Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Advances in Artificial Intelligence for Perception Augmentation and Reasoning
share announcement

Advances in Artificial Intelligence for Perception Augmentation and Reasoning

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (29 July 2022) | Viewed by 32379

Special Issue Editors

Dr. Wenfeng Zheng

E-Mail Website
Guest Editor
School of Automation, University of Electronic Science and Technology of China, Chengdu 610054, China
Interests: surgical robot; AI/ML; haptics; teleoperation; medical robotics; image fusion; surgical vision; 3D visualization; adaptive visualization; artificial neural network; geoinformatics (GIS); artificial intelligence; computer graphics; motion tracking; image processing; machine vision; 3D reconstruction; medical imaging; robotic surgery; data mining; earth surface process; cognitive intelligence; GIS/RS; visual reasoning; visual question answering; cloud computing; perception and cognition, etc.
Special Issues, Collections and Topics in MDPI journals
Dr. Chao Liu

E-Mail Website
Guest Editor
French National Center for Scientific Research (CNRS), LIRMM, 34095 Montpellier, France
Interests: visual augmentation and reconstruction; 3D reconstruction of deformable surface; haptics in human–machine interactions; multimodal sensor-based analysis of manipulation skills; surgical robot; medical image processing
Special Issues, Collections and Topics in MDPI journals
Dr. Bo Yang

E-Mail Website
Guest Editor
School of Automation, University of Electronic Science and Technology of China, Chengdu, China
Interests: computer vision; surgical robots; medical image processing
Special Issues, Collections and Topics in MDPI journals
Dr. Yichao Yang

E-Mail Website
Guest Editor
Department of Pharmaceutical Sciences, School of Pharmacy, Bouve College of Health Sciences, Northeastern University, 140 The Fenway, Boston, MA 02115, USA
Interests: smart medical devices; intelligent systems; nano/microfluidics; 1/f noise; active matter; ASTs

Special Issue Information

Dear Colleagues,

The purpose of this Special Issue is to highlight the recent developments in applications of artificial intelligence (AI) in perception enhancement, activity recognition, natural language processing, intelligent reasoning, and so on. Over the past six decades, AI has been tremendously boosted by new algorithm designs, exponentially increased computing power, and an immense volume of calculation materials (data). At a turning point from "unusable" to "usable", the influence of AI on technological innovations is becoming more critical to social welfare.

The restoration and enhancement techniques for perception are active research areas in AI, and play essential roles in helping us to perceive and understand the world, including human activity recognition, surgical medicine, and remote sensing analysis.

Besides perception augmentation, intelligent reasoning by AI is another invaluable and promising direction. For instance, semantic reasoning and visual reasoning allow machines to function more like human intelligence when performing a reasoning task. This improvement can improve the experience of human–computer interaction and aid the decision-making process. In recent decades, intelligent reasoning has been widely used to address the significant technical issues involved in implementing AI in real-world applications, such as intelligent medical care, environmental analysis and prediction, autonomous driving, intelligent transportation, text classification, recommender systems, machine translation, and analog dialogues.

Success brought by AI can be found in several hot fields. For instance, a series of reusable models, such as deep learning modules and neural networks, have also been proposed to address computer vision (CV) and natural language processing (NLP) tasks. However, an enormous number of tasks involving multiple modalities still require exploration compared to those involving a single modality. For example, integrations between computer vision and natural language processing need to be further explored in cross-modality applications, such as visual question and answer (VQA), visual reasoning, and video translation; these tasks allow the processing of large-scale visual + text and even visual + text + voice-based datasets for different tasks. In addition, multi-source performance demands appropriate feature fusion and high-level and abstract forms of knowledge representation, which is believed to help AI achieve better results. After all, the primary goal of AI research is to enable machines to perform complex tasks that would typically require human intelligence.

