AUTOMATIC COLORIZATION USING CONVOLUTIONAL NEURAL NETWORKS

Automatic Colorization helps to hallucinate what an input gray scale image would look like when colorized. Automatic coloring makes it look and feel better than Grayscale. One of the most important technologies used in Machine learning is Deep Learning. Deep learning is nothing but to train the computer with certain algorithms which imitates the working of the human brain. Some of the areas in which it is used are medical, Industrial Automation, Electronics etc. The main objective of this project is coloring Grayscale images. We have umbrellaed the concepts of convolutional neural networks along with the use of the Opencv library in Python to construct our desired model. A user interface has also been fabricated to get personalized inputs using PIL. The user had to give details about boundaries, what colors to put, etc. Colorization requires considerable user intervention and remains a tedious, time consuming, and expensive task. So, in this paper we try to build a model to colorize the grayscale images automatically by using some modern deep learning techniques. In colorization task, the model needs to find characteristics to map grayscale images with colored ones.

Does AutoML Outperform Naive Forecasting?

The availability of massive amounts of temporal data opens new perspectives of knowledge extraction and automated decision making for companies and practitioners. However, learning forecasting models from data requires a knowledgeable data science or machine learning (ML) background and expertise, which is not always available to end-users. This gap fosters a growing demand for frameworks automating the ML pipeline and ensuring broader access to the general public. Automatic machine learning (AutoML) provides solutions to build and validate machine learning pipelines minimizing the user intervention. Most of those pipelines have been validated in static supervised learning settings, while an extensive validation in time series prediction is still missing. This issue is particularly important in the forecasting community, where the relevance of machine learning approaches is still under debate. This paper assesses four existing AutoML frameworks (AutoGluon, H2O, TPOT, Auto-sklearn) on a number of forecasting challenges (univariate and multivariate, single-step and multi-step ahead) by benchmarking them against simple and conventional forecasting strategies (e.g., naive and exponential smoothing). The obtained results highlight that AutoML approaches are not yet mature enough to address generic forecasting tasks once compared with faster yet more basic statistical forecasters. In particular, the tested AutoML configurations, on average, do not significantly outperform a Naive estimator. Those results, yet preliminary, should not be interpreted as a rejection of AutoML solutions in forecasting but as an encouragement to a more rigorous validation of their limits and perspectives.

Doing more with less

Automated machine learning (AutoML) promises to democratize machine learning by automatically generating machine learning pipelines with little to no user intervention. Typically, a search procedure is used to repeatedly generate and validate candidate pipelines, maximizing a predictive performance metric, subject to a limited execution time budget. While this approach to generating candidates works well for small tabular datasets, the same procedure does not directly scale to larger tabular datasets with 100,000s of observations, often producing fewer candidate pipelines and yielding lower performance, given the same execution time budget. We carry out an extensive empirical evaluation of the impact that downsampling - reducing the number of rows in the input tabular dataset - has on the pipelines produced by a genetic-programming-based AutoML search for classification tasks.

Multiplexed, quantitative serological profiling of COVID-19 from blood by a point-of-care test

Highly sensitive, specific, and point-of-care (POC) serological assays are an essential tool to manage coronavirus disease 2019 (COVID-19). Here, we report on a microfluidic POC test that can profile the antibody response against multiple severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) antigens—spike S1 (S1), nucleocapsid (N), and the receptor binding domain (RBD)—simultaneously from 60 μl of blood, plasma, or serum. We assessed the levels of antibodies in plasma samples from 31 individuals (with longitudinal sampling) with severe COVID-19, 41 healthy individuals, and 18 individuals with seasonal coronavirus infections. This POC assay achieved high sensitivity and specificity, tracked seroconversion, and showed good concordance with a live virus microneutralization assay. We can also detect a prognostic biomarker of severity, IP-10 (interferon-γ–induced protein 10), on the same chip. Because our test requires minimal user intervention and is read by a handheld detector, it can be globally deployed to combat COVID-19.

