Resource Type

Journal Article 14195

Conference Videos 774

Conference Information 487

Conference Topics 6

Year

2022 988

2021 1669

2020 1350

2019 1305

2018 886

2017 932

2016 768

2015 777

2014 659

2013 566

2012 565

2011 564

2010 631

2009 607

2008 654

2007 684

2006 293

2005 211

2004 201

2003 186

open ︾

Keywords

China 103

sustainable development 79

different 78

optimization 70

numerical simulation 66

adsorption 63

development 62

simulation 61

temperature 61

COVID-19 55

development strategy 52

management 49

concrete 46

mechanism 41

engineering management 30

control 29

Machine learning 28

engineering 27

sustainability 26

open ︾

Search scope:

排序： Display mode:

Water Resource Effectiveness of Vegetation Conservation and Restoration in North China

Sun Siqi,Chen Yongzhe,Wang Cong,Hu Qingfang,Lyu Yihe

Strategic Study of Chinese Academy of Engineering doi: 10.15302/J-SSCAE-2022.05.012

Abstract:
In recent years, a series of ecological protection and restoration projects has been implemented in North China, and the
vegetation conditions have changed significantly. Exploring the impact of regional vegetation restoration on the water circulation
process and the balance of water supply and demand is important for improving ecological restoration strategies and realizing the
sustainable utilization of regional water resources. This study conducted a comprehensive analysis using the Pearson correlation
coefficient and Moran’s I index and based on multi-source water covariate data. The spatial and temporal variation of vegetation and
different water covariates is analyzed, the water resource effects of vegetation conservation and restoration are identified, and the
tradeoff between water resources and vegetation restoration is discussed. The results show that the effects of ecological protection and
restoration projects are remarkable, with the net primary productivity increasing at a rate of approximately 2.3 times faster than that
outside the project area; the vegetation expansion and evapotranspiration show strong spatial and temporal correlations; and the
increase in evapotranspiration owing to vegetation restoration is the main reason for the deficit or significant reduction in water
storage. Therefore, it is necessary to improve the implementation strategy of ecological restoration while considering the restriction of
water resources on vegetation conservation and restoration, strengthen the dominant position of the ecosystem’s own resilience, and
promote the sustainability of vegetation restoration and the sustainable use of regional water resources.

Keywords： North China     ecological restoration projects     evapotranspiration     water storage     net primary productivity     atural restoration    

HTML PDF Collect
Share

Industrial Application of Artificial Intelligence in China: Current Status and Challenges

Xu Wenwei, Xiao Lizhi, Liu He

Strategic Study of Chinese Academy of Engineering doi: 10.15302/J-SSCAE-2022.07.010

Abstract:

Deep learning has enhanced the versatility of artificial intelligence (AI) algorithms. In the last decade, the AI industry has been spawned and developing rapidly. However, practice shows that the application of AI technology and algorithms in the industrial field faces huge challenges. Approaches need to be explored for enterprises to properly use AI and for the academia and industry to effectively collaborate to facilitate algorithm application. The study focuses on the sustainable development of China’s AI industry, and presents several practical cases of AI application, through which we analyze the current status, challenges, and their root causes pertaining to industrial application of AI and propose corresponding suggestions. The complexity of AI application for enterprises involves multiple dimensions, including business requirements, data, algorithms, infrastructure, and supporting systems. The maturity of AI application depends on the degree of data preparation and the level of data governance. At the national level, a friendly ecology for AI application should be built to promote the coordinated development of the entire industry chain, and specific measures should be taken to support the research and development of AI technologies that focus on full-stack AI, AI basic platform and tool system, and AI root technology, thus to improve the independence of China’s AI core technologies. Moreover, enterprises should be encouraged to actively participate in digital transformation and intelligent upgrading using AI technologies, thereby forming a strong coupling and a two-way cycle between research and application of AI technologies.