This Special Issue welcomes new research works that show new theories, new methods, unique application strategies, and studies of AI in different fields. Potential topics in this collection include but are not limited to the following topics:

  • Visual question and answer (VQA), visual reasoning;
  • Semantic reasoning, semantic representation, knowledge base;
  • Characterization inference, natural language reasoning;
  • Meta-learning, transfer learning, less sample learning (small sample learning);
  • Geospatial artificial intelligence, geospatial AI (GeoAI);
  • AI in geostatistics, remote sensing, spatio-temporal simulation;
  • AI for geospatial data acquisition, analysis, planning, and prediction;
  • Artificial intelligence for augmented perception;
  • Visual augmentation and reconstruction, 3d reconstruction of deformable surfaces;
  • Medical image (e.g., CT, MRI, ultrasound) processing;
  • Machine translation, text sentiment analysis, text classification;
  • Recommendation algorithms, conversation systems;
  • Video-based activity recognition, sensor-based activity recognition;
  • Contrastive learning, representation learning, reinforcement learning;
  • Haptics in human–machine interaction;
  • Multimodal sensor-based analysis of manipulation skills;
  • Theories, mechanisms, methods, and applications of artificial intelligence.

Prof. Dr. Wenfeng Zheng
Dr. Chao Liu
Prof. Dr. Bo Yang
Dr. Yichao Yang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (13 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Editorial

Jump to: Research

4 pages, 173 KiB  
Editorial
Advances in Artificial Intelligence for Perception Augmentation and Reasoning
by Wenfeng Zheng, Chao Liu, Bo Yang and Yichao Yang
Appl. Sci. 2023, 13(7), 4227; https://0-doi-org.brum.beds.ac.uk/10.3390/app13074227 - 27 Mar 2023
Cited by 1 | Viewed by 826
Abstract
AI has seen great progress in recent decades, with a rapidly increasing computing capacity and the exponentially growing amount and types of processed data [...] Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)

Research

Jump to: Editorial

16 pages, 1057 KiB  
Article
An Enhanced and Secure Trust-Aware Improved GSO for Encrypted Data Sharing in the Internet of Things
by Prabha Selvaraj, Vijay Kumar Burugari, S. Gopikrishnan, Abdullah Alourani , Gautam Srivastava and Mohamed Baza
Appl. Sci. 2023, 13(2), 831; https://0-doi-org.brum.beds.ac.uk/10.3390/app13020831 - 07 Jan 2023
Cited by 4 | Viewed by 1841
Abstract
Wireless sensors and actuator networks (WSNs) are the physical layer implementation used for many smart applications in this decade in the form of the Internet of Things (IoT) and cyber-physical systems (CPS). Even though many research concerns in WSNs have been answered, the [...] Read more.
Wireless sensors and actuator networks (WSNs) are the physical layer implementation used for many smart applications in this decade in the form of the Internet of Things (IoT) and cyber-physical systems (CPS). Even though many research concerns in WSNs have been answered, the evolution of the WSN into an IoT network has exposed it to many new technical issues, including data security, multi-sensory multi-communication capabilities, energy utilization, and the age of information. Cluster-based data collecting in the Internet of Things has the potential to address concerns with data freshness and energy efficiency. However, it may not offer reliable network data security. This research presents an improved method for data sharing and cluster head (CH) selection using the hybrid Vlsekriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method in conjunction with glowworm swarm optimization (GSO) strategies based on the energy, trust value, bandwidth, and memory to address this security-enabled, cluster-based data aggregation in the IoT. Next, we aggregate the data after the cluster has been built using a genetic algorithm (GA). After aggregation, the data are encrypted and delivered securely using the TIGSO-EDS architecture. Cuckoo search is used to analyze the data and choose the best route for sending them. The proposed model’s analysis of the results is analyzed, and its uniqueness has been demonstrated via comparison with existing models. TIGSO-EDS reduces energy consumption each round by 12.71–19.96% and increases the percentage of successfully delivered data packets from 2.50% to 5.66%. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

