SafeMove: monitoring seniors with mild cognitive impairments using deep learning and location prediction

Neural Computing and Applications - Due to society aging, age-related issues such as mild cognitive impairments (MCI) and dementia are attracting the attention of health professionals, scientists...     

基于相似论文增广的深度学习专利质量评估

实际操作中的专利质量评估多采用专家打分或者使用专家设计的质量评价指标,这导致评价过程存在主观性强、评价双方认可分歧大的问题,因此提出一种基于相似论文增广的深度学习专利质量评估方法。首先以论文作为客观评价数据,使用论文计算相似度作为增广数据来进行筛选,然后利用深度神经网络训练出能够实现论文相似性对待评估专利质量的映射的质量评估模型,最后利用评估模型估计专利质量。仿真结果表明不同领域下,在以满分为100分的前提下,所提方法得出的专利质量评估分数与对应的专家评价结果的平均误差均低于4,表明所提方法具备有效的专利质量评估能力。     

基于深度学习的精神分裂症脑电分析

精神分裂症是最常见的精神疾病之一,目前具体病因尚未明确,准确诊断患病与否是治疗该疾病的前提。深度学习是一种构造多层神经网络的机器学习方法,具有发现数据中隐藏的分布式特征表示的能力。针对精神分裂症患者的脑电信号,提出了一种栈式自编码网络深度模型,以达到根据脑电信号自动识别受试者是否患病的效果。     

基于深度强化学习的电子政务云动态化任务调度方法

电子政务云中心的任务调度一直是个复杂的问题。大多数现有的任务调度方法依赖于专家知识,通用性不强,无法处理动态的云环境,通常会导致云中心的资源利用率降低和服务质量下降,任务的完工时间变长。为此,提出了一种基于演员评论家（actor-critic,A2C）算法的深度强化学习调度方法。首先,actor网络参数化策略并根据当前系统状态选择调度动作,同时critic网络对当前系统状态给出评分;然后,使用梯度上升的方式来更新actor策略网络,其中使用了critic网络的评分来计算动作的优劣;最后,使用了两个真实的业务数据集进行模拟实验。结果显示,与经典的策略梯度算法以及五个启发式任务调度方法相比,该方法可以提高云数据中心的资源利用率并缩短离线任务的完工时间,能更好地适应动态的电子政务云环境。     

Real-time scheduling for distributed permutation flowshops with dynamic job arrivals using deep reinforcement learning

Distributed manufacturing plays an important role for large-scale companies to reduce production and transportation costs for globalized orders. However, how to real-timely and properly assign dynamic orders to distributed workshops is a challenging problem. To provide real-time and intelligent decision-making of scheduling for distributed flowshops, we studied the distributed permutation flowshop scheduling problem (DPFSP) with dynamic job arrivals using deep reinforcement learning (DRL). The objective is to minimize the total tardiness cost of all jobs. We provided the training and execution procedures of intelligent scheduling based on DRL for the dynamic DPFSP. In addition, we established a DRL-based scheduling model for distributed flowshops by designing suitable reward function, scheduling actions, and state features. A novel reward function is designed to directly relate to the objective. Various problem-specific dispatching rules are introduced to provide efficient actions for different production states. Furthermore, four efficient DRL algorithms, including deep Q-network (DQN), double DQN (DbDQN), dueling DQN (DlDQN), and advantage actor-critic (A2C), are adapted to train the scheduling agent. The training curves show that the agent learned to generate better solutions effectively and validate that the system design is reasonable. After training, all DRL algorithms outperform traditional meta-heuristics and well-known priority dispatching rules (PDRs) by a large margin in terms of solution quality and computation efficiency. This work shows the effectiveness of DRL for the real-time scheduling of dynamic DPFSP.     

