Person re-identification (Re-ID) systems in edgecloud continuum face critical trade-offs between latency sensitivity and energy efficiency due to the resource-constrained edge environment. This paper proposes Re-IDFaaS, a serverless ReID system that dynamically optimizes energy consumption and computational performance across the edge-cloud continuum. Leveraging serverless architectures, our system implements three key improvements: (1) An event-driven workflow triggered by motion detection, eliminating idle GPU resource consumption during inactive periods. (2) A hardware-aware dynamic scheduler that allocates tasks based on real-time energy states and container availability, achieving balanced resource utilization across heterogeneous nodes. (3) An adaptive batching mechanism that reduces cold-start frequency through latency-constrained request grouping while maintaining the efficiency of GPU memory. Experiments demonstrate a 23.3% improvement in edge node availability and 55% reduction in memory usage compared to existing methods. The system design provides practical insights for building AI services in hybrid computing environments requiring cross-framework compatibility and adaptive resource orchestration, achieving 53% higher throughput than traditional architectures. These innovations address the challenges of dynamic workload scheduling and runtime optimization in hardware-diverse scenarios, ensuring sustainable operation under bursty surveillance workloads.

The significant increase in data generation across various sectors has prompted the development of concepts such as Data Product and Data Economy (DE) to enhance organizational productivity. Concurrently, advancements in AI models have heightened data privacy concerns, particularly as typical AI model training methods often involve data collection and storage in centralized databases, which are exposed to misuse. In response, Federated Learning (FL) has emerged as a promising approach, enabling the collaborative training of AI models without the direct sharing of data. This paper examines the potential of FL in the initial stages of data generation and throughout the data product design process. It further explores how FL can facilitate the generation of data products, providing a range of practical applications across different industries to address privacy concerns effectively in modern AI solutions.

Stream join is a fundamental operation in stream processing and has attracted extensive research due to its large resource consumption and serious impact on system performance. As the theoretical basis of stream join systems, the stream join model greatly affects system performance. State-of-the-art stream join models either consume too much computing resources or too much storage resources, thus resulting in lower throughput or higher latency. In this paper, we propose a new stream join model for processing arbitrary join predicates, called CoModel, which offers a flexible trade-off between memory and computing resource consumption. More importantly, CoModel can achieve the minimum sum of the number of store operations and join operations among all existing join models, and thus can achieve the lowest latency and highest throughput when the overheads associated with the local stream join for each input tuple are approximately constant. We give a trade-off strategy for CoModel and theoretically prove its performance advantages based on queuing theory. Furthermore, we design and implement an adaptive distributed stream join system, CoStream, based on CoModel. CoStream can adaptively adjust its structure according to resource constraints and statistics of input data. We conduct extensive experiments for CoStream to evaluate its performance and adaptivity, and the results show that CoStream has the lowest latency and highest throughput in various scenarios.

Automated program repair (APR) is a key technique for enhancing software maintenance productivity by fixing buggy code automatically. Recently, large code language models (CLMs) have exhibited impressive capabilities in code generation. However, for complex programming tasks, especially program repair, the success rate of CLMs is still low. One of the reasons is that CLMs are typically developed for general purpose and their potential for APR applications has yet to be fully explored. In this paper, we propose APRFiT, a general curricular fine-tuning framework that improves the success rate of CLMs for APR. Firstly, APRFiT generates syntactically diverse but semantically equivalent bug-fixing programs via code augmentation operators to enrich the diversity of bug-fixing dataset automatically. Secondly, APRFiT designs a curriculum learning-based mechanism to help CLMs develop deep understanding of program semantics from these augmented bug-fixing code variants and improve the effectiveness of fine-tuning for APR tasks. We implement APRFiT on different CLMs and evaluate them on Bugs2Fix small and medium datasets. The extensive experiments demonstrate that, the existing CLMs implemented with APRFiT substantially outperform original models and generate 2.5 to 14.5 percent more correct patches than baselines both effectively and efficiently.

We devise in this paper a Multilevel Adaptive Reduction Technique (MART) for time series data. MART extracts the main features of a time series and encodes them in a reduced data structure called reduct. The extracted features are leveraged to establish a distance between reducts that satisfies the lower bounding constraint. Furthermore, we show how MART can be further applied on the reduced data and operate at different levels. We conduct experiments on time series datasets that show MART based classification accuracy and multilevel reduction power. We present also a comparative study with well-known SAX based time series reduction techniques and deep learning time series classification techniques.

