Search results

Automatic defect detection is a fundamental and vital topic in the research field of industrial intelligence. In this work, the authors develop a more flexible deep learning method for the industrial defect detection.

The authors propose a unified framework for detecting defects in industrial products or planar surfaces based on an end-to-end learning strategy. A lightweight deep learning architecture for blade defect detection is specifically demonstrated. In addition, a blade defect data set is collected with the dual-arm image collection system.

Numerous experiments are conducted on the collected data set, and experimental results demonstrate that the proposed system can achieve satisfactory performance over other methods. Furthermore, the data equalization operation helps for a better defect detection result.

An end-to-end learning framework is established for defect detection. Although the adopted fully convolutional network has been extensively used for semantic segmentation in images, to the best knowledge of the authors, it has not been used for industrial defect detection. To remedy the difficulties of blade defect detection which has been analyzed above, the authors develop a new network architecture which integrates the residue learning to perform the efficient defect detection. A dual-arm data collection platform is constructed and extensive experimental validation are conducted.

Computer vision for automated analysis of cells and tissues usually include extracting features from images before analyzing such features via various machine learning and machine vision algorithms. The purpose of this work is to explore and demonstrate the ability of a Convolutional Neural Network (CNN) to classify cells pictured via brightfield microscopy without the need of any feature extraction, using a minimum of images, improving work-flows that involve cancer cell identification.

The methodology involved a quantitative measure of the performance of a Convolutional Neural Network in distinguishing between two cancer lines. In their approach, they trained, validated and tested their 6-layer CNN on 1,241 images of MDA-MB-468 and MCF7 breast cancer cell line in an end-to-end fashion, allowing the system to distinguish between the two different cancer cell types.

They obtained a 99% accuracy, providing a foundation for more comprehensive systems.

Value can be found in that systems based on this design can be used to assist cell identification in a variety of contexts, whereas a practical implication can be found that these systems can be deployed to assist biomedical workflows quickly and at low cost. In conclusion, this system demonstrates the potentials of end-to-end learning systems for faster and more accurate automated cell analysis.

The purpose of this research is to achieve multi-task autonomous driving by adjusting the network architecture of the model. Meanwhile, after achieving multi-task autonomous driving, the authors found that the trained neural network model performs poorly in untrained scenarios. Therefore, the authors proposed to improve the transfer efficiency of the model for new scenarios through transfer learning.

First, the authors achieved multi-task autonomous driving by training a model combining convolutional neural network and different structured long short-term memory (LSTM) layers. Second, the authors achieved fast transfer of neural network models in new scenarios by cross-model transfer learning. Finally, the authors combined data collection and data labeling to improve the efficiency of deep learning. Furthermore, the authors verified that the model has good robustness through light and shadow test.

This research achieved road tracking, real-time acceleration–deceleration, obstacle avoidance and left/right sign recognition. The model proposed by the authors (UniBiCLSTM) outperforms the existing models tested with model cars in terms of autonomous driving performance. Furthermore, the CMTL-UniBiCL-RL model trained by the authors through cross-model transfer learning improves the efficiency of model adaptation to new scenarios. Meanwhile, this research proposed an automatic data annotation method, which can save 1/4 of the time for deep learning.

This research provided novel solutions in the achievement of multi-task autonomous driving and neural network model scenario for transfer learning. The experiment was achieved on a single camera with an embedded chip and a scale model car, which is expected to simplify the hardware for autonomous driving.

The grasping task of robots in dense cluttered scenes from a single-view has not been solved perfectly, and there is still a problem of low grasping success rate. This study aims to propose an end-to-end grasp generation method to solve this problem.

A new grasp representation method is proposed, which cleverly uses the normal vector of the table surface to derive the grasp baseline vectors, and maps the grasps to the pointed points (PP), so that there is no need to add orthogonal constraints between vectors when using a neural network to predict rotation matrixes of grasps.

Experimental results show that the proposed method is beneficial to the training of the neural network, and the model trained on synthetic data set can also have high grasping success rate and completion rate in real-world tasks.

The main contribution of this paper is that the authors propose a new grasp representation method, which maps the 6-DoF grasps to a PP and an angle related to the tabletop normal vector, thereby eliminating the need to add orthogonal constraints between vectors when directly predicting grasps using neural networks. The proposed method can generate hundreds of grasps covering the whole surface in about 0.3 s. The experimental results show that the proposed method has obvious superiority compared with other methods.

