基于深度学习的情感化设计

目的使用深度学习实现情感化设计,满足用户个性化的情感需求,加速传统设计过程,提升用户体验。方法研究深度学习中可用于情感化设计的算法,使用卷积神经网络(CNN)实现名画复制品的个性化自动生成;抓取互联网数据,使用LSTM模型挖掘用户真实需求,进行当前流行游戏的周边产品设计;以张裕葡萄酒庄旅游纪念品设计为例,使用深度学习基于用户个人信息和行为数据推荐个性化的葡萄酒包装。结论基于CNN的名画复制品的个性化生成丰富了图像的可修改空间,满足了用户个性化的情感诉求;基于LSTM的用户需求分析高效和准确地反映了用户的真实需求,加速了传统用户调研过程;基于深度学习的旅游纪念品个性化设计进一步提升了用户体验。将深度学习应用于情感化设计有利于挖掘用户内心的真实需求,节省人力物力,满足用户情感诉求和提升用户体验,进一步为设计学与计算机科学的交叉提供了有效方法。     

The Role of Deep Learning in Parking Space Identification andPredictionSystems

In today’s smart city transportation, traffic congestion is a vexing issue, and vehicles seeking parking spaces have been identified as one of the causes leading to approximately 40% of traffic congestion. Identifying parking spaces alone is insufficient because an identified available parking space may have been taken by another vehicle when it arrives, resulting in the driver’s frustration and aggravating traffic jams while searching for another parking space. This explains the need to predict the availability of parking spaces. Recently, deep learning (DL) has been shown to facilitate drivers to find parking spaces efficiently, leading to a promising performance enhancement in parking identification and prediction systems. However, no work reviews DL approaches applied to solve parking identification and prediction problems. Inspired by this gap, the purpose of this work is to investigate, highlight, and report on recent advances in DL approaches applied to predict and identify the availability of parking spaces. A taxonomy of DL-based parking identification and prediction systems is established as a methodology by classifying and categorizing existing literature, and by doing so, the salient and supportive features of different DL techniques for providing parking solutions are presented. Moreover, several open research challenges are outlined. This work identifies that there are various DL architectures, datasets, and performance measures used to address parking identification and prediction problems. Moreover, there are some open-source implementations available that can be used directly either to extend existing works or explore a new domain. This is the first short survey article that focuses on the use of DL-based techniques in parking identification and prediction systems for smart cities. This study concludes that although the deployment of DL in parking identification and prediction systems provides various benefits, the convergence of these two types of systems and DL brings about new issues that must be resolved in the near future.     

Software Defect Prediction Based on Non-Linear Manifold Learning and Hybrid Deep Learning Techniques

Software defect prediction plays a very important role in software quality assurance, which aims to inspect as many potentially defect-prone software modules as possible. However, the performance of the prediction model is susceptible to high dimensionality of the dataset that contains irrelevant and redundant features. In addition, software metrics for software defect prediction are almost entirely traditional features compared to the deep semantic feature representation from deep learning techniques. To address these two issues, we propose the following two solutions in this paper: (1) We leverage a novel non-linear manifold learning method - SOINN Landmark Isomap (SLIsomap) to extract the representative features by selecting automatically the reasonable number and position of landmarks, which can reveal the complex intrinsic structure hidden behind the defect data. (2) We propose a novel defect prediction model named DLDD based on hybrid deep learning techniques, which leverages denoising autoencoder to learn true input features that are not contaminated by noise, and utilizes deep neural network to learn the abstract deep semantic features. We combine the squared error loss function of denoising autoencoder with the cross entropy loss function of deep neural network to achieve the best prediction performance by adjusting a hyperparameter. We compare the SL-Isomap with seven state-of-the-art feature extraction methods and compare the DLDD model with six baseline models across 20 open source software projects. The experimental results verify that the superiority of SL-Isomap and DLDD on four evaluation indicators.     

