An Enhancement on Convolutional Artificial Intelligent Based Diagnosis for Skin Disease Using Nanotechnology Sensors.

Skin disease is the major health problem around the world. The diagnosis of skin disease remains a challenge to dermatologist profession particularly in the detection, evaluation, and management. Health data are very large and complex due to this processing of data using traditional data processing techniques is very difficult. In this paper, to ease the complexity while processing the inputs, we use multilayered perceptron with backpropagation neural networks (MLP-BPNN). The image is collected from the devices that contain nanotechnology sensors, which is the state-of-art in the proposed model. The nanotechnology sensors sense the skin for its chemical, physical, and biological conditions with better detection specificity, sensitivity, and multiplexing ability to acquire the image for optimal classification. The MLP-BPNN technique is used to envisage the future result of disease type effectively. By using the above MLP-BPNN technique, it is easy to predict the skin diseases such as melanoma, nevus, psoriasis, and seborrheic keratosis.

Segmentation of Optic Disc and Cup Using Modified Recurrent Neural Network.

Glaucoma is one of the leading factors of vision loss, where the people tends to lose their vision quickly. The examination of cup-to-disc ratio is considered essential in diagnosing glaucoma. It is hence regarded that the segmentation of optic disc and cup is useful in finding the ratio. In this paper, we develop an extraction and segmentation of optic disc and cup from an input eye image using modified recurrent neural networks (mRNN). The mRNN use the combination of recurrent neural network (RNN) with fully convolutional network (FCN) that exploits the intra- and interslice contexts. The FCN extracts the contents from an input image by constructing a feature map for the intra- and interslice contexts. This is carried out to extract the relevant information, where RNN concentrates more on interslice context. The simulation is conducted to test the efficacy of the model that integrates the contextual information for optimal segmentation of optical cup and disc. The results of simulation show that the proposed method mRNN is efficient in improving the rate of segmentation than the other deep learning models like Drive, STARE, MESSIDOR, ORIGA, and DIARETDB.

Healthcare Biclustering-Based Prediction on Gene Expression Dataset.

In this paper, we develop a healthcare biclustering model in the field of healthcare to reduce the inconveniences linked to the data clustering on gene expression. The present study uses two separate healthcare biclustering approaches to identify specific gene activity in certain environments and remove the duplication of broad gene information components. Moreover, because of its adequacy in the problem where populations of potential solutions allow exploration of a greater portion of the research area, machine learning or heuristic algorithm has become extensively used for healthcare biclustering in the field of healthcare. The study is evaluated in terms of average match score for nonoverlapping modules, overlapping modules through the influence of noise for constant bicluster and additive bicluster, and the run time. The results show that proposed FCM blustering method has higher average match score, and reduced run time proposed FCM than the existing PSO-SA and fuzzy logic healthcare biclustering methods.

Blockchain-Based Deep Learning to Process IoT Data Acquisition in Cognitive Data.

Remote health monitoring can help prevent disease at the earlier stages. The Internet of Things (IoT) concepts have recently advanced, enabling omnipresent monitoring. Easily accessible biomarkers for neurodegenerative disorders, namely, Alzheimer's disease (AD) are needed urgently to assist the diagnoses at its early stages. Due to the severe situations, these systems demand high-quality qualities including availability and accuracy. Deep learning algorithms are promising in such health applications when a large amount of data is available. These solutions are ideal for a distributed blockchain-based IoT system. A good Internet connection is critical to the speed of these system responses. Due to their limited processing capabilities, smart gateway devices cannot implement deep learning algorithms. In this paper, we investigate the use of blockchain-based deep neural networks for higher speed and delivery of healthcare data in a healthcare management system. The study exhibits a real-time health monitoring for classification and assesses the response time and accuracy. The deep learning model classifies the brain diseases as benign or malignant. The study takes into account three different classes to predict the brain disease as benign or malignant that includes AD, mild cognitive impairment, and normal cognitive level. The study involves a series of processing where most of the data are utilized for training these classifiers and ensemble model with a metaclassifier classifying the resultant class. The simulation is conducted to test the efficacy of the model over that of the OASIS-3 dataset, which is a longitudinal neuroimaging, cognitive, clinical, and biomarker dataset for normal aging and AD, and it is further trained and tested on the UDS dataset from ADNI. The results show that the proposed method accurately (98%) responds to the query with high speed retrieval of classified results with an increased training accuracy of 0.539 and testing accuracy of 0.559.

