The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target domain.However,the multi-genera...The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target domain.However,the multi-generator mechanism is employed among the advanced approaches available to model different domain mappings,which results in inefficient training of neural networks and pattern collapse,leading to inefficient generation of image diversity.To address this issue,this paper introduces a multi-modal unsupervised image translation framework that uses a generator to perform multi-modal image translation.Specifically,firstly,the domain code is introduced in this paper to explicitly control the different generation tasks.Secondly,this paper brings in the squeeze-and-excitation(SE)mechanism and feature attention(FA)module.Finally,the model integrates multiple optimization objectives to ensure efficient multi-modal translation.This paper performs qualitative and quantitative experiments on multiple non-paired benchmark image translation datasets while demonstrating the benefits of the proposed method over existing technologies.Overall,experimental results have shown that the proposed method is versatile and scalable.展开更多
As an alternative to conventional encapsulation concepts for a double glass photovoltaic(PV)module,we introduce an innovative ionomer-based multi-layer encapsulant,by which the application of additional edge sealing t...As an alternative to conventional encapsulation concepts for a double glass photovoltaic(PV)module,we introduce an innovative ionomer-based multi-layer encapsulant,by which the application of additional edge sealing to prevent moisture penetration is not required.The spontaneous moisture absorption and desorption of this encapsulant and its raw materials,poly(ethylene-co-acrylic acid)and an ionomer,are analyzed under different climatic conditions in this work.The relative air humidity is thermodynamically the driving force for these inverse processes and determines the corresponding equilibrium moisture content(EMC).Higher air humidity results in a larger EMC.The homogenization of the absorbed water molecules is a diffusion-controlled process,in which temperature plays a dominant role.Nevertheless,the diffusion coefficient at a higher temperature is still relatively low.Hence,under normal climatic conditions for the application of PV modules,we believe that the investigated ionomer-based encapsulant can“breathe”the humidity:During the day,when there is higher relative humidity,it“inhales”(absorbs)moisture and restrains it within the outer edge of the module;then at night,when there is a lower relative humidity,it“exhales”(desorbs)the moisture.In this way,the encapsulant protects the cell from moisture ingress.展开更多
Effective development and utilization of wood resources is critical.Wood modification research has become an integral dimension of wood science research,however,the similarities between modified wood and original wood...Effective development and utilization of wood resources is critical.Wood modification research has become an integral dimension of wood science research,however,the similarities between modified wood and original wood render it challenging for accurate identification and classification using conventional image classification techniques.So,the development of efficient and accurate wood classification techniques is inevitable.This paper presents a one-dimensional,convolutional neural network(i.e.,BACNN)that combines near-infrared spectroscopy and deep learning techniques to classify poplar,tung,and balsa woods,and PVA,nano-silica-sol and PVA-nano silica sol modified woods of poplar.The results show that BACNN achieves an accuracy of 99.3%on the test set,higher than the 52.9%of the BP neural network and 98.7%of Support Vector Machine compared with traditional machine learning methods and deep learning based methods;it is also higher than the 97.6%of LeNet,98.7%of AlexNet and 99.1%of VGGNet-11.Therefore,the classification method proposed offers potential applications in wood classification,especially with homogeneous modified wood,and it also provides a basis for subsequent wood properties studies.展开更多
Bi2O2Se thin film could be one of the promising material candidates for the next-generation electronic and optoelectronic applications. However, the performance of Bi2O2Se thin film-based device is not fully explored ...Bi2O2Se thin film could be one of the promising material candidates for the next-generation electronic and optoelectronic applications. However, the performance of Bi2O2Se thin film-based device is not fully explored in the photodetecting area. Considering the fact that the electrical properties such as carrier mobility, work function, and energy band structure of Bi2O2Se are thickness-dependent, the in-plane Bi2O2Se homojunctions consisting of layers with different thicknesses are successfully synthesized by the chemical vapor deposition(CVD) method across the terraces on the mica substrates,where terraces are created in the mica surface layer peeling off process. In this way, effective internal electrical fields are built up along the Bi2O2Se homojunctions, exhibiting diode-like rectification behavior with an on/off ratio of 102, what is more, thus obtained photodetectors possess highly sensitive and ultrafast features, with a maximum photoresponsivity of 2.5 A/W and a lifetime of 4.8 μs. Comparing with the Bi2O2Se uniform thin films, the photo-electric conversion efficiency is greatly improved for the in-plane homojunctions.展开更多