Automated Chinese Essay Scoring Based on Deep Learning

Writing is an important part of language learning and is considered the best approach to demonstrate the comprehensive language skills of students. Manually grading student essays is a time-consuming task; however, it is necessary. An automated essay scoring system can not only greatly improve the efficiency of essay scoring, but also provide more objective score. Therefore, many researchers have been exploring automated essay scoring techniques and tools. However, the technique of scoring Chinese essays is still limited, and its accuracy needs to be enhanced further. To improve the accuracy of the scoring model for a Chinese essay, we propose an automated scoring approach based on a deep learning model and validate its effect by conducting two comparison experiments. The experimental results indicate that the accuracy of the proposed model is significantly higher than that of multiple linear regression (MLR), which was commonly used in the past. The three accuracy rates of the proposed model are comparable to those of the novice teacher. The root mean square error (RMSE) of the proposed model is slightly lower than that of the novice teacher, and the correlation coefficient of the proposed model is also significantly higher than that of the novice teacher. Besides, when the predicted scores are not very low or very high, the two predicted models are as good as a novice teacher. However, when the predicted score is very high or very low, the results should be treated with caution.     

Electroencephalogram (EEG) Brain Signals to Detect Alcoholism Based on Deep Learning

The detection of alcoholism is of great importance due to its effects on individuals and society. Automatic alcoholism detection system (AADS) based on electroencephalogram (EEG) signals is effective, but the design of a robust AADS is a challenging problem. AADS’ current designs are based on conventional, hand-engineered methods and restricted performance. Driven by the excellent deep learning (DL) success in many recognition tasks, we implement an AAD system based on EEG signals using DL. A DL model requires huge number of learnable parameters and also needs a large dataset of EEG signals for training which is not easy to obtain for the AAD problem. In order to solve this problem, we propose a multi-channel Pyramidal neural convolutional (MP-CNN) network that requires a less number of learnable parameters. Using the deep CNN model, we build an AAD system to detect from EEG signal segments whether the subject is alcoholic or normal. We validate the robustness and effectiveness of proposed AADS using KDD, a benchmark dataset for alcoholism detection problem. In order to find the brain region that contributes significant role in AAD, we investigated the effects of selected 19 EEG channels (SC-19), those from the whole brain (ALL-61), and 05 brain regions, i.e., TEMP, OCCIP, CENT, FRONT, and PERI. The results show that SC-19 contributes significant role in AAD with the accuracy of 100%. The comparison reveals that the state-of-the-art systems are outperformed by the AADS. The proposed AADS will be useful in medical diagnosis research and health care systems.     

基于深度学习的包装组件检测系统研究

目的 针对人工分拣组成的零件包装盒常常会出现缺少部分零件的问题,开发一套集训练、识别、分选于一体的智能分拣系统.方法 在设计过程中,提出一种基于深度学习的改进Yolov3算法,针对工业现场光照、业零件形状和质地等实际因素,对Yolo算法的训练和检测进行改进,通过对包装盒产品的一次拍摄,检测出画面中出现的预设物体,并与标准设置相比对,从而判断出该盒内产品是否有缺料、多料的情况,以此分选出合格与否的包装盒.结果 在物体摆放相互重叠不超过20％的情况下,物体检测的准确率为98.2％,召回率为99.5％.结论 通过文中提出的改进算法,设计的检测系统能够在复杂的工业现场环境下正常工作,并能对包装的完整性进行准确的检测.     

Adversarial Attacks and Defenses in Deep Learning

With the rapid developments of artificial intelligence (AI) and deep learning (DL) techniques, it is critical to ensure the security and robustness of the deployed algorithms. Recently, the security vulnerability of DL algorithms to adversarial samples has been widely recognized. The fabricated samples can lead to various misbehaviors of the DL models while being perceived as benign by humans. Successful implementations of adversarial attacks in real physical-world scenarios further demonstrate their practicality. Hence, adversarial attack and defense techniques have attracted increasing attention from both machine learning and security communities and have become a hot research topic in recent years. In this paper, we first introduce the theoretical foundations, algorithms, and applications of adversarial attack techniques. We then describe a few research efforts on the defense techniques, which cover the broad frontier in the field. Several open problems and challenges are subsequently discussed, which we hope will provoke further research efforts in this critical area.     

