Physical Activity Detection for Diabetes Mellitus Patients Using Recurrent Neural Networks.

Diabetes mellitus (DM) is a persistent metabolic disorder associated with the hormone insulin. The two main types of DM are type 1 (T1DM) and type 2 (T2DM). Physical activity plays a crucial role in the therapy of diabetes, benefiting both types of patients. The detection, recognition, and subsequent classification of physical activity based on type and intensity are integral components of DM treatment. The continuous glucose monitoring system (CGMS) signal provides the blood glucose (BG) level, and the combination of CGMS and heart rate (HR) signals are potential targets for detecting relevant physical activity from the BG variation point of view. The main objective of the present research is the developing of an artificial intelligence (AI) algorithm capable of detecting physical activity using these signals. Using multiple recurrent models, the best-achieved performance of the different classifiers is a 0.99 area under the receiver operating characteristic curve. The application of recurrent neural networks (RNNs) is shown to be a powerful and efficient solution for accurate detection and analysis of physical activity in patients with DM. This approach has great potential to improve our understanding of individual activity patterns, thus contributing to a more personalized and effective management of DM.

Solid-state fermentation with Zygomycetes fungi as a tool for biofortification of apple pomace with γ-linolenic acid, carotenoid pigments and phenolic antioxidants.

In the last few years, there has been a growing interest in the more efficient utilization of agricultural and food by-products. Apples are among the most processed fruits in the world that generate huge quantities of processing waste biomasses. Therefore, the objective of this study was to improve the nutritional value of apple pomaces with γ-linolenic acid (GLA) and carotenoid pigments by solid-state fermentation (SSF) using two Zygomycetes fungi (Actinomucor elegans and Umbelopsis isabellina). The impact of fermentation periods on the polyphenol content and antioxidant capacity of the bioprocessed apple pomace was also investigated. The accumulated lipids were composed primarily of neutral fractions (mostly triacylglycerols). SSF with U. isabellina yielded a 12.72% higher GLA content than with A. elegans (3.85 g GLA/kg DW of pomace). Contrary to the lipogenic capacity, A. elegans showed higher carotenoids and phenolic antioxidants productivity than U. isabellina. The maximum concentrations for ß-carotene (433.11 µg/g DW of pomace-SSF with A. elegans and 237.68 µg/g DW of pomace-SSF with U. isabellina), lutein (374.48 µg/g DW- A. elegans and 179.04 µg/g DW- U. isabellina) and zeaxanthin (247.35 µg/g DW- A. elegans and 120.41 µg/g DW- U. isabellina) were registered on the 12th day of SSFs. In the case of SSF with A. elegans, the amount of total phenolics increased significantly (27%) by day 4 from the initial value (2670.38 µg of gallic acid equivalents/g DW) before slowly decreasing for the remaining period of the fungal growth. The experimental findings showed that a prolonged fermentation (between 8 and 12 days) should be applied to obtain value-added apple pomaces (rich in GLA and carotenoids) with potential pharmaceutical and functional food applications. Moreover, the SSF processes of simultaneous bioaccumulation of valuable fatty acids, carotenoids and phenolic antioxidants proposed in the present study may open up new challenges for biotechnological production of industrially important biomolecules using abundant and unexploited apple pomaces.

A review on modern defect detection models using DCNNs - Deep convolutional neural networks.

Background: Over the last years Deep Learning has shown to yield remarkable results when compared to traditional computer vision algorithms, in a large variety of computer vision applications. The deeplearning models outperformed in both accuracy and processing time. Thus, once a deeplearning models won the Image Net Large Scale Visual Recognition Contest, it proved that this area of research is of great potential. Furthermore, these increases in recognition performance resulted in more applied research and thus, more applications where deeplearning is useful: one of which is defect detection (or visual defect detection). In the last few years, deeplearning models achieved higher and higher accuracy on the complex testing datasets used for benchmarking. This surge in accuracy and usage is also supported (besides swarms of researchers pouring into the race), by incremental breakthroughs in computing hardware: such as more powerful GPUs(Graphical processing units), CPUs(central processing units) and better computing procedures (libraries and frameworks). Aim of the review: To offer a structured and analytical overview(stating both advantages and disadvantages) of the existing popular object detection models that can be re-purposed for defect detection: such as Region based CNNs(Convolutional neural networks), YOLO(You only look once), SSD(single shot detectors) and cascaded architectures. A further brief summary on model compression and acceleration techniques that enabled the portability of deeplearning detection models is included. Key Scientific Concepts of Review: It is of great use for future developments in the manufacturing industry that many of the popular, above mentioned models are easy to re-purpose for defect detection and, thus could really contribute to the overall increase in productivity of this sector. Moreover, in the experiment performed the YOLOv4 model was trained and re-purposed for industrial cable detection in several hours. The computing needs could be fulfilled by a general purpose computer or by a high-performance desktop setup, depending on the specificity of the application. Hence, the barrier of computing shall be somewhat easier to climb for all types of businesses.

Modelling in Synthesis and Optimization of Active Vaccinal Components.

