Academic literature on the topic 'BBC Dataset'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'BBC Dataset.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "BBC Dataset"
1
Kevin, Sherilyn. "News Summarization of BBC Articles: A Multi-Category Approach." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 01 (2024): 1–10. http://dx.doi.org/10.55041/ijsrem28129.
Full textAbstract:
In this research project, we explore the application of advanced natural language processing techniques to automatically summarize news articles from the BBC. The dataset comprises five distinct categories— business, entertainment, politics, sport, and tech—each containing a wealth of information. Our primary goal is to develop an efficient and accurate news summarization system using state-of-the-art language models. We employ the Hugging Face Transformers library to create a summarization pipeline capable of extracting key information from lengthy news articles.
2
Sidiropoulos, George K., Nikolaos Diamianos, Kyriakos D. Apostolidis, and George A. Papakostas. "Text Classification Using Intuitionistic Fuzzy Set Measures—An Evaluation Study." Information 13, no. 5 (2022): 235. http://dx.doi.org/10.3390/info13050235.
Full textAbstract:
A very important task of Natural Language Processing is text categorization (or text classification), which aims to automatically classify a document into categories. This kind of task includes numerous applications, such as sentiment analysis, language or intent detection, heavily used by social-/brand-monitoring tools, customer service, and the voice of customer, among others. Since the introduction of Fuzzy Set theory, its application has been tested in many fields, from bioinformatics to industrial and commercial use, as well as in cases with vague, incomplete, or imprecise data, highlighting its importance and usefulness in the fields. The most important aspect of the application of Fuzzy Set theory is the measures employed to calculate how similar or dissimilar two samples in a dataset are. In this study, we evaluate the performance of 43 similarity and 19 distance measures in the task of text document classification, using the widely used BBC News and BBC Sports benchmark datasets. Their performance is optimized through hyperparameter optimization techniques and evaluated via a leave-one-out cross-validation technique, presenting their performance using the accuracy, precision, recall, and F1-score metrics.
3
Saraswati, Ni Wayan Sumartini, I. Putu Krisna Suarendra Putra, I. Dewa Made Krishna Muku, and Gede Dana Pramitha. "Support Vector Machine For Hoax Detection." SINTECH (Science and Information Technology) Journal 6, no. 2 (2023): 107–17. http://dx.doi.org/10.31598/sintechjournal.v6i2.1366.
Full textAbstract:
Along with the development of information technology, news media has also developed by presenting information online Along with the rapid development of online news, the spread of fake news information (hoaxes) is also increasing rapidly and widely. Hoax news is often spread intentionally for various purposes. Generally, hoax news aims to direct the reader's perception to believe in a bad perception of an event, character or even a company. The motivation is to invite readers to believe something that is not true with the aim of benefiting the news disseminator is something dangerous. This research aims to detect English-language hoaxes by applying the Support vector machine (SVM) algorithm. In this study, the data used are two data sources, namely English news datasets from Kaggle and English news taken from BBC. The results of this study show that the application of the SVM algorithm turns out to get good performance because the model is able to classify hoax news with an accuracy of 99.4% on Kaggle data while on the BBC news dataset the model gets an accuracy of 98.9%. This research also shows that the SVM method is proven to have good generalization properties. Where it is able to identify test data that is completely different from the training data.
4
Muna, Ghazi Abdulsahib, and E. Abdulmunim Matheel. "Multimodal video abstraction into a static document using deep learning." International Journal of Electrical and Computer Engineering (IJECE) 13, no. 3 (2023): 2752–60. https://doi.org/10.11591/ijece.v13i3.pp2752-2760.
Full textAbstract:
Abstraction is a strategy that gives the essential points of a document in a short period of time. The video abstraction approach proposed in this research is based on multi-modal video data, which comprises both audio and visual data. Segmenting the input video into scenes and obtaining a textual and visual summary for each scene are the major video abstraction procedures to summarize the video events into a static document. To recognize the shot and scene boundary from a video sequence, a hybrid features method was employed, which improves detection shot performance by selecting strong and flexible features. The most informative keyframes from each scene are then incorporated into the visual summary. A hybrid deep learning model was used for abstractive text summarization. The BBC archive provided the testing videos, which comprised BBC Learning English and BBC News. In addition, a news summary dataset was used to train a deep model. The performance of the proposed approaches was assessed using metrics like Rouge for textual summary, which achieved a 40.49% accuracy rate. While precision, recall, and F-score used for visual summary have achieved (94.9%) accuracy, which performed better than the other methods, according to the findings of the experiments.
5
Abdulsahib, Muna Ghazi, and Matheel E. Abdulmunim. "Multimodal video abstraction into a static document using deep learning." International Journal of Electrical and Computer Engineering (IJECE) 13, no. 3 (2023): 2752. http://dx.doi.org/10.11591/ijece.v13i3.pp2752-2760.
Full textAbstract:
<p><span lang="EN-US">Abstraction is a strategy that gives the essential points of a document in a short period of time. The video abstraction approach proposed in this research is based on multi-modal video data, which comprises both audio and visual data. Segmenting the input video into scenes and obtaining a textual and visual summary for each scene are the major video abstraction procedures to summarize the video events into a static document. To recognize the shot and scene boundary from a video sequence, a hybrid features method was employed, which improves detection shot performance by selecting strong and flexible features. The most informative keyframes from each scene are then incorporated into the visual summary. A hybrid deep learning model was used for abstractive text summarization. The BBC archive provided the testing videos, which comprised BBC Learning English and BBC News. In addition, a news summary dataset was used to train a deep model. The performance of the proposed approaches was assessed using metrics like Rouge for textual summary, which achieved a 40.49% accuracy rate. While precision, recall, and F-score used for visual summary have achieved (94.9%) accuracy, which performed better than the other methods, according to the findings of the experiments.</span></p>
6
Niyogisubizo, Jovial, Lyuchao Liao, Fumin Zou, et al. "Predicting traffic crash severity using hybrid of balanced bagging classification and light gradient boosting machine." Intelligent Data Analysis 27, no. 1 (2023): 79–101. http://dx.doi.org/10.3233/ida-216398.