Keywords： artificial intelligence (AI)     enterprise scenarios     intelligent solutions     application     full-stack AI     AI root technology    

HTML PDF Collect
Share

Building a Highly Stable Ultrathin Nanoporous Layer Assisted by Glucose for Desalination Article

Yanqiu Zhang, Fan Yang, Hongguang Sun, Yongping Bai, Songwei Li, Lu Shao

Engineering 2022, Volume 16, Issue 9,   Pages 247-255 doi: 10.1016/j.eng.2020.06.033

Abstract:

Although nanoporous membranes are of great interest in desalination, it is still challenging to construct highly permeable nanoporous membranes with excellent rejections for an efficient desalination process. In this work, highly permeable nanoporous membranes were built from renewable resources, assisted by the versatile functions of glucose and dopamine, with coupling reactive groups via interfacial reaction with 1,3,5-benzenetricarbonyl trichloride (TMC). The small molecules (0.66 nm) of glucose, which have high hydrophilicity, can diffuse into the membrane for an effective reaction to ensure structural integration. Our novel ultrathin (~44 nm) nanofiltration (NF) membrane exhibits ultra-high Na2SO4 flux and excellent rejection of Na2SO4 (66.5 L∙m−2∙h−1, 97.3%) and MgSO4 (63.0 L∙m−2∙h−1, 92.1%) under a pressure of 5 bar (1 bar = 105 Pa) which is much superior to the performance of natural-product NF membranes. The membrane demonstrates excellent long-term stability, as well as tremendous acid-base and alkali-base stability and high anti-pollution capacity. The designed membrane materials and architecture open a new door to biopolymer-based separation membranes beyond existing membrane materials.

Keywords： Nanoporous membrane     Renewable resources     Nanofiltration     Desalination     Glucose    

HTML PDF Collect
Share

A Polarization Programmable Antenna Array Article

Dingzhao Chen, Yanhui Liu, Ming Li, Pan Guo, Zhuo Zeng, Jun Hu, Y. Jay Guo

Engineering 2022, Volume 16, Issue 9,   Pages 100-114 doi: 10.1016/j.eng.2022.03.015

Abstract:

Reconfigurable antennas are becoming a major antenna technology for future wireless communications and sensing systems. It is known that, with a single linear polarization (LP) reconfigurable antenna element, a preferred polarization can be produced from a set of multiple polarization states, thus improving the quality of the communication link. This paper presents a new concept of a polarization programmable reconfigurable antenna array that consists of a number of polarization reconfigurable antenna elements with a finite number of possible polarization states. By employing a new optimization strategy and programming the polarization states of all the array elements, we demonstrate that it is possible to realize any desired LP in the vectorial array radiation pattern with accurate control of sidelobe and crosspolarization levels (XPLs), thereby achieving the desired polarization to perfectly match that of the required communications signal. Both numerical and experimental results are provided to prove the concept, and they agree well with each other.

Keywords： 阵列天线     极化可编程天线     可重构天线    

HTML PDF Collect
Share

The First Stage of the Middle-Line South-to-North Water-Transfer Project

Xinqiang Niu

Engineering 2022, Volume 16, Issue 9,   Pages 21-28 doi: 10.1016/j.eng.2022.07.001

HTML PDF Collect
Share

Introduction of a New Method for Regulating Laves Phases in Inconel 718 Superalloy during a Laser-Repairing Process Article

Shang Sui,Haosheng Li,Zuo Li,Xuan Zhao,Liang Ma,Jing Chen

Engineering 2022, Volume 16, Issue 9,   Pages 239-246 doi: 10.1016/j.eng.2021.08.030

Abstract:

The morphology, size, and distribution of Laves phases have important influences on the mechanical properties of laser-repaired Inconel 718 (IN718) superalloy. Due to the deterioration of the substrate zone, the Laves phase in the laser cladding zone of IN718 superalloy cannot be optimized by a high-temperature solution treatment. In this study, an in situ laser heat-treatment method was proposed to regulate the morphology and size of the Laves phase in the laser cladding zone of IN718 superalloy without impacting the substrate zone. In the in situ laser heat-treatment process, a laser was used to heat previously deposited layers with optimized manufacturing parameters. A thermocouple and an infrared camera were used to analyze thermal cycles and real-time temperature fields, respectively. Microstructures and micro-segregations were observed by optical microscopy, scanning electron microscopy, and electron probe microanalysis. It was found that the in situ laser heat treatment effectively changed the morphology and size of the Laves phase, which was transformed from a continuous strip-like shape to a discrete granular shape. The effective temperature range and duration were the two main factors influencing the Laves phase during the in situ laser heat-treatment process. The effective temperature range was determined by the laser linear energy density, and the peak temperature increased with the increase of the linear energy density. In addition, the temperature amplitude could be reduced by simultaneously increasing the laser power and the scanning velocity. Finally, a flow diagram was developed based on the in situ laser heat-treatment process, and the deposition of a single-walled sample with fine and granular Laves phases was detected.