Segmenting brain tumors in Magnetic Resonance Imaging(MRI)volumes is challenging due to their diffuse and irregular shapes.Recently,2D and 3D deep neural networks have become famous for medical image segmentation beca...Segmenting brain tumors in Magnetic Resonance Imaging(MRI)volumes is challenging due to their diffuse and irregular shapes.Recently,2D and 3D deep neural networks have become famous for medical image segmentation because of the availability of labelled datasets.However,3D networks can be computationally expensive and require significant training resources.This research proposes a 3D deep learning model for brain tumor segmentation that uses lightweight feature extraction modules to improve performance without compromising contextual information or accuracy.The proposed model,called Hybrid Attention-Based Residual Unet(HA-RUnet),is based on the Unet architecture and utilizes residual blocks to extract low-and high-level features from MRI volumes.Attention and Squeeze-Excitation(SE)modules are also integrated at different levels to learn attention-aware features adaptively within local and global receptive fields.The proposed model was trained on the BraTS-2020 dataset and achieved a dice score of 0.867,0.813,and 0.787,as well as a sensitivity of 0.93,0.88,and 0.83 for Whole Tumor,Tumor Core,and Enhancing Tumor,on test dataset respectively.Experimental results show that the proposed HA-RUnet model outperforms the ResUnet and AResUnet base models while having a smaller number of parameters than other state-of-the-art models.Overall,the proposed HA-RUnet model can improve brain tumor segmentation accuracy and facilitate appropriate diagnosis and treatment planning for medical practitioners.展开更多
基金the National Natural Science Foundation of China(No.61976080)the Academic Degrees&Graduate Education Reform Project of Henan Province(No.2021SJGLX195Y)+1 种基金the Teaching Reform Research and Practice Project of Henan Undergraduate Universities(No.2022SYJXLX008)the Key Project on Research and Practice of Henan University Graduate Education and Teaching Reform(No.YJSJG2023XJ006)。
文摘The unsupervised multi-modal image translation is an emerging domain of computer vision whose goal is to transform an image from the source domain into many diverse styles in the target domain.However,the multi-generator mechanism is employed among the advanced approaches available to model different domain mappings,which results in inefficient training of neural networks and pattern collapse,leading to inefficient generation of image diversity.To address this issue,this paper introduces a multi-modal unsupervised image translation framework that uses a generator to perform multi-modal image translation.Specifically,firstly,the domain code is introduced in this paper to explicitly control the different generation tasks.Secondly,this paper brings in the squeeze-and-excitation(SE)mechanism and feature attention(FA)module.Finally,the model integrates multiple optimization objectives to ensure efficient multi-modal translation.This paper performs qualitative and quantitative experiments on multiple non-paired benchmark image translation datasets while demonstrating the benefits of the proposed method over existing technologies.Overall,experimental results have shown that the proposed method is versatile and scalable.
文摘As an alternative to conventional encapsulation concepts for a double glass photovoltaic(PV)module,we introduce an innovative ionomer-based multi-layer encapsulant,by which the application of additional edge sealing to prevent moisture penetration is not required.The spontaneous moisture absorption and desorption of this encapsulant and its raw materials,poly(ethylene-co-acrylic acid)and an ionomer,are analyzed under different climatic conditions in this work.The relative air humidity is thermodynamically the driving force for these inverse processes and determines the corresponding equilibrium moisture content(EMC).Higher air humidity results in a larger EMC.The homogenization of the absorbed water molecules is a diffusion-controlled process,in which temperature plays a dominant role.Nevertheless,the diffusion coefficient at a higher temperature is still relatively low.Hence,under normal climatic conditions for the application of PV modules,we believe that the investigated ionomer-based encapsulant can“breathe”the humidity:During the day,when there is higher relative humidity,it“inhales”(absorbs)moisture and restrains it within the outer edge of the module;then at night,when there is a lower relative humidity,it“exhales”(desorbs)the moisture.In this way,the encapsulant protects the cell from moisture ingress.