Full textAbstract:
Accident severity prediction is a hot topic of research aimed at ensuring road safety as well as taking precautionary measures for anticipated future road crashes. In the past decades, both classical statistical methods and machine learning algorithms have been used to predict traffic crash severity. However, most of these models suffer from several drawbacks including low accuracy, and lack of interpretability for people. To address these issues, this paper proposed a hybrid of Balanced Bagging Classification (BBC) and Light Gradient Boosting Machine (LGBM) to improve the accuracy of crash severity prediction and eliminate the issues of bias and variance. To the best of the author’s knowledge, this is one of the pioneer studies which explores the application of BBC-LGBM to predict traffic crash severity. On the accident dataset of Great Britain (UK) from 2013 to 2019, the proposed model has demonstrated better performance when compared with other models such as Gaussian Naïve Bayes (GNB), Support vector machines (SVM), and Random Forest (RF). More specifically, the proposed model managed to achieve better performance among all metrics for the testing dataset (accuracy = 77.7%, precision = 75%, recall = 73%, F1-Score = 68%). Moreover, permutation importance is used to interpret the results and analyze the importance of each factor influencing crash severity. The accuracy-enhanced model is significant to several stakeholders including drivers for early alarm and government departments, insurance companies, and even hospitals for the services concerned about human lives and property damage in road crashes.
7
Oliveira, Douglas Nunes de, Milo Noronha Rocha Utsch, Diogo Villela Pedro de Almeida Machado, et al. "Evaluating a New Auto-ML Approach for Sentiment Analysis and Intent Recognition Tasks." Journal on Interactive Systems 14, no. 1 (2023): 92–105. http://dx.doi.org/10.5753/jis.2023.3161.
Full textAbstract:
Automated Machine Learning (AutoML) is a research area that aims to help humans solve Machine Learning (ML) problems by automatically discovering good ML pipelines (algorithms and their hyperparameters for every stage of a machine learning process) for a given dataset. Since we have a combinatorial optimization problem for which it is impossible to evaluate all possible pipelines, most AutoML systems use a Genetic Algorithm (GA) or Bayesian Optimization (BO) to find a good solution. These systems usually evaluate the performance of the pipelines using the K-fold cross-validation method, for which the more pipelines are evaluated, the higher the chance of finding an overfitted solution. To avoid the aforementioned issue, we propose a system named Auto-ML System for Text Classification (ASTeC), that uses the Bootstrap Bias Corrected CV (BBC-CV) method to evaluate the performance of the pipelines. More specifically, the proposed system combines GA, BO, and BBC-CV to find a good ML pipeline for the text classification task. We evaluated our approach by comparing it with state-of-the-art systems: in the the Sentiment Analysis (SA) task, we compared our approach to TPOT (Tree-based Pipeline Optimization Tool) and Google Cloud AutoML service, and for the Intent Recognition (IR) task, we compared with TPOT and MLJAR AutoML. Concerning the data, we analysed seven public datasets from the SA domain and sixteen from the IR domain. Four out of those sixteen are composed by written English text, while all of the others are in Brazilian Portuguese. Statistical tests show that, in 21 out of 23 datasets, our system's performance is equivalent to or better than the others.
8
C.P., Patidar, Katara Yogesh, and Sharma Meena. "Hybrid News Recommendation System using TF-IDF and Similarity Weight Index." International Journal of Soft Computing and Engineering (IJSCE) 10, no. 3 (2020): 5–9. https://doi.org/10.35940/ijsce.C3471.1110320.
Full textAbstract:
As the usage of internet is increasing, we are getting more dependent on it in our daily life. The Internet plays an essential role to simplify our tight schedules. In such tough lives, it is very important to stay aware of current affairs. Now for different people coming from different backgrounds and professions, the preferences are different too. Here come Data mining techniques in the picture, which gives us “Recommender system” as the output, capable of delivering more relevant and worthy outcomes. Newspapers are the basic obligation asked by almost every person to stay updated and aware of the world. But as we observe that nowadays, various solutions are been developed to convert paper news system to digital news and raise the bar of the quick news. And that’s how News Recommender systems are have made an important place in our fast running lives.This research paper has investigated the News Recommendation solution right from its core, including the importance, performance, and improvement suggestions. This paper talks about enhancing the performance of states solution by using modified Term Frequency-Inverse Document Frequency (TF-IDF) algorithms. Proposed solution advocates the usage of JAVA technology which reflects fruitful results in the final graphs of accuracy, precision, and F-score. Here, BBC dataset has been used for comparison study purposes.
9
Narayan, Shashi, Shay B. Cohen, and Mirella Lapata. "What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural Networks." Journal of Artificial Intelligence Research 66 (September 19, 2019): 243–78. http://dx.doi.org/10.1613/jair.1.11315.
Full textAbstract:
We introduce "extreme summarization," a new single-document summarization task which aims at creating a short, one-sentence news summary answering the question "What is the article about?". We argue that extreme summarization, by nature, is not amenable to extractive strategies and requires an abstractive modeling approach. In the hope of driving research on this task further: (a) we collect a real-world, large scale dataset by harvesting online articles from the British Broadcasting Corporation (BBC); and (b) propose a novel abstractive model which is conditioned on the article's topics and based entirely on convolutional neural networks. We demonstrate experimentally that this architecture captures long-range dependencies in a document and recognizes pertinent content, outperforming an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans on the extreme summarization dataset.
10
Wang, Cuiping. "Intelligent Matching Method for College Dormitory Roommates: Chameleon Algorithm Based on Optimized Partitioning." Scalable Computing: Practice and Experience 25, no. 4 (2024): 2889–902. http://dx.doi.org/10.12694/scpe.v25i4.2859.
Full textAbstract:
A chameleon algorithm based on optimized partitioning was studied to solve the intelligent matching problem of college dormitory roommates. Using quantitative research methods, data on personal preferences and lifestyle habits of college students were collected, and the K-center object chameleon algorithm was used for data analysis and roommate matching. Test the algorithm performance on the BBC dataset, compare clustering quality indicators such as entropy, purity, and RI value, and verify the effectiveness of the algorithm. This algorithm can accurately assign students to their respective dormitories, avoiding overlapping situations and achieving excellent matching results. In terms of matching accuracy and running time, the K-center object chameleon algorithm shows superior performance compared to other algorithms. In terms of clustering quality evaluation, comparisons were made from three dimensions: entropy value, purity, and RI value. The experimental results show that the closer the entropy value is to 0, the closer the purity and RI value are to 1, and the better the matching effect. This result further validates the effectiveness of the algorithm in the intelligent matching problem of college dormitory roommates. The matching accuracy of this algorithm on the BBC dataset reached 98.82%, showing better clustering quality than other algorithms in terms of entropy, purity, and RI values. The entropy value approached 0, while the purity and RI values approached 1, verifying the efficiency of matching quality. The chameleon algorithm based on optimized partitioning proposed in the study has shown excellent performance in intelligent matching of college dormitory roommates, with the characteristics of high-precision matching and fast running time. It has important practical significance for improving the quality of life and learning efficiency of college dormitory students, and provides new research methods and ideas for related fields.
