Semantic guided knowledge graph for large-scale zero-shot learning

Zero-shot learning has received growing attention, which aims to improve generalization to unseen concepts. The key challenge in zero-shot tasks is to precisely model the relationship between seen and unseen classes. Most existing zero-shot learning methods capture inter-class relationships via a shared embedding space, leading to inadequate use of relationships and poor performance. Recently, knowledge graph-based methods have emerged as a new trend of zero-shot learning. These methods use a knowledge graph to accurately model the inter-class relationships. However, the currently dominant method for zero-shot learning directly extracts the fixed connection from off-the-shelf WordNet, which will inherit the inherent noise in WordNet. In this paper, we propose a novel method that adopts class-level semantic information as a guidance to construct a new semantic guided knowledge graph (SG-KG), which can correct the errors in the existing knowledge graph and accurately model the inter-class relationships. Specifically, our method includes two main steps: noise suppression and semantic enhancement. Noise suppression is used to eliminate noise edges in the knowledge graph, and semantic enhancement is used to connect two classes with strong relations. To promote high efficient information propagation among classes, we develop a novel multi-granularity fusion network (MGFN) that integrates discriminative information from multiple GCN branches. Extensive experiments on the large-scale ImageNet-21K dataset and AWA2 dataset demonstrate that our method consistently surpasses existing methods and achieves a new state-of-the-art result.     

Unsupervised learning of multi-task deep variational model

We propose a general deep variational model (reduced version, full version as well as the extension) via a comprehensive fusion approach in this paper. It is able to realize various image tasks in a completely unsupervised way without learning from samples. Technically, it can properly incorporate the CNN based deep image prior (DIP) architecture into the classic variational image processing models. The minimization problem solving strategy is transformed from iteratively minimizing the sub-problem for each variable to automatically minimizing the loss function by learning the generator network parameters. The proposed deep variational (DV) model contributes to the high order image edition and applications such as image restoration, inpainting, decomposition and texture segmentation. Experiments conducted have demonstrated significant advantages of the proposed deep variational model in comparison with several powerful techniques including variational methods and deep learning approaches.     

基于时空图卷积网络的交通事故风险预测研究

交通事故的预测是通过对过去路段发生的交通事故进行分析,在综合考虑影响交通事故的相关因素后,对未来路段的交通事故发生状态进行预测。以往的大多数研究通常采用传统机器学习方法或单一深度学习模型预测法,利用网格化确定预测空间的单位,忽略了影响交通事故的天气、路况等外部因素,导致模型的预测性能不佳。提出一种基于时空特性的城市交通事故风险预测模型,在模型中使用改进的时空图卷积网络,利用图卷积网络（GCN）提取空间相关特征,并加入批标准化层解决梯度消失爆炸问题。在时间维度上采用门控线性单元（GLU）实现一维卷积操作,提取时间相关特征,并将GCN和GLU组合成时空卷积模块提取时空相关特征,使用均方误差损失函数解决样本数据零膨胀问题。实验结果表明,与GLU、SDCAE和ConvLSTM模型相比,该模型的RMSE指标分别降低了28%、4.87%、4.19%,能有效捕获时空相关性,综合性能得到较大提升。     

An anticrime information support system design: Application of K-means-VMD-BiGRU in the city of Chicago

The sharp rise in urban crime rates is becoming one of the most important issues of public security, affecting many aspects of social sustainability, such as employment, livelihood, health care, and education. Therefore, it is critical to develop a predictive model capable of identifying areas with high crime intensity and detecting trends of crime occurrence in such areas for the allocation of scarce resources and investment in the prevention and reduction of criminal strategies. This study develops a predictive model based on K-means clustering, signal decomposition technique, and neural networks to identify crime distribution in urban areas and accurately forecast the variation tendency of the number of crimes in each area. We find that the time series of the number of crimes in different areas show a correlation in the long term, but this long-term effect cannot be reflected in the short period. Therefore, we argue that short-term joint law enforcement has no theoretical basis because data show that spatial heterogeneity and time lag cannot be timely reflected in short-term prediction. By combining the temporal and spatial effects, a high-precision anticrime information support system is designed, which can help the police to implement more targeted crime prevention strategies at the micro level.     

Mammogram Learning System for Breast Cancer Diagnosis Using Deep Learning SVM

The most common form of cancer for women is breast cancer. Recent advances in medical imaging technologies increase the use of digital mammograms to diagnose breast cancer. Thus, an automated computerized system with high accuracy is needed. In this study, an efficient Deep Learning Architecture (DLA) with a Support Vector Machine (SVM) is designed for breast cancer diagnosis. It combines the ideas from DLA with SVM. The state-of-the-art Visual Geometric Group (VGG) architecture with 16 layers is employed in this study as it uses the small size of 3 × 3 convolution filters that reduces system complexity. The softmax layer in VGG assumes that the training samples belong to exactly only one class, which is not valid in a real situation, such as in medical image diagnosis. To overcome this situation, SVM is employed instead of the softmax layer in VGG. Data augmentation is also employed as DLA usually requires a large number of samples. VGG model with different SVM kernels is built to classify the mammograms. Results show that the VGG-SVM model has good potential for the classification of Mammographic Image Analysis Society (MIAS) database images with an accuracy of 98.67%, sensitivity of 99.32%, and specificity of 98.34%.     

