Search

In computer vision, object recognition and image categorization have proven to be difficult challenges. They have, nevertheless, generated responses to a wide range of difficult issues from a variety of fields. Convolution Neural Networks (CNNs) have recently been identified as the most widely proposed deep learning (DL) algorithms in the literature. CNNs have unquestionably delivered cutting-edge achievements, particularly in the areas of image classification, speech recognition, and video processing. However, it has been noticed that the CNN-training assignment demands a large amount of data, which is in low supply, especially in the medical industry, and as a result, the training process takes longer. In this paper, we describe an attention-aware CNN architecture for classifying chest X-ray images to diagnose Pneumonia in order to address the aforementioned difficulties. Attention Modules provide attention-aware properties to the Attention Network. The attention-aware features of various modules alter as the layers become deeper. Using a bottom-up top-down feedforward structure, the feedforward and feedback attention processes are integrated into a single feedforward process inside each attention module. In the present work, a deep neural network (DNN) is combined with an attention mechanism to test the prediction of Pneumonia disease using chest X-ray pictures. To produce attention-aware features, the suggested network was built by merging channel and spatial attention modules in DNN architecture. With this network, we worked on a publicly available Kaggle chest X-ray dataset. Extensive testing was carried out to validate the suggested model. In the experimental results, we attained an accuracy of 95.47% and an F- score of 0.92, indicating that the suggested model outperformed against the baseline models.

Introduction: Sign language is the only way to communicate for speech-impaired people. But this sign language is not known to normal people so this is the cause of barrier in communicating. This is the problem faced by speech impaired people. In this paper, we have presented our solution which captured hand gestures with Kinect camera and classified the hand gesture into its correct symbol. Method: We used Kinect camera not the ordinary web camera because the ordinary camera does not capture its 3d orientation or depth of an image from camera however Kinect camera can capture 3d image and this will make classification more accurate. Result: Kinect camera will produce a different image for hand gestures for ‘2’ and ‘V’ and similarly for ‘1’ and ‘I’ however, normal web camera will not be able to distinguish between these two. We used hand gesture for Indian sign language and our dataset had 46339, RGB images and 46339 depth images. 80% of the total images were used for training and the remaining 20% for testing. In total 36 hand gestures were considered to capture alphabets and alphabets from A-Z and 10 for numeric, 26 for digits from 0-9 were considered to capture alphabets and Keywords. Conclusion: Along with real-time implementation, we have also shown the comparison of the performance of the various machine learning models in which we have found out the accuracy of CNN on depth- images has given the most accurate performance than other models. All these resulted were obtained on PYNQ Z2 board.

Pneumonia is an infection in one or both the lungs because of virus or bacteria through breathing air. It inflames air sacs in lungs which fill with fluid which further leads to problems in respiration. Pneumonia is interpreted by radiologists by observing abnormality in lungs in case of fluid in Chest X-Rays. Computer Aided Detection Diagnosis (CAD) tools can assist radiologists by improving their diagnostic accuracy. Such CAD tools use neural networks which are trained on Chest X-Ray dataset to classify a Chest X-Ray into normal or infected with Pneumonia. Convolution neural networks have shown remarkable performance in object detection in an image. Quaternion Convolution neural network (QCNN) is a generalization of conventional convolution neural networks. QCNN treats all three channels (R, G, B) of color image as a single unit and it extracts better representative features and which further improves classification. In this paper, we have trained Quaternion residual network on a publicly available large Chest X-Ray dataset on Kaggle repository and obtained classification accuracy of 93.75% and F-score of .94. We have also compared our performance with other CNN architectures. We found that classification accuracy was higher with Quaternion Residual network when we compared it with a real valued Residual network.

This study focusses mainly on assessing the effectiveness of acetone organosolv process as a pretreatment strategy on mustard (Brassica juncea) biomass. We used aqueous acetone as the solvent and sulfuric acid as a catalyst for ease of cellulosic saccharification. The acetone organosolv pretreatment of mustard straw and stalk (MSS) biomass was investigated for the effect of acetone concentration (SC), acid catalyst concentration (AC), and treatment duration (t) using a full factorial design of the experiment and subsequent Pareto analysis of their effects. The 23 full factorials design contained 12 runs, each of which was deployed to pretreat weighed amount of MSS biomass. Each of the different products of these 12 runs was further saccharified using cellulase enzyme produced by Trichoderma reesei. Among the variables, the time has a pronounced effect during pretreatment on glucose yield. Since the increase in time from 30 to 90 min caused an increase of 3.39 g/L in glucose concentration, the increase in acid catalyst concentration from 0.2 to 0.4% caused an increment of 0.7 g/L in glucose content, while the rise in acetone concentration from 50 to 80% caused an increment of 0.44 g/L in glucose concentration. The reducing sugars generated after hydrolysis of MSS biomass can be utilised for the production of bioethanol by Saccharomyces cerevisiae. The FTIR data and SEM studies of untreated and treated MSS biomass were performed to indicate the pretreatment of the MSS biomass. Therefore, after pretreatment MSS biomass can be an alternative substrate for bioethanol production. This study is an attempt to promote the valorization of widely available MSS biomass for bioethanol production by using a statistically optimized process.