Dissertations / Theses on the topic "BBC Dataset"
1
Thompson, Ann Georgina. "Mastering BBC Voices : control and early deployment of a large lexical dataset." Thesis, University of Leeds, 2012. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.590153.
Full textAbstract:
This thesis documents the acquisition, ordering and deployment of lexical material collected for the BBC Voices project, which was conducted during 2004 - 2005. It seeks to present a record of the way in which extensive raw data, generated through an interactive website, were first organised in order to create a coherent and usable database and then applied to initial lexical studies. The work is constructed in two parts. The first part describes the way in which the BBC Voices lexical data were liberated from the encoded format in which they had been collected from respondents, subsequently systematised and finally transferred to a viable database for analysis. Theoretical issues pertaining to the use of the lexical items are identified and discussed in Part 1 and applied in Part 2. The second part of this thesis takes as its focus two studies, using samples of the data in different contexts in order to illustrate their value, accessibility and relevance to linguistic research. The first study is an application to metaphor use in the UK, and the other is geographically based, assessing issues of language stability. The two parts together constitute a synthesis of the formulation and application of a large lexical database. The creation of an accessible lexical resource of this magnitude is of immense value to lexicologists and dialectologists worldwide.
2
Alsabi, Qamar. "Characterizing Basal-Like Triple Negative Breast Cancer using Gene Expression Analysis: A Data Mining Approach." Wright State University / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=wright1578936915199438.
Full textBooks on the topic "BBC Dataset"
1
Belcher, Ellen, and Karina Croucher. Prehistoric Figurines in Anatolia (Turkey). Edited by Timothy Insoll. Oxford University Press, 2017. http://dx.doi.org/10.1093/oxfordhb/9780199675616.013.021.
Full textAbstract:
This chapter discusses prehistoric (c.10,000—5000 bc) figurines from archaeological sites in modern Turkey. Sources and methods of excavation, publication, interpretation, and display are presented and critiqued. We propose a new interpretive method, focusing on manufacture and materials, ambiguities and relationships, gender, and fragmentation. Two case studies of figurine assemblages—Domuztepe and Çatalhöyük—are presented and discussed, demonstrating new possibilities for the interpretation of figurine datasets.
Book chapters on the topic "BBC Dataset"
1
Kopeć, Jakub. "Evaluating Methods of Transferring Large Datasets." In Supercomputing Frontiers. Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-10419-0_7.
Full textAbstract:
AbstractOur society critically depends on data, Big Data. The humanity generates and moves data volumes larger than ever before and their increase is continuously accelerating. The goal of this research is to evaluate tools used for the transfer of large volumes of data. Bulk data transfer is a complex endeavour that requires not only sufficient network infrastructure, but also appropriate software, computing power and storage resources. We report on the series of storage benchmarks conducted using recently developed elbencho tool. The tests were conducted with an objective to understand and avoid I/O bottlenecks during data transfer operation. Subsequently Ethernet and InfiniBand networks performance was compared using Ohio State University bandwidth benchmark (OSU BW) and iperf3 tool. For comparison we also tested traditional (very inefficient) Linux scp and rsync commands as well as tools designed specifically to transfer large datasets more efficiently: bbcp and MDTMFTP. Additionally the impact of using simultaneous multi-threading and Ethernet jumbo frames on transfer rate was evaluated.
2
Lush, Victoria, Jo Lumsden, and Lucy Bastin. "Visualisation of Trust and Quality Information for Geospatial Dataset Selection and Use: Drawing Trust Presentation Comparisons with B2C e-Commerce." In IFIP Advances in Information and Communication Technology. Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-319-95276-5_6.
Full text
3
Mariotti, Ettore, Adarsa Sivaprasad, and Jose Maria Alonso Moral. "Beyond Prediction Similarity: ShapGAP for Evaluating Faithful Surrogate Models in XAI." In Communications in Computer and Information Science. Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-44064-9_10.
Full textAbstract:
AbstractThe growing importance of Explainable Artificial Intelligence (XAI) has highlighted the need to understand the decision-making processes of black-box models. Surrogation, emulating a black-box model (BB) with a white-box model (WB), is crucial in applications where BBs are unavailable due to security or practical concerns. Traditional fidelity measures only evaluate the similarity of the final predictions, which can lead to a significant limitation: considering a WB faithful even when it has the same prediction as the BB but with a completely different rationale. Addressing this limitation is crucial to develop Trustworthy AI practical applications beyond XAI. To address this issue, we introduce ShapGAP, a novel metric that assesses the faithfulness of surrogate models by comparing their reasoning paths, using SHAP explanations as a proxy. We validate the effectiveness of ShapGAP by applying it to real-world datasets from healthcare and finance domains, comparing its performance against traditional fidelity measures. Our results show that ShapGAP enables better understanding and trust in XAI systems, revealing the potential dangers of relying on models with high task accuracy but unfaithful explanations. ShapGAP serves as a valuable tool for identifying faithful surrogate models, paving the way for more reliable and Trustworthy AI applications.
4
Veziroğlu, Merve, Erkan Eziroğlu, and İhsan Ömür Bucak. "PERFORMANCE COMPARISON BETWEEN NAIVE BAYES AND MACHINE LEARNING ALGORITHMS FOR NEWS CLASSIFICATION." In Bayesian Inference - Recent Trends. IntechOpen, 2024. http://dx.doi.org/10.5772/intechopen.1002778.
