Detailed Placement and Global Routing Co-optimization with Complex Constraints

With several divided stages, placement and routing are the most critical and challenging steps in VLSI physical design. To ensure that physical implementation problems can be manageable and converged in a reasonable runtime, placement/routing problems are usually further split into several sub-problems, which may cause conservative margin reservation and mis-correlation. Therefore, it is desirable to design an algorithm that can accurately and efficiently consider placement and routing simultaneously. In this paper, we propose a detailed placement and global routing co-optimization algorithm while considering complex routing constraints to avoid conservative margin reservation and mis-correlation in placement/routing stages. Firstly, we present a rapidly preprocessing technology based on R-tree to improve the initial routing results. After that, a BFS-based approximate optimal addressing algorithm in 3D is designed to find a proper destination for cell movement. We propose an optimal region selection algorithm based on the partial routing solution to jump out of the local optimal solution. Further, a fast partial net rip-up and rerouted algorithm is used in the process of cell movement. Finally, we adopt an efficient refinement technique to reduce the routing length further. Compared with the top 3 winners according to the 2020 ICCAD CAD contest benchmarks, the experimental results show that our algorithm achieves the best routing length reduction for all cases with a shorter runtime. On average, our algorithm can improve 0.7%, 1.5%, and 1.7% for the first, second, and third place, respectively. In addition, we can still obtain the best results after relaxing the maximum cell movement constraint, which further illustrates the effectiveness of our algorithm.

Energetic Glaucoma Segmentation and Classification Strategies Using Depth Optimized Machine Learning Strategies

Glaucoma is a major threatening cause, in which it affects the optical nerve to lead to a permanent blindness to individuals. The major causes of Glaucoma are high pressure to eyes, family history, irregular sleeping habits, and so on. These kinds of causes lead to Glaucoma easily, and the effect of such disease leads to heavy damage to the internal optic nervous system and the affected person will get permanent blindness within few months. The major problem with this disease is that it is incurable; however, the affection stages can be reduced and the same level of effect as that for the long period can be maintained but this is possible only in the earlier stages of identification. This Glaucoma causes structural effect to the eye ball and it is complex to estimate the cause during regular diagnosis. In medical terms, the Cup to Disc Ratio (CDR) is minimized to the Glaucoma patients suddenly and leads to harmful damage to one’s eye in severe manner. The general way to identify the Glaucoma is to take Optical Coherence Tomography (OCT) test, in which it captures the uncovered portion of eye ball (backside) and it is an efficient way to visualize diverse portions of eyes with optical nerve visibility shown clearly. The OCT images are mainly used to identify the diseases like Glaucoma with proper and robust accuracy levels. In this work, a new methodology is introduced to identify the Glaucoma in earlier stages, called Depth Optimized Machine Learning Strategy (DOMLS), in which it adapts the new optimization logic called Modified K-Means Optimization Logic (MkMOL) to provide best accuracy in results, and the proposed approach assures the accuracy level of more than 96.2% with least error rate of 0.002%. This paper focuses on the identification of early stage of Glaucoma and provides an efficient solution to people in case of effect by such disease using OCT images. The exact position pointed out is handled by using Region of Interest- (ROI-) based optical region selection, in which it is easy to point the optical cup (OC) and optical disc (OD). The proposed algorithm of DOMLS proves the accuracy levels in estimation of Glaucoma and the practical proofs are shown in the Result and Discussions section in a clear manner.

HDR-Net-Fusion: Real-time 3D dynamic scene reconstruction with a hierarchical deep reinforcement network

Reconstructing dynamic scenes with commodity depth cameras has many applications in computer graphics, computer vision, and robotics. However, due to the presence of noise and erroneous observations from data capturing devices and the inherently ill-posed nature of non-rigid registration with insufficient information, traditional approaches often produce low-quality geometry with holes, bumps, and misalignments. We propose a novel 3D dynamic reconstruction system, named HDR-Net-Fusion, which learns to simultaneously reconstruct and refine the geometry on the fly with a sparse embedded deformation graph of surfels, using a hierarchical deep reinforcement (HDR) network. The latter comprises two parts: a global HDR-Net which rapidly detects local regions with large geometric errors, and a local HDR-Net serving as a local patch refinement operator to promptly complete and enhance such regions. Training the global HDR-Net is formulated as a novel reinforcement learning problem to implicitly learn the region selection strategy with the goal of improving the overall reconstruction quality. The applicability and efficiency of our approach are demonstrated using a large-scale dynamic reconstruction dataset. Our method can reconstruct geometry with higher quality than traditional methods.

Fault Detection Method of Power Insulator Based on Deep Convolution Neural Network

Aiming at the problem of low detection accuracy of traditional power insulator fault detection methods, a power insulator fault detection method based on deep convolution neural network is designed. For the training of deep convolution neural network, the fault detection of power insulator based on deep convolution neural network is realized by anchor design, loss function design, candidate region selection mechanism establishment and sharing convolution features. The experimental results show that the fault detection method of power insulator based on deep convolution neural network is more accurate than the traditional method, and the detection time is less.

Extremal Region Selection for MSER Detection in Food Recognition

The visual analysis of foods on social media by using food recognition algorithm provides valuable insight from the health, cultural and marketing. Food recognition offers a means to automatically recognise foods as well the useful information such as calories and nutritional estimation by using image processing and machine learning technique. The interest points in food image can be detected effectively by using Maximally Stable Extremal Region (MSER). As MSER used global segmentation and many food images have a complex background, there are numerous irrelevant interest points are detected. These interest points are considered as noises that lead to computation burden in the overall recognition process. Therefore, this research proposes an Extremal Region Selection (ERS) algorithm to improve MSER detection by reducing the number of irrelevant extremal regions by using unsupervised learning based on the k-means algorithm. The performance of ERS algorithm is evaluated based on the classification performance metrics by using classification rate (CR), error rate (ERT), precision (Prec.) and recall (rec.) as well as the number of extremal regions produced by ERS. UECFOOD-100 and UNICT-FD1200 are the two food datasets used to benchmark the proposed algorithm. The results of this research have found that the ERS algorithm by using optimum parameters and thresholds, be able to reduce the number of extremal regions with sustained classification performance.