Cancer is one of the most lethal forms of the disease. And in females, breast cancer is the most common cancer which could even lead to death if not properly diagnosed. Over the years, a lot of advancement can be seen in the field of medical technology but when it comes to detecting breast cancer biopsy is the only way. Pathologists detect cancer by using histological images under the microscope. Inspecting cancer visually is a critical task; it requires a lot of attention, skill and is time-consuming. Therefore, there is a need for a faster and efficient system for detecting breast cancer. Advancements in the field of machine learning and image processing lead to multiple types of research for creating an efficient partially or fully computer monitored diagnosis system. In this paper, we have used histological images to detect and classify invasive ductal carcinoma. Our approach involves convolutional neural networks which are a very advanced and efficient technique when dealing with images in machine learning. We compared various famous deep learning models, and we used these pre-trained CNN architectures with fine-tuning to provide an efficient solution. We also used image augmentation to further improve the efficiency of the solution. In this study, we used VGG, ResNet, DenseNet, MobileNet, EfficientNet. The best result we got was using fine-tuned VGG19 and with proper image augmentation. We achieved a sensitivity of 93.05% and a precision of 94.46 with the mentioned architecture. We improved the F-Score of the latest researches by 10.2%. We have achieved an accuracy of 86.97% using a pre-trained DenseNet model which is greater than the latest researches that achieved 85.41% [30] accuracy.

Microalgal starch was harnessed to produce ethanol, a promising alternative fuel, by simultaneous saccharification and fermentation (SSF) which combined the enzymatic hydrolysis of starch to glucos...

Bioethanol is an excellent alternative for petrol and has long-term economic advantages over non-renewable liquid biofuels. Bioethanol can be produced from different biomass materials, and it is categorized into three generations by biomass. First generation bioethanol directly competes with food items while second generation bioethanol requires more land area and fertilizers. Bioethanol produced from algae comes under third generation bioethanol and has many advantages over first and second generation bioethanol. Algae have higher growth rates than plants and require less land area also they do not need additional fertilizers for their growth. Microalgae can fix atmospheric CO2 from the environment and assimilate it into lipid and carbohydrates which can be used as a substrate for biofuel production. In this work, microalgae Chlorella sp. was cultivated at 28oC and light intensity of 25µmol m-2 s-1 and used as a source of starch for bioethanol production. Chlorella starch was hydrolyzed into fermentable sugars by amylases produced from Aspergillus niger NCIM 616 for bioethanol production by yeast Saccharomyces cerevisiae NCIM 3494. Mathematical modelling gave the insight to predict the experimental profiles of bioethanol production from algal biomass. Microbial growth, reducing sugar consumption, and bioethanol production were described quantitatively by using Logistic, Pirt, and Luedeking-Piret equations respectively. The equations used in modelling of the fermentation kinetics matched very well with the experimental profiles, thus concluding that ethanol production from algal starch hydrolysate was growth-associated under the evaluated conditions.

The continuous decline of petroleum and natural gas reserves and non linear rise of oil price has brought about a realisation of the need for a change in our perpetual dependence on the fossil fuel. A day to day increased consumption of crude and petroleum products has made a considerable impact on our foreign exchange reserves. Hence, an alternate resource for the conversion of energy (both liquid and gas) is essential for the substitution of conventional fuels. Biomass is the alternate solution for the present scenario. Biomass can be converted into both liquid as well as gaseous fuels and other feedstocks for the industries.

