CAAI Transactions on Intelligence Technology

Abstract Lidar and visual data are affected heavily in adverse weather conditions due to sensing mechanisms, which bring potential safety hazards for vehicle navigation. Radar sensing is desirable to build a more robust navigation system. In this paper, a cross‐modality radar localisation on prior lidar maps is presented. Specifically, the proposed workflow consists of two parts: first, bird's‐eye‐view radar images are transferred to fake lidar images by training a generative adversarial network offline. Then with online radar scans, a Monte Carlo localisation framework is built to track the robot pose on lidar maps. The whole online localisation system only needs a rotating radar sensor and a pre‐built global lidar map. In the experimental section, the authors conduct an ablation study on image settings and test the proposed system on Oxford Radar Robot Car Dataset. The promising results show that the proposed localisation system could track the robot pose successfully, thus demonstrating the feasibility of radar style transfer for metric robot localisation on lidar maps.

Huan Yin

Yue Wang

Jun Wu

Rong Xiong

Radar style transfer for metric robot localisation on lidar maps

雷达风格迁移用于激光雷达地图上的度量机器人定位

Abstract Artificial intelligence (AI) applications are observed in different industries including the services, where the impressive changing pace is boosted by the technological advances in AI. The use of AI in the daily work of individuals and in shaping the relationship between firms and customers has resulted in increased efficiency and a higher degree of fascination in interaction. There are, however, customers' fears related to the use of AI. Therefore, understanding how AI affects customer trust is worth investigating. This study focuses on the AI applications and their impact on communication quality and customer trust. The features of AI applications investigated in this study include anthropomorphism, empathy response and interaction. A model was first empirically validated through Confirmatory Factor Analysis and tested using Covariance‐Based Structural Equation Modelling. Data were then collected from a survey of 507 customers of two banks and two big telecommunication firms in Vietnam. Empirical results indicate that anthropomorphism and interaction do not play critical roles in generating customer trust in AI unless they create communication quality with customers. The ability of empathy response makes customers trust in various service situations. AI application seems to be a good solution for service firms to enhance their relationship with customers in difficult circumstances, including a pandemic crisis. This study delivers implications for enhancing AI adoption in the service firms that intend to innovate their future operations.

Nguyen Thi Khanh Chi

Nam Hoang Vu

CAAI Trans on Intel Tech

Investigating the customer trust in artificial intelligence: The role of anthropomorphism, empathy response, and interaction

探究客户对人工智能的信任：拟人化、共情反应与交互的作用

The effective use of wind energy is an essential part of the sustainable development of human society, in particular, at the recent unprecedented pressure in shaping a low carbon energy environment. Accurate wind resource and power forecasting play a key role in improving the wind penetration. However, it has not been well adopted in the real-world applications due to the strong stochastic characteristics of wind energy. In recent years, the application boost of deep learning methods provides new effective tools in wind forecasting. This paper provides a comprehensive overview of the forecasting models based on deep learning in the field of wind energy. Featured approaches include time-series-based recurrent neural networks, restricted Boltzmann machines, convolutional neural networks as well as auto-encoder-based approaches. In addition, future development directions of deep-learning-based wind energy forecasting have also been discussed.

Zhou Wu

Gan Luo

Zhile Yang

Yuanjun Guo

Kang Li

Yusheng Xue

A comprehensive review on deep learning approaches in wind forecasting applications

风力预测应用中的深度学习方法综合评述

Abstract Due to strong learning ability, convolutional neural networks (CNNs) have been developed in image denoising. However, convolutional operations may change original distributions of noise in corrupted images, which may increase training difficulty in image denoising. Using relations of surrounding pixels can effectively resolve this problem. Inspired by that, we propose a robust deformed denoising CNN (RDDCNN) in this paper. The proposed RDDCNN contains three blocks: a deformable block (DB), an enhanced block (EB) and a residual block (RB). The DB can extract more representative noise features via a deformable learnable kernel and stacked convolutional architecture, according to relations of surrounding pixels. The EB can facilitate contextual interaction through a dilated convolution and a novel combination of convolutional layers, batch normalisation (BN) and ReLU, which can enhance the learning ability of the proposed RDDCNN. To address long‐term dependency problem, the RB is used to enhance the memory ability of shallow layer on deep layers and construct a clean image. Besides, we implement a blind denoising model. Experimental results demonstrate that our denoising model outperforms popular denoising methods in terms of qualitative and quantitative analysis. Codes can be obtained at https://github.com/hellloxiaotian/RDDCNN .

