AI in Industrial Internet of Things

With the continuous development of microfluidic technology, continuous-flow microfluidic biochips (CFMBs) are being increasingly used in the Internet of Things. The automation design of CFMBs has also received widespread attention. The architecture design of CFMBs is divided into a high-level synthesis stage and a physical design stage. Among them, the problem of the physical design stage is very complex. At this stage, the chip architecture is generated based on the device library and a set of flow paths, taking into account the actual fluid manipulations, while minimizing the cost of the chip, such as the number of ports, total length of flow channels, number of flow channel intersections. As fabrication technology advances, the number of devices integrated into CFMBs is increasing. The existing physical design algorithms can no longer meet the design requirements of CFMBs in terms of time. Therefore, we propose a three-stage rapid physical design algorithm for CFMBs considering the actual fluid manipulations. The proposed algorithm includes a port-driven preprocessing stage, a force-directed quadratic placement stage, and a negotiation-based routing stage. In the port-driven preprocessing stage, a port-driven preprocessing algorithm is proposed to generate connection matrices between ports and devices to reduce the number of ports introduced. In the force-directed quadratic placement stage, we model the placement problem as an extremum problem of a quadratic cost function, which mathematically reduces the search space significantly and shortens the running time of the algorithm significantly. In the negotiation-based routing stage, a heuristic negotiation-based routing algorithm and a flow channel strategy that prioritizes the construction of parallel execution are proposed to reduce the running time of the algorithm while ensuring that the number of crossings in the routing solution is close to the optimal solution. Experimental results confirm that our proposed method is able to generate the high-quality solutions quickly. Under general scale problems, compared to the existing method based on ILP, our proposed method achieves a speedup ratio of 23,171 in terms of CPU time and optimizations in terms of number of ports and port reuse of 3.18% and 6.52%, respectively. These optimizations come at the cost of only a slight increase in the number of intersections, the flow length, and the number of flow valves. In addition, our proposed method can effectively solve large-scale problems that cannot be solved by existing method based on ILP. Full article

Continuous-flow microfluidic biochips are a type of biochip technology based on microfluidic channels that enable various biological experiments and analyses to be performed on a tiny chip. They have the advantages of a high throughput, high sensitivity, high precision, low cost, and quick response. In the architectural synthesis of continuous-flow microfluidic biochips (CFMBs), prior work has not considered reducing component interconnection requirements, which led to an increase in the number of connection pairs. In this paper, we propose an architectural synthesis flow for continuous-flow microfluidic biochips with connection pair optimization, which includes high-level synthesis, placement, and routing. In the high-level synthesis stage, our method reduces the need for component interconnections, which reduces the number of connection pairs. Our method performs fine-grained binding, ultimately obtaining high-quality binding and scheduling results for flow paths. Based on the high-quality binding results, we propose a port placement strategy based on port correlation and subsequently use a quadratic placer to place the components. During the routing stage, we employ a conflict-aware routing algorithm to generate flow channels to reduce conflicts between liquid transportation tasks. Experimental results on multiple benchmarks demonstrate the effectiveness of our method. Compared with the existing work, the proposed algorithm obtains average reductions of 35.34% in connection pairs, 24.30% in flow channel intersections, 21.71% in total flow channel length, and 18.39% in the execution time of bioassays. Full article

The integration of artificial intelligence with steel manufacturing operations holds great potential for enhancing factory efficiency. Object detection algorithms, as a category within the field of artificial intelligence, have been widely adopted for steel defect detection purposes. However, mainstream object detection algorithms often exhibit a low detection accuracy and high false-negative rates when it comes to detecting small and subtle defects in steel materials. In order to enhance the production efficiency of steel factories, one approach could be the development of a novel object detection algorithm to improve the accuracy and speed of defect detection in these facilities. This paper proposes an improved algorithm based on the YOLOv5s-7.0 version, called YOLOv5s-7.0-FCC. YOLOv5s-7.0-FCC integrates the basic operator C3-Faster (C3F) into the C3 module. Its special T-shaped structure reduces the redundant calculation of channel features, increases the attention weight on the central content, and improves the algorithm’s computational speed and feature extraction capability. Furthermore, the spatial pyramid pooling-fast (SPPF) structure is replaced by the Content Augmentation Module (CAM), which enriches the image feature content with different convolution rates to simulate the way humans observe things, resulting in enhanced feature information transfer during the process. Lastly, the upsampling operator Content-Aware ReAssembly of Features (CARAFE) replaces the “nearest” method, transforming the receptive field size based on the difference in feature information. The three modules that act on feature information are distributed reasonably in YOLOv5s-7.0, reducing the loss of feature information during the convolution process. The results show that compared to the original YOLOv5 model, YOLOv5s-7.0-FCC increases the mean average precision (mAP) from 73.1% to 79.5%, achieving a 6.4% improvement. The detection speed also increased from 101.1 f/s to 109.4 f/s, an improvement of 8.3 f/s, further meeting the accuracy requirements for steel defect detection. Full article