基于深度学习的界面设计美学评价研究

目的美感已经成为人机交互(HCI)的核心结构之一,对用户的感知和态度具有明显的有益影响。然而界面美观性评价方法仍是设计师及其团队所面临的重要问题。引入深度学习技术来探讨其评价界面设计美感的可能性。方法分别使用基于深度卷积神经网络的闪屏美学分类方法和Google提出的基于深度学习NIMA神经网络,来预测闪屏图像的美学评价分布。结果通过研究发现,使用基于深度学习NIMA神经网络可以得到比传统方法更具体的评价结果,帮助设计师有效而客观地评价界面设计。结论将计算机图像美学评价的研究领域拓展到界面设计领域,验证了深度卷积神经网络在界面设计美学评价领域使用的可行性。未来图像美学评价还可以介入更多的设计相关领域,辅助设计师做出更有效的设计和商业决策。     

基于深度学习的易拉罐缺陷检测技术

目的 现有的易拉罐缺陷检测系统在高速生产线中存在错检率和漏检率高,检测精度相对较低等问题,为了提高易拉罐缺陷识别的准确性,使易拉罐生产线实现进一步自动化、智能化,基于深度学习技术和迁移学习技术,提出一种适用于易拉罐制造的在线检测的算法。方法 利用深度卷积网络提取易拉罐缺陷特征,通过优化卷积核,减短易拉罐缺陷检测的时间。针对国内外数据集缺乏食品包装制造的缺陷图像,构建易拉罐缺陷数据集,结合预训练网络,通过调整VGG16提升对易拉罐缺陷的识别准确率。结果 对易拉罐数据集在卷积神经网络、迁移学习和调整后的预训练网络进行了易拉罐缺陷检测的性能对比,验证了基于深度学习的易拉罐缺陷检测技术在学习率为0.0005,训练10个迭代后可达到较好的识别效果,最终二分类缺陷识别率为99.7%,算法耗时119 ms。结论 相较于现有的易拉罐检测算法,文中提出的基于深度学习的易拉罐检测算法的识别性能更优,智能化程度更高。同时,该研究有助于制罐企业利用深度学习等AI技术促进智能化生产,减少人力成本,符合国家制造业产业升级的策略,具有一定的实际意义。     

Deep Learning Control for Autonomous Robot

Several applications of machine learning and artificial intelligence, have acquired importance and come to the fore as a result of recent advances and improvements in these approaches. Autonomous cars are one such application. This is expected to have a significant and revolutionary influence on society. Integration with smart cities, new infrastructure and urban planning with sophisticated cyber-security are some of the current ramifications of self-driving automobiles. The autonomous automobile, often known as self-driving systems or driverless vehicles, is a vehicle that can perceive its surroundings and navigate predetermined routes without human involvement. Cars are on the verge of evolving into autonomous robots, thanks to significant breakthroughs in artificial intelligence and related technologies, and this will have a wide range of socio-economic implications. However, in order for these automobiles to become a reality, they must be endowed with the perception and cognition necessary to deal with high-pressure real-life events and make proper judgments and take appropriate action. The majority of self-driving car technologies are based on computer systems that automate vehicle control parts. From forward-collision warning and antilock brakes to lane-keeping and adaptive drive control, to fully automated driving, these technological components have a wide range of capabilities. A self-driving car combines a wide range of sensors, actuators, and cameras. Recent researches on computer vision and deep learning are used to control autonomous driving systems. For self-driving automobiles, lane-keeping is crucial. This study presents a deep learning approach to obtain the proper steering angle to maintain the robot in the lane. We propose an advanced control for a self-driving robot by using two controllers simultaneously. Convolutional neural networks (CNNs) are employed, to predict the car’ and a proportional-integral-derivative (PID) controller is designed for speed and steering control. This study uses a Raspberry PI based camera to control the robot car.     

