Selective fusion in adolescent idiopathic scoliosis

Despite the continual evolution in the surgical treatment of adolescent idiopathic scoliosis （AIS）,the goals of surgery remain to correct and stabilize the deformity in three dimensions, to maintain equilibrium of the shoulders and trunk, and to leave as many mobile spinal segments as possible. The essence is to fuse the smallest possible number of vertebrae to maintain maximum residual mobility, but end with corrected and well-balanced spine. Selective fusion is termed when both the main thoracic and thoracolumbar/lumbar （TL/L） curves deviate completely from the midline （Figure 1）, but only the major curve （the largest Cobb measurement） is fused, leaving the minor curve unfused and mobile. For the single curve, such as thoracic, thoracolumbar, or lumbar curve, there are fewer differences of opinion amongst spinal surgeons regarding the selection of the fusion level than the surgical approach. However, the choice of fusion levels in some types of curves, such as double curves and triple controversy issue. If the fusion is incorrect, it curvature deterioration, curves remains a difficult and decision to perform selective may result in postoperative shoulder imbalance, trunk decompensation, or even produce new deformity, an early revision by extending the fusion or reducing the correction may need. The non-selective approach rarely leads to early troubles that require a second procedure and is often perceived as being safer in the short-term. But it may be more difficult in the long-term as distal degeneration is more likely. This raises the question： ＂Is it better to be safe in the short-term or take a chance avoiding later degenerative problems with a shorter motion-sparing fusion？＂ Thus, the aim of selective fusion is to identify the compensatory curves （minor curve） that will straighten spontaneously after correcting and fusing the major curve, thereby avoid the fusion of these flexible compensatory curves.

Virtual sensing for gearbox condition monitoring based on kernel factor analysis

Vibration and oil debris analysis are widely used in gearbox condition monitoring as the typical indirect and direct sensing techniques. However, they have their own advantages and disadvantages. To better utilize the sensing information and overcome its shortcomings, this paper presents a virtual sensing technique based on artificial intelligence by fusing low-cost online vibration measurements to derive a gearbox condition indictor, and its performance is comparable to the costly offline oil debris measurements. Firstly, the representative features are extracted from the noisy vibration measurements to characterize the gearbox degradation conditions. However, the extracted features of high dimensionality present nonlinearity and uncertainty in the machinery degradation process. A new nonlinear feature selection and fusion method,named kernel factor analysis, is proposed to mitigate the aforementioned challenge. Then the virtual sensing model is constructed by incorporating the fused vibration features and offline oil debris measurements based on support vector regression. The developed virtual sensing technique is experimentally evaluated in spiral bevel gear wear tests,and the results show that the developed kernel factor analysis method outperforms the state-of-the-art featureselection techniques in terms of virtual sensing model accuracy.

Joint Rain Streaks & Haze Removal Network for Object Detection

In the realm of low-level vision tasks,such as image deraining and dehazing,restoring images distorted by adverse weather conditions remains a significant challenge.The emergence of abundant computational resources has driven the dominance of deep Convolutional Neural Networks(CNNs),supplanting traditional methods reliant on prior knowledge.However,the evolution of CNN architectures has tended towards increasing complexity,utilizing intricate structures to enhance performance,often at the expense of computational efficiency.In response,we propose the Selective Kernel Dense Residual M-shaped Network(SKDRMNet),a flexible solution adept at balancing computational efficiency with network accuracy.A key innovation is the incorporation of an M-shaped hierarchical structure,derived from the U-Net framework as M-Network(M-Net),within which the Selective Kernel Dense Residual Module(SDRM)is introduced to reinforce multi-scale semantic feature maps.Our methodology employs two sampling techniques-bilinear and pixel unshuffled and utilizes a multi-scale feature fusion approach to distil more robust spatial feature map information.During the reconstruction phase,feature maps of varying resolutions are seamlessly integrated,and the extracted features are effectively merged using the Selective Kernel Fusion Module(SKFM).Empirical results demonstrate the comprehensive superiority of SKDRMNet across both synthetic and real rain and haze datasets.