Keywords： Laser repair     In situ laser heat treatment     Inconel 718 alloy     Laves phase    

HTML PDF Collect
Share

Mesoscopic Modeling Approach and Application for Steel Fiber Reinforced Concrete under Dynamic Loading: A Review Review

Jinhua Zhang,Zhangyu Wu,Hongfa Yu,Haiyan Ma,Bo Da

Engineering 2022, Volume 16, Issue 9,   Pages 220-238 doi: 10.1016/j.eng.2022.01.011

Abstract:

Steel fiber reinforced concrete (SFRC) has drawn extensive attention in recent years for its superior mechanical response to dynamic and impact loadings. Based on the existing test results, the highstrength steel fibers embedded in a concrete matrix usually play a strong bridging effect to enhance the bonding force between fiber and the matrix, and directly contribute to the  improvement of the post-cracking behavior and residual strength of SFRC. To gain a better understanding of the action behavior of steel fibers in matrix and further capture the failure mechanism of SFRC under dynamic loads, the mesoscopic modeling approach that assumes SFRC to be composed of different mesoscale phases (i.e., steel fibers, coarse aggregates, mortar matrix, and interfacial transition zone (ITZ)) has been widely employed to simulate the dynamic responses of SFRC material and structural members. This paper presents a comprehensive review of the state-of-the-art mesoscopic models and simulations for SFRC under dynamic loading. Generation approaches for the SFRC mesoscale model in the simulation works, including steel fiber, coarse aggregate, and the ITZ between them, are reviewed and compared systematically. The material models for different phases and the interaction relationship between fiber and concrete matrix are summarized comprehensively. Additionally, some example applications for SFRC under dynamic loads (i.e., compression, tension, and contact blast) simulated using the general mesoscale models are given. Finally, some critical analysis on the current shortcomings of the mesoscale modeling of SFRC is highlighted, which is of great significance for the future investigation and development of SFRC.

Keywords： Steel fiber reinforced concrete     Mesoscale modeling     Dynamic loading     Materials model     Interfacial characteristic    

HTML PDF Collect
Share

Demand Flexibility of Residential Buildings: Definitions, Flexible Loads, and Quantification Methods Review

Zhengyi Luo, Jinqing Peng, Jingyu Cao, Rongxin Yin, Bin Zou, Yutong Tan, Jinyue Yan

Engineering 2022, Volume 16, Issue 9,   Pages 123-140 doi: 10.1016/j.eng.2022.01.010

Abstract:

This paper reviews recent research on the demand flexibility of residential buildings in regard to definitions, flexible loads, and quantification methods. A systematic distinction of the terminology is made, including the demand flexibility, operation flexibility, and energy flexibility of buildings. A comprehensive definition of building demand flexibility is proposed based on an analysis of the existing definitions. Moreover, the flexibility capabilities and operation characteristics of the main residential flexible loads are summarized and compared. Models and evaluation indicators to quantify the flexibility of these flexible loads are reviewed and summarized. Current research gaps and challenges are identified and analyzed as well. The results indicate that previous studies have focused on the flexibility of central air conditioning, electric water heaters, wet appliances, refrigerators, and lighting, where the proportion of studies focusing on each of these subjects is 36.7%, 25.7%, 14.7%, 9.2%, and 8.3%, respectively. These flexible loads are different in running modes, usage frequencies, seasons, and capabilities for shedding, shifting, and modulation, while their response characteristics are not yet clear. Furthermore, recommendations are given for the application of white-, black-, and grey-box models for modeling flexible loads in different situations. Numerous static flexibility evaluation indicators that are based on the aspects of power, temporality, energy, efficiency, economics, and the environment have been proposed in previous publications, but a consensus and standardized evaluation framework is lacking. This review can help readers better understand building demand flexibility and learn about the characteristics of different residential flexible loads, while also providing suggestions for future research on the modeling techniques and evaluation metrics of residential building demand flexibility.