Cancer is the second leading cause of mortality worldwide, behind heart diseases, accounting for 10 million deaths each year. This study focusses on adenocarcinoma, which is a target of a number of anticancer therapies presently being tested in medical and pharmaceutical studies. The innovative study for a therapeutic vaccine comprises the investigation of gold nanoparticles and their influence on the immune response for the annihilation of cancer cells. The model is intended to be realized using Quantitative-Structure Activity Relationship (QSAR) methods, explicitly artificial neural networks combined with fuzzy rules, to enhance automated properties of neural nets with human perception characteristics. Image processing techniques such as morphological transformations and watershed segmentation are used to extract and calculate certain molecular characteristics from hyperspectral images. The quantification of single-cell properties is one of the key resolutions, representing the treatment efficiency in therapy of colon and rectum cancerous conditions. This was accomplished by using manually counted cells as a reference point for comparing segmentation results. The early findings acquired are conclusive for further study; thus, the extracted features will be used in the feature optimization process first, followed by neural network building of the required model.

Simultaneous enrichment of grape pomace with γ-linolenic acid and carotenoids by solid-state fermentation with Zygomycetes fungi and antioxidant potential of the bioprocessed substrates.

Two filamentous fungi (Actinomucor elegans and Umbelopsis isabellina), were tested for their ability to enrich white grape pomace simultaneously with both γ-linolenic acid (GLA) and carotenoids through solid-state fermentation (SSF) processes. U. isabellina presented higher ability to produce GLA-rich lipids (composed mainly of neutral fractions) than A. elegans (the 6-th day of SSF: 378.85 mg/100 g of pomace -U. isabellina and 193.36 mg/100 g of pomace- A. elegans). The amounts of ß-carotene and lutein for both SSFs gradually increased until the end of the fermentation processes. The effect of fermentation time on the phenolic content and antioxidant activity of grape pomace was also studied. The SSF with A. elegans increased significantly total phenolic and flavonoid contents and DPPH scavenging activity of grape popmace. These bioprocessed grape pomaces with significant amounts of carotenoids and GLA-rich lipids (>94% nutritionally-valuable polyunsaturated fatty acids at the sn-2 position) could be very attractive for food industry.

Phenolic compounds, flavonoids, lipids and antioxidant potential of apricot (Prunus armeniaca L.) pomace fermented by two filamentous fungal strains in solid state system.

BACKGROUND: The use of agricultural and food by-products is an economical solution to industrial biotechnology. The apricot press residues are abounding by-products from juice industry which can be used as substrates in solid state fermentation process (SSF), thus allowing a liberation and increase of content from various biomolecules with high added value. METHODS: The evolutions of phenolic levels (by colorimetric assays and high performance liquid chromatography, HPLC-MS) and antioxidant activities (by DPPH assay) during SSF of apricot pomaces with Aspergillus niger and Rhizopus oligosporus were investigated. The changes in fatty acid compositions of oils in apricot kernels during SSFs were also analyzed by gas chromatography (GC-MS). RESULTS: The results showed that the levels of total phenolics increased by over 70% for SSF with R. oligosporus and by more than 30% for SSF with A. niger. A similar trend was observed in the amounts of total flavonoids (increases of 38, and 12% were recorded for SSF by R. oligosporus and A. niger, respectively). Free radical scavenging capacities of methanolic extracts were also significantly enhanced. The main phenolic compounds identified through HPLC-MS in fermented apricot press residues were chlorogenic acid, neochlorogenic acid, rutin, and quercetin 3-acetyl- glucoside. This work also demonstrated that the SSF with filamentous fungal strains not only helped in higher lipid recovery from apricot kernels, but also resulted in oils with better quality attributes (high linoleic acid content). CONCLUSION: The utilization of apricot by-products resulting from the juice industry as waste could provide an extra income and at the same time can help in solving solid waste management problems Graphical abstract Changes in phenolic compositions, antioxidant activities and total lipid contents during solid state fermentation (SSF) of apricot pomaces from juice industry with Aspergillus niger and Rhizopus oligosporus.

Total phenolic contents, antioxidant activities, and lipid fractions from berry pomaces obtained by solid-state fermentation of two Sambucus species with Aspergillus niger.

The aim of this study was to investigate the effect of solid-state fermentation (SSF) by Aspergillus niger on phenolic contents and antioxidant activity in Sambucus nigra L. and Sambucus ebulus L. berry pomaces. The effect of fermentation time on the total fats and major lipid classes (neutral and polar) was also investigated. During the SSF, the extractable phenolics increased with 18.82% for S. ebulus L. and 11.11% for S. nigra L. The levels of antioxidant activity of methanolic extracts were also significantly enhanced. The HPLC-MS analysis indicated that the cyanidin 3-sambubioside-5-glucoside is the major phenolic compound in both fermented Sambucus fruit residues. In the early stages of fungal growth, the extracted oils (with TAGs as major lipid fraction) increased with 12% for S. nigra L. and 10.50% for S. ebulus L. The GC-MS analysis showed that the SSF resulted in a slight increase of the linoleic and oleic acids level.