With the demand for flexible manufacturing of curved ship blocks, a bracket system with fixtures has emerged for positioning curved compliant parts. However, current experience-based fixturing schemes struggle to determine the appropriate amount and layout of flexible fixtures for compliant parts from various curved ship blocks. Thus, it is urgent to design fixturing schemes for corresponding parts to mitigate the impact of redundant fixtures and suboptimal layouts, ultimately reducing the total cost. In this paper, a novel fixturing scheme design policy (FSDP) is proposed for curved compliant parts. Firstly, a finite element equation-based method is built to calculate the dimensional deformation of parts under different fixturing schemes. Secondly, a fixturing scheme optimization model is formulated considering fixture amount and layout as the decision variables. The objective is to minimize the overall cost, which includes the fixture cost, quality loss, and penalty cost for violating the accuracy requirement. Finally, three curved shell plates with different aspect ratios from the shipyard are used to demonstrate the effectiveness and expandability of the FSDP. The results indicate that compared with the current fixed fixture layouts, the proposed FSDP can significantly reduce the fixture cost and quality loss by 70-85% while controlling the part deformation within the accuracy requirement. It can help shipyards adaptively optimize the flexible fixturing schemes under different compliant parts during ship construction. Note to Practitioners—This work is motivated by designing a fixturing scheme for various curved compliant parts in the shipbuilding industry. Traditional fixturing schemes result in redundant costs and poor geometrical quality of curved shell panels. The large and uneven deformation of parts will hinder the welding of subsequent stiffening members with manual trimming, which is time-consuming and labor-intensive. Thus, it is not suitable for a wide range of diverse compliant parts in the flexible construction transformation of curved blocks. In this paper, we introduce the FSDP to find optimal fixturing schemes for different curved compliant parts. Compared with the current practice, the FSDP significantly reduces the total cost. Besides, the geometrical quality of the parts is improved. The proposed policy enables practitioners to implement the optimal fixturing schemes instead of relying on experience-based current practice in the flexible construction of curved blocks.

Visual feature extraction is a key technology of computer vision for intelligent video processing. Efficient feature extraction is a fundamental problem in computer vision applications. Scale-Invariant Feature Transform (SIFT) is one of the most popular feature extraction algorithms because SIFT features are invariant to image scale and rotation and robust to changes in illumination and noise. However, SIFT is a computationally-intensive and power-hungry algorithm, which needs to be accelerated by efficient hardware design to achieve both high-speed feature extraction and high energy efficiency for many high frame-rate video applications at Artificial-intelligent Internet of Things edges. In this work, an energy-efficient SIFT based feature extraction accelerator is proposed. In the Gaussian pyramid and Differences of Gaussian (DoG) pyramid construction process, three design methods are proposed to reduce power consumption and improve information fidelity: a fast and slow dual clock domain design method with a reconfigurable design strategy is proposed to reduce the computation resources; a partial sum reuse design method is proposed to further reduce the computation resources and the amount of computation; a dynamic padding design method is proposed to solve the problem of information loss at image edges and corners after convolution operation. In the keypoint descriptor generation process, an optimized algorithm using circular region and polar coordinates is proposed to parallelize the main orientation assignment and descriptor generation to achieve high-speed processing, while maintaining a comparable matching accuracy with the state-of-the-art designs. The experiment results show that the proposed SIFT hardware accelerator is able to extract features by up to 162 frames per second ($640\times 480$pixels) under 100 MHz, with the power consumption of 364.26 mW and energy efficiency of 2.25 mJ/frame based on 180 nm technology, which is suitable for many high frame-rate AIoT applications including autonomous driving cars and unmanned aerial vehicles.

Tensors, as the multidimensional generalization of matrices, are naturally suited for representing and processing high-dimensional data. To date, tensors have been widely adopted in various data-intensive applications, such as machine learning and big data analysis. However, due to the inherent large-size characteristics of tensors, tensor algorithms, as the approaches that synthesize, transform or decompose tensors, are very computation and storage expensive, thereby hindering the potential further adoptions of tensors in many application scenarios, especially on the resource-constrained hardware platforms. In this paper, we propose a reduced-complexity SVD (Singular Vector Decomposition) scheme, which serves as the key operation in Tucker decomposition. By using iterative self-multiplication, the proposed scheme can significantly reduce the storage and computational costs of SVD, thereby reducing the complexity of the overall process. Then, corresponding hardware architecture is developed with 28nm CMOS technology. Our synthesized design can achieve 102GOPS with 1.09 mm2area and 37.6 mW power consumption, and thereby providing a promising solution for accelerating Tucker decomposition.

