Dementia has become a social problem in the aging society of advanced countries. Currently, 46.8 million people have dementia worldwide, and that figure is predicted to increase threefold to 130 million people by 2050...
详细信息
ISBN:
(纸本)9783319754178;9783319754161
Dementia has become a social problem in the aging society of advanced countries. Currently, 46.8 million people have dementia worldwide, and that figure is predicted to increase threefold to 130 million people by 2050. Alzheimer's disease (AD) is the most common form of dementia. The cost of care for AD patients in 2015 was 818 billion US dollars and is expected to increase dramatically in the future, due to the increasing number of patients as a result of the aging society. However, it is still very difficult to cure AD;thus, the detection of AD is crucial. This study proposes the use of machine learning to detect AD using brain image data, with the goal of reducing the cost of diagnosing and caring for AD patients. Most machine learning algorithms rely on good feature representations, which are commonly obtained manually and require domain experts to provide guidance. Feature extraction is a time-consuming and labor-intensive task. In contrast, the 3D Convolutional Neural Network (3DCNN) automatically learns feature representation from images and is not greatly affected by imageprocessing. However, the performance of CNN depends on its layer architecture. This study proposes a novel 3DCNN architecture for MRI image diagnosis of AD.
SpatialHadoop is an extended MapReduce framework supporting global indexing techniques that partition spatial data across several machines and improve query processing performance compared to traditional Hadoop system...
详细信息
ISBN:
(纸本)9783030008567;9783030008550
SpatialHadoop is an extended MapReduce framework supporting global indexing techniques that partition spatial data across several machines and improve query processing performance compared to traditional Hadoop systems. SpatialHadoop supports several spatial operations efficiently (e.g. k Nearest Neighbor search, spatial intersection join, etc.). Distance Join Queries (DJQs), e.g. k Nearest Neighbors Join Query, k Closest Pairs Query, etc., are important and common operations used in numerous spatial applications. DJQs are costly operations, since they combine joins with distance-based search. Therefore, performing DJQs efficiently is a challenging task. In this paper, a new partitioning technique based on Voronoi Diagrams is designed and implemented in SpatialHadoop. A new kNNJQ MapReduce algorithm and an improved kCPQ MapReduce algorithm, using the new partitioning mechanism, are also developed for SpatialHadoop. Finally, the results of an extensive set of experiments are presented, demonstrating that the new partitioning technique and the new DJQ MapReduce algorithms are efficient, scalable and robust in SpatialHadoop.
This study presents an image analysis framework coupled with machine learning algorithms for the classification of microscopy pollen grain images. Pollen grain classification has received notable attention concerning ...
详细信息
ISBN:
(数字)9781728138688
ISBN:
(纸本)9781728138695
This study presents an image analysis framework coupled with machine learning algorithms for the classification of microscopy pollen grain images. Pollen grain classification has received notable attention concerning a wide range of applications such as paleontology and honey certification, forecasting of allergies caused of airborne pollen and food technology. It requires an extensive qualitative process that is mostly performed manually by an expert. Although manual classification shows satisfactory performance, it may suffer from intra and inter-observer variability and it is time consuming. This study benefits from the advances of imageprocessing and machine learning and proposes a fully-automated analysis pipeline aiming to: A) calculate morphological characteristics from the images using a cost-effective microscope, and b) classify images into 6 pollen classes. A private dataset from the Department of Agriculture of the Hellenic Mediterranean University in Crete containing 564 images was used in this study. A Random Forest (RF) classifier was utilized to classify images. A repeated nested cross-validation (nested-CV) schema was used to estimate the generalization performance and prevent overfitting. image preprocessing, extraction of geometric and textural characteristics and feature selection were implemented prior to the assessment of the classification performance and a mean accuracy of 88.24% was reported.
Swarm autonomy, coordination and surveillance capabilities for multi-mission multi-functional aerial systems depend on distributed control, sensing and data acquisition. Recently emerged multi-degree-of-freedom microe...
详细信息
ISBN:
(纸本)9781538663837
Swarm autonomy, coordination and surveillance capabilities for multi-mission multi-functional aerial systems depend on distributed control, sensing and data acquisition. Recently emerged multi-degree-of-freedom microelectronic and MEMS acoustic, electromagnetic, image and inertial sensors empower autonomy, perception of reality, computer vision, augmented reality, situational awareness and other mission-critical tasks. Open problems in system design, complexity and software-hardware co-design motivate authors to focus on fundamental studies and technology developments in sensing and information fusion. Networking and data fusion from multi-mode navigation and image sensors are studied. We examine control and autonomy capabilities emulating tasks and mission environments. The distributed algorithms empower individual-and swarm aerial systems. We report solutions developed in Python, C and MATLAB supporting data processing, data visualization, interactions, interfacing and physical-and-virtual reality. The descriptive reality and information management are demonstrated by performing low-fidelity studies for DJI Phantom with heterogeneous sensors. Augmentation of control and tactical autonomy are studied.
Active imaging at the picosecond timescale reveals transient light transport effects otherwise not accessible by computer vision and imageprocessingalgorithms. For example, analyzing the time of flight of short lase...
详细信息
ISBN:
(纸本)9781538625262
Active imaging at the picosecond timescale reveals transient light transport effects otherwise not accessible by computer vision and imageprocessingalgorithms. For example, analyzing the time of flight of short laser pulses emitted into a scene and scattered back to a detector allows for depth imaging, which is crucial for autonomous driving and many other applications. Moreover, analyzing or removing global light transport effects from photographs becomes feasible. While several transient imaging systems have recently been proposed using various imaging technologies, none is capable of acquiring transient images at interactive framerates. In this paper, we present an imaging system that records transient images at up to 25 Hz. We show several transient video clips recorded with this system and demonstrate transient imaging applications, including direct-global light transport separation and enhanced depth imaging.
