation of performance metrics in cloud services. Maat adopts a novel two-stage paradigm for anomaly anticipation, consisting of metric forecasting and anomaly detection on forecasts. The metric forecasting stage employs a conditional denoising diffusion model to enable multi-step forecasting in an auto-regressive manner. The detection stage extracts anomaly-indicating features based on domain knowledge and applies isolation forest with incremental learning to detect upcoming anomalies. Thus, our method can uncover anomalies that better conform to human expertise. Evaluation on three publicly available datasets demonstrates that Maat can anticipate anomalies faster than real-time comparatively or more effectively compared with state-of-the-art real-time anomaly detectors. We also present cases highlighting Maat's success in forecasting abnormal metrics and discovering anomalies.
Linearizability is an important correctness criterion for concurrent objects, and there have been several existing tools for checking linearizability. However, due to the inherent exponential complexity of the problem...
详细信息
ISBN:
(数字)9783031352577
ISBN:
(纸本)9783031352560;9783031352577
Linearizability is an important correctness criterion for concurrent objects, and there have been several existing tools for checking linearizability. However, due to the inherent exponential complexity of the problem, existing tools have difficulty scaling up to large, industrial-sized concurrent objects. In this paper, we introduce VeriLin, a new linearizability checker that incorporates a more general checking algorithm as well as associated testing strategies, that allow it to continue to be effective for large-scale concurrent objects and long histories. For evaluation, we apply VeriLin to checking linearizability of student implementations of a train ticketing system, as well as the task management and scheduling module of a proprietary multicore operating system.
Addressing the challenges posed by the insufficient computational power of low-spec devices to achieve the inference efficiency of prevailing deep learning models, alongside the variability in type and shape within in...
详细信息
Recognition of Bengali sign language characters is crucial for facilitating communication for the deaf and hard-of-hearing population in Bengali-speaking regions, which encompass approximately 430 million people world...
详细信息
Emergency response systems, water treatment facilities, wastewater collection systems, Oil and gas pipelines, electrical power transmission systems, wind farms, defence networks, and large-scale communication networks...
详细信息
Traditional Non-homogeneous Poisson process (NHPP) software reliability growth models (SRGM) enable quantitative assessment of software systems based on failure data collected during testing. However,traditional model...
详细信息
暂无评论