The graph coloring problem (GCP) is a classic combinatorial optimization problem that has been widely applied in various fields such as mathematics, computer science, and biological science. Due to the NP hard nature ...
详细信息
The demand for a variety of situational data from the traffic environment and its participants has intensified with the development of applications in Intelligent Transport Systems (ITS). Among these data, the road su...
详细信息
ISBN:
(数字)9781728182865
ISBN:
(纸本)9781728182872
The demand for a variety of situational data from the traffic environment and its participants has intensified with the development of applications in Intelligent Transport Systems (ITS). Among these data, the road surface type classification is one of the most important and can be used in the entire ITS domain. For its widespread application, it is necessary to employ a robust technology for the generation of raw data and to develop of a reliable and stable model to process these data in order to produce the classification. The developed model must operate correctly in different vehicles, under different driving styles and in different environments in which a vehicle can travel. In this work we employ inertial sensors, represented by accelerometers and gyroscopes, which are a safe, non-polluting, and low-cost alternative, ideal for large-scale use. We collect nine datasets with contextual variations, including three different vehicles, with three different drivers, in three different environments, in which there are three different road surface types, in addition to variations in the conservation state and presence of anomalies and obstacles such as potholes and speed bumps. After data collection, these data were used in experiments to evaluate various aspects, such as the influence of the vehicle data collection point, the analysis domain, the model input features, and the data window. Afterwards we evaluated the learning and generalization capacity of the models for unknown contexts. In a third step, the data were used in three Deep Neural Network (DNN) models: LSTM-based, GRU-based, and CNN-based. Through a multi-aspect and multi-contextual analysis, we considered the CNN-based model as the best one, which obtained an average accuracy between the data collection placements of 94.27% for learning and 92.70% for validation, classifying the road surface between asphalt, cobblestone or dirt road segments.
As a popular evolutionary algorithm, artificial bee colony (ABC) algorithm has been successfully applied into the threshold-based image segmentation problem. Based on our analysis, we find that the Otsu segmentation f...
详细信息
Aiming at the accurate and effective coaxiality measurement for twist drill with irregular surface, an optical measurement mechanism is proposed in this paper. First, A high-precision rotation instrument based on four...
详细信息
There are some challenges in multimodal medical image segmentation. Based on this, the Model-Data Co-driven U-Net Segmentation Network for Multimodal Lung Tumor images is proposed. About “How to extract edge features...
详细信息
There are some challenges in multimodal medical image segmentation. Based on this, the Model-Data Co-driven U-Net Segmentation Network for Multimodal Lung Tumor images is proposed. About “How to extract edge features in CT image?”, Edge-Driven U-Net is designed, which includes CT Data Stream Edge-Driven Module. The model ability to perceive lesion edge features is improved. About “How to extract position features in PET image?”, Position-Driven U-Net is designed, which includes PET Data Stream Position-Driven Module. The model ability to perceive lesion position features is improved. About “How to extract content features in PET/CT image?”, Content-Driven U-Net is designed, which includes PET/CT Data Stream Content-Driven Module. Under the guidance of semantic information in deep features, the model ability to perceive lesion content features is improved. About “How to fuse image features of PET/CT, PET and CT images?”, Model-Data Co-driven Module is designed. The main work of this model are as following: Firstly, the Shallow Model-Data Co-driven Module is designed, which realizes the interactive learning of different model data streams. Secondly, the Deep Model-Data Co-driven Module is designed, which realizes the interactive guide to learn position, edge and content features. The effectiveness of Model-Data Co-driven U-Net Segmentation Network for Multimodal Lung Tumor images is validated on a clinical multimodal lung medical image dataset. The results for Miou, Dice, Voe, Rvd, Acc, and Recall are 91.60 %,95.94 %,95.92 %,95.73 %,97.92 and 95.28 % in lung lesion segmentation. The method proposed in this paper has positive significance for computer-aided diagnosis.
Recently, multi-wavelength narrow linewidth random fiber laser has very interested for every researcher in this field, because of their useful advantages application, such as high-resolution spectroscopy and fiber opt...
详细信息
ISBN:
(数字)9781728155586
ISBN:
(纸本)9781728155593
Recently, multi-wavelength narrow linewidth random fiber laser has very interested for every researcher in this field, because of their useful advantages application, such as high-resolution spectroscopy and fiber optic sensing. In this paper, the standard single-mode fiber is used to form a half-opened cavity structure for generating the narrow linewidth random fiber laser and used the FBG-FP as a filter to form the narrow linewidth RFL into multi-wavelength. Firstly, we used the Rayleigh scattering that processed as well as in a standard single-mode fiber to provide random distribution feedback at the same time while using erbium-doped fiber (EDF) to provide the gain or amplification for achieving a broadband random laser output. Then, FBG-FP is added to the half-open cavity random laser structure. The multi-wavelength and narrow linewidth RFL can be achieved when the broadband RFL goes through the FBG-FP. In this paper we have generated the multi-wavelength narrow linewidth random fiber laser which has more than 10 wavelengths and the 3dB bandwidth is less than 0.01 nm and the mode separation of each wavelength is 0.04nm.
Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to thei...
详细信息
In this paper, a new image encryption algorithm is proposed by integrating Sine and piecewise linear chaotic maps. In order to realize the effect of encrypted image, the security key and 2D Sine-piecewise linear chaot...
详细信息
In this paper, a new image encryption algorithm is proposed by integrating Sine and piecewise linear chaotic maps. In order to realize the effect of encrypted image, the security key and 2D Sine-piecewise linear chaotic map (SPLCM) are used to encrypt the image by using random sequence and random matrix, and then using the replacement operation and the diffusion operation of the original image. The proposed image encryption algorithm is simple and practical, and the simulation results show that this algorithm is able to encrypt different types of digital images into unidentifiable random images. The security analysis also shows that this algorithm has a higher security level.
Collaborative representation based classifier (CRC) and its probabilistic improvement ProCRC have achieved satisfactory performance in many image classification applications. They, however, do not comprehensively take...
详细信息
ISBN:
(纸本)9781509060689
Collaborative representation based classifier (CRC) and its probabilistic improvement ProCRC have achieved satisfactory performance in many image classification applications. They, however, do not comprehensively take account of the structure characteristics of the training samples. In this paper, we present an extended probabilistic collaborative representation based classifier (EProCRC) for image classification. Compared with CRC and ProCRC, the proposed EProCRC further considers a prior information that describes the distribution of each class in the training data. This prior information enlarges the margin between different classes to enhance the discriminative capacity of EProCRC. Experiments on two challenging databases, namely CUB200-2011 and Caltech-256, are conducted to evaluate EProCRC, and comparison results demonstrate that it outperforms several state-of-the-art classifiers.
Ongoing and future climate change driven expansion of aeroallergen-producing plant species comprise a major human health problem across Europe and elsewhere. There is an urgent need to produce accurate, temporally dyn...
详细信息
暂无评论