Early Detection of Diabetic Retinopathy Using Machine Intelligence through Deep Transfer and Representational Learning

Diabetic retinopathy (DR) is a retinal disease that causes irreversible blindness. DR occurs due to the high blood sugar level of the patient, and it is clumsy to be detected at an early stage as no early symptoms appear at the initial level. To prevent blindness, early detection and regular treatment are needed. Automated detection based on machine intelligence may assist the ophthalmologist in examining the patients’ condition more accurately and efficiently. The purpose of this study is to produce an automated screening system for recognition and grading of diabetic retinopathy using machine learning through deep transfer and representational learning. The artificial intelligence technique used is transfer learning on the deep neural network, Inception-v4. Two configuration variants of transfer learning are applied on Inception-v4: Fine-tune mode and fixed feature extractor mode. Both configuration modes have achieved decent accuracy values, but the fine-tuning method outperforms the fixed feature extractor configuration mode. Fine-tune configuration mode has gained 96.6% accuracy in early detection of DR and 97.7% accuracy in grading the disease and has outperformed the state of the art methods in the relevant literature.     

Deep Learning Based Underground Sewer Defect Classification Using a Modified RegNet

The sewer system plays an important role in protecting rainfall and treating urban wastewater. Due to the harsh internal environment and complex structure of the sewer, it is difficult to monitor the sewer system. Researchers are developing different methods, such as the Internet of Things and Artificial Intelligence, to monitor and detect the faults in the sewer system. Deep learning is a promising artificial intelligence technology that can effectively identify and classify different sewer system defects. However, the existing deep learning based solution does not provide high accuracy prediction and the defect class considered for classification is very small, which can affect the robustness of the model in the constraint environment. As a result, this paper proposes a sewer condition monitoring framework based on deep learning, which can effectively detect and evaluate defects in sewer pipelines with high accuracy. We also introduce a large dataset of sewer defects with 20 different defect classes found in the sewer pipeline. This study modified the original RegNet model by modifying the squeeze excitation (SE) block and adding the dropout layer and Leaky Rectified Linear Units (LeakyReLU) activation function in the Block structure of RegNet model. This study explored different deep learning methods such as RegNet, ResNet50, very deep convolutional networks (VGG), and GoogleNet to train on the sewer defect dataset. The experimental results indicate that the proposed system framework based on the modified-RegNet (RegNet+) model achieves the highest accuracy of 99.5 compared with the commonly used deep learning models. The proposed model provides a robust deep learning model that can effectively classify 20 different sewer defects and be utilized in real-world sewer condition monitoring applications.     

Enhanced Deep Autoencoder Based Feature Representation Learning for Intelligent Intrusion Detection System

In the era of Big data, learning discriminant feature representation from network traffic is identified has as an invariably essential task for improving the detection ability of an intrusion detection system (IDS). Owing to the lack of accurately labeled network traffic data, many unsupervised feature representation learning models have been proposed with state-of-the-art performance. Yet, these models fail to consider the classification error while learning the feature representation. Intuitively, the learnt feature representation may degrade the performance of the classification task. For the first time in the field of intrusion detection, this paper proposes an unsupervised IDS model leveraging the benefits of deep autoencoder (DAE) for learning the robust feature representation and one-class support vector machine (OCSVM) for finding the more compact decision hyperplane for intrusion detection. Specially, the proposed model defines a new unified objective function to minimize the reconstruction and classification error simultaneously. This unique contribution not only enables the model to support joint learning for feature representation and classifier training but also guides to learn the robust feature representation which can improve the discrimination ability of the classifier for intrusion detection. Three set of evaluation experiments are conducted to demonstrate the potential of the proposed model. First, the ablation evaluation on benchmark dataset, NSL-KDD validates the design decision of the proposed model. Next, the performance evaluation on recent intrusion dataset, UNSW-NB15 signifies the stable performance of the proposed model. Finally, the comparative evaluation verifies the efficacy of the proposed model against recently published state-of-the-art methods.     