Structural health monitoring by using a sparse coding-based deep learning algorithm with wireless sensor networks

Structural health monitoring has received remarkable attention due to the arising structural safety problems. Most of these structural health problems are accumulative damages such as slight changes in structural deformations which are very hard to be detected. In addition, the complexity of real structure and environmental noises make structural health monitoring more difficult. Existing methods largely use various types of sensors to collect useful parameters and then train a machine learning model to diagnose damage level and location, in which a large amount of training data are needed for the model training, while the labeled data are rare in the real world. To overcome this problem, sparse coding is employed in this paper to achieve structural health monitoring of a bridge equipped with a wireless sensor network, so that a large amount of unlabeled examples can be used to train a feature extractor based on the sparse coding algorithm. Features learned from sparse coding are then used to train a neural network classifier to distinguish different statuses of the bridge. Experimental results show the sparse coding-based deep learning algorithm achieves higher accuracy for structural health monitoring under the same level of environmental noises, compared with some existing methods.     

保护数据隐私的深度学习训练数据生成方案

深度学习模型训练存在缺少大量带标签训练数据和数据隐私泄露等问题.为了解决这些问题,借由生成对抗网络可生成大量与真实数据同分布的对抗样本的特点,提出了一个基于条件生成对抗网络的深度学习模型训练数据生成方案.该方案采用条件生成对抗网络生成数据,满足了生成大量带标签训练数据的需求;结合数据变形方法实现数据隐私保护,解决了数据隐私泄露的问题.实验结果表明该方案是高效可行的,而且与其他方案相比,其在数据可用性和保护隐私方面具有优势.     

Audio fingerprint analysis for speech processing using deep learning method

International Journal of Speech Technology - We are generating truly mind-boggling amounts of audio data on a daily basis simply by using the Internet. In different audio-based applications, it...     

Stock prediction using deep learning

Stock market is considered chaotic, complex, volatile and dynamic. Undoubtedly, its prediction is one of the most challenging tasks in time series forecasting. Moreover existing Artificial Neural Network (ANN) approaches fail to provide encouraging results. Meanwhile advances in machine learning have presented favourable results for speech recognition, image classification and language processing. Methods applied in digital signal processing can be applied to stock data as both are time series. Similarly, learning outcome of this paper can be applied to speech time series data. Deep learning for stock prediction has been introduced in this paper and its performance is evaluated on Google stock price multimedia data (chart) from NASDAQ. The objective of this paper is to demonstrate that deep learning can improve stock market forecasting accuracy. For this, (2D)²PCA + Deep Neural Network (DNN) method is compared with state of the art method 2-Directional 2-Dimensional Principal Component Analysis (2D)²PCA + Radial Basis Function Neural Network (RBFNN). It is found that the proposed method is performing better than the existing method RBFNN with an improved accuracy of 4.8% for Hit Rate with a window size of 20. Also the results of the proposed model are compared with the Recurrent Neural Network (RNN) and it is found that the accuracy for Hit Rate is improved by 15.6%. The correlation coefficient between the actual and predicted return for DNN is 17.1% more than RBFNN and it is 43.4% better than RNN.     

COVID-19 classification by CCSHNet with deep fusion using transfer learning and discriminant correlation analysis

Aim: COVID-19 is a disease caused by a new strain of coronavirus. Up to 18th October 2020, worldwide there have been 39.6 million confirmed cases resulting in more than 1.1 million deaths. To improve diagnosis, we aimed to design and develop a novel advanced AI system for COVID-19 classification based on chest CT (CCT) images.Methods: Our dataset from local hospitals consisted of 284 COVID-19 images, 281 community-acquired pneumonia images, 293 secondary pulmonary tuberculosis images; and 306 healthy control images. We first used pretrained models (PTMs) to learn features, and proposed a novel (L, 2) transfer feature learning algorithm to extract features, with a hyperparameter of number of layers to be removed (NLR, symbolized as L). Second, we proposed a selection algorithm of pretrained network for fusion to determine the best two models characterized by PTM and NLR. Third, deep CCT fusion by discriminant correlation analysis was proposed to help fuse the two features from the two models. Micro-averaged (MA) F1 score was used as the measuring indicator. The final determined model was named CCSHNet.Results: On the test set, CCSHNet achieved sensitivities of four classes of 95.61%, 96.25%, 98.30%, and 97.86%, respectively. The precision values of four classes were 97.32%, 96.42%, 96.99%, and 97.38%, respectively. The F1 scores of four classes were 96.46%, 96.33%, 97.64%, and 97.62%, respectively. The MA F1 score was 97.04%. In addition, CCSHNet outperformed 12 state-of-the-art COVID-19 detection methods.Conclusions: CCSHNet is effective in detecting COVID-19 and other lung infectious diseases using first-line clinical imaging and can therefore assist radiologists in making accurate diagnoses based on CCTs.     

