China
Africa
Explore chapters and articles related to this topic
Big data in radiation oncology: Opportunities and challenges
Published in Jun Deng, Lei Xing, Big Data in Radiation Oncology, 2019
Each physician has a specific way of reporting and writing medical notes. To leverage this kind of data, natural language processing (NLP) is required in order to make sense of stored files and extract meaningful data. NLP is a part of machine learning that can help in understanding, segmenting, parsing, or even translating text written in a natural language.27 It can be used to repurpose electronic medical records (EMR) to automatically identify postoperative complications,28 create a database from chest radiographic reports,29 or even rapidly create a clinical summary from data collected for a patient’s disease.30 This kind of technology will be essential for big data analytics in radiation oncology, mostly for clinical information.
Speech and Language Interfaces, Applications, and Technologies
Published in Julie A. Jacko, The Human–Computer Interaction Handbook, 2012
Clare-Marie Karat, Jennifer Lai, Osamuyimen Stewart, Nicole Yankelovich
Language remains one of the major barriers in a linguistically diverse and globally connected world with an ever-increasing need for people to communicate and collaborate with each other. Thus, it is common to find, in formal settings like the United Nations, representatives of the various nations wearing head-phones through which they receive translations by a human translator or interpreter who works behind the scenes. Moreover, with recent advances in machine translation technology, computers (translation software programs on a PC, smartphones, or other handheld devices) are now also used to facilitate communication between people who speak different languages or to empower people to consume information that is typically only available in a language different from theirs. The process whereby a computer (e.g., smartphones or handheld devices) systematically transfers (translates) the meaning of a text string or a speech utterance from one natural language to another is called machine translation.
A proposed model for predicting stock market behavior based on detecting fake news
Published in Yuli Rahmawati, Peter Charles Taylor, Empowering Science and Mathematics for Global Competitiveness, 2019
A.M. Idrees, M.H. Ibrahim, N.Y. Hegazy
Machine learning includes supervised and unsupervised approaches (Witten et al., 2011; Kaseb et al., 2018) is applied in different directions (Sarhan, Ghalwash & Khafagy, 2009; Sahal, Khafagy & Omara, 2018; Mahmoud, Hegazy, & Khafagy, 2018). Text mining is a process of handling unstructured data and is considered a step of knowledge discovery. Text preprocessing techniques include tokenization, stemming, and stopping word removal. Sentiment analysis is the process of determining people’s attitudes, opinions, evaluations, appraisals, and emotions toward entities such as products, services, organizations, attributes using Natural Language Processing (NLP), statistics, or machine-learning methods from text data.
Mining typhoon victim information based on multi-source data fusion using social media data in China: a case study of the 2019 Super Typhoon Lekima
Published in Geomatics, Natural Hazards and Risk, 2022
Novel and additional disaster information is presented by crowdsourcing through social media (Simon et al. 2015), especially during tropical cyclone disaster management. Li et al. (2021) concluded that using social media in cyclone disasters serves three major purposes: emotional expression, situational updates, and disaster-related information exchange. Many studies on social media converge on themes of sentiment analysis and emergency response. For example, Wu and Cui (2018) developed a data processing framework and analyzed Twitter (www.twitter.com) postings using multidimensional analysis containing reverse geocoding, emotion analysis, subject tags, and high-frequency methods to track public responses to Superstorm Sandy. Spruce et al. (2020) applied detailed sentiment analysis on the public's negative feelings about the storm to measure the impact of storms. Additionally, with sentiment analysis on calculation of the emotional intensity of an event, Ragini et al. (2018) used a data-driven approach for disaster response, while Yuan and Liu (2020) assessed the damage caused by Hurricane Matthew. Sentiment analysis is a common method of natural language processing, which is based on text word analysis to determine the specific sentiment and other markers contained in it (Feldman 2013). The sentiment changes revealed in social media are thought to reflect temporal and spatial mood changes in society (Wu and Cui 2018). The above studies showed that sentiment analysis is a common step when using social media for the disaster management of cyclones.
Application of machine learning algorithms in wind power: a review
Published in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2021
Yao-Chao Deng, Xue-Hua Tang, Zhi-Yong Zhou, Yang Yang, Fan Niu
NLP is an important research direction in the field of artificial intelligence, which mainly aims to realize the effective communication between humans and computers by natural language so that computers can understand the human language from the data dimensions (Wang, Shi-Wen, and Zhu et al. 2015). For humans, it is easy to understand what a king or a queen means, but for computers, it is hard to understand every word because its storage form is based on binary digits (Bing, Fan, and Wei et al. 2017). To study NLP, various machine learning algorithms have been invented. Latent Semantic Analysis (LSA) (Wild 2015), Probabilistic Latent Semantic Analysis (pLSA) (Zuo, Wang, and Lai 2017), and Latent Dirichlet Allocation (LDA) are topic models, word2vec, fastText and glove are fixed representations based on word vectors, and ELMo (embedding from language model), GPT (Generative Pre-Training) and Bert (Bidirectional Encoder Representation from Transformers) which are dynamic representations based on word vectors (Peng, Yan, and Lu 2019). Our purpose is to analyze papers related to wind power and to use word-embedding of related words to obtain their word vectors and analyze them. Thus, the word2vec algorithm is adopted to conduct this research.
Identifying traffic conditions from non-traffic related sources
Published in Journal of Intelligent Transportation Systems, 2020
Jorge C. Chamby-Diaz, Rhuam Sena Estevam, Ana L. C. Bazzan
Due to the fact that most of the data collected is in natural language and/or not geolocated, the following two processing phases are necessary.Named Entity Recognition (NER): when it is necessary to find named entities in a text in natural language (as, for example, names of streets and other locations), NER is a common technique, which processes a document and recognizes words or sentences that mention named entities. These are predefined categories, such as names of locations, of people, or organizations. Some tools were already developed to perform this task, e.g., spaCy, NLTK, AllenNLP etc.Geolocation: Names of streets and other locations were recognized by a NER tool, it is necessary to geolocate them using a given system of coordinates.