13 pages, 3424 KiB  
Article
An Effective Rainfall–Ponding Multi-Step Prediction Model Based on LSTM for Urban Waterlogging Points
by Yongzhi Liu, Wenting Zhang, Ying Yan, Zhixuan Li, Yulin Xia and Shuhong Song
Appl. Sci. 2022, 12(23), 12334; https://0-doi-org.brum.beds.ac.uk/10.3390/app122312334 - 02 Dec 2022
Cited by 4 | Viewed by 1295
Abstract
With the change in global climate and environment, the prevalence of extreme rainstorms and flood disasters has increased, causing serious economic and property losses. Therefore, accurate and rapid prediction of waterlogging has become an urgent problem to be solved. In this study, Jianye [...] Read more.
With the change in global climate and environment, the prevalence of extreme rainstorms and flood disasters has increased, causing serious economic and property losses. Therefore, accurate and rapid prediction of waterlogging has become an urgent problem to be solved. In this study, Jianye District in Nanjing City of China is taken as the study area. The time series data recorded by rainfall stations and ponding monitoring stations from January 2015 to August 2018 are used to build a ponding prediction model based on the long short-term memory (LSTM) neural network. MSE (mean square error), MAE (mean absolute error) and MSLE (mean squared logarithmic error) were used as loss functions to conduct and train the LSTM model, then three ponding prediction models were built, namely LSTM (mse), LSTM (mae) and LSTM (msle), and a multi-step model was used to predict the depth of ponding in the next 1 h. Using the measured ponding data to evaluate the model prediction results, we selected rmse (root mean squared error), mae, mape (mean absolute percentage error) and NSE (Nash–Sutcliffe efficiency coefficient) as the evaluation indicators. The results showed that LSTM (msle) was the best model among the three models, with evaluation indicators as follows: rmse 5.34, mae 3.45, mape 53.93% and NSE 0.35. At the same time, we found that LSTM (mae) has a better prediction effect than the LSTM (mse) and LSTM (msle) models when the ponding depth exceeds 30 mm. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

12 pages, 6739 KiB  
Article
Road Extraction Based on Improved Convolutional Neural Networks with Satellite Images
by Lei He, Bo Peng, Dan Tang and Yuxia Li
Appl. Sci. 2022, 12(21), 10800; https://0-doi-org.brum.beds.ac.uk/10.3390/app122110800 - 25 Oct 2022
Cited by 4 | Viewed by 1209
Abstract
Deep learning has been applied in various fields for its effective and accurate feature learning capabilities in recent years. Currently, information extracted from remote sensing images with the learning methods has become the most relevant research area for its developed precision. In terms [...] Read more.
Deep learning has been applied in various fields for its effective and accurate feature learning capabilities in recent years. Currently, information extracted from remote sensing images with the learning methods has become the most relevant research area for its developed precision. In terms of developing segmentation precision and reducing calculation power consumption, the improved deep learning methods have received more attention, and the improvement of semantic segmentation architectures has been a popular solution. This research presents a learning method named D-DenseNet with a new structure for road extraction. The methods for the improvement are divided into two stages: (1) alternate the consecutive dilated convolutions number in the structure of the network (2) the stem block is arranged as the initial block. So, dilated convolution can obtain more global context information through the whole network. Further, the D-DenseNet restructures D-LinkNet by taking DenseNet as its backbone instead of ResNet, which can expand the receptive field and accept more feature information. The D-DenseNet is effective because of its 119 M model size and 57.96% IoU on the processing test data and 99.3 M modes size and 66.26% on the public dataset, which achieved the research objective for reducing model size and developing segmentation precision—IoU. The experiment indicates that the D-Dense block and the stem block are effective for developing road extraction, and the appropriate number of convolution layers is also essential for model evaluation. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

13 pages, 2503 KiB  
Article
An Improved Algorithm of Drift Compensation for Olfactory Sensors
by Siyu Lu, Jialiang Guo, Shan Liu, Bo Yang, Mingzhe Liu, Lirong Yin and Wenfeng Zheng
Appl. Sci. 2022, 12(19), 9529; https://0-doi-org.brum.beds.ac.uk/10.3390/app12199529 - 22 Sep 2022
Cited by 75 | Viewed by 2386
Abstract
This research mainly studies the semi-supervised learning algorithm of different domain data in machine olfaction, also known as sensor drift compensation algorithm. Usually for this kind of problem, it is difficult to obtain better recognition results by directly using the semi-supervised learning algorithm. [...] Read more.
This research mainly studies the semi-supervised learning algorithm of different domain data in machine olfaction, also known as sensor drift compensation algorithm. Usually for this kind of problem, it is difficult to obtain better recognition results by directly using the semi-supervised learning algorithm. For this reason, we propose a domain transformation semi-supervised weighted kernel extreme learning machine (DTSWKELM) algorithm, which converts the data through the domain and uses SWKELM algorithmic classification to transform the semi-supervised classification problem of different domain data into a semi-supervised classification problem of the same domain data. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

