The impact of machine learning algorithms on everyday life is overwhelming until the novel concept of datacracy as a new social paradigm. In the field of computational environmental science and, in particular, of appl...
详细信息
ISBN:
(数字)9781728156866
ISBN:
(纸本)9781728156873
The impact of machine learning algorithms on everyday life is overwhelming until the novel concept of datacracy as a new social paradigm. In the field of computational environmental science and, in particular, of applications of large data science proof of concept on the natural resources management this kind of approaches could make the difference between species surviving to potential extinction and compromised ecological niches. In this scenario, the use of high throughput workflow engines, enabling the management of complex data flows in production is rock solid, as demonstrated by the rise of recent tools as Parsl and DagOnStar. Nevertheless, the availability of dedicated computational resources, although mitigated by the use of cloud computing technologies, could be a remarkable limitation. In this paper, we present a novel and improved version of DagOnStar, enabling the execution of lightweight but recurring computational tasks on the microservice architecture. We present our preliminary results motivating our choices supported by some evaluations and a real-world use case.
An automatic recognizer system based in Artificial Intelligence for thermographic images of the electric power distribution network is proposed in this article. The infrared thermography is usually used to conduct ins...
详细信息
An automatic recognizer system based in Artificial Intelligence for thermographic images of the electric power distribution network is proposed in this article. The infrared thermography is usually used to conduct inspections in electrical power distribution lines, assisted by a human operator, which is usually responsible for operating all the equipment, selecting the hottest spots in the image (corresponding to the places needing maintenance), making reports and calling the technical team, which will do the repairs. The proposed automatic diagnosis system aims to replace the manual inspection operation using imageprocessingalgorithms. An old method of segmentation for thermal images known as JSEG is implemented and tested and a Deep Learning Neural Network is responsible to recognize the segmented elements. A comparison between the exclusive Deep Learning based image recognition with the same method preceded by the JSEG segmentation algorithm is done in this article, showing better performance with this previous segmentation of the thermographic images. (C) 2018 The Authors. Published by Elsevier Ltd.
This paper examines techniques for real-time terrain classification and solar irradiance mapping for outdoor, solar-powered mobile robots using a vision-based Artificial Neural Network (ANN). This process is completed...
详细信息
ISBN:
(纸本)9781538680940
This paper examines techniques for real-time terrain classification and solar irradiance mapping for outdoor, solar-powered mobile robots using a vision-based Artificial Neural Network (ANN). This process is completed sequentially. First, terrain classification is completed by extracting key features from visual-spectrum images captured from an on-board camera using Haar wavelet transform to identify both color and textural information. These features are then classified using an ANN to identify grass, concrete, asphalt, gravel, and mulch. Using the terrain classes, the image is then analyzed using concepts from high dynamic range imagery to establish the solar irradiance map of the area. In this way, our sequential methodology presented allows unmanned vehicles to classify the terrain and map the irradiance of a given area with no prior knowledge. Whereas, the terrain classification can be used in determining energy consumption or traversability criteria and the irradiance map can be used to estimate the energy harvesting capabilities.
The human body exhibits many vital signs, such as heart rate (HR) and respiratory rate (RR) used to assess fitness and health. Vital signs are typically measured by a trained health professional and may be difficult f...
详细信息
This study introduces an innovative non-contact sensing technique for vision-based displacement measurement. Existing vision-based displacement measurement techniques utilizes physical target panels or physical featur...
详细信息
ISBN:
(数字)9781510616936
ISBN:
(纸本)9781510616936
This study introduces an innovative non-contact sensing technique for vision-based displacement measurement. Existing vision-based displacement measurement techniques utilizes physical target panels or physical features to compute relative displacement between the target and the observation point. Instead, the proposed method exploits the optical reference of a speckle pattern. A coherent light that is diffusely reflected on the surface of the target structure creates the speckle pattern. In this study, a camera records the changes in the speckle pattern in real time. Because the speckle pattern is sensitive to small changes of surface, the ambient vibration is enough to affect it. To estimate the displacement of the target from the raw speckle images, speckle contrast imaging (SCI), speckle flow imaging (SFI), and k-means clustering algorithm were used. After SCI and SFI quantifies the blurring effect in each image, the k-means clustering algorithm creates virtual sensing node from each image. The connection of virtual nodes from frame to frame highlights the displacements of the surface in time domain. Because the algorithms are time-consuming and computationally intensive, a GPU executes the entire post-processing operation in parallel and identifies the natural frequencies of the structure.