Deep Convolutional Neural Network Approach for COVID-19 Detection

Coronavirus disease 2019 (Covid-19) is a life-threatening infectious disease caused by a newly discovered strain of the coronaviruses. As by the end of 2020, Covid-19 is still not fully understood, but like other similar viruses, the main mode of transmission or spread is believed to be through droplets from coughs and sneezes of infected persons. The accurate detection of Covid-19 cases poses some questions to scientists and physicians. The two main kinds of tests available for Covid-19 are viral tests, which tells you whether you are currently infected and antibody test, which tells if you had been infected previously. Routine Covid-19 test can take up to 2 days to complete; in reducing chances of false negative results, serial testing is used. Medical image processing by means of using Chest X-ray images and Computed Tomography (CT) can help radiologists detect the virus. This imaging approach can detect certain characteristic changes in the lung associated with Covid-19. In this paper, a deep learning model or technique based on the Convolutional Neural Network is proposed to improve the accuracy and precisely detect Covid-19 from Chest Xray scans by identifying structural abnormalities in scans or X-ray images. The entire model proposed is categorized into three stages: dataset, data pre-processing and final stage being training and classification.     

Performance Analysis of Machine Learning Algorithms for Classifying Hand Motion-Based EEG Brain Signals

Brain-computer interfaces (BCIs) records brain activity using electroencephalogram (EEG) headsets in the form of EEG signals; these signals can be recorded, processed and classified into different hand movements, which can be used to control other IoT devices. Classification of hand movements will be one step closer to applying these algorithms in real-life situations using EEG headsets. This paper uses different feature extraction techniques and sophisticated machine learning algorithms to classify hand movements from EEG brain signals to control prosthetic hands for amputated persons. To achieve good classification accuracy, denoising and feature extraction of EEG signals is a significant step. We saw a considerable increase in all the machine learning models when the moving average filter was applied to the raw EEG data. Feature extraction techniques like a fast fourier transform (FFT) and continuous wave transform (CWT) were used in this study; three types of features were extracted, i.e., FFT Features, CWT Coefficients and CWT scalogram images. We trained and compared different machine learning (ML) models like logistic regression, random forest, k-nearest neighbors (KNN), light gradient boosting machine (GBM) and XG boost on FFT and CWT features and deep learning (DL) models like VGG-16, DenseNet201 and ResNet50 trained on CWT scalogram images. XG Boost with FFT features gave the maximum accuracy of 88%.     

Defect Prediction Using Akaike and Bayesian Information Criterion

Data available in software engineering for many applications contains variability and it is not possible to say which variable helps in the process of the prediction. Most of the work present in software defect prediction is focused on the selection of best prediction techniques. For this purpose, deep learning and ensemble models have shown promising results. In contrast, there are very few researches that deals with cleaning the training data and selection of best parameter values from the data. Sometimes data available for training the models have high variability and this variability may cause a decrease in model accuracy. To deal with this problem we used the Akaike information criterion (AIC) and the Bayesian information criterion (BIC) for selection of the best variables to train the model. A simple ANN model with one input, one output and two hidden layers was used for the training instead of a very deep and complex model. AIC and BIC values are calculated and combination for minimum AIC and BIC values to be selected for the best model. At first, variables were narrowed down to a smaller number using correlation values. Then subsets for all the possible variable combinations were formed. In the end, an artificial neural network (ANN) model was trained for each subset and the best model was selected on the basis of the smallest AIC and BIC value. It was found that combination of only two variables’ ns and entropy are best for software defect prediction as it gives minimum AIC and BIC values. While, nm and npt is the worst combination and gives maximum AIC and BIC values.     

Instructing students on effective sequences of examples and problems: Does self-regulated learning improve from knowing what works and why?

Nowadays, students often practice problem-solving skills in online learning environments with the help of examples and problems. This requires them to self-regulate their learning. It is questionable how novices self-regulate their learning from examples and problems and whether they need support. The present study investigated the open questions (1) to what extent students' (novices) task selections align with instructional design principles and (2) whether informing them about these principles would improve their task selections, learning outcomes, and motivation. Higher education students (N = 150) learned a problem-solving procedure by fixed sequences of examples and problems (FS-condition), or by self-regulated learning (SRL). The SRL participants selected tasks from a database, varying in format, complexity, and cover story, either with (ISRL-condition) or without (SRL-condition) watching a video detailing the instructional design principles. Students' task-selection patterns in both SRL conditions largely corresponded to the principles, although tasks were built up in complexity more often in the ISRL-condition than in the SRL-condition. Moreover, there was still room for improvement in students' task selections after solving practice problems. The video instruction helped students to better apply certain principles, but did not enhance learning and motivation. Finally, there were no test performance or motivational differences among conditions. Although these findings might suggest it is relatively ‘safe’ to allow students to independently start learning new problems-solving tasks using examples and problems, caution is warranted: It is unclear whether these findings generalize to other student populations, as the students participating in this study have had some experience with similar tasks or learning with examples. Moreover, as there was still room for improvement in students' task selections, follow-up research should investigate how we can further improve self-regulated learning from examples and practice problems.