Keywords： Residential building     Demand flexibility     Flexible loads     Modeling techniques     Quantification indicators    

HTML PDF Collect
Share

Implementing An “Impracticable” Copolymerization to Fabricate A Desired Polymer Precursor for N-doped Porous Carbons Article

Shi-Chao Qi, Xiao-Jie Lu, Yin-Cong Lou, Rui Zhou, Ding-Ming Xue, Xiao-Qin Liu, Lin-Bing Sun

Engineering 2022, Volume 16, Issue 9,   Pages 154-161 doi: 10.1016/j.eng.2021.07.031

Abstract:

It is common that a proof-of-concept of a desired reaction, which might generate materials with new functions or application potential, is eventually proved impracticable or commercially unfeasible. Considerable efforts have been made but wasted in searching for unknown reaction conditions in solvent environments because it was believed that the activity of reactants can be enhanced to facilitate reactions by dissolving them in solvents. However, an abnormal case was discovered in this study. A desired copolymerization reaction between 1,3,5-tris(chloromethyl)-2,4,6-trimethylbenzene and melamine was confirmed to be impracticable under various solvent conditions; however, it was successfully implemented using a solvent-free method. Using first-principle calculations and molecular dynamics simulations, two decisive factors that the reaction in solvents cannot possess, namely the reaction equilibrium being pushed by the timely release of by-products and the confined thermal motions of the activated monomer molecules in the solid phase, were demonstrated to make the copolymerization successful in the solvent-free method. Owing to the high aromaticity and azacyclo-content, the as-synthetic copolymer exhibited good application potential as a precursor to fabricate N-doped porous carbons with satisfactory carbon yields, ideal N contents, desired textural properties, and competitive CO2 capture abilities compared to other representative counterparts reported recently.

Keywords： Solvent-free method     Solvent effect     Copolymerization     N-doped porous carbon    

HTML PDF Collect
Share

The Roles of Nuclear Energy in Hydrogen Production Views & Comments

Shinji Kubo

Engineering 2022, Volume 16, Issue 9,   Pages 16-20 doi: 10.1016/j.eng.2021.12.024

HTML PDF Collect
Share

Countermeasures for Assuring Water Ecological Environment Security in China

Huo Shouliang,Zhang Hanxiao,Jin Xiaowei ,Cao Xiaofeng,Wu Fengchang

Strategic Study of Chinese Academy of Engineering doi: 10.15302/J-SSCAE-2022.05.001

Abstract:
A good water ecological environment is crucial for the sustainable development and ecological civilization of China.
However, various problems remain for China’s water ecological environment, including eutrophication, pollution of drinking water
sources, contamination of groundwater and coastal waters, emerging pollutants, and shortage of ecological water. In this study, we
analyzed the overall situation of the water ecological environment in China, pinpointed the major challenges, and proposed the
strategic thinking and several basic principles. These principles focus on improving the water ecological environment and
comprehensively consider water quality improvement, water ecological protection, and water environmental risk prevention and
control. Three major scientific and technological projects were proposed pertaining to (1) coordinated governance and overall
restoration of mountains, rivers, forests, fields, lakes, grasses, and sand in key basins, (2) overall improvement of water environment
and water ecology in the Beijing‒Tianjin‒Hebei Collaborative Development Area, and (3) assurance of drinking water safety in the
new era. Furthermore, we proposed the following four countermeasures: (1) revising the Environmental Quality Standards for Surface
Water to strengthen its leading role in the construction of water ecological civilization in China; (2) evaluating the spatial and temporal
differences of nitrogen and phosphorus nutrients in China’s lakes and implementing differentiated nutrients standards; (3) assessing
the current status of water ecology in China and promoting water ecology monitoring and assessment; and (4) establishing an
intelligent supervision platform for drinking water safety based on big data fusion.