Application of Internet of Things on the Healthcare Field Using Convolutional Neural Network Processing.

Population at risk can benefit greatly from remote health monitoring because it allows for early detection and treatment. Because of recent advances in Internet-of-Things (IoT) paradigms, such monitoring systems are now available everywhere. Due to the essential nature of the patients being monitored, these systems demand a high level of quality in aspects such as availability and accuracy. In health applications, where a lot of data are accessible, deep learning algorithms have the potential to perform well. In this paper, we develop a deep learning architecture called the convolutional neural network (CNN), which we examine in this study to see if it can be implemented. The study uses the IoT system with a centralised cloud server, where it is considered as an ideal input data acquisition module. The study uses cloud computing resources by distributing CNN operations to the servers with outsourced fitness functions to be performed at the edge. The results of the simulation show that the proposed method achieves a higher rate of classifying the input instances from the data acquisition tools than other methods. From the results, it is seen that the proposed CNN achieves an average accurate rate of 99.6% on training datasets and 86.3% on testing datasets.

Thermal neutron sensitive inorganic compound loaded thin-film composite plastic scintillators.

The paper describes the preparation and characterization methodology of thermal neutron sensitive inorganic compound loaded polystyrene based thin-film Plastic Scintillators (PS). Inorganic compounds with thermal neutron sensitive elements such as B2O3, LiF, Gd2O2S:Tb, Gd2O3, Gd(BO2)3:Tb is loaded in plastic scintillators, at predetermined weight percentage in a solvent-based fabrication method. The PS base solution is prepared by dissolving required quantities of polystyrene, 2,5-Diphenyloxazole (PPO), 1,4-bis(5-Phenyloxazol-2-yl) Benzene (POPOP) in the p-xylene solvent. The loading material is mixed with the scintillator solution and coated over cellulose acetate-based transparency sheet. Thin sheets of 200 × 150 mm size and 250 ± 50 µm thickness PS are prepared through multiple coating. Photoluminescence (PL), Radioluminescence (RL) and pulse height spectra (PHS) of α, ß, γ and neutron sources of the composite scintillators are studied. The selection of loading compounds is decided on their physical properties such as refractive index, the atomic percentage of neutron sensitive elements in the inorganic compound, band gap, and cost and availability of material. Gadolinium based compounds as a thermal neutron absorber showed higher detection capability for low-energy neutrons. Among the gadolinium loaded PS, Gd(BO2)3:Tb (14.3 wt%) composite scintillator showed the highest RL. A comprehensive analysis of PL, RL, PHS of α, pure ß and γ sources, un-moderated and moderated Am-Be neutron source is discussed in the paper.

Wind-Induced Pressure Prediction on Tall Buildings Using Generative Adversarial Imputation Network.

Wind tunnel testing techniques are the main research tools for evaluating the wind loadings of buildings. They are significant in designing structurally safe and comfortable buildings. The wind tunnel pressure measurement technique using pressure sensors is significant for assessing the cladding pressures of buildings. However, some pressure sensors usually fail and cause loss of data, which are difficult to restore. In the literature, numerous techniques are implemented for imputing the single instance data values and data imputation for multiple instantaneous time intervals with accurate predictions needs to be addressed. Thus, the data imputation capacity of machine learning models is used to predict the missing wind pressure data for tall buildings in this study. A generative adversarial imputation network (GAIN) is proposed to predict the pressure coefficients at various instantaneous time intervals on tall buildings. The proposed model is validated by comparing the performance of GAIN with that of the K-nearest neighbor and multiple imputations by chained equation models. The experimental results show that the GAIN model provides the best fit, achieving more accurate predictions with the minimum average variance and minimum average standard deviation. The average mean-squared error for all four sides of the building was the minimum (0.016), and the average R-squared error was the maximum (0.961). The proposed model can ensure the health and prolonged existence of a structure based on wind environment.

