This paper presents a framework for adaptive multimodal feature fusion that employs attention-based feature selection mechanisms to enhance the classification of histopathology images. The framework integrates medical images and clinical texts through three core modules: the Unified Feature Processing Module (UFPM) for standardized feature preprocessing, the Cross-Modal Attention Module (CMAM) for facilitating interactions between image and text features, and the Selective Feature Alignment Module (SFAM) for aligning features across different modalities. Experimental results on the Quilt-BCGG and Quilt-Derm4 datasets demonstrate the framework's good classification performance, which improves the accuracy and efficiency of histopathology diagnosis through optimized feature selection and alignment. The link to the code: https://github.com/leibabaya/Attention-guided-Adaptive-Fusion

Overlay networks serve as the de facto network virtualization technique for providing connectivity among distributed containers. Despite the flexibility in building customized private container networks, overlay networks incur significant performance loss compared to physical networks (i.e., the native). The culprit lies in the inclusion of multiple network processing stages in overlay networks, which prolongs the network processing path and overloads CPU cores. In this paper, we propose mFlow, a novel packet steering approach to parallelize the in-kernel data path of network flows. mFlow exploits packet-level parallelism in the kernel network stack by splitting the packets of the same flow into multiple micro-flows, which can be processed in parallel on multiple cores. mFlow devises new, generic mechanisms for flow splitting while preserving in-order packet delivery with little overhead. Our evaluation with both micro-benchmarks and real-world applications demonstrates the effectiveness of mFlow, with significantly improved performance – e.g., by 81% in TCP throughput and 139% in UDP compared to vanilla overlay networks. mFlow even achieved higher TCP throughput than the native (e.g., 29.8 vs. 26.6 Gbps).

Advanced high-speed network cards have made packet processing in host operating systems a major performance bottleneck. The kernel network stack gives rise to various sources of overheads that limit the throughput and lengthen the per-packet processing latency. The problem is further exacerbated for short-lived, latency-sensitive network flows such as control packets, online gaming, database requests, etc. — in a highly utilized system, especially in virtualized (containerized) cloud environments, short flows can experience excessively long in-kernel queuing delays. As a consequence, recent research works propose to bypass the kernel network stack to enable lightweight, custom userspace network stacks for improved performance, but at a heavy cost of compatibility and security. In this paper, we take a different approach: We first analyze various sources of inefficiencies in the kernel network stack and propose ways to mitigate them without compromising systems compatibility, security, or flexibility. Further, we propose Prism, a novel mechanism in the kernel network stack to differentiate incoming packets based on their performance requirements and streamline the processing stages of multi-stage packet processing pipelines (e.g., in container overlay networks). Our evaluation demonstrates that Prism can significantly improve the latency of high-priority flows in container overly networks in the presence of heavy low-priority background traffic.

This paper proposed a multiple-mode animal behavior analysis system integrating a wireless bio-potential recorder and two 120fps video streams. A 16-channel analog-front-end (AFE) featuring a chopper low noise amplifier (LNA) and a 12-bit successive approximation analog-to-digital converter (SAR ADC) is designed as the sensor interface. Bluetooth Low Energy (BLE) based in-the-air protocol is implemented for wireless data transmission. A precise synchronization method is proposed featuring a millisecond level synchronization accuracy between the video frames and the acquired bio-potential. The compact wireless bio-potential recorder features a size of 2 × 2.5 × 1cm and a battery life of 9 hours. In-vivo test has been performed on rats with long-term implantable electrodes. The proposed system successfully recorded the electroneurogram (ENG) signal from sciatic nerves and electromyography (EMG) signal from leg muscles. Also video-based gait analysis was performed and provided the labels to train an EMG-based gait phase classifier.

This paper proposes SaleNet - an end-to-end convolutional neural network (CNN) for sustained attention level evaluation using prefrontal electroencephalogram (EEG). A bias-driven pruning method is proposed together with group convolution, global average pooling (GAP), near-zero pruning, weight clustering and quantization for the model compression, achieving a total compression ratio of 183. 11x. The compressed SaleNet obtains a state-of-the-art subject-independent sustained attention level classification accuracy of 84.2% on the recorded 6-subject EEG database in this work. The SaleNet is implemented on a Artix-7 FPGA with a competitive power consumption of 0.11 W and an energy-efficiency of 8.19 GOps/w.

Container networking, which provides connectivity among containers on multiple hosts, is crucial to building and scaling container-based microservices. While overlay networks are widely adopted in production systems, they cause significant performance degradation in both throughput and latency compared to physical networks. This paper seeks to understand the bottlenecks of in-kernel networking when running container overlay networks. Through profiling and code analysis, we find that a prolonged data path, due to packet transformation in overlay networks, is the culprit of performance loss. Furthermore, existing scaling techniques in the Linux network stack are ineffective for parallelizing the prolonged data path of a single network flow.

Container storage commonly relies on overlay file systems to interpose read-only container images upon backing file systems. While being transparent to and compatible with most existing backing file systems, the overlay file-system approach imposes nontrivial I/O overhead to containerized applications, especially for writes: To write a file originating from a read-only container image, the whole file will be copied to a separate, writable storage layer, resulting in long write latency and inefficient use of container storage. In this paper, we present BAOverlay, a lightweight, block-accessible overlay file system: Equipped with a new block-accessibility attribute, BAOverlay not only exploits the benefit of using an asynchronous copy-on-write mechanism for fast file updates but also enables a new file format for efficient use of container storage space. We have developed a prototype of BAOverlay upon Linux Ext4. Our evaluation with both micro-benchmarks and real-world applications demonstrates the effectiveness of BAOverlay with improved write performance and on-demand container storage usage.