16 pages, 2123 KiB  
Article
A Semi-Supervised Extreme Learning Machine Algorithm Based on the New Weighted Kernel for Machine Smell
by Wei Dang, Jialiang Guo, Mingzhe Liu, Shan Liu, Bo Yang, Lirong Yin and Wenfeng Zheng
Appl. Sci. 2022, 12(18), 9213; https://0-doi-org.brum.beds.ac.uk/10.3390/app12189213 - 14 Sep 2022
Cited by 70 | Viewed by 2007
Abstract
At present, machine sense of smell has shown its important role and advantages in many scenarios. The development of machine sense of smell is inseparable from the support of corresponding data and algorithms. However, the process of olfactory data collection is relatively cumbersome, [...] Read more.
At present, machine sense of smell has shown its important role and advantages in many scenarios. The development of machine sense of smell is inseparable from the support of corresponding data and algorithms. However, the process of olfactory data collection is relatively cumbersome, and it is more difficult to collect labeled data. However, in many scenarios, to use a small amount of labeled data to train a good-performing classifier, it is not feasible to rely only on supervised learning algorithms, but semi-supervised learning algorithms can better cope with only a small amount of labeled data and a large amount of unlabeled data. This study combines the new weighted kernel with SKELM and proposes a semi-supervised extreme learning machine algorithm based on the weighted kernel, SELMWK. The experimental results show that the proposed SELMWK algorithm has good classification performance and can solve the semi-supervised gas classification task of the same domain data well on the used dataset. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

13 pages, 2730 KiB  
Article
2D/3D Multimode Medical Image Alignment Based on Spatial Histograms
by Yuxi Ban, Yang Wang, Shan Liu, Bo Yang, Mingzhe Liu, Lirong Yin and Wenfeng Zheng
Appl. Sci. 2022, 12(16), 8261; https://0-doi-org.brum.beds.ac.uk/10.3390/app12168261 - 18 Aug 2022
Cited by 61 | Viewed by 2501
Abstract
The key to image-guided surgery (IGS) technology is to find the transformation relationship between preoperative 3D images and intraoperative 2D images, namely, 2D/3D image registration. A feature-based 2D/3D medical image registration algorithm is investigated in this study. We use a two-dimensional weighted spatial [...] Read more.
The key to image-guided surgery (IGS) technology is to find the transformation relationship between preoperative 3D images and intraoperative 2D images, namely, 2D/3D image registration. A feature-based 2D/3D medical image registration algorithm is investigated in this study. We use a two-dimensional weighted spatial histogram of gradient directions to extract statistical features, overcome the algorithm’s limitations, and expand the applicable scenarios under the premise of ensuring accuracy. The proposed algorithm was tested on CT and synthetic X-ray images, and compared with existing algorithms. The results show that the proposed algorithm can improve accuracy and efficiency, and reduce the initial value’s sensitivity. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

16 pages, 3337 KiB  
Article
PCB Network Analysis for Circuit Partitioning
by Yali Zheng, Da Meng and Libing Bai
Appl. Sci. 2022, 12(16), 8200; https://0-doi-org.brum.beds.ac.uk/10.3390/app12168200 - 17 Aug 2022
Cited by 1 | Viewed by 1427
Abstract
The complexity of automatic placement and routing is proportional to the scale of the circuit. Through netlist partition algorithms, printed circuit board (PCB) circuits are divided into different submodules, and the problem scale is effectively reduced in order to obtain the optimal automatic [...] Read more.
The complexity of automatic placement and routing is proportional to the scale of the circuit. Through netlist partition algorithms, printed circuit board (PCB) circuits are divided into different submodules, and the problem scale is effectively reduced in order to obtain the optimal automatic layout and routing. In this paper, we analyze net attributes and potential patterns in netlists through visualization, and propose a heuristic PCB netlist partition approach based on net attributes and potential patterns which we discover from netlists. Our partition approach takes the netlist as input, and module partition set as output. Firstly, the modules are prepartitioned using net attributes. Further, the special patterns in circuits are discovered, and the scattered resistors, capacitors, and other components caused by prepartitioning would be allocated to initial modules by three rules—classifying, matching, and force strategy. Our method is evaluated on 11 PCB netlists which are built manually. Experimental results show that our proposed netlist partition approach significantly outperforms the state of the art on all evaluation indices, which can achieve 80–96% partition accuracy. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