Full textAbstract:
The surge in digital content has fueled the need for automated text classification methods, particularly in news categorization using natural language processing (NLP). This work introduces a Python-based news classification system, focusing on Naive Bayes algorithms for sorting news headlines into predefined categories. Naive Bayes is favored for its simplicity and effectiveness in text classification. Our objective includes exploring the creation of a news classification system and evaluating various Naive Bayes algorithms. The dataset comprises BBC News headlines spanning technology, business, sports, entertainment, and politics. Analyzing category distribution and headline length provided dataset insights. Data preprocessing involved text cleaning, stop word removal, and feature extraction with Count Vectorization to convert text into machine-readable numerical data. Four Naive Bayes variants were evaluated: Gaussian, Multinomial, Complement, and Bernoulli. Performance metrics such as accuracy, precision, recall, and F1 score were employed, and Naive Bayes algorithms were compared to other classifiers like Logistic Regression, Random Forest, Linear Support Vector Classification (SVC), Multi-Layer Perceptron (MLP) Classifier, Decision Trees, and K-Nearest Neighbors. The MLP Classifier achieved the highest accuracy, underscoring its effectiveness, while Multinomial and Complement Naive Bayes proved robust in news classification. Effective data preprocessing played a pivotal role in accurate categorization. This work contributes insights into Naive Bayes algorithm performance in news classification, benefiting NLP and news categorization systems.
5
Goel, Lavika, Lavanya B., and Pallavi Panchal. "Hybridization of Biogeography-Based Optimization and Gravitational Search Algorithm for Efficient Face Recognition." In Advances in Computational Intelligence and Robotics. IGI Global, 2019. http://dx.doi.org/10.4018/978-1-5225-7338-8.ch012.
Full textAbstract:
This chapter aims to apply a novel hybridized evolutionary algorithm to the application of face recognition. Biogeography-based optimization (BBO) has some element of randomness to it that apart from improving the feasibility of a solution could reduce it as well. In order to overcome this drawback, this chapter proposes a hybridization of BBO with gravitational search algorithm (GSA), another nature-inspired algorithm, by incorporating certain knowledge into BBO instead of the randomness. The migration procedure of BBO that migrates SIVs between solutions is done between solutions only if the migration would lead to the betterment of a solution. BBO-GSA algorithm is applied to face recognition with the LFW (labelled faces in the wild) and ORL datasets in order to test its efficiency. Experimental results show that the proposed BBO-GSA algorithm outperforms or is on par with some of the nature-inspired techniques that have been applied to face recognition so far by achieving a recognition rate of 80% with the LFW dataset and 99.75% with the ORL dataset.
6
Rashid, Tarik A., Mohammad K. Hassan, Mokhtar Mohammadi, and Kym Fraser. "Improvement of Variant Adaptable LSTM Trained With Metaheuristic Algorithms for Healthcare Analysis." In Advances in Medical Technologies and Clinical Practice. IGI Global, 2019. http://dx.doi.org/10.4018/978-1-5225-7796-6.ch006.
Full textAbstract:
Recently, the population of the world has increased along with health problems. Diabetes mellitus disease as an example causes issues to the health of many patients globally. The task of this chapter is to develop a dynamic and intelligent decision support system for patients with different diseases, and it aims at examining machine-learning techniques supported by optimization techniques. Artificial neural networks have been used in healthcare for several decades. Most research works utilize multilayer layer perceptron (MLP) trained with back propagation (BP) learning algorithm to achieve diabetes mellitus classification. Nonetheless, MLP has some drawbacks, such as, convergence, which can be slow; local minima can affect the training process. It is hard to scale and cannot be used with time series data sets. To overcome these drawbacks, long short-term memory (LSTM) is suggested, which is a more advanced form of recurrent neural networks. In this chapter, adaptable LSTM trained with two optimizing algorithms instead of the back propagation learning algorithm is presented. The optimization algorithms are biogeography-based optimization (BBO) and genetic algorithm (GA). Dataset is collected locally and another benchmark dataset is used as well. Finally, the datasets fed into adaptable models; LSTM with BBO (LSTMBBO) and LSTM with GA (LSTMGA) for classification purposes. The experimental and testing results are compared and they are promising. This system helps physicians and doctors to provide proper health treatment for patients with diabetes mellitus. Details of source code and implementation of our system can be obtained in the following link “https://github.com/hamakamal/LSTM.”
7
Rashid, Tarik A., Mohammad K. Hassan, Mokhtar Mohammadi, and Kym Fraser. "Improvement of Variant Adaptable LSTM Trained With Metaheuristic Algorithms for Healthcare Analysis." In Research Anthology on Artificial Intelligence Applications in Security. IGI Global, 2021. http://dx.doi.org/10.4018/978-1-7998-7705-9.ch048.
Full textAbstract:
Recently, the population of the world has increased along with health problems. Diabetes mellitus disease as an example causes issues to the health of many patients globally. The task of this chapter is to develop a dynamic and intelligent decision support system for patients with different diseases, and it aims at examining machine-learning techniques supported by optimization techniques. Artificial neural networks have been used in healthcare for several decades. Most research works utilize multilayer layer perceptron (MLP) trained with back propagation (BP) learning algorithm to achieve diabetes mellitus classification. Nonetheless, MLP has some drawbacks, such as, convergence, which can be slow; local minima can affect the training process. It is hard to scale and cannot be used with time series data sets. To overcome these drawbacks, long short-term memory (LSTM) is suggested, which is a more advanced form of recurrent neural networks. In this chapter, adaptable LSTM trained with two optimizing algorithms instead of the back propagation learning algorithm is presented. The optimization algorithms are biogeography-based optimization (BBO) and genetic algorithm (GA). Dataset is collected locally and another benchmark dataset is used as well. Finally, the datasets fed into adaptable models; LSTM with BBO (LSTMBBO) and LSTM with GA (LSTMGA) for classification purposes. The experimental and testing results are compared and they are promising. This system helps physicians and doctors to provide proper health treatment for patients with diabetes mellitus. Details of source code and implementation of our system can be obtained in the following link “https://github.com/hamakamal/LSTM.”
8
Rashid, Tarik A., Mohammad K. Hassan, Mokhtar Mohammadi, and Kym Fraser. "Improvement of Variant Adaptable LSTM Trained With Metaheuristic Algorithms for Healthcare Analysis." In Research Anthology on Artificial Intelligence Applications in Security. IGI Global, 2021. http://dx.doi.org/10.4018/978-1-7998-7705-9.ch048.
