AI

Overview – Predict power consumption of various sites based on past data and weather data. – Serverless system running on AWS – Collect data from IOT Advantages – Cost savings – Environmental protection – Avoid wasting energy Problem – Real-time processing – Build on AWS, get data from a variety of sources – The data is not much, some data is not stable, still in the testing process Solution – Use appropriate models for time series data – Data analysis, noise processing, removal or labeling of anomalous data – Combine services on AWS into one complete flow Product

Overview: Advantages: – Save cost and training efforts – Avoid redundant resources and employees. – Save cost – Help people recognize health problems from a very early stage – Become a reliable reference to doctor when diagnosing and making decisons

OVERVIEW – Procedures such as detecting tumors, artery stenosis, organ delineation employ various different methods and frameworks like MapReduce to find optimal parameters for tasks like lung texture classification. – It applies machine learning methods, support vector machines (SVM), content-based medical image indexing, and wavelet analysis for solid texture classification. – Moreover, with a wide range of state-of-the-art deep learning neural networks and models, it is completely possible to detect and segment abnormal from medical images. Advantages – Fast – High accuracy – Save cost – Help people recognize health problems from a very early stage – Become a reliable reference to doctor when diagnosing and making decisons

Overview Sharingan is a Smart System with core technology is facial identification by Artificial Intelligence. The system provides 2 main services: Automatic Attendance Automatic Surveillance Demo Automatic Attendance Fast Accurate identification Easily deploy and leverage enterprise infrastructure Can time attendance many people at the same time Put an end to fake and forged timekeeping Automatic Surveillance Supervise employees in the workplace of the enterprise Supervise students in the classroom and notify parents

Problem: Image Captioning Given an image, our goal is to generate a caption. Input: Image Output: Caption for image Solution For this problem, we use will use InceptionV3 (which is pre-trained on Imagenet) to classify each image. We will extract features from the last convolutional layer. The RNN (here GRU) attends over the image to predict the next word. Experimental Results

Overview for Semantic Segmentation For segmentation, demonstrates the steps to use the DeepLab model to perform semantic segmentation on a sample input image. Expected outputs are semantic labels overlayed on the sample image, such as some of examples including. Atrous Spatial Pyramid Pooling (1/2) – It is proposed such as the Atrous Spatial Pyramid Pooling where four parallel atrous convolutions with different atrous rates are applied on top of the feature map. – The resulting features from all the branches are then concatenated and pass through another 1 × 1 convolution (also with 256 filters and batch normalization) before the final 1 × 1 convolution which generates the final logits. Atrous Spatial Pyramid Pooling (2/2)  How to segment every objects at each frames – Collecting data for training and Calibrating or loading the latest version of the pretrained DeepLab model (supported by Tensorflow) – Load the colormap from the PASCAL VOC dataset – Adds colors to various labels, such as “pink” for people, “green” for bicycle, e.t.c – Visualize an image, and add an overlay of colors on various regions Experimental Results