Probiotics and its functionally valuable products-a review.

During the past two decades probiotic bacteria have been increasingly proposed as health promoting bacteria in variety of food system, because of its safety, functional, and technological characteristics. Commonly, Lactobacillus spp., Bifidobacterium spp., Saccharomyces boulardii, and some other microorganisms have been considered as probiotic strains. Possibly these bacterial strains exerted several beneficial effects into gastrointestinal tract of host while administered with variety of food system. Lactic acid bacteria (LAB) usually produce antimicrobial substances like bacteriocin which have broad spectrum of antagonist effect against closely related Gram positive and Gram negative pathogens. LAB strains often produce polymeric substances such as exopolysaccharides (EPS) which increase the colonization of probiotic bacteria by cell-cell interactions in gastrointestinal tract. LAB also produces biosurfactant which showed that the wide range of antimicrobial activity against bacterial pathogen as well as its antiadhesive properties reduces the adhesion of pathogens into gastric wall membrane. Furthermore, LAB strains have also been reported for production of antioxidants which are ability to scavenge the free radicals such as superoxide anions and hydroxyl radicals. For this sense, this review article is mainly focused on the ecology, biosynthesis, genetics, target sites, and applications of bacteriocins and EPS from LAB strains. Moreover, this review discusses about the production and functions of nutritive essential element folate and iron chelating agent such as siderophores from LAB.

Synthesis and functional characterization of antibiofilm exopolysaccharide produced by Enterococcus faecium MC13 isolated from the gut of fish.

The synthesis and functional characterization of an antibiofilm exopolysaccharide (EPS) from a probiotic Enterococcus faecium MC13 were investigated. The temperature of 35 °C, pH of 6.5, and salinity of 1-2% were found to be optimum for EPS production. The sucrose (30 g l⁻¹) and yeast extract (20 g l⁻¹) acted as suitable carbon and nitrogen sources, respectively, which strongly influenced EPS production with yield of 11.33 and 11.91 g l⁻¹. Based on the thin layer chromatography, EPS of E. faecium MC13 was found to be a heteropolysaccharide, composed of galactose and glucose sugar units with a molecular mass of 2.0 × 105 Da. Fourier transform infrared spectrum analysis of the EPS revealed many predominant functional groups including hydroxyl, carboxyl, and amide groups. EPS exhibited better emulsifying and flocculating activities which is relatively similar to those of commercial polysaccharides. In vitro antioxidant inspect of EPS showed lesser antioxidant activity than that of the control ascorbic acid. Thermal behavior of EPS was different from the other EPS produced by other lactic acid bacteria. In vitro antibiofilm assay of EPS exhibited significant biofilm inhibition, especially with Listeria monocytogenes. To the best of our knowledge, this is the first report on EPS of E. faecium with strong emulsifying and flocculating activities.

Traditional Indian fermented foods: a rich source of lactic acid bacteria.

This review describes the diversity of Indian fermented food and its significance as a potential source of lactic acid bacteria (LAB). Fermented foods consumed in India are categorized based upon their base material. Fermented foods such as dahi, gundruk, sinki, iniziangsang, iromba, fermented rai, kanjika and handua were reported to have significant medicinal properties. Some fermented products such as koozh, dahi and kanjika are consumed unknowingly as, probiotic drinks, by local people. There are very few reports regarding isolation of LAB from Indian fermented foods available in the past; however, due to growing consciousness about potential health benefits of LAB, we now have scores of reports in this field. There is an abundant opportunity available for food microbiologists to explore the Indian fermented foods for the isolation of new LAB strains for their potential role in probiotic research.

Application of response surface methodology in the optimisation of a growth medium for enhanced natural preservative bacteriocin production by a probiotic bacterium.

