Music generation is a very hot topic these years. Since music signals are chronologic, and usually represented by discrete notes, NLP techniques are utilized in music generation. However, normal language models concentrate on the absolute semantic meaning of tokens, i.e. music notes, which discards the similarity of interval between notes. Besides, these language models should be set with a fixed time gap to distinguish long and short notes. Such setting lacks in generating complex rhythm, and models with very short gap suffer from the enormous representation space, resulting in shortage for generating long-term music. In this study, we propose a novel sample-based method for encoding music phrases into low-dimensional space. The samples could track local pitch tendencies of contour and flexible rhythms. We also designed two conditional variational autoencoders (VAEs) with pitch class set for generating music within a consistent style and controllable rhythm fashion.

In typical data-based grasping methods, a grasp based on parallel-jaw grippers is parameterized by the center of the gripper, the rotation angle, and the gripper opening width so as to predict the quality and pose of grasps at every pixel. In contrast, a grasp is represented using only two contact points for contact-points-based grasp representation, which allows for fusion with tactile sensors more naturally. In this work, we propose a method using contact-points-based grasp representation to get a robust grasp using only one contact points quality map generated by a neural network, which significantly reduces the complexity of the network with fewer parameters. We provide a synthetic dataset including depth image and contact points quality map generated by thousands of 3D models. We also provide the method for data generation, which can be used for contact-points-based multi-fingers grasp. Experiments show that contact points quality network can plan an available grasp in 0.15 seconds. The grasping success rate for unknown household objects is 94%. Our method is also available for deformable objects with a success rate of 95%. The dataset and reference code can be found on the project website: https://sites.google.com/view/cpqnet.

The use of computer vision technology to analyse the characteristics of smoke such as Ringelmann blackness coefficient and colour information can directly and efficiently reflect the situation of smoke emissions in industrial production, which has great significance in improving air quality. As many factors stand in the way, including the amount and speed of industrial smoke emissions, natural wind speed, illumination etc., an accurate and complete detection of the targeted smoke in images becomes a difficult issue in this field. In this study, a local binary pattern Silhouettes coefficient variant (LBPSCV) is proposed to segment industrial smoke images. The variant of Silhouettes coefficient was used as the weight when calculating the local binary pattern (LBP) feature vector in the LBPSCV. The algorithm overcame the shortcoming that the texture information described by LBP lacks local contrast information, making the extracted texture features more easily to be distinguished between smoke and non‐smoke images. Smoke emission monitoring videos with different characteristics have been used in experiments, such as smoke emission videos with low light, multiple chimney exhaust, multi‐colour smoke etc. The results show that the proposed method has higher detection accuracy and a lower false‐positive rate.

In recent years, with the development of Internet of Things (IoT) technology and the development of various types of electricity interconnection businesses in smart grids, IoT in smart grid has caused extensive research. Long Term Evolution-Advanced (LTE-A) is a promising technology for power wireless private networks, we can combine it with IoT. A major challenge brought by the combination of LTE-A and IoT in smart grid is that a large number of devices attempt simultaneously to access to the network in a short time, which will greatly reduce the performance of the network and affect the execution in smart grid. In this paper, we classify IoT devices according to the types of businesses carried by it, and establish a hierarchical architecture that uses IoT gateways to connect IoT devices to eNBs. Under this architecture, we propose a resource allocation algorithm for multi-class businesses of IoT uplink communication based on LTE-A to improve the resource utilization of the network. In the simulation, we evaluate the proposed algorithm from rate and delay respectively. The results show that the algorithm can provide better data rate and delay for businesses with different requirements for QoS in both saturated and unsaturated situations.