Qi Zhang

Jingyu Xiao

Chunwei Tian

Jerry Chun‐Wei Lin

Shichao Zhang

A robust deformed convolutional neural network (CNN) for image denoising

一种用于图像去噪的鲁棒变形卷积神经网络（CNN）

Abstract Human‐machine cooperative control has become an important area of intelligent driving, where driver intention recognition and dynamic control authority allocation are key factors for improving the performance of cooperative decision‐making and control. In this paper, an online learning method is proposed for human‐machine cooperative control, which introduces a priority control parameter in the reward function to achieve optimal allocation of control authority under different driver intentions and driving safety conditions. Firstly, a two‐layer LSTM‐based sequence prediction algorithm is proposed to recognise the driver's lane change (LC) intention for human‐machine cooperative steering control. Secondly, an online reinforcement learning method is developed for optimising the steering authority to reduce driver workload and improve driving safety. The driver‐in‐the‐loop simulation results show that our method can accurately predict the driver's LC intention in cooperative driving and effectively compensate for the driver's non‐optimal driving actions. The experimental results on a real intelligent vehicle further demonstrate the online optimisation capability of the proposed RL‐based control authority allocation algorithm and its effectiveness in improving driving safety.

Yan Jiang

Yuyan Ding

Xinglong Zhang

Xin Xu

Junwen Huang

A self‐learning human‐machine cooperative control method based on driver intention recognition

基于驾驶员意图识别的自学习人机协同控制方法

Abstract Intelligent sorting is an important prerequisite for the full quantitative consumption and harmless disposal of kitchen waste. The existing object detection method based on an ImageNet pre‐trained model is an effective way of sorting. Owing to significant domain gaps between natural images and kitchen waste images, it is difficult to reflect the characteristics of diverse scales and dense distribution in kitchen waste based on an ImageNet pre‐trained model, leading to poor generalisation. In this article, the authors propose the first pre‐trained model for kitchen waste sorting called KitWaSor, which combines both contrastive learning (CL) and masked image modelling (MIM) through self‐supervised learning (SSL). First, to address the issue of diverse scales, the authors propose a mixed masking strategy by introducing an incomplete masking branch based on the original random masking branch. It prevents the complete loss of small‐scale objects while avoiding excessive leakage of large‐scale object pixels. Second, to address the issue of dense distribution, the authors introduce semantic consistency constraints on the basis of the mixed masking strategy. That is, object semantic reasoning is performed through semantic consistency constraints to compensate for the lack of contextual information. To train KitWaSor, the authors construct the first million‐level kitchen waste dataset across seasonal and regional distributions, named KWD‐Million. Extensive experiments show that KitWaSor achieves state‐of‐the‐art (SOTA) performance on the two most relevant downstream tasks for kitchen waste sorting (i.e. image classification and object detection), demonstrating the effectiveness of the proposed KitWaSor.

Leyuan Fang

Shuaiyu Ding

Hao Feng

Junwu Yu

Lin Tang

Pedram Ghamisi

KitWaSor: Pioneering pre‐trained model for kitchen waste sorting with an innovative million‐level benchmark dataset

KitWaSor：厨房垃圾分拣的开创性预训练模型及创新百万级基准数据集

Abstract Audio‐visual scene classification (AVSC) poses a formidable challenge owing to the intricate spatial‐temporal relationships exhibited by audio‐visual signals, coupled with the complex spatial patterns of objects and textures found in visual images. The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures, inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio‐visual data. The authors present a feature pyramid attention network (FPANet) for audio‐visual scene understanding, which extracts semantically significant characteristics from audio‐visual data. The authors’ approach builds multi‐scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module (FPAM). A dimension alignment (DA) strategy is employed to align feature maps from multiple layers, a pyramid spatial attention (PSA) to spatially locate essential regions, and a pyramid channel attention (PCA) to pinpoint significant temporal frames. Experiments on visual scene classification (VSC), audio scene classification (ASC), and AVSC tasks demonstrate that FPANet achieves performance on par with state‐of‐the‐art (SOTA) approaches, with a 95.9 F1‐score on the ADVANCE dataset and a relative improvement of 28.8%. Visualisation results show that FPANet can prioritise semantically meaningful areas in audio‐visual signals.