Full textAbstract:
Recently, the population of the world has increased along with health problems. Diabetes mellitus disease as an example causes issues to the health of many patients globally. The task of this chapter is to develop a dynamic and intelligent decision support system for patients with different diseases, and it aims at examining machine-learning techniques supported by optimization techniques. Artificial neural networks have been used in healthcare for several decades. Most research works utilize multilayer layer perceptron (MLP) trained with back propagation (BP) learning algorithm to achieve diabetes mellitus classification. Nonetheless, MLP has some drawbacks, such as, convergence, which can be slow; local minima can affect the training process. It is hard to scale and cannot be used with time series data sets. To overcome these drawbacks, long short-term memory (LSTM) is suggested, which is a more advanced form of recurrent neural networks. In this chapter, adaptable LSTM trained with two optimizing algorithms instead of the back propagation learning algorithm is presented. The optimization algorithms are biogeography-based optimization (BBO) and genetic algorithm (GA). Dataset is collected locally and another benchmark dataset is used as well. Finally, the datasets fed into adaptable models; LSTM with BBO (LSTMBBO) and LSTM with GA (LSTMGA) for classification purposes. The experimental and testing results are compared and they are promising. This system helps physicians and doctors to provide proper health treatment for patients with diabetes mellitus. Details of source code and implementation of our system can be obtained in the following link “https://github.com/hamakamal/LSTM.”
9
Subha Ramakrishnan, Manuskandan, and Nagarajan Ganapathy. "Extreme Gradient Boosting Based Improved Classification of Blood-Brain-Barrier Drugs." In Studies in Health Technology and Informatics. IOS Press, 2022. http://dx.doi.org/10.3233/shti220612.
Full textAbstract:
In this study, the analysis based on boosting approach namely linear and tree method are explored in extreme gradient boosting (XGBoost) to classify blood brain barrier drugs using clinical phenotype. The clinical phenotype features of BBB drugs are Public available SIDER dataset. The clinical features namely drug’s side effect, drug’s indication and the combination is fed to XGBoost. Results shows that the proposed approach is able to discriminate BBB drugs. The combination of XGBoost with tree boosting is found to be most accurate (F1=78.5%) in classifying BBB drugs. This method of tree boosting in XGBoost may be extended to access the drugs for precision medicine.
10
Spanakis Gerasimos, Weiss Gerhard, and Roefs Anne. "Bagged Boosted Trees for Classification of Ecological Momentary Assessment Data." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2016. https://doi.org/10.3233/978-1-61499-672-9-1612.
Full textAbstract:
Ecological Momentary Assessment (EMA) data is organized in multiple levels (per-subject, per-day, etc.) and this particular structure should be taken into account in machine learning algorithms used in EMA like decision trees and its variants. We propose a new algorithm called BBT (standing for Bagged Boosted Trees) that is enhanced by a over/under sampling method and can provide better estimates for the conditional class probability function. Experimental results on a real-world dataset show that BBT can benefit EMA data classification and performance.
Conference papers on the topic "BBC Dataset"
1
Yunus, Said, Cengiz Hark, and Fatih Okumuş. "Comparison of Extractive and Abstractive Approaches in Automatic Text Summarization: An Evaluation on BBC-News and PubMed Datasets." In 2024 8th International Artificial Intelligence and Data Processing Symposium (IDAP). IEEE, 2024. http://dx.doi.org/10.1109/idap64064.2024.10710907.
Full text
2
Woollam, Richard C., Joshua Owen, Yasmin Hayatgheib, and Richard Barker. "Corrosion Inhibitor Surfactant Optimization: Part 1 – Inhibitor Efficiency." In CONFERENCE 2022. AMPP, 2022. https://doi.org/10.5006/c2022-18043.
Full textAbstract:
Abstract A homologous series of alkyldimethylbenzylammonium chlorides (BAC) was used as a model for a composite commercial corrosion inhibitor formulation. The homologous series consisted of three BACs with C12, C14 and C16 tail lengths. A 10-point, three-component mixture design experimentation was performed to determine the composition for achieving the ‘optimal’ corrosion inhibitor performance. The CMC of each mixture combination (single, binary or ternary) was firstly evaluated using the lipophilic dye Nile Red. The corrosion inhibition performance of each mixture was subsequently determined at the respective CMC in a 1 wt.% NaCl solution under approximately 1 bar partial pressure of carbon dioxide (CO2) at 30 °C. In order to calculate the corrosion inhibitor efficiency for each mixture of components, the corrosion rates before and after the injection of the corrosion inhibitor mixture were measured by linear polarization resistance (LPR). The measured CMC values and corrosion inhibitor efficiencies for each mixture were plotted on a ternary diagram and a cubic response curve fitted to each dataset. The ‘peak’ in the mixture CMC response curve and the peak in the corrosion inhibitor efficiency response curve were then compared, and an optimal composition was estimated from the mixture response analysis.
3
Gushchin, Alexander, Anastasia Antsiferova, and Dmitriy Vatolin. "Shot Boundary Detection Method Based on a New Extensive Dataset and Mixed Features." In 31th International Conference on Computer Graphics and Vision. Keldysh Institute of Applied Mathematics, 2021. http://dx.doi.org/10.20948/graphicon-2021-3027-188-198.
Full textAbstract:
Shot boundary detection in video is one of the key stages of video data processing. A new method for shot boundary detection based on several video features, such as color histograms and object boundaries, has been proposed. The developed algorithm was tested on the open BBC Planet Earth [1] and RAI [2] datasets, and the MSU CC datasets, based on videos used in the video codec comparison conducted at MSU, as well as videos from the IBM set, were also plotted. The total dataset for algorithm development and testing exceeded the known TRECVID datasets. Based on the test results, the proposed algorithm for scene change detection outperformed its counterparts with a final F-score of 0.9794.
4
Obika, F. C., N. U. Okereke, F. M. Eze, and B. C. Ekeh. "Unveiling the Potential of Random Undersampling in Geothermal Lithology Classification for Improved Geothermal Resource Exploration." In SPE Nigeria Annual International Conference and Exhibition. SPE, 2024. http://dx.doi.org/10.2118/221656-ms.