Keywords： water ecological environment     ecological civilization     quality improvement     water ecological security     drinking water safety    

HTML PDF Collect
Share

Exploring Water-and-Land-Adapted Spatial Layout of Crop Planting in North China

Huang Feng,Yang Xiaolin,Fang Yu,Wang Sufen,Kang Shaozhong

Strategic Study of Chinese Academy of Engineering doi: 10.15302/J-SSCAE-2022.05.011

Abstract:
North China has specific regional advantages in the overall economic and social development of China, and water resources are the most prominent factor that affects the sustainable development of this region. This study focuses on the land spatial layout of water-and-land adapted planting in North China. Based on the analysis of agricultural planting structure and water and land resource layout in the current year (2018) of North China, and considering varied population, climate, and socio-economic scenarios and water resource constraints, the study proposes a scheme for optimizing the agricultural planting layout in North China that adapts to local water and land resource conditions. We suggest that the burden on production and supply of commercial grain and other commercial agricultural products in North China should be appropriately reduced. In terms of improving the regional resource carrying capacity, Hebei Province should alleviate its water shortage through water transfer. Shanxi Province should improve the agricultural water use efficiency through agricultural mechanization and modernization. Shandong Province and Henan Province can moderately fallow the land and improve forest and grass coverage. It is also recommended to optimize the spatial layout of agricultural planting and adjust the planting structure to adapt to water. In shallow groundwater overexploitation areas as well as Tianjin City and the southeast of Hebei Plain where deep groundwater overexploitation is severe, semi-arid land planting systems and structures that adapt to precipitation should be developed, and the specific recuperation period should be determined according to the rate of groundwater recharge.

Keywords： North China     water balance     land spatial planning     water-adapted land use     matching of water and land resources     water-adapted planting    

HTML PDF Collect
Share

Groundwater Pollution Prevention and Control: Current Status and Countermeasures

Ren Jing,Li Juan,Xi Beidou,Yang Yang ,Lu Haojie,Shi Junxiang

Strategic Study of Chinese Academy of Engineering doi: 10.15302/J-SSCAE-2022.05.019

Abstract:
Groundwater is a significant source of drinking water and a strategic resource for China. However, the groundwater quality
in China is unoptimistic and China faces a severe situation regarding groundwater environment protection as its groundwater pollution
prevention and control started late. Therefore, problems faced by groundwater pollution prevention and control should be researched
and targeted countermeasures be proposed to curb the trend of groundwater pollution and improve groundwater quality. The study
reviews the existing regulations and policies, management status, and requirements of groundwater pollution prevention and control in
China, and predicts the future management trend. The results indicate the following challenges. (1) The groundwater pollution status
is still unclear and hierarchical and classified management of groundwater pollution is lacking. (2) The groundwater pollution forms
become increasingly complex and the regulatory system requires improvement. (3) The groundwater pollution control becomes
increasingly difficult and only few control technologies were applied to underground pollution treatment. (4) The requirements of
groundwater environmental management are constantly improving; however, the innovation impetus is insufficient. Therefore, we
proposed several countermeasures. The pollution status should be identified through continuous investigation and assessment of
groundwater environment in key regions, to support the construction of a hierarchical and classified management system. Intelligent,
visualized, and coordinated supervision should be achieved by establishing a multilevel groundwater environmental monitoring
network and adopting supervisory measures based on information technologies. Green and sustainable models should be formed and
promoted through the experimental implementation of groundwater pollution prevention and control projects and by constructing 21
pilot sites. The original innovation and management capacities should be enhanced by focusing on key technical issues such as
groundwater pollution traceability, standards system construction, and development of relevant software with proprietary intellectual
property rights.

Keywords： Groundwater Pollution prevention and control     Groundwater monitoring system     Groundwater environment management    

HTML PDF Collect
Share

Evaluating the Methods for Assessing Implementation Effects of River Chief System in China

Yin Hailong, Ge Jia’ning, Xu Zuxin, Xu Jin

Strategic Study of Chinese Academy of Engineering doi: 10.15302/J-SSCAE-2022.05.020

Abstract:
Establishing a river chief system is stipulated in the newly amended Law of the People’s Republic of China on Prevention
and Control of Water Pollution, which clarifies the liability of party or administrative heads at various levels for water environment
rehabilitation in their own administrative regions. In this article, we analyze the implementation effects of the river chief in China,
current assessment methods, and their deficiencies, and propose two quantitative assessing methods: (1) comprehensive water quality
assessment for the cross sections of rivers and lakes and (2) assessment using the pollutant load intercepting rate of sewer networks,
aiming to improve the scientific rationality for effect assessment of the river chief system. With Suzhou Creek rehabilitation in
Shanghai as an example, application of the comprehensive water quality assessment method was introduced. By analyzing the
pollutant load intercepting rate in various provinces (autonomous regions or municipalities) in China, we find that on average 34%
wastewater is still discharged into water courses in an untreated state, leading to repeated occurrence of water quality deterioration.
Introducing the comprehensive water quality assessment and the pollutant load intercepting rate into the river chief assessment will
effectively push the government at all levels to concentrate their human, material, and financial resources onto urban drainage network
correction and the interception of pollution sources discharged into watercourses.