Machining quality monitoring (MQM) in laser-assisted micro-milling of glass using cutting force signals: an image-based deep transfer learning

Journal of Intelligent Manufacturing - This research proposes a method for machining quality monitoring (MQM) in laser-assisted micro-milling (LAMM) of glass. In tool-based mechanical processing...     

基于深度学习的智能动态防御系统

在面对日益突出的网络安全问题,现有的基于威胁特征感知的防御机制,在应对未知风险、高级持续性威胁(APT)、机器流量中,暴露其不足之处,论文提出了基于深度学习的智能动态防御系统架构,提升了互联网应用网络安全威胁应对能力。     

Cell tracking using deep neural networks with multi-task learning

Cell tracking plays crucial role in biomedical and computer vision areas. As cells generally have frequent deformation activities and small sizes in microscope image, tracking the non-rigid and non-significant cells is quite difficult in practice. Traditional visual tracking methods have good performances on tracking rigid and significant visual objects, however, they are not suitable for cell tracking problem. In this paper, a novel cell tracking method is proposed by using Convolutional Neural Networks (CNNs) as well as multi-task learning (MTL) techniques. The CNNs learn robust cell features and MTL improves the generalization performance of the tracking. The proposed cell tracking method consists of a particle filter motion model, a multi-task learning observation model, and an optimized model update strategy. In the training procedure, the cell tracking is divided into an online tracking task and an accompanying classification task using the MTL technique. The observation model is trained by building a CNN to learn robust cell features. The tracking procedure is started by assigning the cell position in the first frame of a microscope image sequence. Then, the particle filter model is applied to produce a set of candidate bounding boxes in the subsequent frames. The trained observation model provides the confidence probabilities corresponding to all of the candidates and selects the candidate with the highest probability as the final prediction. Finally, an optimized model update strategy is proposed to enable the multi-task observation model for the variation of the tracked cell over the entire tracking procedure. The performance and robustness of the proposed method are analyzed by comparing with other commonly-used methods. Experimental results demonstrate that the proposed method has good performance to the cell tracking problem.     

Aspect based sentiment analysis using deep learning approaches: A survey

The wealth of unstructured text on the online web portal has made opinion mining the most thrust area for researchers, academicians, and businesses to extract information for gathering, analyzing, and aggregating human emotions. The extraction of public sentiment from the text at an aspect level has contributed exceptionally to various businesses in the marketplace. In recent times, deep learning-based techniques have learned high-level linguistic features without high-level feature engineering. Therefore, this paper focuses on a rigorous survey on two primary subtasks, aspect extraction and aspect category detection of aspect-based sentiment analysis (ABSA) methods based on deep learning. The significant advancement in the ABSA sector is demonstrated by a thorough evaluation of state-of-the-art and latest aspect extraction methodologies.     

