RESUMO
EDXRF spectrometry is a well-established and often-used analytical technique in examining materials from which cultural heritage objects are made. The analytical results are traditionally subjected to additional multivariate analysis for archaeometry studies to reduce the initial data's dimensionality based on informative features. Nowadays, artificial intelligence (AI) techniques are used more for this purpose. Different soft computing techniques are used to improve speed and accuracy. Choosing the most suitable AI method can increase the sustainability of the analytical process and postprocessing activities. An autoencoder neural network has been designed and used as a dimension reduction tool of initial [Formula: see text] data collected in the raw EDXRF spectra, containing information about the selected points' elemental composition on the canvas paintings' surface. The autoencoder network design enables the best possible reconstruction of the original EDXRF spectrum and the most informative feature extraction, which has been used for dimension reduction. Such configuration allows for efficient classification algorithms and their performances. The autoencoder neural network approach is more sustainable, especially in processing time consumption and experts' manual work.
RESUMO
Wall segmentation is a special case of semantic segmentation, and the task is to classify each pixel into one of two classes: wall and no-wall. The segmentation model returns a mask showing where objects like windows and furniture are located, as well as walls. This article proposes the module's structure for semantic segmentation of walls in 2D images, which can effectively address the problem of wall segmentation. The proposed model achieved higher accuracy and faster execution than other solutions. An encoder-decoder architecture of the segmentation module was used. Dilated ResNet50/101 network was used as an encoder, representing ResNet50/101 network in which dilated convolutional layers replaced the last convolutional layers. The ADE20K dataset subset containing only interior images, was used for model training, while only its subset was used for model evaluation. Three different approaches to model training were analyzed in the research. On the validation dataset, the best approach based on the proposed structure with the ResNet101 network resulted in an average accuracy at the pixel level of 92.13% and an intersection over union (IoU) of 72.58%. Moreover, all proposed approaches can be applied to recognize other objects in the image to solve specific tasks.
RESUMO
Process automation, in general, enables the enhancement of productivity, product quality, and consistency alongside other production metrics. Liquor production on an industrial scale also follows the automation trend. However, small and medium producers lag with equipment modernization due to the high costs of industrial equipment. One of the important sensors in automation equipment for distilleries is the alcohol concentration sensor used for fraction separation, process automation, and supervision. This paper proposes a novel low-cost approach to alcohol concentration sensing by employing deep learning on the visual perception of traditional alcoholmeter. For purposes of the training model, dataset acquisition apparatus is developed and a large dataset of labeled images of alcoholmeter readings is acquired. The problem of reading alcohol concentration from an alcoholometer image is treated as a regression and classification problem. Performances of both regression and classification models were investigated with Resnet18 as an architecture of choice. Both models achieved satisfying performance metrics demonstrating the feasibility of the proposed approaches. The proposed system implemented on Raspberry Pi with a camera can be integrated into new distillation equipment. Additionally, it can be used for retrofitting existing equipment due to its non-invasive nature of reading. The scope of use can be further expanded to the reading of other types of analog instruments simply by retraining the model.
Assuntos
Aprendizado Profundo , Redes Neurais de Computação , Automação , Processamento de Imagem Assistida por Computador/métodos , Percepção VisualRESUMO
Monitoring and classification of dairy cattle behaviours is essential for optimising milk yields. Early detection of illness, days before the critical conditions occur, together with automatic detection of the onset of oestrus cycles is crucial for obviating prolonged cattle treatments and improving the pregnancy rates. Accelerometer-based sensor systems are becoming increasingly popular, as they are automatically providing information about key cattle behaviours such as the level of restlessness and the time spent ruminating and eating, proxy measurements that indicate the onset of heat events and overall welfare, at an individual animal level. This paper reports on an approach to the development of algorithms that classify key cattle states based on a systematic dimensionality reduction process through two feature selection techniques. These are based on Mutual Information and Backward Feature Elimination and applied on knowledge-specific and generic time-series extracted from raw accelerometer data. The extracted features are then used to train classification models based on a Hidden Markov Model, Linear Discriminant Analysis and Partial Least Squares Discriminant Analysis. The proposed feature engineering methodology permits model deployment within the computing and memory restrictions imposed by operational settings. The models were based on measurement data from 18 steers, each animal equipped with an accelerometer-based neck-mounted collar and muzzle-mounted halter, the latter providing the truthing data. A total of 42 time-series features were initially extracted and the trade-off between model performance, computational complexity and memory footprint was explored. Results show that the classification model that best balances performance and computation complexity is based on Linear Discriminant Analysis using features selected through Backward Feature Elimination. The final model requires 1.83 ± 1.00 ms to perform feature extraction with 0.05 ± 0.01 ms for inference with an overall balanced accuracy of 0.83.
Assuntos
Algoritmos , Ingestão de Alimentos , Acelerometria , Animais , Bovinos , Feminino , Análise dos Mínimos Quadrados , GravidezRESUMO
Wearable sensors and advanced algorithms can provide significant decision support for clinical practice. Currently, the motor symptoms of patients with neurological disorders are often visually observed and evaluated, which may result in rough and subjective quantification. Using small inertial wearable sensors, fine repetitive and clinically important movements can be captured and objectively evaluated. In this paper, a new methodology is designed for objective evaluation and automatic scoring of bradykinesia in repetitive finger-tapping movements for patients with idiopathic Parkinson's disease and atypical parkinsonism. The methodology comprises several simple and repeatable signal-processing techniques that are applied for the extraction of important movement features. The decision support system consists of simple rules designed to match universally defined criteria that are evaluated in clinical practice. The accuracy of the system is calculated based on the reference scores provided by two neurologists. The proposed expert system achieved an accuracy of 88.16% for files on which neurologists agreed with their scores. The introduced system is simple, repeatable, easy to implement, and can provide good assistance in clinical practice, providing a detailed analysis of finger-tapping performance and decision support for symptom evaluation.
Assuntos
Técnicas Biossensoriais , Hipocinesia/fisiopatologia , Movimento/fisiologia , Dispositivos Eletrônicos Vestíveis , Dedos/fisiologia , HumanosRESUMO
BACKGROUND: Portable energy dispersive X-ray fluorescence (pEDXRF) spectrometry analysis was applied for the characterisation of archaeological ceramic findings from three Neolithic sites in Serbia. Two dimension reduction techniques, principal component analysis (PCA) and scattering matrices-based dimension reduction were used to examine the possible classification of those findings, and to extract the most discriminant features. RESULTS: A decision-making procedure is proposed, whose goal is to classify unknown ceramic findings based on their elemental compositions derived by pEDXRF spectrometry. As a major part of decision-making procedure, the possibilities of two dimension reduction methods were tested. Scattering matrices-based dimension reduction was found to be the more efficient method for the purpose. Linear classifiers designed based on the desired output allowed for 7 of 8 unknown samples from the test set to be correctly classified. CONCLUSIONS: Based on the results, the conclusion is that despite the constraints typical of the applied analytical technique, the elemental composition can be considered as viable information in provenience studies. With a fully-developed procedure, ceramic artefacts can be classified based on their elemental composition and well-known provenance.