Keywords： river chief system     comprehensive water quality     water environmental quality     pollution load     sewage collection     water pollution prevention and control    

HTML PDF Collect
Share

On visual understanding Perspective

Yunhe PAN

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 9,   Pages 1287-1289 doi: 10.1631/FITEE.2130000

Abstract: 1 Problems and development in the field of visual recognition From the beginning of artificial intelligence (AI), pattern recognition has been an important aspect of the field. In recent years, the maturity of deep neural networks (DNNs) has significantly improved the accuracy of visual recognition. DNN has been widely used in applications such as medical image classification, vehicle identification, and facial recognition, and has thus promoted the development of the AI industry to a climax. However, there are currently critical defects in visual recognition based on DNN technology. For example, these networks usually require a very large amount of labeled training data, and have weak cross-domain transferability and task generalization. Their learning and reasoning processes are still hard to understand, which leads to unexplainable predictions. These challenges present an obstacle to the development of AI research and application. If we look at the current visual recognition technology from a larger and broader perspective, we can find that the above defects are fundamental, because the currently used DNN model needs to be trained with a large amount of labeled visual data, and then used in the process of visual recognition. In essence, it is a classification process based on data statistics and pattern matching (), so it is heavily dependent on training sample distribution. However, to have interpretability and transferability, visual classification is not good enough, while visual understanding becomes indispensable. 2 Three-step model of visual understanding Visual recognition is not equivalent to visual understanding. We propose that there are three steps in visual understanding, of which classification is only the first. After classification, one proceeds to the second step: visual parsing. In the process of visual parsing, the components of the visual object and their structural relationship are further identified and compared. Identification involves finding components and structures in visual data that correspond to the components and structures of known visual concepts. Parsing verifies the correctness of the classification results and establishes the structure of visual object data. After completing visual parsing, one proceeds to the third step: visual simulation. In this step, predictive motion simulation and operations including causal reasoning are carried out on the structure of the visual objects to judge the rationality of meeting physical constraints in reality, so as to verify the previous recognition and parsing results. We can take a picture of a cat as an example to illustrate the modeling process of visual understanding. The process is as follows: 1. Recognition: It is a cat. Extract the visual concept of the cat and proceed to the next step; otherwise, stop here. 2. Parsing: Based on the structure contained in the visual concept, identify whether the cat’s head, body, feet, tail, and their relationships are suitable for the cat concept. If not, return to step 1 for re-identification; if yes, proceed to the next step. 3. Simulation: Simulate various activities of the cat to investigate whether the cat’s activities in various environments can be completed reasonably. If not, return to step 2; if yes, proceed to the next step. 4. End visual understanding: Incorporate the processed structured data into the knowledge about cats. 3 Characteristics of the three-step visual understanding model To further understand the above-mentioned three-step visual understanding model, we will further discuss some of its characteristics: 1. The key step in visual understanding is visual parsing. This is an identification of the components contained in the object according to a conceptual structure based on the visual concept (), obtained by visual recognition. Parsing a visual object, in order from top to bottom, is a process of identifying and constructing visual data from the root of the concept tree to the branches and leaves. 2. Human visual parsing tasks are often aimed only at the main components of concepts. The main components have existing, commonly used names. For subsidiary parts that have not been described in language, such as the area between the cheekbones and chin of the face, only experts specialized in anatomy (such as doctors or artists) have professional concepts and memories. Therefore, visual parsing is a cross-media () process that incorporates multiple knowledge () including vision and language. 3. Visual knowledge () is essential for visual parsing and visual simulation, because the visual concept structure provides a reliable source for component identification and comparison. Parents and teachers play a large role in establishing visual knowledge. When they say to a child, “Look, this is a kitten. Kittens have pointed ears, round eyes, long whiskers, and four short legs. When they run fast and leap high, they can catch a mouse,” they are guiding children in constructing basic visual knowledge in their long-term memory. 4. Visual data that have been understood have actually been structured to form visual knowledge. Such visual knowledge can easily be incorporated into long-term memory. For example, when one sees a cat whose head is very small, or whose fur color and markings are unusual, or who has a particular gait, this information may be included in one’s “cat” memory by expanding the concept of “cat” (). The category of visual concepts is very important, and its extent reflects the general degree of knowledge. In fact, it is not always useful to collect a large amount of sample data to train a DNN model. However, the more widely distributed and balanced the data are within a concept category, the better, because the robustness and generalization ability of the model trained based on such sample data are stronger. 5. The learned visual information can naturally be explained, because it has deep structural cognition; it can also be used for transfer learning because the semantic concepts have cross-media relevance. This semantic information can clearly indicate the reasonable direction of transferable recognition. 4 Advancing visual recognition to visual understanding Visual understanding is important, because it can potentially work with visual knowledge () and multiple knowledge representation () to open a new door to AI research. Visual understanding involves not only in-depth visual recognition, but also thorough learning and application of visual knowledge (). AI researchers have been studying visual recognition for more than half a century. Speech recognition, a research task started in parallel with visual recognition, moved on to analysis of words, sentences, and paragraphs quite early, and has successfully developed human-computer dialogue and machine translation, setting a well-known milestone. Therefore, we suggest that it is necessary to advance visual recognition to visual understanding, and that this is an appropriate time to target this deeper visual intelligence behavior.
HTML PDF Collect
Share