16 pages, 5133 KiB  
Article
Research on Tiny Target Detection Technology of Fabric Defects Based on Improved YOLO
by Xi Yue, Qing Wang, Lei He, Yuxia Li and Dan Tang
Appl. Sci. 2022, 12(13), 6823; https://0-doi-org.brum.beds.ac.uk/10.3390/app12136823 - 05 Jul 2022
Cited by 20 | Viewed by 3090
Abstract
Fabric quality plays a crucial role in modern textile industry processes. How to detect fabric defects quickly and effectively has become the main research goal of researchers. The You Only Look Once (YOLO) series of networks have maintained a dominant position in the [...] Read more.
Fabric quality plays a crucial role in modern textile industry processes. How to detect fabric defects quickly and effectively has become the main research goal of researchers. The You Only Look Once (YOLO) series of networks have maintained a dominant position in the field of target detection. However, detecting small-scale objects, such as tiny targets in fabric defects, is still a very challenging task for the YOLOv4 network. To address this challenge, this paper proposed an improved YOLOv4 target detection algorithm: using a combined data augmentation method to expand the dataset and improve the robustness of the algorithm, obtaining the anchors suitable for fabric defect detection by using the k-means algorithm to cluster the ground truth box of the dataset, adding a new prediction layer in yolo_head in order to have a better effect on tiny target detection, integrating a convolutional block attention module into the backbone feature extraction network, and innovatively replacing the CIOU loss function with the CEIOU loss function to achieve accurate classification and localization of defects. Experimental results show that compared with the original YOLOv4 algorithm, the detection accuracy of the improved YOLOv4 algorithm for tiny targets has been greatly increased, the AP value of tiny target detection has increased by 12%, and the overall mean average precision (mAP) has increased by 3%. The prediction results of the proposed algorithm can provide enterprises with more accurate defect positioning, reduce the defect rate of fabric products, and improve their economic effect. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

15 pages, 2430 KiB  
Article
Research on Long Text Classification Model Based on Multi-Feature Weighted Fusion
by Xi Yue, Tao Zhou, Lei He and Yuxia Li
Appl. Sci. 2022, 12(13), 6556; https://0-doi-org.brum.beds.ac.uk/10.3390/app12136556 - 28 Jun 2022
Cited by 2 | Viewed by 1749
Abstract
Text classification in the long-text domain has become a development challenge due to the significant increase in text data, complexity enhancement, and feature extraction of long texts in various domains of the Internet. A long text classification model based on multi-feature weighted fusion [...] Read more.
Text classification in the long-text domain has become a development challenge due to the significant increase in text data, complexity enhancement, and feature extraction of long texts in various domains of the Internet. A long text classification model based on multi-feature weighted fusion is proposed for the problems of contextual semantic relations, long-distance global relations, and multi-sense words in long text classification tasks. The BERT model is used to obtain feature representations containing global semantic and contextual feature information of text, convolutional neural networks to obtain features at different levels and combine attention mechanisms to obtain weighted local features, fuse global contextual features with weighted local features, and obtain classification results by equal-length convolutional pooling. The experimental results show that the proposed model outperforms other models in terms of accuracy, precision, recall, F1 value, etc., under the same data set conditions compared with traditional deep learning classification models, and it can be seen that the model has more obvious advantages in long text classification. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