Compared with traditional methods relying on manual teaching or system modeling, data-driven learning methods, such as deep reinforcement learning and imitation learning, show more promising potential to cope with the challenges brought by increasingly complex tasks and environments, which have become the hot research topic in the field of robot skill learning. However, the contradiction between the difficulty of collecting robot–environment interaction data and the low data efficiency causes all these methods to face a serious data dilemma, which has become one of the key issues restricting their development. Therefore, this paper aims to comprehensively sort out and analyze the cause and solutions for the data dilemma in robot skill learning.

First, this review analyzes the causes of the data dilemma based on the classification and comparison of data-driven methods for robot skill learning; Then, the existing methods used to solve the data dilemma are introduced in detail. Finally, this review discusses the remaining open challenges and promising research topics for solving the data dilemma in the future.

This review shows that simulation–reality combination, state representation learning and knowledge sharing are crucial for overcoming the data dilemma of robot skill learning.

To the best of the authors’ knowledge, there are no surveys that systematically and comprehensively sort out and analyze the data dilemma in robot skill learning in the existing literature. It is hoped that this review can be helpful to better address the data dilemma in robot skill learning in the future.

This study aims to analyze driver risks in the driving environment. A complete analysis of context aware assistive driving techniques. Context awareness in assistive driving by probabilistic modeling techniques. Advanced techniques using Spatio-temporal techniques, computer vision and deep learning techniques.

Autonomous vehicles have been aimed to increase driver safety by introducing vehicle control from the driver to Advanced Driver Assistance Systems (ADAS). The core objective of these systems is to cut down on road accidents by helping the user in various ways. Early anticipation of a particular action would give a prior benefit to the driver to successfully handle the dangers on the road. In this paper, the advancements that have taken place in the use of multi-modal machine learning for assistive driving systems are surveyed. The aim is to help elucidate the recent progress and techniques in the field while also identifying the scope for further research and improvement. The authors take an overview of context-aware driver assistance systems that alert drivers in case of maneuvers by taking advantage of multi-modal human processing to better safety and drivability.

There has been a huge improvement and investment in ADAS being a key concept for road safety. In such applications, data is processed and information is extracted from multiple data sources, thus requiring training of machine learning algorithms in a multi-modal style. The domain is fast gaining traction owing to its applications across multiple disciplines with crucial gains.

The research is focused on deep learning and computer vision-based techniques to generate a context for assistive driving and it would definitely adopt by the ADAS manufacturers.

As context-aware assistive driving would work in real-time and it would save the lives of many drivers, pedestrians.

This paper provides an understanding of context-aware deep learning frameworks for assistive driving. The research is mainly focused on deep learning and computer vision-based techniques to generate a context for assistive driving. It incorporates the latest state-of-the-art techniques using suitable driving context and the driver is alerted. Many automobile manufacturing companies and researchers would refer to this study for their enhancements.

This paper aims to apply a methodology that is capable to classify and localize mechanical, electrical and plumbing (MEP) elements to assist facility managers. Furthermore, it assists in decreasing the technical complexity and sophistication of different systems to the facility management (FM) team.

This research exploits artificial intelligence (AI) in FM operations through proposing a new system that uses a deep learning pre-trained model for transfer learning. The model can identify new MEP elements through image classification with a deep convolutional neural network using a support vector machine (SVM) technique under supervised learning. Also, an expert system is developed and integrated with an Android application to the proposed system to identify the required maintenance for the identified elements. FM team can reach the identified assets with bluetooth tracker devices to perform the required maintenance.

The proposed system aids facility managers in their tasks and decreases the maintenance costs of facilities by maintaining, upgrading, operating assets cost-effectively using the proposed system.

The paper considers three fire protection systems for proactive maintenance, where other structural or architectural systems can also significantly affect the level of service and cost expensive repairs and maintenance. Also, the proposed system relies on different platforms that required to be consolidated for facility technicians and managers end-users. Therefore, the authors will consider these limitations and expand the study as a case study in future work.

This paper assists in a proactive manner to decrease the lack of knowledge of the required maintenance to MEP elements that leads to a lower life cycle cost. These MEP elements have a big share in the operation and maintenance costs of building facilities.