Full textAbstract:
Abstract Lithology classification in geothermal exploration has been of great significance in the understanding of subsurface geology and geophysics, which can enhance the exploration and exploitation of geothermal resources. Alongside other known industrial means of classifying lithologies, the application of machine learning models has shown viable prospects in this regard. However, there seems to be poor accuracy in the performance of some of these models due to class imbalance associated with the lithologies to be classified. Hence, in this study, robust class imbalance handling techniques were investigated to efficiently classify lithology in a geothermal field. The investigated techniques which involved Synthetic Minority Oversampling Technique (SMOTE), Random Oversampling (RO), Random Undersampling (RU), and the Near Miss Undersampling (NMU) Techniques, were each employed with two ensemble bagging methods; Random Forest Classifier (RFC) and Balanced Bagging Classifier (BBC). F1 score was the key evaluation metric, as it considers both precision and recall, giving a more comprehensive picture of the models’ performance. It was observed that by leveraging real-time drilling data such as mud flow in, rate of penetration (ROP), surface torque, pump pressure and rotary speed as input parameters, RFC performed better with the resampling techniques than BBC did. Moreover, RFC combined with RU greatly outperformed other combination techniques in the prediction of the geothermal lithology with an F1 score of 93.6% for the minority class (Plutonic) and 99.3% for the majority class (Alluvium) on the testing dataset, while other combinations had F1 scores of less than 37%. This solution alongside other vital insights from this study, showed that class imbalance handling techniques can be efficiently adopted towards building more robust machine learning models for geothermal resource exploration with prevailing high temperature and unfavorable subsurface conditions that limit the use of known traditional methods.
5
Palma, Guillermo, Maria-Esther Vidal, Eric Haag, Louiqa Raschid, and Andreas Thor. "Measuring Relatedness Between Scientific Entities in Annotation Datasets." In BCB'13: ACM-BCB2013. ACM, 2013. http://dx.doi.org/10.1145/2506583.2506651.
Full text
6
Blaszczak-Bak, Wioleta, Andrzej Dumalski, and Anna Sobieraj-Zlobinska. "Application of the Optimum Dataset Method in Archeological Studies on Barrows." In 2018 Baltic Geodetic Congress (BGC Geomatics). IEEE, 2018. http://dx.doi.org/10.1109/bgc-geomatics.2018.00019.
Full text
7
Kolias, Vasilis, Ioannis Anagnostopoulos, and Eleftherios Kayafas. "A Covering Classification Rule Induction Approach for Big Datasets." In 2014 IEEE/ACM International Symposium on Big Data Computing (BDC). IEEE, 2014. http://dx.doi.org/10.1109/bdc.2014.17.
Full text
8
Koontz, Jared, Matthew Malensek, and Sangmi Pallickara. "GeoLens: Enabling Interactive Visual Analytics over Large-Scale, Multidimensional Geospatial Datasets." In 2014 IEEE/ACM International Symposium on Big Data Computing (BDC). IEEE, 2014. http://dx.doi.org/10.1109/bdc.2014.12.
Full text
9
Agapito, Giuseppe, Pietro Hiram Guzzi, and Mario Cannataro. "Using GenotypeAnalytics to Analyze Pharmacogenomic Datasets." In BCB '17: 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. ACM, 2017. http://dx.doi.org/10.1145/3107411.3108177.
Full text
10
Blaszczak-Bak, Wioleta, and Anna Sobieraj. "Application of Regression Line to Obtain Specified Number of Points in Reduced Large Datasets." In 2016 Baltic Geodetic Congress (BGC Geomatics). IEEE, 2016. http://dx.doi.org/10.1109/bgc.geomatics.2016.16.
Full textReports on the topic "BBC Dataset"
1
Abrahamson, Norman, Nicolas Kuehn, Zeynep Gulerce, et al. Update of the BC Hydro Subduction Ground-Motion Model using the NGA- Subduction Dataset. Pacific Earthquake Engineering Research Center, University of California, Berkeley, CA, 2018. http://dx.doi.org/10.55461/oycd7434.
Full textAbstract:
An update to the BCHydro ground-motion model for subduction earthquakes has been developed using the 2018 PEER NGA-SUB dataset. The selected subset includes over 70,000 recordings from 1880 earthquakes. The update modifies the BCHydro model to include regional terms for the VS30 scaling, large distance (linear R) scaling, and constant terms, which is consistent with the regionalization approach used in the NGA-W2 ground-motion models. A total of six regions were considered: Cascadia, Central America, Japan, New Zealand, South America, and Taiwan. Region- independent terms are used for the small-magnitude scaling, geometrical spreading, depth to top of rupture (ZTOR ) scaling, and slab/interface scaling. The break in the magnitude scaling at large magnitudes for slab earthquakes is based on thickness of the slab and is subduction-zone dependent. The magnitude scaling for large magnitudes is constrained based on finite-fault simulations as given in the 2016 BCHydro model. Nonlinear site response is also constrained to be the same as the 2016 BCHydro model. The sparse ground-motion data from Cascadia show a factor of 2–3 lower ground motions than for other regions. Without a sound physical basis for this large reduction, the Cascadia model is adjusted to be consistent with the average from all regions for the center range of the data: M = 6.5, R = 100 km, VS30 = 400 m/sec. Epistemic uncertainty is included using the scaled backbone approach, with high and low models based on the range of average ground motions for the different regions. For the Cascadia region, the ground-motion model is considered applicable to distance up to 1000 km, magnitudes of 5.0 to 9.5, and periods from 0 to 10 sec. The intended use of this update is to provide an improved ground-motion model for consideration for use in the development of updated U.S. national hazard maps. This update ground-motion model will be superseded by the NGA-SUB ground-motion model when they are completed.
2
Johnson, Timothy, Judith Robinson, and Vicky Freedman. Surface 3D Electrical Resistivity Tomography Inversion of 2005 BC Cribs and Trenches Datasets. Office of Scientific and Technical Information (OSTI), 2022. http://dx.doi.org/10.2172/1846148.
Full text
3
Douglas, K., and A. Podhorodeski. British Columbia coastal anchor marks. Natural Resources Canada/CMSS/Information Management, 2023. http://dx.doi.org/10.4095/331346.