In this study, a statistics-based experimental design was utilised for the optimisation of a growth medium which possibly enhanced bacteriocin production by Streptococcus phocae PI80. Carbon, nitrogen sources and a bio-surfactant were first screened using a one variable at a time technique and scored for increasing yield production. The selected variables were further statistically optimised using response surface methodology with a central composite design. The high- and low-level limits of the selected variables were determined, and a set of 34 experimental runs were performed. The concentration of each medium ingredient influenced the bacteriocin activity to about 22,500 AU mL⁻¹. The carbon and nitrogen sources were identified as significant factors in restraining the bacteriocin activity produced by S. phocae PI80. The statistics-based experimental design was found to be very efficient in optimising the media components in a number of experimental runs, with a three-fold increase in bacteriocin activity compared to the un-optimised medium. The optimum medium composition was found to be sodium succinate (10.0 g L⁻¹), yeast extract (4.0 g L⁻¹), glucose (9.0 g L⁻¹), NaCl (10.0 g L⁻¹), Tween 80 (6.0 g L⁻¹) and K2HPO4 (1.0 g L⁻¹). This optimised medium is two-fold more cost effective than the commercial Lactobacillus MRS medium.

Lactobacillus plantarum AS1 isolated from south Indian fermented food Kallappam suppress 1,2-dimethyl hydrazine (DMH)-induced colorectal cancer in male Wistar rats.

The relationship between antioxidant and anticancer properties of probiotic bacterium strain Lactobacillus plantarum AS1 (AS1) in colon cancer induced by 1,2-dimethylhydrazine (DMH) has been studied. In this study, an increased level of lipid peroxide (LPO) products and increased activities of antioxidant enzymes (superoxide dismutase, catalase and glutathione-S transferase) and marker enzymes (alkaline phosphatase and acid phosphatase) in colon and plasma of cancer-bearing animals have been observed. AS1 was supplemented either before initiation or during initiation and selection/promotion phases of colon carcinogenesis and was found to be effective in altering lipid peroxidation and antioxidant enzyme activities and marker enzymes to a statistically significant level measured either in the colon and in the plasma. These alterations inclined towards normal in a time-dependent manner on AS1 supplementation. The mean tumor volume diameter and total number of tumors were found to be statistically decreased in AS1 pre- and post-treated rats. Furthermore, histopathological examination shows remarkable difference between control and treated groups. The in vitro antioxidant assay shows that AS1 has promising antioxidant property. These results demonstrate that AS1 strain can modulate the development of DMH-induced rat colon carcinogenesis through an antioxidant-dependent mechanism.

Seagrass as a potential source of natural antioxidant and anti-inflammatory agents.

CONTEXT: Halophila spp. is a strong medicine against malaria and skin diseases and is found to be very effective in early stages of leprosy. Seagrasses are nutraceutical in nature and therefore of importance as food supplements. OBJECTIVE: The antibacterial, antioxidant, and anti-inflammatory activities of Halophila ovalis R. Br. Hooke (Hydrocharitaceae) methanol extract were investigated and the chemical constituents of purified fractions were analyzed. MATERIALS AND METHODS: Plant materials were collected from Pondicherry coastal line, and antimicrobial screening of crude extract, and purified fractions was carried out by the disc diffusion method and the minimum inhibitory concentration (MICs) of the purified fractions and reference antibiotics were determined by microdilution method. Antioxidant and anti-inflammatory activities were investigated in vitro. Chemical constituents of purified fractions V and VI were analyzed by gas chromatography-mass spectrometry (GC-MS), and the phytochemicals were quantitatively determined. RESULTS: Methanol extract inhibited the growth of Bacillus cereus at a minimum inhibitory concentration of 50 µg/mL and other Gram-negative pathogens at 75 µg/ml, except Vibrio vulnificus. Reducing power and total antioxidant level increased with increasing extract concentration. H. ovalis exhibited strong scavenging activity on 2,2-diphenyl-1-picrylhydrazyl (DPPH) and superoxide radicals at IC(50) of 0.13 and 0.65 mg/mL, respectively. Methanol extract of H. ovalis showed noticeable anti-inflammatory activity at IC(50) of 78.72 µg/mL. The GC-MS analysis of H. ovalis revealed the presence of triacylglycerols as major components in purified fractions. Quantitative analysis of phytochemicals revealed that phenols are rich in seagrass H. ovalis. DISCUSSION AND CONCLUSION: These findings demonstrated that the methanol extract of H. ovalis exhibited appreciable antibacterial, noticeable antioxidant, and anti-inflammatory activities, and thus could be use as a potential source for natural health products.