Contact modeling from images using cut finite element solvers

This paper presents a robust digital pipeline from CT images to the simulation of contact between multiple bodies. The proposed strategy relies on a recently developed immersed finite element algorithm that is capable of simulating unilateral contact between solids without meshing (Claus and Kerfriden in Int J Numer Methods Eng 113(6):938–966, 2018). It was shown that such an approach reduces the difficulties associated with the digital flow of information from analytically defined geometries to mechanical simulations. We now propose to extend our approach to include geometries, which are not defined mathematically but instead are obtained from images, and encoded in 3D arrays of voxels. This paper introduces two novel elements. Firstly, we reformulate our contact algorithm into an extension of an augmented Lagrangian CutFEM algorithm. Secondly, we develop an efficient algorithm to convert the surface data generated by standard segmentation tools used in medical imaging into level-set functions. These two elements give rise to a robust digital pipeline with minimum user intervention. We demonstrate the capabilities of our algorithm on a hip joint geometry with contact between the femur and the hip bone.

Wireless Power Transfer Technologies Applied to Electric Vehicles: A Review

The expansion on the use of Electric Vehicles demands new mechanisms to ease the charging process, making it autonomous and with a reduced user intervention. This paper reviews the technologies applied to the wireless charge of Electric Vehicles. In particular, it focuses on the technologies based on the induction principle, the capacitive-based techniques, those that use radiofrequency waves and the laser powering. As described, the convenience of each technique depends on the requirements imposed on the wireless power transfer. Specifically, we can state that the power level, the distance between the power source and the electric vehicle or whether the transfer is executed with the vehicle on the move or not or the cost are critical parameters that need to be taken into account to decide which technology to use. In addition, each technique requires some complementary electronics. This paper reviews the main components that are incorporated into these systems and it provides a review of their most relevant configurations.

High diversity droplet microfluidic libraries generated with a commercial liquid spotter

Droplet libraries consisting of many reagents encapsulated in separate droplets are necessary for applications of microfluidics, including combinatorial chemical synthesis, DNA-encoded libraries, and massively multiplexed PCR. However, existing approaches for generating them are laborious and impractical. Here, we describe an automated approach using a commercial array spotter. The approach can controllably emulsify hundreds of different reagents in a fraction of the time of manual operation of a microfluidic device, and without any user intervention. We demonstrate that the droplets produced by the spotter are similarly uniform to those produced by microfluidics and automate the generation of a ~ 2 mL emulsion containing 192 different reagents in ~ 4 h. The ease with which it can generate high diversity droplet libraries should make combinatorial applications more feasible in droplet microfluidics. Moreover, the instrument serves as an automated droplet generator, allowing execution of droplet reactions without microfluidic expertise.

Steganographic visual story with mutual-perceived joint attention

Social media plays an increasingly important role in providing information and social support to users. Due to the easy dissemination of content, as well as difficulty to track on the social network, we are motivated to study the way of concealing sensitive messages in this channel with high confidentiality. In this paper, we design a steganographic visual stories generation model that enables users to automatically post stego status on social media without any direct user intervention and use the mutual-perceived joint attention (MPJA) to maintain the imperceptibility of stego text. We demonstrate our approach on the visual storytelling (VIST) dataset and show that it yields high-quality steganographic texts. Since the proposed work realizes steganography by auto-generating visual story using deep learning, it enables us to move steganography to the real-world online social networks with intelligent steganographic bots.

A review: preprocessing techniques and data augmentation for sentiment analysis

In literature, the machine learning-based studies of sentiment analysis are usually supervised learning which must have pre-labeled datasets to be large enough in certain domains. Obviously, this task is tedious, expensive and time-consuming to build, and hard to handle unseen data. This paper has approached semi-supervised learning for Vietnamese sentiment analysis which has limited datasets. We have summarized many preprocessing techniques which were performed to clean and normalize data, negation handling, intensification handling to improve the performances. Moreover, data augmentation techniques, which generate new data from the original data to enrich training data without user intervention, have also been presented. In experiments, we have performed various aspects and obtained competitive results which may motivate the next propositions.