IoT Devices have revolutionized how people interact with each other and their surroundings, with Gartner predicting 50 billion devices by 2020. IoT devices emerging from WSN to RFIDs are capable of sensing, actuating ...
详细信息
With the rapid development of the world population, large area of land is utilized to develop housing and the ability of producing food is reduced. Farming has become crucial in present trend and keeps food on the tab...
详细信息
The real-time pick and place of 3D industrial parts randomly filed in a part-bin plays an important role for manufacturing automation. Approaches based solely on the conventional engineering discipline have been shown...
详细信息
ISBN:
(数字)9781728160344
ISBN:
(纸本)9781728160344
The real-time pick and place of 3D industrial parts randomly filed in a part-bin plays an important role for manufacturing automation. Approaches based solely on the conventional engineering discipline have been shown limitations in terms of handling multiple parts of arbitrary 3D geometries in real-time. In this paper, we present a hybrid approach of deep learning and engineering as a means of breaking through the current limitations of industrial bin picking toward enabling the real-time pick and place of multiple 3D parts of arbitrary geometries. The proposed approach, first, makes use of deep learning based object detectors configured in a cascaded form for both detecting parts in a bin and extracting features associated with the individual parts detected. The concatenation of the part label and the feature labels and their positions associated with the part allows the subsequent part net to have its part recognition rate close to 100%, Furthermore, the part features and their positions arc to be fed directly into the estimation of the 3D pose of the corresponding part in a bin as well as its degree of occlusion. The experimental results demonstrate that the proposed approach is able to perform a real-time multiple part bin picking operation for multiple 3D parts of arbitrary geometries with a high precision.
With the rapid development of e-commerce, a large amount of consumption data has been generated, and consumers have also put forward personalized requirements for the purchased goods, so the traditional marketing mode...
详细信息
This research work focuses on analysing weather data, described by plenty of attributes, creating a high-dimensional data. After fetching the real-time observations recorded at the city on interest, the data is pre-pr...
详细信息
ISBN:
(数字)9789811501357
ISBN:
(纸本)9789811501357;9789811501340
This research work focuses on analysing weather data, described by plenty of attributes, creating a high-dimensional data. After fetching the real-time observations recorded at the city on interest, the data is pre-processed for the purpose of feature selection;this also ensures data correctness, consistency and prepares data for analysis. Statistical model arrives at the aggregate of the insights observed in the empirical data. The statistical model delivers the parameters which are used to estimate the future weather attributes. Substitution of results in underlying statistical model fitness equation, the predictions can be obtained.
With advancements in modern technology in the current era, very large volumes of big data have been generated and collected in numerous real-life applications. These have formed a connected world comprising webs of ag...
详细信息
ISBN:
(纸本)9781665419246
With advancements in modern technology in the current era, very large volumes of big data have been generated and collected in numerous real-life applications. These have formed a connected world comprising webs of agents, data, people, things and trust. Some of these webs have also emerged in health and smart living. As valuable information and knowledge is embedded in these rich sets of webs, web intelligence is in demand. In this paper, we focus on a data science task of web usage mining. In particular, we present a web intelligent solution to conduct explainable machine learning and mining of influential patterns from sparse web. It provides a compressed representation of sparse web, discovers influential websites and/or web pages that are frequently browsed or surfed by web surfers, and recommends these influential websites and/or web pages to other web surfers. Evaluation results show the effectiveness (especially, in data compression), interpretability and practicality of our solution.
With the deployment of smart homes, we find that human activity recognition (HAR) is essentially important to many applications, e.g., child/senior care, intelligent information push and exercise promotion. Although i...
详细信息
ISBN:
(纸本)9781728169972
With the deployment of smart homes, we find that human activity recognition (HAR) is essentially important to many applications, e.g., child/senior care, intelligent information push and exercise promotion. Although it is always better to build HAR model for each smart home to resolve the practical problem that homes have different floorplans or adopted sensors, it is intractable to acquire labeled data for each home due to cost and privacy. We thus propose a method to transfer the HAR model from multiple labeled source homes to the unlabeled target home. Specifically, we first generate transferable representations for the sensors of these homes, based on which we build the HAR model using the data of labeled source homes. Then, we employ the built HAR model into the unlabeled target home. Experiment results on CASAS dataset illustrate that our proposed method outperforms baseline methods in general and also avoids potential negative transfer caused by using only one source home.
With the development and improvement of the information technologies, the increasing of the upper application systems and the rapid expansion of the data accumulated in the campus information environment, a typical ca...
详细信息
ISBN:
(纸本)9783030152352;9783030152345
With the development and improvement of the information technologies, the increasing of the upper application systems and the rapid expansion of the data accumulated in the campus information environment, a typical campus big data environment has initially been formed. Because of the characteristics of the higher education, students' mobility is great and their learning environment is uncertain, so that the students' attendance mostly used the manual naming. The student attendance system based on the big data architecture is relying on the campus network, and adopting the appropriate sensors. Through the data mining technology, combined with the campus One Card solution, we can realize the management of the attendance without naming in class. It can not only strengthen the management of the students, but can also improve the management levels of the colleges and universities.
It is generally observed that billing at shopping stores takes a lot of time, especially during holidays and weekends. A person in India visits a grocery store 1.6 times every 15 days and spends nearly 43 mi...
详细信息
Among numerous emergency responses to maritime emergencies, the most critical part is the search and rescue (SAR) for victims in distress on the sea. Maritime search and rescue missions are usually divided into two: s...
详细信息
暂无评论