Microbial decolorization of synthetic dyes and reactive dyes of industrial effluents by using a novel fungus Aspergillus proliferans.

A decolorizing fungal strain was isolated and identified by the morphology and genotypic characterization as Aspergillus proliferans. The effect of A. proliferans on decolorization of synthetic dyes (70 mg ml(-1)) and colored effluent was evaluated in liquid culture medium. A. proliferans expressed their effective decolorization activity in effectual decolorization of synthetic dyes and industrial effluent. Synthetic dyes were decolorized by 76 to 89% within 6 days of treatment and 73.5% of color was removed in industrial effluent within 8 days. The addition of optimum carbon and nitrogen sources were effectively stimulated the decolorization activity. The high concentration of glucose repressed the decolorization activity and supplementation of yeast extract has significantly enhanced the effluent decolorization at p < 0.05. Laccase enzyme was isolated from liquid state fermentation, which showed significant enzyme activity (10,200 Uml(-1)) at p < 0.005. The crude enzyme decolorizes the dyes aniline blue and congo red in 14 hours (40.9 to 70%) and the effluent in 14 hours (88.6%). Moreover, the culture free supernatant without the fungal biomass has also effectively decolorized the effluent and synthetic dyes. The fungi Aspergillus proliferans was used not only for decolorization but also for better bioremediation of industrial effluent.

Purification and characterization of enterocin MC13 produced by a potential aquaculture probiont Enterococcus faecium MC13 isolated from the gut of Mugil cephalus.

A bacteriocin producer strain MC13 was isolated from the gut of Mugil cephalus (grey mullet) and identified as Enterococcus faecium. The bacteriocin of E. faecium MC13 was purified to homogeneity, as confirmed by Tricine sodium dodecyl sulphate - polyacrylamide gel electrophoresis (SDS-PAGE). Reverse-phase high-performance liquid chromatography (HPLC) analysis showed a single active fraction eluted at 26 min, and matrix-assisted laser desorption ionization time of flight (MALDI-TOF) mass spectrometry analysis showed the molecular mass to be 2.148 kDa. The clear zone in native PAGE corresponding to enterocin MC13 band further substantiated its molecular mass. A dialyzed sample (semicrude preparation) of enterocin MC13 was broad spectrum in its action and inhibited important seafood-borne pathogens: Listeria monocytogenes , Vibrio parahaemolyticus, and Vibrio vulnificus. This antibacterial substance was sensitive to proteolytic enzymes: trypsin, protease, and chymotrypsin but insensitive to catalase and lipase, confirming that inhibition was due to the proteinaceous molecule, i.e., bacteriocin, and not due to hydrogen peroxide. Enterocin MC13 tolerated heat treatment (up to 90 °C for 20 min). Enterococcus faecium MC13 was effective in bile salt tolerance, acid tolerance, and adhesion to the HT-29 cell line. These properties reveal the potential of E. faecium MC13 to be a probiotic bacterium. Enterococcus faecium MC13 could be used as potential fish probiotic against pathogens such as V. parahaemolyticus, Vibrio harveyi, and Aeromonas hydrophila in fisheries. Also, this could be a valuable seafood biopreservative against L. monocytogenes.

Lactobacillus plantarum AS1 binds to cultured human intestinal cell line HT-29 and inhibits cell attachment by enterovirulent bacterium Vibrio parahaemolyticus.