Full textAbstract:
The marks left in the seabed by the commercial anchoring process can be seen as linear features in high-resolution multibeam bathymetry data. These features have been digitized to polylines for individual marks and polygons for anchor scour zones for British Columbia's (BC) commercial anchorages. They are made available via the Federal Geospatial Platform (FGP) for use in a Geographical Information System (GIS). This feature dataset is complete for published BC commercial anchorages and the multibeam bathymetry data available in 2021. It does not represent features produced since the collection of each multibeam bathymetry survey nor any features infilled since. The data are intended to be used for scientific research to better understand the cumulative impacts to the seabed from commercial anchoring at a 1:5000 scale or greater.
4
Kingston, A. W., A. Mort, C. Deblonde, and O H Ardakani. Hydrogen sulfide (H2S) distribution in the Triassic Montney Formation of the Western Canadian Sedimentary Basin. Natural Resources Canada/CMSS/Information Management, 2022. http://dx.doi.org/10.4095/329797.
Full textAbstract:
The Montney Formation is a highly productive hydrocarbon reservoir with significant reserves of hydrocarbon gases and liquids making it of great economic importance to Canada. However, high concentrations of hydrogen sulfide (H2S) have been encountered during exploration and development that have detrimental effects on environmental, health, and economics of production. H2S is a highly toxic and corrosive gas and therefore it is essential to understand the distribution of H2S within the basin in order to enhance identification of areas with a high risk of encountering elevated H2S concentrations in order to mitigate against potential negative impacts. Gas composition data from Montney wells is routinely collected by operators for submission to provincial regulators and is publicly available. We have combined data from Alberta (AB) and British Columbia (BC) to create a basin-wide database of Montney H2S concentrations. We then used an iterative quality control and quality assurance process to produce a dataset that best represents gas composition in reservoir fluids. This included: 1) designating gas source formation based on directional surveys using a newly developed basin-wide 3D model incorporating AGS's Montney model of Alberta with a model in BC, which removes errors associated with reported formations; 2) removed injection and disposal wells; 3) assessed wells with the 50 highest H2S concentrations to determine if gas composition data is accurate and reflective of reservoir fluid chemistry; and 4) evaluated spatially isolated extreme values to ensure data accuracy and prevent isolated highs from negatively impacting data interpolation. The resulting dataset was then used to calculate statistics for each x, y location to input into the interpolation process. Three interpolations were constructed based on the associated phase classification: H2S in gas, H2S in liquid (C7+), and aqueous H2S. We used Empirical Bayesian Kriging interpolation to generate H2S distribution maps along with a series of model uncertainty maps. These interpolations illustrate that H2S is heterogeneously distributed across the Montney basin. In general, higher concentrations are found in AB compared with BC with the highest concentrations in the Grande Prairie region along with several other isolated region in the southeastern portion of the basin. The interpolations of H2S associated with different phases show broad similarities. Future mapping research will focus on subdividing intra-Montney sub-members plus under- and overlying strata to further our understanding of the role migration plays in H2S distribution within the Montney basin.
5
Chepeliev, Maksym. Development of the Air Pollution Database for the GTAP 10A Data Base. GTAP Research Memoranda, 2020. http://dx.doi.org/10.21642/gtap.rm33.
Full textAbstract:
The purpose of this note is to document data sources and steps used to develop the air pollution database for the GTAP Data Base Version 10A. Emissions for nine substances are reported in the database: black carbon (BC), carbon monoxide (CO), ammonia (NH3), non-methane volatile organic compounds (NMVOC), nitrogen oxides (NOx), organic carbon (OC), particulate matter 10 (PM10), particulate matter 2.5 (PM2.5) and sulfur dioxide (SO2). The dataset covers four reference years – 2004, 2007, 2011 and 2014. EDGAR Version 5.0 database is used as the main data source. To assist with emissions redistribution across consumption-based sources, IIASA GAINS-based model and IPCC-derived emission factors are applied. Each emission flow is associated with one of the four sets of emission drivers: output by industries, endowment by industries, input use by industries and household consumption. In addition, emissions from land use activities (biomass burning) are estimated by land cover types. These emissions are reported separately without association with emission drivers.
6
Mackie, S. J., C. M. Furlong, P. K. Pedersen, and O. H. Ardakani. Stratigraphy, facies heterogeneities, and structure in the Montney Formation of northeastern British Columbia: relation to H2S distribution. Natural Resources Canada/CMSS/Information Management, 2022. http://dx.doi.org/10.4095/329796.
Full textAbstract:
In the last decade, the Lower Triassic Montney Formation of the Western Canada Sedimentary Basin (WCSB) has undergone significant development, providing a rich dataset to study structural, stratigraphic, and facies control on the variations in hydrogen sulphide (H2S) gas content. Splitting the siltstone dominated Montney into the three regional members (i.e., Lower Montney, Middle Montney, and Upper Montney) allows for detailed analysis on the enrichment of H2S within a local-scale study area in northeastern British Columbia (BC). Within this study area, Upper Montney H2S content increases within individual parasequences both up-dip and towards the east. In addition to potential up-dip migration, there may be greater sulphur-bearing components in the east, allowing for the sulphate reduction required to generate H2S. The overlying Middle Triassic thins eastward, providing proximity to the overlying anhydrite-rich beds of the Upper Triassic Charlie Lake Formation. Further, the overlying Middle Triassic Sunset Prairie Formation has an erosional edge that corresponds with eastern elevated H2S concentrations within the Upper Montney unit. Mapped structures are syn-depositional to the Middle Triassic, potentially providing conduits for early sulphate-rich fluid migration. In the Middle and Lower Montney, elevated H2S generally occurs with proximity to the top of the Permian Belloy Formation. Within this study area, limited Lower Montney data is available and thus needs to be further corroborated with regional data. Both the Middle and Lower Montney display elevated H2S in trends that generally align with mapped faults. The faults may have acted as conduits for sulphate-rich fluids to migrate during early burial then migrate laterally through facies that may have been permeable during early burial, such as the carbonate-rich facies at the boundary between the Middle and Lower Montney. Further core and isotope analyses are required to fully understand this relationship.
7
Huntley, D., D. Rotheram-Clarke, R. Cocking, J. Joseph, and P. Bobrowsky. Current research on slow-moving landslides in the Thompson River valley, British Columbia (IMOU 5170 annual report). Natural Resources Canada/CMSS/Information Management, 2022. http://dx.doi.org/10.4095/331175.