Most source recording device identification models for Web media forensics are based on a single feature to complete the identification task and often have the disadvantages of long time and poor accuracy. The purpose of this paper is to propose a new method for end-to-end network source identification of multi-feature fusion devices.

This paper proposes an efficient multi-feature fusion source recording device identification method based on end-to-end and attention mechanism, so as to achieve efficient and convenient identification of recording devices of Web media forensics.

The authors conducted sufficient experiments to prove the effectiveness of the models that they have proposed. The experiments show that the end-to-end system is improved by 7.1% compared to the baseline i-vector system, compared to the authors’ previous system, the accuracy is improved by 0.4%, and the training time is reduced by 50%.

With the development of Web media forensics and internet technology, the use of Web media as evidence is increasing. Among them, it is particularly important to study the authenticity and accuracy of Web media audio.

This paper aims to promote the development of source recording device identification and provide effective technology for Web media forensics and judicial record evidence that need to apply device source identification technology.

The aim of this study is to investigate subject independent emotion recognition capabilities of EEG and peripheral physiological signals namely: electroocoulogram (EOG), electromyography (EMG), electrodermal activity (EDA), temperature, plethysmograph and respiration. The experiments are conducted on both modalities independently and in combination. This study arranges the physiological signals in order based on the prediction accuracy obtained on test data using time and frequency domain features.

DEAP dataset is used in this experiment. Time and frequency domain features of EEG and physiological signals are extracted, followed by correlation-based feature selection. Classifiers namely – Naïve Bayes, logistic regression, linear discriminant analysis, quadratic discriminant analysis, logit boost and stacking are trained on the selected features. Based on the performance of the classifiers on the test set, the best modality for each dimension of emotion is identified.

 The experimental results with EEG as one modality and all physiological signals as another modality indicate that EEG signals are better at arousal prediction compared to physiological signals by 7.18%, while physiological signals are better at valence prediction compared to EEG signals by 3.51%. The valence prediction accuracy of EOG is superior to zygomaticus electromyography (zEMG) and EDA by 1.75% at the cost of higher number of electrodes. This paper concludes that valence can be measured from the eyes (EOG) while arousal can be measured from the changes in blood volume (plethysmograph). The sorted order of physiological signals based on arousal prediction accuracy is plethysmograph, EOG (hEOG + vEOG), vEOG, hEOG, zEMG, tEMG, temperature, EMG (tEMG + zEMG), respiration, EDA, while based on valence prediction accuracy the sorted order is EOG (hEOG + vEOG), EDA, zEMG, hEOG, respiration, tEMG, vEOG, EMG (tEMG + zEMG), temperature and plethysmograph.

Many of the emotion recognition studies in literature are subject dependent and the limited subject independent emotion recognition studies in the literature report an average of leave one subject out (LOSO) validation result as accuracy. The work reported in this paper sets the baseline for subject independent emotion recognition using DEAP dataset by clearly specifying the subjects used in training and test set. In addition, this work specifies the cut-off score used to classify the scale as low or high in arousal and valence dimensions. Generally, statistical features are used for emotion recognition using physiological signals as a modality, whereas in this work, time and frequency domain features of physiological signals and EEG are used. This paper concludes that valence can be identified from EOG while arousal can be predicted from plethysmograph.

Conventional learning-based visual odometry (VO) systems usually use convolutional neural networks (CNN) to extract features, where some important context-related and attention-holding global features might be ignored. Without essential global features, VO system will be sensitive to various environmental perturbations. The purpose of this paper is to design a novel learning-based framework that aims to improve accuracy of learning-based VO without decreasing the generalization ability.

Instead of CNN, a context-gated convolution is adopted to build an end-to-end learning framework, which enables convolutional layers that dynamically capture representative local patterns and composes local features of interest under the guidance of global context. In addition, an attention mechanism module is introduced to further improve learning ability and enhance robustness and generalization ability of the VO system.

The proposed system is evaluated on the public data set KITTI and the self-collected data sets of our college building, where it shows competitive performance compared with some classical and state-of-the-art learning-based methods. Quantitative experimental results on the public data set KITTI show that compared with CNN-based VO methods, the average translational error and rotational error of all the test sequences are reduced by 45.63% and 37.22%, respectively.

The main contribution of this paper is that an end-to-end deep context gate convolutional VO system based on lightweight attention mechanism is proposed, which effectively improves the accuracy compared with other learning-based methods.