Short term prediction of atmospheric temperature using neural networks

In this paper, a neural network based forecasting model for the maximum and the minimum temperature for the ground level is proposed. A backpropagation method of gradient-decent learning in multi-layer perceptron (MLP) type of neural network with only one hidden layer is considered. This network consists of 25 input nodes and two output nodes. The network is trained with a varying number of nodes in the hidden layer using a set of training sample and each of them is tested with a set of test sample. It accepts previous two consecutive days information (such as pressures, temperatures, relative humidities, etc.) as inputs for the estimation of the maximum and the minimum temperature as output. The network with 20 or less neurons in the hidden layer is found to be "optimum" and it produces an error within ±2° C for 80% of test cases.

A Novel Generative Method for Machine Fault Diagnosis

Deep learning is widely used in fault diagnosis of mechanical equipment and has achieved good results. However, these deep learning models require a large number of labeled samples for training, which is difficult to obtain enough labeled samples in the actual production process. However, it is easier to obtain unlabeled samples in the industrial environment. To overcome this problem, this paper proposes a novel method to generative enough label samples for training deep learning models. Unlike the generative adversarial networks, which required complex computing time, the calculation of the proposed novel generative method is simple and effective. First, we calculate the Euclidean distance between the training sample and the test sample; then, the weight coefficient between the training sample and the test sample is settled to generate pseudosamples; finally, combine with the pseudosamples, the deep learning method is training for machine fault diagnosis. In order to verify the effectiveness of the proposed method, two experiment datasets with planetary gearboxes and wind gearboxes are carried out with different activation functions. Experimental results show that the proposed method is effective for most activation function models.

UVC inactivation of pathogenic samples suitable for cryo-EM analysis

Cryo-electron microscopy has become an essential tool to understand structure and function of biological samples. Especially for pathogens, such as disease-causing bacteria and viruses, insights gained by cryo-EM can aid in developing cures. However, due to the biosafety restrictions of pathogens, samples are often treated by chemical fixation to render the pathogen inert, affecting the ultrastructure of the sample. Alternatively, researchers use in vitro or ex vivo models, which are non-pathogenic but lack the complexity of the pathogen of interest. Here we show that ultraviolet-C (UVC) radiation applied at cryogenic temperatures can be used to eliminate or dramatically reduce the infectivity of Vibrio cholerae and the bacterial virus, the ICP1 bacteriophage. We show no discernable structural impact of this treatment of either sample using two cryo-EM methods: cryo-electron tomography followed by sub-tomogram averaging, and single particle analysis (SPA). Additionally, we applied the UVC irradiation to the protein apoferritin (ApoF), which is a widely used test sample for high-resolution SPA studies. The UVC-treated ApoF sample resulted in a 2.1 Å structure indistinguishable from an untreated published map. This research demonstrates that UVC treatment is an effective and inexpensive addition to the cryo-EM sample preparation toolbox.

Supervised Learning in image enhance from electron microscopy inversion results

In Nondestructive testing there is a variety of applications in Material Science, where the specimen is imaged by an Electron Microscope and then by image inversion, informationis extracted for the material interior. This type of information might contain noise either by the imaging procedure or by the numerical part of the inversion. We present a method that can improve the interior density results of an inversed material from a series of Scanning Electron Microscope (SEM) images. For this method, the material density can contain some discontinuity, such as regions where it is dense and regions where there are voids.The proposed method directly stands on the Bayesian learning framework, adopting Gaussian Stochastic Processes (GSPs). Two test sample cases that contain some discontinuities in the density are tested. We also provide a comparison between two different GSP modelling approaches; one is a typical GSP and the other accounts for discontinuity, by introducing hyperparameters. The GSP method gives reconstructed data in reasonable agreement with the known original density distribution, giving confidence that the method can be applied to experimentally obtained SEM images.

Interface Reactions Responsible for Run-Out in Active Brazing: Part 4

This study examined the interface reaction between Ag-xAl filler metals having x = 0.2, 0.5, or 1.0 wt-% and Kovar™ base materials. The present investigation used the braze joint test sample configuration. The brazing conditions were 965°C (1769°F), 5 min; 995°C (1823°F), 20 min, and a vacuum of 10–7 Torr. Run-out was absent from all test samples. Combining these results with those of the Part 2 study that used high-Al, Ag-xAl filler metals (x = 2.0, 5.0, and 10 wt-%) established these conditions for run-out: Ag-xAl filler metals having x ≥ 2.0 wt-% Al, which result in reaction layer compositions, and (Fe, Ni, Co)y Alz , having z ≥ 26 at.-% Al. The limited occurrences of run-out lobes resulted from the surface tension effect that quickly reduced the driving force for additional run-out events. The interface reactions were controlled by a driving force that was an expressed function of filler metal composition (Ag-xAl) and brazing temperature, as opposed to simply thermally activated rate kinetics. The differences of reaction layer composition and thickness confirmed that the interface reactions differed between the braze joint and sessile drop configurations. Collectively, the findings from the Parts 1–4 investigations concluded that the most-effective means to mitigate run-out is to place a barrier coating on the Kovar base material that will prevent formation of the (Fe, Ni, Co)y Alz reaction layer.