基金This study was supported by the Fundamental Research Funds for the Central Universities(No.2572023DJ02).
文摘Effective development and utilization of wood resources is critical.Wood modification research has become an integral dimension of wood science research,however,the similarities between modified wood and original wood render it challenging for accurate identification and classification using conventional image classification techniques.So,the development of efficient and accurate wood classification techniques is inevitable.This paper presents a one-dimensional,convolutional neural network(i.e.,BACNN)that combines near-infrared spectroscopy and deep learning techniques to classify poplar,tung,and balsa woods,and PVA,nano-silica-sol and PVA-nano silica sol modified woods of poplar.The results show that BACNN achieves an accuracy of 99.3%on the test set,higher than the 52.9%of the BP neural network and 98.7%of Support Vector Machine compared with traditional machine learning methods and deep learning based methods;it is also higher than the 97.6%of LeNet,98.7%of AlexNet and 99.1%of VGGNet-11.Therefore,the classification method proposed offers potential applications in wood classification,especially with homogeneous modified wood,and it also provides a basis for subsequent wood properties studies.
基金Project supported by the National Natural Science Foundation of China(Grant No.61705066)the Open Fund of State Key Laboratory of Information Photonics and Optical Communications(Beijing University of Posts and Telecommunications),China(Grant No.IPOC2018B004)the National Key Research and Development Program,China(Grant No.2016YFA0202401)
文摘Bi2O2Se thin film could be one of the promising material candidates for the next-generation electronic and optoelectronic applications. However, the performance of Bi2O2Se thin film-based device is not fully explored in the photodetecting area. Considering the fact that the electrical properties such as carrier mobility, work function, and energy band structure of Bi2O2Se are thickness-dependent, the in-plane Bi2O2Se homojunctions consisting of layers with different thicknesses are successfully synthesized by the chemical vapor deposition(CVD) method across the terraces on the mica substrates,where terraces are created in the mica surface layer peeling off process. In this way, effective internal electrical fields are built up along the Bi2O2Se homojunctions, exhibiting diode-like rectification behavior with an on/off ratio of 102, what is more, thus obtained photodetectors possess highly sensitive and ultrafast features, with a maximum photoresponsivity of 2.5 A/W and a lifetime of 4.8 μs. Comparing with the Bi2O2Se uniform thin films, the photo-electric conversion efficiency is greatly improved for the in-plane homojunctions.
基金supported by“Human Resources Program in Energy Technology”of the Korea Institute of Energy Technology Evaluation and Planning(KETEP),granted financial resources from the Ministry of Trade,Industry&Energy,Republic of Korea.(No.20204010600090).
文摘Segmenting brain tumors in Magnetic Resonance Imaging(MRI)volumes is challenging due to their diffuse and irregular shapes.Recently,2D and 3D deep neural networks have become famous for medical image segmentation because of the availability of labelled datasets.However,3D networks can be computationally expensive and require significant training resources.This research proposes a 3D deep learning model for brain tumor segmentation that uses lightweight feature extraction modules to improve performance without compromising contextual information or accuracy.The proposed model,called Hybrid Attention-Based Residual Unet(HA-RUnet),is based on the Unet architecture and utilizes residual blocks to extract low-and high-level features from MRI volumes.Attention and Squeeze-Excitation(SE)modules are also integrated at different levels to learn attention-aware features adaptively within local and global receptive fields.The proposed model was trained on the BraTS-2020 dataset and achieved a dice score of 0.867,0.813,and 0.787,as well as a sensitivity of 0.93,0.88,and 0.83 for Whole Tumor,Tumor Core,and Enhancing Tumor,on test dataset respectively.Experimental results show that the proposed HA-RUnet model outperforms the ResUnet and AResUnet base models while having a smaller number of parameters than other state-of-the-art models.Overall,the proposed HA-RUnet model can improve brain tumor segmentation accuracy and facilitate appropriate diagnosis and treatment planning for medical practitioners.