Estimating accurate and reliable fruit and vegetable counts from images in real-world settings, such as orchards, is a challenging problem that has received significant recent attention. Estimating fruit counts before...
详细信息
ISBN:
(纸本)9781538680940
Estimating accurate and reliable fruit and vegetable counts from images in real-world settings, such as orchards, is a challenging problem that has received significant recent attention. Estimating fruit counts before harvest provides useful information for logistics planning. While considerable progress has been made toward fruit detection, estimating the actual counts remains challenging. In practice, fruits are often clustered together. Therefore, methods that only detect fruits fail to offer general solutions to estimate accurate fruit counts. Furthermore, in horticultural studies, rather than a single yield estimate, finer information such as the distribution of the number of apples per cluster is desirable. In this work, we formulate fruit counting from images as a multi-class classification problem and solve it by training a Convolutional Neural Network. We first evaluate the per-image accuracy of our method and compare it with a state of the art method based on Gaussian Mixture Models over four test datasets. Even though the parameters of the Gaussian Mixture Model based method are specifically tuned for each dataset, our network outperforms it in three out of four datasets with a maximum of 94% accuracy. Next, we use the method to estimate the yield for two datasets for which we have ground truth. Our method achieved 96-97% accuracies. For additional details please see our video here: https://***/watch?v=Le0mb5PSYc.
We propose VLASE, a framework to use semantic edge features from images to achieve on-road localization. Semantic edge features denote edge contours that separate pairs of distinct objects such as building-sky, road-s...
详细信息
ISBN:
(纸本)9781538680940
We propose VLASE, a framework to use semantic edge features from images to achieve on-road localization. Semantic edge features denote edge contours that separate pairs of distinct objects such as building-sky, road-sidewalk, and building-ground. While prior work has shown promising results by utilizing the boundary between prominent classes such as sky and building using skylines, we generalize this to consider 19 semantic classes. We extract semantic edge features using CASENet architecture and utilize VLAD framework to perform image retrieval. We achieve improvement over state-of-the-art localization algorithms such as SIFT-VLAD and its deep variant NetVLAD. Ablation study shows the importance of different semantic classes, and our unified approach achieves better performance compared to individual prominent features such as skylines. We also introduce SLC Marathon dataset, a challenging dataset covering most of Salt Lake City with sufficient lighting variations.
This book presents a compilation of selected papers from the first International conference on Big Data Analysis and Deep Learning Applications (ICBDL 2018), and focuses on novel techniques in the fields of big data a...
ISBN:
(纸本)9789811308680
This book presents a compilation of selected papers from the first International conference on Big Data Analysis and Deep Learning Applications (ICBDL 2018), and focuses on novel techniques in the fields of big data analysis, machine learning, system monitoring, imageprocessing, conventional neural networks, communication, industrial information, and their applications. Readers will find insights to help them realize more efficient algorithms and systems used in real-life applications and contexts, making the book an essential reference guide for academic researchers, professionals, software engineers in the industry, and regulators of aviation authorities.
We present a fast and efficient algorithm for the semi-supervised colorization of line-art images (e.g. hand-made cartoons), based on two successive steps: 1. A geometric analysis of the stroke contours, and their clo...
详细信息
The proceedings contain 100 papers. The topics discussed include: a Tetris-based legalization heuristic for standard cell placement with obstacles;prediction of chaotic time series by using ANNs, ANFIS and SVMs;spiral...
ISBN:
(纸本)9781538647882
The proceedings contain 100 papers. The topics discussed include: a Tetris-based legalization heuristic for standard cell placement with obstacles;prediction of chaotic time series by using ANNs, ANFIS and SVMs;spiral inductor design based on fireworks optimization combined with free search;development of the address in real time (ART) data driver card (ADDC) test procedures of the new small wheel upgrade project;a portable imageprocessing accelerator using FPGA;extending a 65nm CMOS process design kit for high total ionizing dose effects;efficient stochastic EM studies via dimensionality reduction of polynomial-chaos expansions;bandwidth enhancement of rectangular patch antennas using multiple feeding points: a review;an energy efficient modulation scheme for body-centric nano-communications in the THz band;a very compact population count circuit for associative memories;a survey on spectrum sensing algorithms for cognitive radio networks;software design for a sound processing embedded system;function supervisors for storage systems;and using color signatures for the classification of skin disorders.
暂无评论