The objective of this paper is to develop a smart marketing system for farmers cultivating mango (Mangifera indica) and papaya (Carica papaya). This research involves wireless sensor network and Information technology...
详细信息
Pathological is crucial to cancer diagnosis. Usually, Pathologists draw their conclusion based on observed cell and tissue structure on histology slides. Rapid development in machine learning, especially deep learning...
详细信息
ISBN:
(纸本)9781728118680
Pathological is crucial to cancer diagnosis. Usually, Pathologists draw their conclusion based on observed cell and tissue structure on histology slides. Rapid development in machine learning, especially deep learning have established robust and accurate classifiers. They are being used to analyze histopathological slides and assist pathologists in diagnosis. Most machine learning systems rely heavily on annotated data sets to gain experiences and knowledge to correctly and accurately perform various tasks such as classification and segmentation. Generally, annotations made in pathology-related datasets have inherited annotation methods from natural scene images. This work investigates different granularity of annotations in histopathological data set including image-wise, bounding box, ellipse-wise, and pixel-wise to verify the influence of annotation in pathological slide on deep learning models. We design corresponding experiments to test classification and segmentation performance of deep learning models based on annotations with different annotation granularity. In classification, state-of-the-art deep learning-based classifiers perform better when trained by pixel-wise annotation dataset. On average, precision, recall and F1-score improves by 7.87%, 8.83% and 7.85% respectively. Thus, it is suggested that finer granularity annotations are better utilized by deep learning algorithms in classification tasks. Similarly, semantic segmentation algorithms can achieve 8.33% better segmentation accuracy when trained by pixel-wise annotations. Our study shows not only that finer-grained annotation can improve the performance of deep learning models, but also help they extract more accurate phenotypic information from histopathological slides. The accurate and spatially precise acquisitions of phenotypic information can improve the reliability of the model prediction. Intelligence systems trained on granular annotations may help pathologists inspecting certain regions a
Abnormal detection using UAV platform become more and more popular for operation and maintenance, in particularly for large-scale constructions like building, bridge etc. UAV-used detection system could be expected to...
详细信息
ISBN:
(数字)9781510617988
ISBN:
(纸本)9781510617988
Abnormal detection using UAV platform become more and more popular for operation and maintenance, in particularly for large-scale constructions like building, bridge etc. UAV-used detection system could be expected to reduce the cost, ensure the safety and provide stability for O&M on infrastructures. image registration and change detection method plays a central role in an abnormal detection system. Two key factors in this respect are needed to be improved. Firstly, due to the near-distance photographing and complex surface composition of structures, a robust plane-level matching method is significant to make high-precision image registration for the change detection. However, as many part of the surface of structures do not have enough feature points, it seems difficult to make a plane matching using homography transformation based on the correspondence feature points. Secondly, plane-level change detection have much noise in the border area because of homography transfer deviation and information redundancy. In order to solve these two problems, a robust method based on a combination of edge detection and geometry constraint is proposed to make plane-level registration and change detection noise reduction. For registration, making good use of pixel information in the border area, we expand the border area to extract each plane regardless of the number of feature points. And for noise reduction, we excise the border information to reduce the effect of information redundancy. Validation experiments were performed with several sets of image pairs. We succeed to extract planes in images with a 92% coverage and 91% precision while the number of noise is reduced as 30% as before for average. The evaluation shows that our proposed method is of high precision with high robustness for abnormal detection system.
The development of mobile Internet greatly facilitates information communication. The mobile live broadcasting platform has made video-sharing popular. In a long live broadcast, it is necessary to generate a video sum...
详细信息
ISBN:
(数字)9781728147437
ISBN:
(纸本)9781728147444
The development of mobile Internet greatly facilitates information communication. The mobile live broadcasting platform has made video-sharing popular. In a long live broadcast, it is necessary to generate a video summary or some pieces of news for secondary information spreading. In order to produce a video summary in real-time, shot boundary detection (SBD) of video stream is badly needed. Traditionally, shot boundaries are determined by a threshold of feature distance in adjacent frames. It is difficult to decide a threshold applied in kinds of media content with good performance. Another, researchers have proposed Support Vector Machines (SVM) to classify shot boundaries, whose model relies much on the characteristics of training data. In terms of live broadcasting, real-time signal processing is required. This paper proposes an Unsupervised Clustering based Real-time SBD method (UCR-SBD), in which consideration is given to both detection efficiency and accuracy. Experiments show that the F value of SBD reaches 97.24% and the detection speed is 17 ms per frame on average. Finally, the proposed algorithm has been successfully applied in a real-time news reporting system for the live broadcast of CUC TV station.
In this paper, synthetic aperture radar (SAR) images are investigated theoretically and experimentally for a high two-dimensional (2D) resolution (cm level). In situ measured data of two soda cans at different spatial...
详细信息
ISBN:
(纸本)9789811032295;9789811032288
In this paper, synthetic aperture radar (SAR) images are investigated theoretically and experimentally for a high two-dimensional (2D) resolution (cm level). In situ measured data of two soda cans at different spatial location are collected using a PulsON 410 ultra-wideband (UWB) radar with a pair of improved directional planar antennas. The images are obtained using two SAR imaging algorithms: Time Domain Correlation (TDC) and range Doppler (RD) respectively, and the results of RD are preferable to images via TDC. Compared to the simulation, the measurement results can provide more accurate targets location information.
暂无评论