Title Author Date Type Operation

Water Resource Effectiveness of Vegetation Conservation and Restoration in North China

Sun Siqi,Chen Yongzhe,Wang Cong,Hu Qingfang,Lyu Yihe

Journal Article

Industrial Application of Artificial Intelligence in China: Current Status and Challenges

Xu Wenwei, Xiao Lizhi, Liu He

Journal Article

Building a Highly Stable Ultrathin Nanoporous Layer Assisted by Glucose for Desalination

Yanqiu Zhang, Fan Yang, Hongguang Sun, Yongping Bai, Songwei Li, Lu Shao

Journal Article

A Polarization Programmable Antenna Array

Dingzhao Chen, Yanhui Liu, Ming Li, Pan Guo, Zhuo Zeng, Jun Hu, Y. Jay Guo

Journal Article

The First Stage of the Middle-Line South-to-North Water-Transfer Project

Xinqiang Niu

Journal Article

Introduction of a New Method for Regulating Laves Phases in Inconel 718 Superalloy during a Laser-Repairing Process

Shang Sui,Haosheng Li,Zuo Li,Xuan Zhao,Liang Ma,Jing Chen

Journal Article

Mesoscopic Modeling Approach and Application for Steel Fiber Reinforced Concrete under Dynamic Loading: A Review

Jinhua Zhang,Zhangyu Wu,Hongfa Yu,Haiyan Ma,Bo Da

Journal Article

Demand Flexibility of Residential Buildings: Definitions, Flexible Loads, and Quantification Methods

Zhengyi Luo, Jinqing Peng, Jingyu Cao, Rongxin Yin, Bin Zou, Yutong Tan, Jinyue Yan

Journal Article

Implementing An “Impracticable” Copolymerization to Fabricate A Desired Polymer Precursor for N-doped Porous Carbons

Shi-Chao Qi, Xiao-Jie Lu, Yin-Cong Lou, Rui Zhou, Ding-Ming Xue, Xiao-Qin Liu, Lin-Bing Sun

Journal Article

The Roles of Nuclear Energy in Hydrogen Production

Shinji Kubo

Journal Article

Countermeasures for Assuring Water Ecological Environment Security in China

Huo Shouliang,Zhang Hanxiao,Jin Xiaowei ,Cao Xiaofeng,Wu Fengchang

Journal Article

Exploring Water-and-Land-Adapted Spatial Layout of Crop Planting in North China

Huang Feng,Yang Xiaolin,Fang Yu,Wang Sufen,Kang Shaozhong

Journal Article

Groundwater Pollution Prevention and Control: Current Status and Countermeasures

Ren Jing,Li Juan,Xi Beidou,Yang Yang ,Lu Haojie,Shi Junxiang

Journal Article

Evaluating the Methods for Assessing Implementation Effects of River Chief System in China

Yin Hailong, Ge Jia’ning, Xu Zuxin, Xu Jin

Journal Article

On visual understanding

Yunhe PAN

Journal Article