While U-Net and its variants perform well in medical image segmentation, their encoders have limitations that hinder the capture of global context. Moreover, traditional skip connections do not fully utilize essential features. To address these issues, we propose a novel segmentation architecture called RLK-Net, which integrates Residual Large Kernel Convolution (RLK) block and Channel-wise Adaptive Feature Fusion (CAFF) module. RLK-Net effectively enhances feature extraction and context capture through RLK block, while the CAFF module adaptively adjusts channel importance, optimizing feature fusion and the performance of skip connections. Compared to Transformer-based models, RLK-Net achieves high segmentation performance while significantly reducing computational resource requirements. Experimental evaluations on three ultrasound medical image datasets and one dermoscopy dataset demonstrate that RLK-Net outperforms several leading medical image segmentation models.

Trace data is crucial for system observability and maintainability within microservices architectures, and many operation algorithms depend heavily on trace data, including anomaly detection, root cause analysis, etc. However, the actual performance of these algorithms might be unsatisfactory due to the absence of high-quality labeled datasets for effective training and evaluation. Since billions of traces could be generated daily for large-scale microservices, labeling overhead is the main hurdle to obtaining high-quality trace datasets.In this paper, we propose LabelEase, a novel semi-automatic trace labeling tool, which uses active learning techniques to achieve efficient and accurate trace labeling. For anomaly trace labeling, LabelEase clusters similar traces with a graph-based trace representation technique and selects a few representative traces for human labeling, avoiding labeling most of the traces. For root cause labeling, LabelEase aggregates the labeled anomalous traces and identifies the service’s failures for operators to label. Our systematic experiments on two large-scale datasets show that LabelEase achieves over 0.98 F1-score in anomaly trace labeling and 0.89 precision of failure detection in root cause labeling, LabelEase can reduce operators’ labeling overhead by more than 99.9%. To the best of our knowledge, we are the first to propose a semi-automatic trace labeling tool capable of achieving efficient and accurate trace labeling.

With the increasing demands on industrial products, the design and manufacturing problems of industrial products are becoming more and more complex. Many industrial design problems belong to nonlinear optimization problems and NP-hard problems, such as shop scheduling, path planning, and industrial part design problems. In the last decade, more and more researchers have developed heuristic- based algorithms to deal with industrial design problems. Tunicate swarm algorithm (TSA) is a newly proposed high performance heuristic optimization algorithm. The TSA algorithm has the problems of low solution accuracy, slow convergence and easy attraction by local extrema. In order to solve some drawbacks of TSA, this paper improves TSA and proposes the Sine cosine -Levy-Opposition-based Tunicate swarm algorithm (SLOTSA) by combining opposition-based learning, Levy flight and positive cosine operator. Comparative experiments on SLOTSA in 10 benchmark functions fully demonstrate the rationality of the three improvement strategies. In addition, this paper applies SLOTSA to two practical industrial design problems, and the optimization results demonstrate the wide applicability of SLOTSA to industrial design problems.

Microservice invocation anomalies can have a detrimental impact on user experience and service revenue. While existing trace anomaly detection approaches typically focus on anomalies in response time and invocation structure, they often overlook the importance of using fine-grained features to detect anomalies. Additionally, trace data obtained from real-world scenarios is typically accompanied by noise, which can hinder the effectiveness of anomaly detection approaches. Furthermore, large-scale trace data can significantly impact model training efficiency. To address these challenges, we propose TraceSieve, an unsupervised trace anomaly detection method that accurately detects trace anomalies. Our approach leverages an auto-encoder architecture within an adversarial training framework to filter out noise data. Additionally, we integrate VGAE-EWC, which combines Variational Graph Auto-Encoder (VGAE) with Elastic Weight Consolidation (EWC), to overcome the challenges of enormous time consumption during the training phase. Finally, we localize the root cause of trace anomalies. Our proposed method is evaluated using two different datasets, and our results demonstrate that TraceSieve achieves an F1-score of 0.970 and 0.925, respectively, outperforming state-of-the-art trace anomaly detection approaches.