Understanding the fine-grained distribution of telecommunication (Telco) signals in terms of a three-dimensional (3D) space is important for Telco operators to manage, operate and optimize Telco networks. It is particularly true in nowadays urban cities with a large number of high buildings. One of the key tasks is to infer the location height of mobile devices, e.g., the floor within a high building where mobile devices are located. However, precise height estimation is challenging due to complex Telco signal propagation within an indoor 3D space, sparse cell tower deployment and scarce training samples. To tackle these issues, in this paper, we propose an indoor MR height estimation framework, namely IFLoc, via a machine learning model. IFLoc first builds a training MR database via a pre-processing step to comfortably tag raw MR samples by precisely inferred height from auxiliary data such as GPS and barometer readings. Next, IFLoc trains a regression model for height estimation by a set of developed techniques including 3D space division, post-processing techniques, feature augmentation and an improved SVR (Supported Vector Regression) model. Our evaluation on eight real datasets collected within five representative high buildings in Shanghai validates that IFLoc outperforms state-of-the-art counterparts in particularly with scarce training data.

Massive Multiple Input Multiple Output (MIMO) at millimeter wave bands is able to boost the system throughput. A key challenge for the hybrid beamforming design in massive MIMO systems is the acquisition of the full channel state information, since the number of radio frequency chains is much smaller than that of the antennas. Conventional methods require a longer measurement time, a large overhead, or costly signal processing efforts. Therefore, we propose an efficient and adaptable deep neural network based low-rank channel recovery scheme for a hybrid array based massive MIMO system. The proposed neural network architecture includes a common feature extraction module and the adaptable recovery module. The feature extraction, built on the convolutional neural network with residual learning functionality, can efficiently learn the essential features from the low-rank measurements. The adaptable key recovery module maps the essential features to the full channel information. The proposed architecture enables an efficient learning procedure and can be easily adapted to different cases. Simulation results are carried out and compared with existing solutions, showing the potential of applying deep learning concepts in millimeter wave massive MIMO systems.

Successive interference cancellation (SIC) is an effective way of multipacket reception to combat interference. As conventional CSMA (Carrier Sense Multiple Access) is designed for single packet reception, it is unclear whether or not CSMA performs well to exploit the SIC capability. In this paper, we analyze the performance of a simple CSMA protocol in a network with SIC. For a given link, we derive the residing areas of an interfering node when simultaneous transmission is allowed and when the interference is harmful, respectively. We show that, though SIC provides many new transmission opportunities, CSMA cannot effectively exploit them. There is a fundamental tradeoff in a CSMA protocol between exploiting the transmission opportunities from SIC and capturing the harmful interference. In many cases, when CSMA achieves its best performance, almost all new transmission opportunities are not exploited. It is therefore very necessary to design a new distributed access protocol in wireless networks with SIC.

Faster convergence and optimized traffic engineering are always the pursuits of network operators. However, the link state protocols nowadays have obvious inabilities in achieving these network objectives. In link state network, flooding scheme is usually used to spread the state of link connectivity over the network. Generally, link state flooding introduces various timer configurations for tuning convergence performance. The configuration complexity becomes the major reason of protocol inability to optimize routing convergence. On the other hand, traffic engineering is poorly supported by link state protocol because of temporary status which may cause unexpected traffic migration and packets loss. In this paper, we propose a routing model through which the link state information is disseminated in a globally controllable way. Our model removes existing limitations for accelerating convergence. Meanwhile, our model can integrate traffic engineering into link state protocol by disseminating optimized link weight, thus avoiding the inefficiencies of massive network configurations. Our experiments show that our model can achieve better convergence time and significantly reduce overhead. At the same time, our model is fully scalable with network size. We believe that our model can enhance network convergence and traffic engineering performance simultaneously, as well as prevent unexpected network transitions to improve network reliability.

In the challenged networks, such as interplanetary networks, satellite networks, military networks and so on, a complete path from the source to the destination does not exist for most of the time. The lack of end-to-end path makes the message delivery a great challenge in these networks. In this paper, we propose the spray and routing message delivery mechanism, which combines the simplicity of epidemic routing and the efficiency of direct routing. We evaluate the performance of Spray and Routing via simulation using the ONE simulator, in comparison with the traditional Epidemic, Prophet and Spray and Waiting protocols. The simulation results show that our method can achieve better performance.

This paper presents the monotonic indices space (MIS) method used for the extended complex system capability indices effectiveness analysis. Based on the assumption that indices are monotonic with respect to the requirement measurements, an algorithm is proposed and applied to attain numerical approximation of monotonic indices requirement locus with hyperboxes. Two algorithms for acquiring intersection of several monotonic indices requirement loci are proposed, and two system analysis models based on MIS, the system evaluation model and the index sensitivity analysis model, are put forward. Finally, the models previously mentioned are used to analyze the capability indices effectiveness of a notional antistealth information system. The results show that the MIS method is promising.