Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- Machine learning applied to an intelligent and adaptive robotic inspection stationPublication . Variz, Luis; Piardi, Luis; Rodrigues, Pedro João; Leitão, PauloIndustry 4.0 promotes the use of emergent technologies, such as Internet of Things (IoT), Big Data, artificial intelligence (AI) and cloud computing, sustained by cyber-physical systems to reach smart factories. The idea is to decen-tralize the production systems and allow to reach monitoring, adaptation and optimization to be made in real time, based on the large amount of data available at shop floor that feed the use of machine learning techniques. This technological revolution will bring significant productivity gains, resources savings and reduced maintenance costs, as machines will have information to operate more efficiently, adaptable and following demand fluctuations. This paper discusses the application of supervised Machine Learning techniques allied with artificial vision, to implement an intelligent, collaborative and adaptive robotic inspection station, which carries out the quality control of Human Machine Interface (HMI) consoles, equipped with pressure buttons and LCD displays. Machine learning techniques were applied for the recognition of the operator's face, to classify the type of HMI console to be inspected, to classify the state condition of the pressure buttons and detect anomalies in the LCD displays. The developed solution reaches promising results, with almost 100% accuracy in the correct classification of the consoles and anomalies in the pressure buttons, and also high values in the detection of defects in the LCD displays.
- Fall detection systems to be used by elderly peoplePublication . Igrejas, Getúlio; Amaral, Joana S.; Rodrigues, Pedro JoãoStatistics show that, each year, falls affect tens of millions of elderly people throughout the world. Falls are the leading cause of injury deaths and injury-related hospitalization among people over 65 years old. A system able to automatically detect falls could be an important tool from a social point of view, as it would contribute to the prompt assistance of these emergency cases. Currently, many researchers are interested in the development of fall detection systems. This chapter presents several approaches suggested so far, with special attention to the different strategies and technologies applied. Other sen- sor technologies that could be applied to this field are also referred. Additionally, a new fall detection system based on a machine learning paradigm, using neural networks, is suggested. The system was trained using fall and non-fall examples. Although the test set has included some particular examples, problematic for detection of the correspondent motion, the obtained results present good specificity (88.9%) and sensitivity (93.9%) rates.
- Machine learning approaches applied to GC-FID fatty acid profiles to discriminate wild from farmed salmonPublication . Grazina, Liliana; Rodrigues, Pedro João; Igrejas, Getúlio; Nunes, Maria A.; Mafra, Isabel; Arlorio, Marco; Oliveira, Beatriz; Amaral, Joana S.In the last decade, there has been an increasing demand for wild-captured fish, which attains higher prices compared to farmed species, thus being prone to mislabeling practices. In this work, fatty acid composition coupled to advanced chemometrics was used to discriminate wild from farmed salmon. The lipids extracted from salmon muscles of different production methods and origins (26 wild from Canada, 25 farmed from Canada, 24 farmed from Chile and 25 farmed from Norway) were analyzed by gas chromatography with flame ionization detector (GC-FID). All the tested chemometric approaches, namely principal components analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE) and seven machine learning classifiers, namely k-nearest neighbors (kNN), decision tree, support vector machine (SVM), random forest, artificial neural networks (ANN), naïve Bayes and AdaBoost, allowed for differentiation between farmed and wild salmons using the 17 features obtained from chemical analysis. PCA did not allow clear distinguishing between salmon geographical origin since farmed samples from Canada and Chile overlapped. Nevertheless, using the 17 features in the models, six out of the seven tested machine learning classifiers allowed a classification accuracy of ≥99%, with ANN, naïve Bayes, random forest, SVM and kNN presenting 100% accuracy on the test dataset. The classification models were also assayed using only the best features selected by a reduction algorithm and the best input features mapped by t-SNE. The classifier kNN provided the best discrimination results because it correctly classified all samples according to production method and origin, ultimately using only the three most important features (16:0, 18:2n6c and 20:3n3 + 20:4n6). In general, the classifiers presented good generalization with the herein proposed approach being simple and presenting the advantage of requiring only common equipment existing in most labs.
- Automatic detection and classification of honey bee comb cells using deep learningPublication . Alves, Thiago da Silva; Pinto, M. Alice; Ventura, Paulo J.C.; Neves, Cátia J.; Biron, David G.; Candido Junior, Arnaldo; Paula Filho, Pedro L. de; Rodrigues, Pedro JoãoIn a scenario of worldwide honey bee decline, assessing colony strength is becoming increasingly important for sustainable beekeeping. Temporal counts of number of comb cells with brood and food reserves offers researchers data for multiple applications, such as modelling colony dynamics, and beekeepers information on colony strength, an indicator of colony health and honey yield. Counting cells manually in comb images is labour intensive, tedious, and prone to error. Herein, we developed a free software, named DeepBee©, capable of automatically detecting cells in comb images and classifying their contents into seven classes. By distinguishing cells occupied by eggs, larvae, capped brood, pollen, nectar, honey, and other, DeepBee© allows an unprecedented level of accuracy in cell classification. Using Circle Hough Transform and the semantic segmentation technique, we obtained a cell detection rate of 98.7%, which is 16.2% higher than the best result found in the literature. For classification of comb cells, we trained and evaluated thirteen different convolutional neural network (CNN) architectures, including: DenseNet (121, 169 and 201); InceptionResNetV2; InceptionV3; MobileNet; MobileNetV2; NasNet; NasNetMobile; ResNet50; VGG (16 and 19) and Xception. MobileNet revealed to be the best compromise between training cost, with ~9 s for processing all cells in a comb image, and accuracy, with an F1-Score of 94.3%. We show the technical details to build a complete pipeline for classifying and counting comb cells and we made the CNN models, source code, and datasets publicly available. With this effort, we hope to have expanded the frontier of apicultural precision analysis by providing a tool with high performance and source codes to foster improvement by third parties (https://github.com/AvsThiago/DeepBeesource).