Investigation on the Chinese Text Sentiment Analysis Based on Convolutional Neural Networks in Deep Learning

Nowadays, the amount of wed data is increasing at a rapid speed, which presents a serious challenge to the web monitoring. Text sentiment analysis, an important research topic in the area of natural language processing, is a crucial task in the web monitoring area. The accuracy of traditional text sentiment analysis methods might be degraded in dealing with mass data. Deep learning is a hot research topic of the artificial intelligence in the recent years. By now, several research groups have studied the sentiment analysis of English texts using deep learning methods. In contrary, relatively few works have so far considered the Chinese text sentiment analysis toward this direction. In this paper, a method for analyzing the Chinese text sentiment is proposed based on the convolutional neural network (CNN) in deep learning in order to improve the analysis accuracy. The feature values of the CNN after the training process are nonuniformly distributed. In order to overcome this problem, a method for normalizing the feature values is proposed. Moreover, the dimensions of the text features are optimized through simulations. Finally, a method for updating the learning rate in the training process of the CNN is presented in order to achieve better performances. Experiment results on the typical datasets indicate that the accuracy of the proposed method can be improved compared with that of the traditional supervised machine learning methods, e.g., the support vector machine method.     

Automated Deep Learning Based Melanoma Detection and Classification Using Biomedical Dermoscopic Images

Melanoma remains a serious illness which is a common form of skin cancer. Since the earlier detection of melanoma reduces the mortality rate, it is essential to design reliable and automated disease diagnosis model using dermoscopic images. The recent advances in deep learning (DL) models find useful to examine the medical image and make proper decisions. In this study, an automated deep learning based melanoma detection and classification (ADL-MDC) model is presented. The goal of the ADL-MDC technique is to examine the dermoscopic images to determine the existence of melanoma. The ADL-MDC technique performs contrast enhancement and data augmentation at the initial stage. Besides, the k-means clustering technique is applied for the image segmentation process. In addition, Adagrad optimizer based Capsule Network (CapsNet) model is derived for effective feature extraction process. Lastly, crow search optimization (CSO) algorithm with sparse autoencoder (SAE) model is utilized for the melanoma classification process. The exploitation of the Adagrad and CSO algorithm helps to properly accomplish improved performance. A wide range of simulation analyses is carried out on benchmark datasets and the results are inspected under several aspects. The simulation results reported the enhanced performance of the ADL-MDC technique over the recent approaches.     

Deep Transfer Learning Based Detection and Classification of Citrus Plant Diseases

Citrus fruit crops are among the world’s most important agricultural products, but pests and diseases impact their cultivation, resulting in yield and quality losses. Computer vision and machine learning have been widely used to detect and classify plant diseases over the last decade, allowing for early disease detection and improving agricultural production. This paper presented an automatic system for the early detection and classification of citrus plant diseases based on a deep learning (DL) model, which improved accuracy while decreasing computational complexity. The most recent transfer learning-based models were applied to the Citrus Plant Dataset to improve classification accuracy. Using transfer learning, this study successfully proposed a Convolutional Neural Network (CNN)-based pre-trained model (EfficientNetB3, ResNet50, MobiNetV2, and InceptionV3) for the identification and categorization of citrus plant diseases. To evaluate the architecture’s performance, this study discovered that transferring an EfficientNetb3 model resulted in the highest training, validating, and testing accuracies, which were 99.43%, 99.48%, and 99.58%, respectively. In identifying and categorizing citrus plant diseases, the proposed CNN model outperforms other cutting-edge CNN model architectures developed previously in the literature.     

On the Detection of COVID-19 from Chest X-Ray Images Using CNN-Based Transfer Learning

Coronavirus disease (COVID-19) is an extremely infectious disease and possibly causes acute respiratory distress or in severe cases may lead to death. There has already been some research in dealing with coronavirus using machine learning algorithms, but few have presented a truly comprehensive view. In this research, we show how convolutional neural network (CNN) can be useful to detect COVID-19 using chest X-ray images. We leverage the CNN-based pre-trained models as feature extractors to substantiate transfer learning and add our own classifier in detecting COVID-19. In this regard, we evaluate performance of five different pre-trained models with fine-tuning the weights from some of the top layers. We also develop an ensemble model where the predictions from all chosen pre-trained models are combined to generate a single output. The models are evaluated through 5-fold cross validation using two publicly available data repositories containing healthy and infected (both COVID-19 and other pneumonia) chest X-ray images. We also leverage two different visualization techniques to observe how efficiently the models extract important features related to the detection of COVID- 19 patients. The models show high degree of accuracy, precision, and sensitivity. We believe that the models will aid medical professionals with improved and faster patient screening and pave a way to further COVID-19 research.     

