Neural network-supported patient-adaptive fall prevention system

Neural Computing and Applications - Patient falls due to unattended bed-exits are costly to patients, healthcare personnel and hospitals. Numerous researches based on up to three predetermined...     

Biodegradable Implantable Sensors: Materials Design,Fabrication, and Applications

The ability to monitor diseases, therapies, and their effects on the body is a critical component of modern care and personalized medicine. Real time monitoring can be achieved by analyzing body fluids or by applying sensors on, or alternatively, inside the body. Implantable sensors, however, must be removed. Second removal procedures lead to further tissue damage, which can be a problem in tissues such as those of the central nervous system. The use of biodegradable sensors alleviates these problems since they do not require removal procedures. Recent advances in material science made it possible for all sensor components to be biodegradable. Small size and power of implants, and the limited selection of materials are the main constraints determining the capabilities of the biodegradable device. Thus, the design will be always a challenge exploring a trade-off among these parameters. Despite of the encouraging results illustrating that biodegradable sensors can be as accurate and reliable as commercially available nondegradable ones, biodegradable implantable sensors are still in their infancy. Significant advances made in this area are critically reviewed in this paper, and future prospects are highlighted.     

An adaptive wavelet network for function learning

In this article, a wavelet neural network (WNN) model is proposed for approximating arbitrary nonlinear functions. Our WNN model structure comes from the idea of adaptive neuro-fuzzy inference system (ANFIS) which is used for obtaining fuzzy rule base from the input–output data of an unknown function. The WNN model which is called in this study as adaptive wavelet network (AWN) consists of wavelet scaling functions in its processing units whereas in an ANFIS, mostly Gaussian-type membership functions are used for a function approximation. We present to train an AWN by a hybrid-learning method containing least square estimation (LSE) with gradient-based optimization algorithm to obtain the optimal translation and dilation parameters of our AWN for model accuracy. Simulation examples are also given to illustrate the effectiveness of the method.     

Classification of organic and conventional olives using convolutional neural networks

Neural Computing and Applications - This paper presents a convolutional neural network (CNN) to classify between the conventionally and organically cultivated Memecik varieties of green olives. The...     

Use of Bacillus indicus HU36 as a probiotic culture in set‐type,recombined nonfat yoghurt production and its effects on quality

Viability of a probiotic and carotenoid‐producing bacterium, Bacillus indicus HU36 in vegetative form, along with the yoghurt cultures in set‐type, recombined nonfat yoghurt and its effects on quality were determined during the storage at 4 °C. The number of B. indicus HU36 cells in yoghurt remained about 5 log cfu/mL after 14 days, but decreased to 3.5 log after 21 days. The bacterium resulted in increased yellowness, but did not affect the rheological properties of the yoghurt. Sensorial properties of the yoghurt were acceptable compared to a commercial probiotic yoghurt. B. indicus HU36 can thus be used as a probiotic culture in yoghurt production.     

Recognition of the Gastric Molecular Image Based on Decision Tree and Discriminant Analysis Classifiers by using Discrete Fourier Transform and Features

ABSTRACT

This article presents the development and evaluation of a computerized decision support system (DSS), aiming to Show the feasibility and potential toward maximizing the benefits of a new algorithm by combining the machine-learning techniques which are not used in the literature for automatic recognition of the gastric images. The object of this article is fivefold: first, the features Maximally Stable Extremal Regions (MSER), Speeded Up Robust Features (SRF), and Binary Robust Invariant Scalable Keypoints (BRISK) of histopathological gastric images were analyzed. Second, the Fourier Transform (FT) was applied to these properties which were calculated to equalize the dimensions of the obtained features. Third, MS and LE size reduction methods have been applied. Fourth, the decision tree (DT) and discriminant analysis (DA) classifiers are used to classify the histopathological gastric images. Fifth, these classification results have been compared. In this article, the highest accuracy result obtained by using the SRF_FT_MS_DT method is found to be 86.66%. Fast and multimodality computerized DSS can beneficial to patients for early detection of gastric diseases. It may facilitate early diagnosis of the disease.     

Microbial Safety and Shelf Life of UV‐C Treated Freshly Squeezed White Grape Juice

The effects of UV‐C irradiation on the inactivation of Escherichia coli K‐12 (ATCC 25253), a surrogate of E. coli O157:H7, and on the shelf life of freshly squeezed turbid white grape juice (FSWGJ) were investigated. FSWGJ samples were processed at 0.90 mL/s for 32 min by circulating 8 times in an annular flow UV system. The UV exposure time was 244 s per cycle. The population of E. coli K‐12 was reduced by 5.34 log cycles after exposure to a total UV dosage of 9.92 J/cm² (1.24 J/cm² per cycle) at 0.90 mL/s flow rate. The microbial shelf life of UV‐C treated FSWGJ was extended up to 14 d at 4 °C. UV exposure was not found to alter pH, total soluble solid, and titratable acidity of juice. There was a significant effect (P < 0.05) on turbidity, absorbance coefficient, color, and ascorbic acid content. Furthermore, all physicochemical properties were altered during refrigerated storage. The microbial shelf life of FSWGJ was doubled after UV‐C treatment, whereas the quality of juice was adversely affected similarly observed in the control samples.