15 pages, 4173 KiB  
Article
A Few Shot Classification Methods Based on Multiscale Relational Networks
by Wenfeng Zheng, Xia Tian, Bo Yang, Shan Liu, Yueming Ding, Jiawei Tian and Lirong Yin
Appl. Sci. 2022, 12(8), 4059; https://0-doi-org.brum.beds.ac.uk/10.3390/app12084059 - 17 Apr 2022
Cited by 105 | Viewed by 3214
Abstract
Learning information from a single or a few samples is called few-shot learning. This learning method will solve deep learning’s dependence on a large sample. Deep learning achieves few-shot learning through meta-learning: “how to learn by using previous experience”. Therefore, this paper considers [...] Read more.
Learning information from a single or a few samples is called few-shot learning. This learning method will solve deep learning’s dependence on a large sample. Deep learning achieves few-shot learning through meta-learning: “how to learn by using previous experience”. Therefore, this paper considers how the deep learning method uses meta-learning to learn and generalize from a small sample size in image classification. The main contents are as follows. Practicing learning in a wide range of tasks enables deep learning methods to use previous empirical knowledge. However, this method is subject to the quality of feature extraction and the selection of measurement methods supports set and the target set. Therefore, this paper designs a multi-scale relational network (MSRN) aiming at the above problems. The experimental results show that the simple design of the MSRN can achieve higher performance. Furthermore, it improves the accuracy of the datasets within fewer samples and alleviates the overfitting situation. However, to ensure that uniform measurement applies to all tasks, the few-shot classification based on metric learning must ensure the task set’s homologous distribution. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

18 pages, 2083 KiB  
Article
A Deep Fusion Matching Network Semantic Reasoning Model
by Wenfeng Zheng, Yu Zhou, Shan Liu, Jiawei Tian, Bo Yang and Lirong Yin
Appl. Sci. 2022, 12(7), 3416; https://0-doi-org.brum.beds.ac.uk/10.3390/app12073416 - 27 Mar 2022
Cited by 99 | Viewed by 2923
Abstract
As the vital technology of natural language understanding, sentence representation reasoning technology mainly focuses on sentence representation methods and reasoning models. Although the performance has been improved, there are still some problems, such as incomplete sentence semantic expression, lack of depth of reasoning [...] Read more.
As the vital technology of natural language understanding, sentence representation reasoning technology mainly focuses on sentence representation methods and reasoning models. Although the performance has been improved, there are still some problems, such as incomplete sentence semantic expression, lack of depth of reasoning model, and lack of interpretability of the reasoning process. Given the reasoning model’s lack of reasoning depth and interpretability, a deep fusion matching network is designed in this paper, which mainly includes a coding layer, matching layer, dependency convolution layer, information aggregation layer, and inference prediction layer. Based on a deep matching network, the matching layer is improved. Furthermore, the heuristic matching algorithm replaces the bidirectional long-short memory neural network to simplify the interactive fusion. As a result, it improves the reasoning depth and reduces the complexity of the model; the dependency convolution layer uses the tree-type convolution network to extract the sentence structure information along with the sentence dependency tree structure, which improves the interpretability of the reasoning process. Finally, the performance of the model is verified on several datasets. The results show that the reasoning effect of the model is better than that of the shallow reasoning model, and the accuracy rate on the SNLI test set reaches 89.0%. At the same time, the semantic correlation analysis results show that the dependency convolution layer is beneficial in improving the interpretability of the reasoning process. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

16 pages, 4255 KiB  
Article
2D/3D Multimode Medical Image Registration Based on Normalized Cross-Correlation
by Shan Liu, Bo Yang, Yang Wang, Jiawei Tian, Lirong Yin and Wenfeng Zheng
Appl. Sci. 2022, 12(6), 2828; https://0-doi-org.brum.beds.ac.uk/10.3390/app12062828 - 09 Mar 2022
Cited by 74 | Viewed by 6215
Abstract
Image-guided surgery (IGS) can reduce the risk of tissue damage and improve the accuracy and targeting of lesions by increasing the surgery’s visual field. Three-dimensional (3D) medical images can provide spatial location information to determine the location of lesions and plan the operation [...] Read more.
Image-guided surgery (IGS) can reduce the risk of tissue damage and improve the accuracy and targeting of lesions by increasing the surgery’s visual field. Three-dimensional (3D) medical images can provide spatial location information to determine the location of lesions and plan the operation process. For real-time tracking and adjusting the spatial position of surgical instruments, two-dimensional (2D) images provide real-time intraoperative information. In this experiment, 2D/3D medical image registration algorithm based on the gray level is studied, and the registration based on normalized cross-correlation is realized. The Gaussian Laplacian second-order differential operator is introduced as a new similarity measure to increase edge information and internal detail information to solve single information and small convergence regions of the normalized cross-correlation algorithm. The multiresolution strategy improves the registration accuracy and efficiency to solve the low efficiency of the normalized cross-correlation algorithm. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Perception Augmentation and Reasoning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-13
Back to TopTop