The continuous decline of petroleum and natural gas reserves and non linear rise of oil price has brought about a realisation of the need for a change in our perpetual dependence on the fossil fuel. A day to day increased consumption of crude and petroleum products has made a considerable impact on our foreign exchange reserves. Hence, an alternate resource for the conversion of energy (both liquid and gas) is essential for the substitution of conventional fuels. Biomass is the alternate solution for the present scenario. Biomass can be converted into both liquid as well as gaseous fuels and other feedstocks for the industries., {"references":["T. K. Ghose, \"Technoeconomic Feasibility of Liquid Fuels and\nFeedestocks through Biomass Refining\", In Bioconversion and\nBiochemical Engineering, Vol 2 (Ed T. K. Ghose), IIT Delhi and SFIT\nZurich, 1980, pp. 31-56.","C. Lewis, \"Energy requirements for the bioconversion of cellulosic raw\nmaterials\", In Bioconversion and Biochemical Engineering, Vol 2 (Ed T.\nK. Ghose), IIT Delhi and SFIT Zurich, 1980, pp. 57-72.","\"Green Energy from Wastes\", An UNDP/GEF assisted Project on\n\"Development of High Rate Biomethanation Processes as means of\nReducing Greenhouse Gases Emission\" Ministry of Non - Conventional\nEnergy Sources Government of India, March 2006.","T. K. Ghose and B. Ghosh, \"Organic Feedstocks – Chemical versus\nBiochemical Routes\", Proc. VII International Biotechnology\nSymposium, New Delhi, 1984, pp. 41-44.","W. E. Batch, G. E. Fox, L. G. Magrum, C. R. Woese and R. S. Wolfe,\n\"Methanogens: Reevaluation of a Unique Biological Group\", Microbial\nRev., 1979, pp. 43, 260-296.","J. G. Zeikus and V. G. Bowen, \"Fine structure of Methanospirillum\nHangati\", J. Bact., 1975, pp. 121, 373-380.","Z. P. A. Silva, S. I. Mussatto, I. C. Robarto and J. A. Teixeira, \"Ethanol\nproduction from xylose by Pichia stipitis NRRL Y-7124 in a stirred tank\nbioreactor\", Braz. J. Chem. Eng., 2011, Vol 28, pp. 151-156.","M. Yoon, J. Choi, G. H. Kim, D. Kim and D. Park, \"Proteomic analysis\nof Spirogyra varians mutant with high starch content and growth rate\ninduced by gamma irradiation\", Bioprocess Biosyst Eng., 2013, Vol. 36\n(6), pp. 765-774.","I. K. Kapdan and F. Kargi, \"Bio-hydrogen production from waste\nmaterials\", Enzyme and Microbial Technology, 2006, Vol 38, pp. 569-\n582.\n[10] C. Uttamrao, \"Fermentative hydrogen Production from temple and food\nwaste by batch mode using Enterobacter aerogenes\", M. Tech.\nDissertation Thesis, 2014, School of Biochemical Engineering, IIT\n(BHU), India.\n[11] S. N. Mukhopadhyay and T. K. Ghose, \"Integration of Bioconversion,\nEnvironmental and Genetic Engineering Concepts in Bioenergy\nSystem\", Proc. BESI Second Convention, 1985, pp. 260-263.\n[12] Unpublished data of the author.\n[13] S. Kundu, S. Singh, S. Ojha and K. Kundu, \"Role of Biorefining and\nBiomass Utilization in Environmental Control\", Proc. International\nScience Index, London United Kingdom Jan 19-20, 2015, 13 (01) Part\nIV, pp. 886-889."]}

Sustainable and Effectual Bio Fabrication of Gold Nanoparticles for Screening of Milk Adulteration In the present scenario, the amelioration of bio fabrication of nanoparticles has been extensively studied to overcome the harmful effects of chemical synthesis. Gold nanoparticles have found eminence in food and pharmaceutical industries due to their unique physico-chemical properties as well as their inert nature. The present work focuses upon less-stringent, non toxic and eco-friendly biosynthesis of Gold nanoparticles by Aspergillus versicolor as a reducing agent. An efficient approach for fungal growth was discussed wherein the biomass was cultivated under non-limiting conditions, followed by addition of gold salt solution. Production of gold nanoparticles has been successfully achieved using Aspergillus versicolor and the change of biomass colour from colourless to maroon was achieved within 18 hours of incubation period. Cyclic Voltammetry studies were conducted to show to the reducing efficiency of the strain. UV-Vis Spectroscopy studies of blank Czapek Dox media revealed no characteristic peak near the 540 nm range indicating no extracellular synthesis (as per no change in media colour) and only intracellular Gold Nanoparticle formation. FT-IR analysis confirmed the presence of peaks which were ascribed to functional groups of NH2, O-H, C=O, C-N, N-H, C-Cl and C-Br. The XRD results revealed varied particle sizes of 29.22 nm, 18.9 nm, 20.43 nm, 16.04 nm, 15.26 nm Gold nanoparticles. SEM results depicted the irregular spherical shape and morphology of the intracellularly adhered gold nanoparticles. The role of pH was emphasized in the mechanistic aspects of nanoparticle formation. Further, the efficacy of the gold nanoparticles was evaluated to screen varied concentrations of melamine adulteration in milk samples. Melamine is a common adulterant in milk and milk products, especially in baby foods leading to several cases of renal failure. To the best of our knowledge, this is the first report on screening of milk adulteration by biologically synthesized gold nanoparticles.

Cherry virus A (CVA) is a graft-transmissible member of the genus Capillovirus that infects different stone fruits. Sweet cherry (Prunus avium L; family Rosaceae) is an important deciduous temperate fruit crop in the Western Himalayan region of India. In order to determine the health status of cherry plantations and the incidence of the virus in India, cherry orchards in the states of Jammu and Kashmir (J&K) and Himachal Pradesh (H.P.) were surveyed during the months of May and September 2009. The incidence of CVA was found to be 28 and 13% from J&K and H.P., respectively, by RT-PCR. In order to characterize the virus at the molecular level, the complete genome was amplified by RT-PCR using specific primers. The amplicon of about 7.4 kb was sequenced and was found to be 7,379 bp long, with sequence specificity to CVA. The genome organization was similar to that of isolates characterized earlier, coding for two ORFs, in which ORF 2 is nested in ORF1. The complete sequence was 81 and 84% similar to that of the type isolate at the nucleotide and amino acid level, respectively, with 5′ and 3′ UTRs of 54 and 299 nucleotides, respectively. This is the first report of the complete nucleotide sequence of cherry virus A infecting sweet cherry in India.