AIM: Lactobacillus plantarum AS1 was incubated with HT-29 adenocarcinoma cell line to assess its adhesion potency and examined for its inhibitory effect on the cell attachment by an enterovirulent bacterium Vibrio parahaemolyticus. METHODS AND RESULTS: Lactobacillus plantarum AS1 attached efficiently to HT-29 cells as revealed by scanning electron microscopy and bacterial adhesion assay. Lactobacillus plantarum AS1 significantly reduced V. parahaemolyticus attached to HT-29 cells by competition, exclusion and displacement mode. Lactobacillus plantarum AS1 seems to adhere to human intestinal cells via mechanisms that involve different combinations of carbohydrate and protein factors on the bacteria and eukaryotic cell surface. CONCLUSION: Strain Lact. plantarum AS1 inhibits the cell attachment of a pathogen V. parahaemolyticus by steric hindrance mechanism. Also, antibacterial factors such as bacteriocins, lactic acid and exopolysaccharides could be involved. SIGNIFICANCE AND IMPACT OF THE STUDY: The ability to inhibit the adhesion of V. parahaemolyticus to intestinal cell line warrants further investigation to explore the use of probiotic strain Lact. plantarum AS1 in the management of gastroenteritis caused by V. parahaemolyticus.

Optimization of media components for enhanced production of streptococcus phocae pi80 and its bacteriocin using response surface methodology

The standard MRS components were optimized using response surface methodology for increasing yield of Streptococcus phocae PI80 viable cells and its bacteriocin. The highest amounts of bacteriocin activity and viable cells were recorded from prediction point of optimized MRS medium and achieved two fold higher (33049.8 AU.mL-1 and 14.05 LogCFU.mL-1) than un-optimized counterpart.

Production and purification of a novel exopolysaccharide from lactic acid bacterium Streptococcus phocae PI80 and its functional characteristics activity in vitro.

Optimum culture conditions which ease the synthesis of a novel exopolysaccharide (EPS) from a potent marine strain Streptococcus phocae was proposed in this study. The strain grows well at 35 °C, pH 7.0 and NaCl (2%) with lactose and yeast extract as best carbon and nitrogen sources. The maximum yield of EPS (11.75 and 12.14 g/L) was obtained in the presence of lactose and yeast extract at a concentration of 20 g/L respectively. EPS was refined by gel filtration chromatography using phenyl Sepharose column which revealed the presence of arabinose, fructose and galactose sugar units with molecular mass about 2.8 × 10(5) Da. Emulsifying and flocculating stability of EPS compared with three commercial hydrocolloids. EPS exhibited better activities which are similar to that of commercial hydrocolloids. Both crude and purified EPS exhibited strong antioxidant potential by quenching hydroxyl and superoxide anion radicals. Antibiofilm activity by inhibition of Gram positive and Gram negative biofilm forming bacteria was evident in our studies. Potential antioxidant activity and biofilm inhibiting property of EPS may lead to the development of novel food grade adjuncts.

Design and optimization of fermentation medium for enhanced bacteriocin production by probiotic bacterium Enterococcus faecium MC13.

Statistics-based experimental designs were used to develop a cost-effective medium for enhanced production of viable cells and bacteriocin by probiotic Enterococcus faecium MC13. Carbon, nitrogen, and mineral sources were first screened by one-variable-at-a-time (OVAT) methods. In order to increase yield production, the selected variables were further statistically optimized using response-surface methodology (RSM) with central composite design (CCD). The maximum and minimum levels of the selected variables were determined and a set of 34 experimental runs was performed. The optimum concentrations of the tested variables for production of viable cells (12.24 log CFU mL(-1)) and bacteriocin activity (25,600 AU mL(-1)) were tryptone (10.0 g/L), peptone (6.0 g/L), maltose (3.0 g/L), glucose (9.0 g/L), NaCl (15.0 g/L), sodium citrate (2.5 g/L), sodium acetate (1.0 g/L), and dipotassium PO(4) (0.1 g/L). Threefold increased yield of bacteriocin was achieved in optimized medium compared to the unoptimized counterpart, and this was two times less cost than commercial MRS medium.

Optimization of media components for enhanced production of streptococcus phocae pi80 and its bacteriocin using response surface methodology.

The standard MRS components were optimized using response surface methodology for increasing yield of Streptococcus phocae PI80 viable cells and its bacteriocin. The highest amounts of bacteriocin activity and viable cells were recorded from prediction point of optimized MRS medium and achieved two fold higher (33049.8 AU.mL(-1) and 14.05 LogCFU.mL(-1)) than un-optimized counterpart.