A deep feature manifold embedding method for hyperspectral image classification

Liu, Jiamin; Yang, Song; Hong, Huixiao; Li, Zhengying; Shi, Guangyao

doi:10.1080/2150704x.2020.1746855

Cited by 7 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research [27] proposes a novel DL approach called deep manifold reconstruction neural network (DMRNet) to address this problem. The approach in the research [28] uses a qualified auto-encoder to extract deep features from a hyperspectral image (HSI), followed by the construction of an intrinsic graph and a penalty graph to discover the discriminant manifold structure of deep features. Finally, the deep features are mapped into a low-dimensional embedding space in which intra-class manifold samples are compressed and interclass manifold samples are isolated.…”

Section: Volume XX 2017mentioning

confidence: 99%

Spatial Augmented Reality Based Customer Satisfaction Enhancement and Monitoring System

et al. 2021

View full text Add to dashboard Cite

The research proposes a novel scheme that enhances customer satisfaction through spatial augmented reality and a customer expression-based deep learning network to customize the dining environment in high-grade restaurants. The perception of the quality of food was also enhanced by the recreation of the live environment on the preparation of the menu ordered utilizing the waiting time after each ordering session. Initially, a virtual menu driven by a web page is projected onto the table using a Three-dimensional (3D) projection by which the customers can interactively choose dishes after examining how the dish looks in quality and quantity. The dishes are being portrayed in 3D also adding Spatial Augmented Reality (SAR) features in a special angle creating a 3D illusion to the naked eye. By using photogrammetry we could portrait an identical 3D model of restaurant dishes. With the use of software's parallax effect was added to the video animation to bring out the 3D effect. A virtual restaurant background is created on the walls with relaxing videos and soothing soundtracks to enhance the restaurant ambiance as the restaurant ambiance deals more with the sensory and emotional aspects. On the analysis of the ordered menu and based on preferences available within the database, menu suggestions are also proposed depending on the recommendations of the customer satisfaction analysis model. . This provides customers with a firsthand experience at the restaurant; known as "Business to Customer" (B2C) strategy in marketing. The deep learning-based facial expression recognition system is running in the background to monitor customer satisfaction levels through facial expressions. The captured data will be processed loaded into a database containing a ranking system, which the restaurant management can use for future analytics, to re-arrange prices and upgrade profit margins. The performance was analyzed with numerous experimental evaluations with ambient light levels and desired viewing angles, where we found optimal angle values for spatial augmented reality applications. A survey was done on a sample with different ages, gender, and social status to analyze user perception on evaluating the proposed system. The results revealed 87.5% of responders were very satisfied with the 3D virtual experience. 79.2% indicated rareness of feedback on food and service and more than 50% liked a system that will automatically measure their satisfaction. The outcome and resulting insights may lay a foundation for a novel approach towards the management of customer experience.

show abstract

Section: Volume XX 2017mentioning

confidence: 99%

Spatial Augmented Reality Based Customer Satisfaction Enhancement and Monitoring System

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In the field of medical processing, the experimental results of the author in [10] show the improvements of performance on hyperspectral image classification tasks based on a deep feature manifold embedding method. The first extracted features are discovered the discriminant manifold structure by an intrinsic and a penalty graph, then those features are mapped into a low-dimensional embedding space.…”

Section: A Literature Review On Medical Images Processingmentioning

confidence: 99%

“…The improvements of deep learning bring medical technology to light with promising results, for instance, medical events prediction [5,6], antibiotic discovery [7], or analysis of electronic health records [8]. Moreover, the improvements of image classification, image segmentation [9,10] offering plenty of encouragement for the developments of medical imaging. Several deep learning approaches in medical imaging have been proposed for disease detection and diagnosis, skin cancer classification [11], or a deep encoder-decoder architecture for 3D image biomedical segmentation [12].…”

Section: Introductionmentioning

confidence: 99%

Explanation of the Convolutional Neural Network Classifying Chest X-Ray Images Supporting Pneumonia Diagnosis

Nguyễn¹,

Huynh²,

Tran³

et al. 2020

EAI Endorsed Transactions on Context-aware Systems and Applicat

View full text Add to dashboard Cite

Medical images are valuable sources for disease diagnosis. Besides, advancements in deep learning in recent years have been supporting disease diagnosis methods based on images to obtain numerous achievements. However, deep learning algorithms still work as a black-box so it is difficult to interpret output from these algorithms. In this study, we propose a convolutional network architecture to classify Chest X-ray images as well as apply explanation approaches for trained models to support disease diagnosis. The proposed method provides insights in medical images to support Pneumonia diagnosis.

show abstract