Skeleton-Based Action Recognition with Joint Coordinates as Feature Using Neural Oblivious Decision Ensembles

Recognition of human behavior is critical in video monitoring, human-computer interaction, video comprehension, and virtual reality. The key problem with behaviour recognition in video surveillance is the high degree of variation between and within subjects. Numerous studies have suggested background-insensitive skeleton-based as the proven detection technique. The present state-of-the-art approaches to skeleton-based action recognition rely primarily on Recurrent Neural Networks (RNN) and Convolution Neural Networks (CNN). Both methods take dynamic human skeleton as the input to the network. We chose to handle skeleton data differently, relying solely on its skeleton joint coordinates as the input. The skeleton joints’ positions are defined in (x, y) coordinates. In this paper, we investigated the incorporation of the Neural Oblivious Decision Ensemble (NODE) into our proposed action classifier network. The skeleton is extracted using a pose estimation technique based on the Residual Network (ResNet). It extracts the 2D skeleton of 18 joints for each detected body. The joint coordinates of the skeleton are stored in a table in the form of rows and columns. Each row represents the position of the joints. The structured data are fed into NODE for label prediction. With the proposed network, we obtain 97.5% accuracy on RealWorld (HAR) dataset. Experimental results show that the proposed network outperforms one the state-of-the-art approaches by 1.3%. In conclusion, NODE is a promising deep learning technique for structured data analysis as compared to its machine learning counterparts such as the GBDT packages; Catboost, and XGBoost.

Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification

Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification. GNN performs feature propagation by a neural network to make predictions, while LPA uses label propagation across graph adjacency matrix to get results. However, there is still no effective way to directly combine these two kinds of algorithms. To address this issue, we propose a novel Unified Message Passaging Model (UniMP) that can incorporate feature and label propagation at both training and inference time. First, UniMP adopts a Graph Transformer network, taking feature embedding and label embedding as input information for propagation. Second, to train the network without overfitting in self-loop input label information, UniMP introduces a masked label prediction strategy, in which some percentage of input label information are masked at random, and then predicted. UniMP conceptually unifies feature propagation and label propagation and is empirically powerful. It obtains new state-of-the-art semi-supervised classification results in Open Graph Benchmark (OGB).

Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels with Variational Auto-Encoder

Multi-instance learning is a type of weakly supervised learning. It deals with tasks where the data is a set of bags and each bag is a set of instances. Only the bag labels are observed whereas the labels for the instances are unknown. An important advantage of multi-instance learning is that by representing objects as a bag of instances, it is able to preserve the inherent dependencies among parts of the objects. Unfortunately, most existing algorithms assume all instances to be identically and independently distributed, which violates real-world scenarios since the instances within a bag are rarely independent. In this work, we propose the Multi-Instance Variational Autoencoder (MIVAE) algorithm which explicitly models the dependencies among the instances for predicting both bag labels and instance labels. Experimental results on several multi-instance benchmarks and end-to-end medical imaging datasets demonstrate that MIVAE performs better than state-of-the-art algorithms for both instance label and bag label prediction tasks.

Multi-Label Prediction for Political Text-as-Data

Political scientists increasingly use supervised machine learning to code multiple relevant labels from a single set of texts. The current “best practice” of individually applying supervised machine learning to each label ignores information on inter-label association(s), and is likely to under-perform as a result. We introduce multi-label prediction as a solution to this problem. After reviewing the multi-label prediction framework, we apply it to code multiple features of (i) access to information requests made to the Mexican government and (ii) country-year human rights reports. We find that multi-label prediction outperforms standard supervised learning approaches, even in instances where the correlations among one’s multiple labels are low.

Fault Diagnosis of Reciprocating Compressor Valve Based on Transfer Learning Convolutional Neural Network

Reciprocating compressors play a vital role in oil, natural gas, and general industrial processes. Their safe and stable operation directly affects the healthy development of the enterprise economy. Since the valve failure accounts for 60% of the total failures when the reciprocating compressor fails, it is of great significance to quickly find and diagnose the failure type of the valve for the fault diagnosis of the reciprocating compressor. At present, reciprocating compressor valve fault diagnosis based on deep neural networks requires sufficient labeled data for training, but valve in real-case reciprocating compressor (VRRC) does not have enough labeled data to train a reliable model. Fortunately, the data of valve in laboratory reciprocating compressor (VLRC) contains relevant fault diagnosis knowledge. Therefore, inspired by the idea of transfer learning, a fault diagnosis method for reciprocating compressor valves based on transfer learning convolutional neural network (TCNN) is proposed. This method uses convolutional neural network (CNN) to extract the transferable features of gas temperature and pressure data from VLRC and VRRC and establish pseudolabels for VRRC unlabeled data. Three regularization terms, the maximum mean discrepancy (MMD) of the transferable features of VLRC and VRRC data, the error between the VLRC sample label prediction and the actual label, and the error between the VRRC sample label prediction and the pseudolabel, are proposed. Their weighted sum is used as an objective function to train the model, thereby reducing the distribution difference of domain feature transfer and increasing the distance between learning feature classes. Experimental results show that this method uses VLRC data to identify the health status of VRRC, and the fault recognition rate can reach 98.32%. Compared with existing methods, this method has higher diagnostic accuracy, which proves the effectiveness of this method.

Deep Learning Approach to DGA Classification for Effective Cyber Security

In recent years, invaders are increasing rapidly in an internet world. Generally, in order to detect the anonymous attackers algorithm needs more number of features. Many algorithms fail in the efficiency of detection malicious code. Immediately this codes will not infect the system; it will attack server after communicate later. Our research focuses on analyzing the traffic of botnets for the domain name determination to the IP address of the server. This botnet creates the domain name differently. Many domains are generated by attackers and create the huge Domain Name System (DNS) traffic. In this research paper, uses both public and real time environments datasets to detect the text features as well as knowledge based feature extraction. The classifying of Domain Generation Algorithm (DGA) generated malicious domains randomly making the efficiency down in many algorithms which were used preprocessing without proper feature extraction. Effectively, our proposed algorithm is used to detect DGA which generates malicious domains randomly. This effective detection of our proposed algorithm performs with text based label prediction and additional features for extraction to improve the efficiency of the model. Our proposed model achieved 94.9% accuracy for DGA classification with help of additional feature extraction and knowledge based extraction in the deep learning architecture.