Electric Drive Supervisor for Milling Process 4.0 Automation: A Process Analytical Approach with IIoT NIR Devices for Common Wheat.

The milling industry envisions solutions to become fully compatible with the industry 4.0 technology where sensors interconnect devices, machines and processes. In this contest, the work presents an integrated solution merging a deeper understanding and control of the process due to real-time data collection by MicroNIR sensors (VIAVI, Santa Rosa, CA)-directly from the manufacturing process-and data analysis by Chemometrics. To the aim the sensors were positioned at wheat cleaning and at the flour blends phase and near infrared spectra (951-1608 nm) were collected online. Regression models were developed merging the spectra information with the results obtained by reference analyses, i.e., chemical composition and rheological properties of dough by Farinograph® (Brabender GmbH and Co., Duisburg, Germany), Alveograph® (Chopin, NG Villeneuve-la-Garenne Cedex, France) and Extensograph®.(Brabender GmbH and Co., Duisburg, Germany) The model performance was tested by an external dataset obtaining, for most of the parameters, RPRED higher than 0.80 and Root Mean Squares Errors in prediction lower than two-fold the value of the reference method errors. The real-time implementation resulted in optimal (100% of samples) or really good (99.9%-80% of samples) prediction ability. The proposed work succeeded in the implementation of a process analytical approach with Industrial Internet of Things near infrared (IIoT NIR) devices for the prediction of relevant grain and flour characteristics of common wheat at the industrial level.

An Ad Hoc Random Initialization Deep Neural Network Architecture for Discriminating Malignant Breast Cancer Lesions in Mammographic Images.

Breast cancer is one of the most common cancers in women, with more than 1,300,000 cases and 450,000 deaths each year worldwide. In this context, recent studies showed that early breast cancer detection, along with suitable treatment, could significantly reduce breast cancer death rates in the long term. X-ray mammography is still the instrument of choice in breast cancer screening. In this context, the false-positive and false-negative rates commonly achieved by radiologists are extremely arduous to estimate and control although some authors have estimated figures of up to 20% of total diagnoses or more. The introduction of novel artificial intelligence (AI) technologies applied to the diagnosis and, possibly, prognosis of breast cancer could revolutionize the current status of the management of the breast cancer patient by assisting the radiologist in clinical image interpretation. Lately, a breakthrough in the AI field has been brought about by the introduction of deep learning techniques in general and of convolutional neural networks in particular. Such techniques require no a priori feature space definition from the operator and are able to achieve classification performances which can even surpass human experts. In this paper, we design and validate an ad hoc CNN architecture specialized in breast lesion classification from imaging data only. We explore a total of 260 model architectures in a train-validation-test split in order to propose a model selection criterion which can pose the emphasis on reducing false negatives while still retaining acceptable accuracy. We achieve an area under the receiver operatic characteristics curve of 0.785 (accuracy 71.19%) on the test set, demonstrating how an ad hoc random initialization architecture can and should be fine tuned to a specific problem, especially in biomedical applications.

A random initialization deep neural network for discriminating malignant breast cancer lesions.

Breast cancer is one of the most common cancer in women, with more than 1,300,000 cases and 450,000 deaths each year worldwide. Recent studies show that early breast cancer detection, along with suitable treatment, could significantly reduce breast cancer death rates in the long-term. While the consequences of a false positive diagnosis can be psychologically and socioeconomically burdensome, the result of a false negative diagnosis can be devastating, especially in terms of health detriment. In this context, the false positive and false negative rates commonly achieved by radiologists are extremely arduous to estimate and control, and some authors have estimated figures of up to 20% of total diagnoses or more. Novel ideas in computer-assisted diagnosis have been prompted by the introduction of deep learning techniques in general and of convolutional neural networks (CNN) in particular. In this paper, we design and validate an ad-hoc CNN architecture specialized in breast lesion classification and heuristically explore possible parameter combinations and architecture styles in order to propose a model selection criterion which can pose the emphasis on reducing false negatives while still retaining acceptable accuracy. We achieve good classification performance on the validation and test set, demonstrating how an ad-hoc, random initialization CNN architecture can provide practical aid in the classification and staging of breast cancer.