Deep Learning and Machine Learning for Early Detection of Stroke and Haemorrhage

Stroke and cerebral haemorrhage are the second leading causes of death in the world after ischaemic heart disease. In this work, a dataset containing medical, physiological and environmental tests for stroke was used to evaluate the efficacy of machine learning, deep learning and a hybrid technique between deep learning and machine learning on the Magnetic Resonance Imaging (MRI) dataset for cerebral haemorrhage. In the first dataset (medical records), two features, namely, diabetes and obesity, were created on the basis of the values of the corresponding features. The t-Distributed Stochastic Neighbour Embedding algorithm was applied to represent the high-dimensional dataset in a low-dimensional data space. Meanwhile,the Recursive Feature Elimination algorithm (RFE) was applied to rank the features according to priority and their correlation to the target feature and to remove the unimportant features. The features are fed into the various classification algorithms, namely, Support Vector Machine (SVM), K Nearest Neighbours (KNN), Decision Tree, Random Forest, and Multilayer Perceptron. All algorithms achieved superior results. The Random Forest algorithm achieved the best performance amongst the algorithms; it reached an overall accuracy of 99%. This algorithm classified stroke cases with Precision, Recall and F1 score of 98%, 100% and 99%, respectively. In the second dataset, the MRI image dataset was evaluated by using the AlexNet model and AlexNet + SVM hybrid technique. The hybrid model AlexNet + SVM performed is better than the AlexNet model; it reached accuracy, sensitivity, specificity and Area Under the Curve (AUC) of 99.9%, 100%, 99.80% and 99.86%, respectively.     

Quasi-Phase Equilibrium Prediction of Multi-Element Alloys Based on Machine Learning and Deep Learning

In this study, a phase field model is established to simulate the microstructure formation during the solidification of dendrites by taking the Al-Cu-Mg ternary alloy as an example, and machine learning and deep learning methods are combined with the Kim-Kim-Suzuki (KKS) phase field model to predict the quasi-phase equilibrium. The paper first uses the least squares method to obtain the required data and then applies eight machine learning methods and five deep learning methods to train the quasi-phase equilibrium prediction models. After obtaining different models, this paper compares the reliability of the established models by using the test data and uses two evaluation criteria to analyze the performance of these models. This work find that the performance of the established deep learning models is generally better than that of the machine learning models, and the Multilayer Perceptron (MLP) based quasi-phase equilibrium prediction model achieves the best performance. Meanwhile the Convolutional Neural Network (CNN) based model also achieves competitive results. The experimental results show that the model proposed in this paper can predict the quasi-phase equilibrium of the KKS phase-field model accurately, which proves that it is feasible to combine machine learning and deep learning methods with phase-field model simulation.     

HDLIDP: A Hybrid Deep Learning Intrusion Detection and Prevention Framework

Distributed denial-of-service (DDoS) attacks are designed to interrupt network services such as email servers and webpages in traditional computer networks. Furthermore, the enormous number of connected devices makes it difficult to operate such a network effectively. Software defined networks (SDN) are networks that are managed through a centralized control system, according to researchers. This controller is the brain of any SDN, composing the forwarding table of all data plane network switches. Despite the advantages of SDN controllers, DDoS attacks are easier to perpetrate than on traditional networks. Because the controller is a single point of failure, if it fails, the entire network will fail. This paper offers a Hybrid Deep Learning Intrusion Detection and Prevention (HDLIDP) framework, which blends signature-based and deep learning neural networks to detect and prevent intrusions. This framework improves detection accuracy while addressing all of the aforementioned problems. To validate the framework, experiments are done on both traditional and SDN datasets; the findings demonstrate a significant improvement in classification accuracy.