Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
7,150
result(s) for
"Maschinelles Lernen"
Sort by:
A new red wine prediction framework using machine learning
Red wine has become an integral part of people's lives and culture. Modeling the red wine quality is crucial. We propose a new framework to predict the red wine quality ratings. MF-DCCA was utilized to quantitatively investigate the cross-correlation between quality and physicochemical data. The long-range correlations importance was ranked. We compared two machine learning algorithms with other common algorithms implemented on the red wine data set, which was taken from UC Irvine Machine Learning Repository to ensure the reliability and performance. These data sets contain 1599 instances for red wine with 11 features of physicochemical data. Our model has better performance than other results.
Journal Article
A multivariate approach to investigate the associations of electrophysiological indices with schizophrenia clinical and functional outcome
Different electrophysiological (EEG) indices have been investigated as possible biomarkers of schizophrenia. However, these indices have a very limited use in clinical practice, as their associations with clinical and functional outcomes remain unclear. This study aimed to investigate the associations of multiple EEG markers with clinical variables and functional outcomes in subjects with schizophrenia (SCZs).
Resting-state EEGs (frequency bands and microstates) and auditory event-related potentials (MMN-P3a and N100-P3b) were recorded in 113 SCZs and 57 healthy controls (HCs) at baseline. Illness- and functioning-related variables were assessed both at baseline and at 4-year follow-up in 61 SCZs. We generated a machine-learning classifier for each EEG parameter (frequency bands, microstates, N100-P300 task, and MMN-P3a task) to identify potential markers discriminating SCZs from HCs, and a global classifier. Associations of the classifiers' decision scores with illness- and functioning-related variables at baseline and follow-up were then investigated.
The global classifier discriminated SCZs from HCs with an accuracy of 75.4% and its decision scores significantly correlated with negative symptoms, depression, neurocognition, and real-life functioning at 4-year follow-up.
These results suggest that a combination of multiple EEG alterations is associated with poor functional outcomes and its clinical and cognitive determinants in SCZs. These findings need replication, possibly looking at different illness stages in order to implement EEG as a possible tool for the prediction of poor functional outcome.
Journal Article
Beginning artificial intelligence with the Raspberry Pi
\"A gentle introduction to the world of Artificial Intelligence (AI) using the Raspberry Pi as the computing platform. Most of the major AI topics will be explored, including expert systems, machine learning both shallow and deep, fuzzy logic control, and more! AI in action will be demonstrated using the Python language on the Raspberry Pi. The Prolog language will also be introduced and used to demonstrate fundamental AI concepts. In addition, the Wolfram language will be used as part of the deep machine learning demonstrations. A series of projects will walk readers through how to implement AI concepts with the Raspberry Pi. Minimal expense is needed for the projects as only a few sensors and actuators will be required. Beginners and hobbyists can jump right in to creating AI projects with the Raspberry Pi using this book.\"--Back cover.
Book
IndoAcro: An Indonesian Acronym and Expansion Repository with Data Auto-Update Implementation
IndoAcro is an Indonesian acronym and expansion repository created using machine learning and big data technology. The repository can be publicly accessed from www.indoacro.cs.unsyiah.ac.id. Six important steps of IndoAcro have been developed and implemented, which consists of (1) data crawling, (2) data cleaning, (3) generating candidate pairs of acronym and expansion, (4) generating numerical features, (5) classifying the candidate pairs, and (6) filtering the classification results. In this study, we introduce and analyze the implementation of data auto-update for IndoAcro. Since it was developed, IndoAcro has 2,232 pairs of acronym and expansion, collected from more than 50 thousand online news articles. Because no auto-update approach has been implemented previously, the number of acronym and expansion pairs in the database is monotonous, dull, and static. In this study, we introduce and analyze the implementation of data auto-update for IndoAcro. We have analyzed and evaluated the data auto-update process for 180 days, each process consists of 2 days interval. We found that the data auto-update approach has successfully implemented and updated the data for IndoAcro. We collected 1,639 pairs of acronym and expansion in the first run, 343 and 224 pairs in the second and third runs.
Journal Article
Inverse molecular design using machine learning: Generative models for matter engineering
The discovery of new materials can bring enormous societal and technological progress. In this context, exploring completely the large space of potential materials is computationally intractable. Here, we review methods for achieving inverse design, which aims to discover tailored materials from the starting point of a particular desired functionality. Recent advances from the rapidly growing field of artificial intelligence, mostly from the subfield of machine learning, have resulted in a fertile exchange of ideas, where approaches to inverse molecular design are being proposed and employed at a rapid pace. Among these, deep generative models have been applied to numerous classes of materials: rational design of prospective drugs, synthetic routes to organic compounds, and optimization of photovoltaics and redox flow batteries, as well as a variety of other solid-state materials.
Journal Article
Identification of connected arguments based on reasoning schemes \from expert opinion\
The work presented describes a combined approach to the partial extraction of the argumentative structure of a text that can be employed in the absence of sufficient annotated data to apply efficiently the machine learning methods for the direct detection of arguments and their relations. In this case, argument identification is performed by using the patterns of argumentation indicators created by a linguist and automatically expanded. These patterns enable the recognition of specific argument types with fine precision. In this study, arguments \"from expert opinion\" serve as such a pivot type. Besides, potential relations between recognized arguments are analyzed by dividing the text into superphrasal units (fragments united by one topic). The criterion for connecting arguments in an argumentative structure is their inclusion in the same superphrasal unit. An experiment for identifying potentially related arguments is conducted on a set of popular science texts with a minimum size of 1000 words.
Journal Article
A software defect prediction method based on sampling and integration
This paper mainly analyzes the characteristics of software defect prediction from the perspective of machine learning, and proposes a semi-supervised software defect prediction method based on sampling and integration for the problem of class imbalance in software defect data and the incomplete classification of data sets. SISDP). SISDP firstly constructs a robust KNN marking model by taking a balanced sample of samples to mark a batch of unmarked data, and then iteratively adds the newly marked data to the original data set for the next marking model. , iterate until the data is marked. For the marked data set, the hybrid sampling algorithm is used to obtain the training set, and the integrated classification model composed of the multi-classification algorithm is classified and trained. SISDP not only reduces the interference of a few classes on the marking process, but also improves the generalization ability of the defect prediction model.
Journal Article
Predict New App Quality By Using Machine Learning
Increasingly, individuals and companies are developing applications and selling them online. Competition between different companies has led to tens of thousands of applications being put on the market for users to choose from. There are numerous functions on the market to give app evaluation. For users, they do not need to contemplate how to select an app for a long time, because user comments and ratings can give them a clear instruction for user to select an app they need from abundant apps. As a result, we would like to explore the possibility. Hence, we think that we can make a prediction function for the prospect of the app market of whether we can make a prediction function for the app market, akin to a weather forecast or stock market forecast. Our group not only wants to know what the future of the app market is, but also want to find out why some high-quality apps are not getting the downloads they should. With the development of AR and VR technology, the future application will combine with these technology to bring user a immersive experience. In addition, high quality application without AR or VR are less competitive. We plan to answer these questions by using machine learning techniques.
Journal Article