Recent developments of Internet technologies have accelerated the growth of Web services (e.g., open APIs). As many services provide similar functionality, service recommendation systems use the Quality of Service (QoS) to help users find optimal services. Space partition attracts significant attention in service recommendation since it improves the diversity of recommendations and accelerates skyline services query. However, existing partition-based service recommendation systems are all implemented on complete QoS. They are not sufficient when some services’ QoS values are missing or invalid. To this end, we develop a new partition-based service recommendation method on incomplete QoS (named IQSrec) that combines probabilistic skyline query and space partition. The probabilistic skyline query measures top-$k$skyline services on incomplete QoS. A dimension-based partition is specially designed for splitting the incomplete QoS service space into$d$-dimensional partitions with the most representative services. The candidate skyline services are chosen from each partition and merged together for probabilistic skyline computation. IQSrec selects the highest skyline probability services in each partition as recommendations. The experiments on the synthetic and real-world datasets show IQSrec can efficiently recommend skyline services on incomplete QoS. IQSrec has higher accuracy and diversity compared to the state-of-the-art service recommendation approaches.

For a stream processing system that uses checkpoints as a fault-tolerant method, selecting the appropriate checkpoint period is the key to ensuring the efficient operation of streaming applications. State-of-art stream processing systems currently only support fixed-cycle checkpoints, which is difficult to make a good trade-off between fault-tolerant processing and the cost of failure recovery in dynamically changing streaming application scenarios. Moreover, in a complex distributed streaming application environment, the dynamic environmental indicators (e.g., the values of workloads and failure rates) are not in coincidence with the model assumptions, such as the dynamics of Twitter’s hot events data changing quickly. In this paper, we consider the dynamic changes of environmental indicators and adaptively optimize the processing delay and fault recovery time. Then, we propose a dynamic adjustment method for the checkpoint interval by reinforcement learning, which is named DACM. DACM adaptively optimizes the processing delay and fault recovery time, while avoiding the overall environment modeling of streaming applications. The experiments conducted on the Flink platform show that DACM reduces the processing delay by 10% and the failure recovery time by 37% compared with the existing checkpoint interval optimization models.

To improve the efficiency of QoS-centric service selection, skyline query is often used to get small candidates from a large number of services. Recently, interval-valued skyline service selection attracts a lot of attention due to the QoS value fluctuation during execution. To simplify skyline computation, existing interval-valued skyline service selection methods assume the probability density function (PDF) of QoS intervals follows general mathematical distribution, such as the Uniform distribution or the Gaussian distribution, which leads to the inaccurate dominant relationship between QoS intervals. In addition to the impractical assumption of intervals, another problem of existing interval-valued skyline service selection methods is that they are all implemented for complete QoS and are not sufficient when some services’ QoS values are missing or invalid. To this end, we develop a new skyline service selection method on incomplete QoS, named ISkySel, which combines probabilistic skyline query and missing QoS prediction. ISkySel uses valid QoS values to build the PDF of QoS intervals and employs the early termination and sorting techniques to accelerate the probabilistic skyline computation. The experiments on the synthetic and real-world datasets show ISkySel has higher accuracy and efficiency compared to the state-of-the-art skyline service selection.

This note investigates sampled-data control for chaotic systems. A memory sampled-data control scheme that involves a constant signal transmission delay is employed for the first time to tackle the stabilization problem for Takagi-Sugeno fuzzy systems. The advantage of the constructed Lyapunov functional lies in the fact that it is neither necessarily positive on sampling intervals nor necessarily continuous at sampling instants. By introducing a modified Lyapunov functional that involves the state of a constant signal transmission delay, a delay-dependent stability criterion is derived so that the closed-loop system is asymptotically stable. The desired sampled-data controller can be achieved by solving a set of linear matrix inequalities. Compared with the existing results, a larger sampling period is obtained by this new approach. A simulation example is presented to illustrate the effectiveness and conservatism reduction of the proposed scheme.

The fault correction process is very important in software testing, and it has been considered into some software reliability growth models (SRGMs). In these models, the time-delay functions are often used to describe the dependency of the fault detection and correction processes. In this paper, a more direct variable "correction lag", which is defined as the difference between the detected and corrected fault numbers, is addressed to characterize the dependency of the two processes. We investigate the correction lag and find that it appears Bell-shaped. Therefore, we adopt the Gamma function to describe the correction lag. Based on this function, a new SRGM which includes the fault correction process is proposed. And the experimental results show that the new model gives better fit and prediction than other models.