Full textAbstract:
Interdepartmental Memorandum of Understanding (IMOU) 5170 between Natural Resources Canada (NRCAN), the Geological Survey of Canada (GSC) and Transport Canada Innovation Centre (TC-IC) aims to gain new insight into slow-moving landslides, and the influence of climate change, through testing conventional and emerging monitoring technologies. IMOU 5107 focuses on strategically important sections of the national railway network in the Thompson River valley, British Columbia (BC), and the Assiniboine River valley along the borders of Manitoba (MN) and Saskatchewan (SK). Results of this research are applicable elsewhere in Canada (e.g., the urban-rural-industrial landscapes of the Okanagan Valley, BC), and around the world where slow-moving landslides and climate change are adversely affecting critical socio-economic infrastructure. Open File 8931 outlines landslide mapping and changedetection monitoring protocols based on the successes of IMOU 5170 and ICL-IPL Project 202 in BC. In this region, ice sheets, glaciers, permafrost, rivers and oceans, high relief, and biogeoclimatic characteristics contribute to produce distinctive rapid and slow-moving landslide assemblages that have the potential to impact railway infrastructure and operations. Bedrock and drift-covered slopes along the transportation corridors are prone to mass wasting when favourable conditions exist. In high-relief mountainous areas, rapidly moving landslides include rock and debris avalanches, rock and debris falls, debris flows and torrents, and lahars. In areas with moderate to low relief, rapid to slow mass movements include rockslides and slumps, debris or earth slides and slumps, and earth flows. Slow-moving landslides include rock glaciers, rock and soil creep, solifluction, and lateral spreads in bedrock and surficial deposits. Research efforts lead to a better understanding of how geological conditions, extreme weather events and climate change influence landslide activity along the national railway corridor. Combining field-based landslide investigation with multi-year geospatial and in-situ time-series monitoring leads to a more resilient railway national transportation network able to meet Canada's future socioeconomic needs, while ensuring protection of the environment and resource-based communities from landslides related to extreme weather events and climate change. InSAR only measures displacement in the east-west orientation, whereas UAV and RTK-GNSS change-detection surveys capture full displacement vectors. RTK-GNSS do not provide spatial coverage, whereas InSAR and UAV surveys do. In addition, InSAR and UAV photogrammetry cannot map underwater, whereas boat-mounted bathymetric surveys reveal information on channel morphology and riverbed composition. Remote sensing datasets, consolidated in a geographic information system, capture the spatial relationships between landslide distribution and specific terrain features, at-risk infrastructure, and the environmental conditions expected to correlate with landslide incidence and magnitude. Reliable real-time monitoring solutions for critical railway infrastructure (e.g., ballast, tracks, retaining walls, tunnels, and bridges) able to withstand the harsh environmental conditions of Canada are highlighted. The provision of fundamental geoscience and baseline geospatial monitoring allows stakeholders to develop robust risk tolerance, remediation, and mitigation strategies to maintain the resilience and accessibility of critical transportation infrastructure, while also protecting the natural environment, community stakeholders, and Canadian economy. We propose a best-practice solution involving three levels of investigation to describe the form and function of the wide range of rapid and slow-moving landslides occurring across Canada that is also applicable elsewhere. Research activities for 2022 to 2025 are presented by way of conclusion.
8
Tel-Zur, Neomi, and Jeffrey J. Doyle. Role of Polyploidy in Vine Cacti Speciation and Crop Domestication. United States Department of Agriculture, 2012. http://dx.doi.org/10.32747/2012.7697110.bard.
Full textAbstract:
1. Abstract: Over the past 25 years, vine cacti of the genera Hylocereus and Selenicereus have been introduced into Israel and southern California as new exotic fruit crops. The importance of these crops lies in their high water use efficiency and horticultural potential as exotic fruit crops. Our collaboration focused on the cytological, molecular and evolutionary aspects of vine cacti polyploidization to confront the agricultural challenge of genetic improvement, ultimately to improve success of vine cacti as commercial fruit crop plants. More specifically, we worked on the: 1- Identification of the putative ancestor(s) of the tetraploid H. megalanthus; 2- Determination of the number of origins of H. megalanthus (single vs. multiple origins of polyploidy); 3- Cytogenetic analysis of BC1 and F1 hybrids; 4- Determination of important agricultural traits and the selection of superior hybrids for cultivation. The plant material used in this study comprised interspecific Hylocereus F1 and first backcross (BC1) hybrids, nine Hylocereus species (58 genotypes), nine Selenicereus species (14 genotypes), and four Epiphyllum genotypes. Two BC1 hexaploids (BC-023 and BC-031) were obtained, a high ploidy level that can be explained only by a fertilization event between one unreduced female gamete from the triploid hybrid and a balanced gamete from the pollen donor, the diploid H. monacanthus. These findings are scientific evidence that support the possibility that “hybridization followed by chromosome doubling” could also occur in nature. Cytomixis, the migration of chromatin between adjacent cells through connecting cytoplasmatic channels, was observed in vine cacti hybrids and may thus imply selective DNA elimination in response to the allopolyploidization process. Evidence from plastid and nrDNA internal transcribed spacers (ITS) sequences support the placement of H. megalanthus within a monophyletic Hylocereus group. Furthermore, both plastid and ITS datasets are most consistent with a conclusion that this tetraploid species is an autopolyploid, despite observations that the species appears to be morphologically intermediate between Hylocereus and Selenicereus. Although the possibility of very narrow allopolyploidly (i.e., derivation from parents that are barely diverged from each other such as closely related species in the same genus) cannot be ruled out entirely based on our data (in part due to the unavailability of Hylocereus species considered to be morphologically the closest relatives of H. megalanthus), the possibility of H. megalanthus representing an intergeneric cross (i.e., Hylocereus × Selenicereus) seems extremely unlikely. Interestingly, the process of homogenization of ITS sequences (concerted evolution) is either incomplete or lacking in both Hylocereus and Selenicereus, and the inclusion of several artificial hybrids in the molecular study revealed the potential for biparental plastid inheritance in Hylocereus. The most important agricultural implication of this research project was the information collected for F1 and BC1 hybrids. Specifically, this project concluded with the selection of four superior hybrids in terms of fruit quality and potential yields under extreme high temperatures. These selected hybrids are self-compatible, avoiding the need for hand cross pollination to set fruits, thus reducing manpower costs. We recently offered these hybrids to growers in Israel for prioritized rapid evaluation and characterization.