Text summarization using unsupervised deep learning

We present methods of extractive query-oriented single-document summarization using a deep auto-encoder (AE) to compute a feature space from the term-frequency (tf) input. Our experiments explore both local and global vocabularies. We investigate the effect of adding small random noise to local tf as the input representation of AE, and propose an ensemble of such noisy AEs which we call the Ensemble Noisy Auto-Encoder (ENAE). ENAE is a stochastic version of an AE that adds noise to the input text and selects the top sentences from an ensemble of noisy runs. In each individual experiment of the ensemble, a different randomly generated noise is added to the input representation. This architecture changes the application of the AE from a deterministic feed-forward network to a stochastic runtime model. Experiments show that the AE using local vocabularies clearly provide a more discriminative feature space and improves the recall on average 11.2%. The ENAE can make further improvements, particularly in selecting informative sentences. To cover a wide range of topics and structures, we perform experiments on two different publicly available email corpora that are specifically designed for text summarization. We used ROUGE as a fully automatic metric in text summarization and we presented the average ROUGE-2 recall for all experiments.     

Pneumonia classification using quaternion deep learning

Pneumonia is an infection in one or both the lungs because of virus or bacteria through breathing air. It inflames air sacs in lungs which fill with fluid which further leads to problems in respiration. Pneumonia is interpreted by radiologists by observing abnormality in lungs in case of fluid in Chest X-Rays. Computer Aided Detection Diagnosis (CAD) tools can assist radiologists by improving their diagnostic accuracy. Such CAD tools use neural networks which are trained on Chest X-Ray dataset to classify a Chest X-Ray into normal or infected with Pneumonia. Convolution neural networks have shown remarkable performance in object detection in an image. Quaternion Convolution neural network (QCNN) is a generalization of conventional convolution neural networks. QCNN treats all three channels (R, G, B) of color image as a single unit and it extracts better representative features and which further improves classification. In this paper, we have trained Quaternion residual network on a publicly available large Chest X-Ray dataset on Kaggle repository and obtained classification accuracy of 93.75% and F-score of .94. We have also compared our performance with other CNN architectures. We found that classification accuracy was higher with Quaternion Residual network when we compared it with a real valued Residual network.

     

基于深度机器学习的霾污染监测技术

传统的霾污染监测技术监测准确率低,收集的图像完整度差,为了解决上述问题,基于深度学习研究了一种新的霾污染监测技术。通过污染数据收集精准划分其产生的地点,整合获取的追踪信息,在三维分布空间图掌控霾污染可能存在的条件,多次进行机器飞行追踪实验,根据不同的污染项目组对霾污染进行数据监测,根据霾污染数据的浓度信息以及深度机器学习的输入数据类型对收集数据进行分类,查询数据类型,同时监测气溶胶的厚度、霾污染中具有毒性的二氧化硫及二氧化氮物质以及兴趣区域。为验证技术的有效性,设定对比实验,结果表明,基于深度机器学习的霾污染监测技术监测结果准确率为90%,图像收集完整度平均值为82%,具有更强的监测能力。     

Identification using ANFIS with intelligent hybrid stable learning algorithm approaches and stability analysis of training methods

This paper proposes a novel hybrid learning algorithm with stable learning laws for Adaptive Network based Fuzzy Inference System (ANFIS) as a system identifier and studies the stability of this algorithm. The new hybrid learning algorithm is based on particle swarm optimization (PSO) for training the antecedent part and forgetting factor recursive least square (FFRLS) for training the conclusion part. Two famous training algorithms for ANFIS are the gradient descent (GD) to update antecedent part parameters and using GD or recursive least square (RLS) to update conclusion part parameters. Lyapunov stability theory is used to study the stability of the proposed algorithms. This paper, also studies the stability of PSO as an optimizer in training the identifier. Stable learning algorithms for the antecedent and consequent parts of fuzzy rules are proposed. Some constraints are obtained and simulation results are given to validate the results. It is shown that instability will not occur for the leaning rate and PSO factors in the presence of constraints. The learning rate can be calculated on-line and will provide an adaptive learning rate for the ANFIS structure. This new learning scheme employs adaptive learning rate that is determined by input–output data. Also, stable learning algorithms for two common methods are proposed based on Lyapunov stability theory and some constraints are obtained.