Mechanical Properties and Apparent Morphology of Sandstone under Chemical Corrosion Conditions

The rise of the underground engineering provides more guarantee and convenience for human life, and the mechanical property of the surrounding rock is gradually lost, which has great harm to the long-term stability of the project. in that context of the environmental background of the project under the base of this article, firstly, a sandstone sample is taken at the site, a test sample of suitable size is made in the chamber, and then the test sample is arranged in a special device to simulate the simulated corrosion in the background of the simulation environment, Finally, the mechanical properties and apparent morphology of rock samples under different corrosion conditions were studied. The results show that the loss of the mechanical properties of the rock under different corrosion conditions is large, and the change of the acid and alkali of the solution is larger and the rock is The more obvious the damage difference of mechanical properties is, the more obvious the difference is that the pH value is from low to high, the peak strength loses 52%, 27.7%, 7%, 23%, 54% respectively. The failure morphology of corroded sandstone shows special conical morphology. Finally, the equivalent strain principle is used to interpret the corrosion of sandstone. The research results can be used for reference and reference for the long-term stability control of underground engineering based on water corrosion environment.

The use of RS-485 and CAN interfaces for connecting sensors in climate control systems of greenhouse complexes

Purpose of this article is to demonstrate the features of the use of existing connection interfaces for the functioning of climate control systems of agricultural complexes. The article contains the author's classification of the characteristics of the connection interfaces. The two most suitable interfaces are considered. The article compares RS-485 and CAN protocols. Key differences between CAN and RS-485 for use in agricultural complexes are shown. A test sample of a system containing 3 sensors was presented.

Development of a Machine Learning Model for Image-based Email Spam Detection

Combatting email spam has remained a very daunting task. Despite the over 99% accuracy in most non-image-based spam email detection, studies on image-based spam hardly attain such a high level of accuracy as new email spamming techniques that defeat existing spam filters emerges from time to time. The number of email spams sent out daily has remained a key factor in the continued use of spam. In this paper, a simple convolutional neural network model, 123DNet was developed and trained with 28,929 images drawn from 2 public datasets and a Personally Generated dataset. The model was optimized to the least set of layers to have 1 input layer, 2 embedded Convolutional layers as a hidden layer, and 3 neural network layers. The model was tested with a total of 4,339 images of the three dataset samples and then with a separate set of 1,200 images to test performance on never-seen-before images. A Classification Performance analysis was carried out using the confusion matrix. Performance metrics including Accuracy, Precision, True Negative Accuracy, Sensitivity, Specificity, and F1 Measure were computed to ascertain the model’s performance. The Model returned an F1 Score of 97% on a public dataset’s test sample and 88% on Never-seen-before test samples outperforming some pre-existing models while performing significantly well on the newly generated image test samples. It is recommended that a model that performed so well with new never-seen-before spam images be integrated into spam filtering systems. Keywords- Convolutional Neural Network, Deep Learning, Image-based Spam Detection

Photoconductivity of Thin Films Obtained from a New Type of Polyindole

The optoelectronic properties of a new poly(2-ethyl-3-methylindole) (MPIn) are discussed in this paper. The absorption and photoluminescence spectra were studied. The electronic spectrum of MPIn showed a single absorption maximum at 269 nm that is characteristic of the entire series of polyindoles. The fluorescence spectra show that the emission peaks of the test sample are centered around 520 nm. The photoconductivity of thin film samples of MPIn polyindole was studied by measuring the current-voltage characteristics under ultraviolet radiation with a wavelength of 350 nm. Samples of phototransistors were obtained, where thin films of MPIn polyindole were used as a transport layer, and their characteristics were measured and analyzed. The value of the quantum efficiency and the values of the mobility of charge carriers in thin polyindole films were estimated.

​Health-promoting Effects of Developed Probiotic Orange Beverage: An in vitro Study

Background: Probiotic food has evolved as the new trend among the health fanatics because of their proven benefits in preventing many diseases. With change in time the way of consuming probiotics has also changed. Unlike past dairy is not the only option for commercial probiotic production, recently fruit juices have become the popular choice for it. So the current study aimed to assess the feasibility of orange juice (Citrus reticulate) as a potential probiotic carrier for the production of probiotic orange juice with lactic acid bacteria. Methods: Three test samples (TS) were developed with different combination of lactic acid probiotic bacteria viz. test sample 1 (TS1) (L. bulgaricus and L. casei), TS2 (L. bulgaricus, L. casei and L. gasseri) and TS3 (L. bulgaricus, L. casei, L. gasseri and L. fermentum). The orange juice was pasteurized for 2 min at 90°C and was inoculated at a rate of 10% inoculum. All the test samples were fermented for 4 hrs at 37°C and the physicochemical and nutritional characteristics were evaluated along with their in vitro hypocholesterolemic and in vitro hypoglycemic efficacies. Result: The probiotic orange test samples did not show inferior properties than the control in terms of physicochemical and nutritional properties. The bacterial count was decreased with time but remained above standard limit (107cfu/100ml) until 28th day of refrigerated storage. All the test samples showed promising antioxidant activity, in vitro hypocholesterolemic activity and in vitro hypoglycemic activities. Hence orange juice could be used as a suitable probiotic carrier for production of novel probiotic beverages.