Liguang Zhou

Yuhongze Zhou

Xiaonan Qi

Junjie Hu

Tin Lun Lam

Yangsheng Xu

Feature pyramid attention network for audio‐visual scene classification

音频-视觉场景分类的特征金字塔注意力网络

Abstract In a multi‐row facility layout problem (MRFLP), facilities are arranged in more than one row under the limited layout area. Considering different layout factors, various extensions of MRFLP have been modelled. However, the orientation of input/output (I/O) point in a facility, as a key factor that plays a direct impact on flow cost, is seldom taken into account. Hence, a novel MRFLP is formulated to minimise both the layout area and flow cost, in which the position of I/O point is employed to calibrate the position of a facility and its orientation determines the flow cost for transporting materials among facilities. To solve the problem, a decomposition‐based multi‐objective evolutionary algorithm with perceiving discontinuity characteristic of Pareto front (PF) is put forward. After judging the discontinuity of PF, the weight vectors are adjusted to enhance the exploitation in continuous regions. To avoid premature convergence, a re‐initialisation mechanism is introduced to help the population jump out of the local optima. Moreover, an improved adaptive epsilon constraint‐handling technique is designed to effectively balance the diversity and feasibility of a population during the evolution. Experimental results of 12 instances expose that the proposed algorithm outperforms other state‐of‐the‐art algorithms significantly.

Yinan Guo

Yao Huang

Jian Cheng

Xiaoyu Ban

Xiaoxiao Zhao

Tianyu Liu

MOEA/D‐based multi‐row facility layout optimisation method with discontinuity perceiving of the Pareto front

基于MOEA/D的多排设施布局优化方法与Pareto前沿不连续感知

Abstract Disease identification for fruits and leaves in the field of agriculture is important for estimating production, crop yield, and earnings for farmers. In the specific case of pomegranates, this is challenging because of the wide range of possible diseases and their effects on the plant and the crop. This study presents an adaptive histogram‐based method for solving this problem. Our method describe is domain independent in the sense that it can be easily and efficiently adapted to other similar smart agriculture tasks. The approach explores colour spaces, namely, Red, Green, and Blue along with Grey. The histograms of colour spaces and grey space are analysed based on the notion that as the disease changes, the colour also changes. The proximity between the histograms of grey images with individual colour spaces is estimated to find the closeness of images. Since the grey image is the average of colour spaces (R, G, and B), it can be considered a reference image. For estimating the distance between grey and colour spaces, the proposed approach uses a Chi‐Square distance measure. Further, the method uses an Artificial Neural Network for classification. The effectiveness of our approach is demonstrated by testing on a dataset of fruit and leaf images affected by different diseases. The results show that the method outperforms existing techniques in terms of average classification rate.

Mohanmuralidhar Prajwala

Prabhuswamy Prajwal Kumar

Shanubhog Maheshwarappa Gopinath

Shivakumara Palaiahnakote

Mahadevappa Basavanna

Daniel P. Lopresti

Domain‐independent adaptive histogram‐based features for pomegranate fruit and leaf diseases classification

域无关自适应直方图特征用于石榴果实和叶片病害分类

Abstract Currently, the link prediction algorithms primarily focus on studying the interaction between nodes based on chain structure and star structure, which predominantly rely on low‐order structural information and do not explore the multivariate interactions between nodes from the perspective of higher‐order structural information present in the network. The cycle structure is a higher‐order structure that lies between the star and clique structures, where all nodes within the same cycle can interact with each other, even in the absence of direct edges. If a node is encompassed by multiple cycles, it indicates that the node interacts and associates with a greater number of nodes in the network, and it means the node is more important in the network to some extent. Furthermore, if two nodes are included in multiple cycles, it signifies the two nodes are more likely to be connected. Therefore, firstly, a multi‐information fusion node importance algorithm based on the cycle structure information is proposed, which integrates both high‐order and low‐order structural information. Secondly, the obtained integrated structure information and node feature information is regarded as the input features, a two‐channel graph neural network model is designed to learn the cycle structure information. Then, the cycle structure information is utilised for the task of link prediction, and a graph neural link predictor with multi‐information interactions based on the cycle structure is developed. Finally, extensive experimental validation and analysis show that the node ranking result of the proposed node importance index is more consistent with the actual situation, the proposed graph neural network model can effectively learn the cycle structure information, and using higher‐order structural information—cycle information proves to significantly enhance the overall link prediction performance.

Abbreviation	CAAI Trans on Intel Tech
Journal Impact	8.39
Quartiles(Global)	COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE(Q1)

ISSN	2468-2322, 2468-6557
h-index	34

Publication Information	Publisher: John Wiley & Sons Inc.，Publishing cycle: ，Journal Type: journal，Open Access Journals: Yes
Basic data	Year of publication: 2017，Proportion of original research papers: 94.74%，Self Citation Rate:8.30%， Gold OA Rate: 86.74%
Journal Fees	$2680Details
Average review cycle	网友分享经验：35 Weeks

CAAI Transactions on Intelligence Technology

Journal Citation Format

A journal article with 1 author

A journal article with 2 authors

A journal article with 3 authors

A journal article with 5 or more authors

Books Citation Format

Thesis Citation Format

Web sites Citation Format

Patent Citation Format

Staying up late manually editing references? ivySCI automatically matches journals and helps you generate references with a single click.

Share Submission Experience