The increasing frequency of natural disasters has led to situations in which small urban centers and critical infrastructures become isolated from the main utility grid. The microgrids' ability to work autonomousl...
详细信息
The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing dee...
详细信息
The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.
Visible‐infrared person re‐identification(VI‐ReID)is a supplementary task of single‐modality re‐identification,which makes up for the defect of conventional re‐identification under insufficient *** is more chall...
详细信息
Visible‐infrared person re‐identification(VI‐ReID)is a supplementary task of single‐modality re‐identification,which makes up for the defect of conventional re‐identification under insufficient *** is more challenging than single‐modality ReID because,in addition to difficulties in pedestrian posture,camera shoot-ing angle and background change,there are also difficulties in the cross‐modality *** works only involve coarse‐grained global features in the re‐ranking calculation,which cannot effectively use fine‐grained ***,fine‐grained features are particularly important due to the lack of information in cross‐modality re‐*** this end,the Q‐center Multi‐granularity K‐reciprocal Re‐ranking Algorithm(termed QCMR)is proposed,including a Q‐nearest neighbour centre encoder(termed QNC)and a Multi‐granularity K‐reciprocal Encoder(termed MGK)for a more comprehensive feature *** converts the probe‐corresponding modality features into gallery corresponding modality features through modality transfer to narrow the modality *** takes a coarse‐grained mutual nearest neighbour as the dominant and combines a fine‐grained nearest neighbour as a supplement for similarity *** experiments on two widely used VI‐ReID benchmarks,SYSU‐MM01 and RegDB have shown that our method achieves state‐of‐the‐art ***,the mAP of SYSU‐MM01 is increased by 5.9%in all‐search mode.
Phasor measurement units(PMUs)provide useful data for real-time monitoring of the smart ***,there may be time-varying deviation in phase angle differences(PADs)between both ends of the transmission line(TL),which may ...
详细信息
Phasor measurement units(PMUs)provide useful data for real-time monitoring of the smart ***,there may be time-varying deviation in phase angle differences(PADs)between both ends of the transmission line(TL),which may deteriorate application performance based on *** address that,this paper proposes two robust methods of correcting time-varying PAD deviation with unknown parameters of TL(ParTL).First,the phenomena of time-varying PAD deviation observed from field PMU data are *** general formulations for PAD estimation are then *** simplify the formulations,estimation of PADs is converted into the optimal problem with a single ParTL as the variable,yielding a linear estimation of *** latter is used by second-order Taylor series expansion to estimate PADs *** reduce the impact of possible abnormal amplitude data in field data,the IGG(Institute of Geodesy&Geophysics,Chinese Academy of Sciences)weighting function is *** using both simulated and field data verify the effectiveness and robustness of the proposed methods.
This article introduces a novel mechatronic system for coupling the stems of seedlings and plants to wooden stakes or ropes, a crucial process for supporting them during growth, transportation, and fruiting in plant p...
详细信息
This article proposed a fully low-temperature polysilicon thin-film transistor (LTPS-TFT)-based bidirectional biomedical pixel interface integrated with a high linearity stimulator and a high-performance biopotential ...
详细信息
Introducing all-electric aircraft (AEA) is a viable option to reduce greenhouse gas (GHG) emissions from the aviation sector. The wide-body AEA's electric power system needs higher voltage levels (a few kVs) than ...
详细信息
A scheme for edge computing-enabled offloading in a digital twin (DT) enabled heterogeneous network (HetNet) of multi-services IoT devices (IDs) is proposed. This scheme optimizes the association and handover of IDs, ...
详细信息
For the large amount of waste heat wasted in daily life and industrial production,we propose a new type of flexible thermoelectric generators(F-TEGs)which can be used as a large area bionic skin to achieve energy harv...
详细信息
For the large amount of waste heat wasted in daily life and industrial production,we propose a new type of flexible thermoelectric generators(F-TEGs)which can be used as a large area bionic skin to achieve energy harvesting of thermal *** reference to biological structures such as pinecone,succulent,and feathers,we have designed and fabricated a biomimetic flexible TEG that can be applied in a wide temperature range which has the highest temperature energy harvesting capability *** laminated free structure of the bionic F-TEG dramatically increases the efficiency and density of energy *** F-TEGs(single TEG only 101.2 mg in weight),without an additional heat sink,demonstrates the highest output voltage density of 286.1 mV/cm^(2)and the maximum power density is 66.5 mW/m^(2) at a temperature difference of nearly 1000℃.The flexible characteristics of F-TEGs make it possible to collect the diffused thermal energy by flexible attachment to the outer walls of high-temperature pipes and vessels of different diameters and *** work shows a new design and application concept for flexible thermal energy collectors,which fills the gap of flexible energy harvesting in high-temperature environment.
Damage to parcels reduces customer satisfactionwith delivery services and increases return-logistics *** can be prevented by detecting and addressing the damage before the parcels reach the ***,various studies have be...
详细信息
Damage to parcels reduces customer satisfactionwith delivery services and increases return-logistics *** can be prevented by detecting and addressing the damage before the parcels reach the ***,various studies have been conducted on deep learning techniques related to the detection of parcel *** study proposes a deep learning-based damage detectionmethod for various types of *** is intended to be part of a parcel information-recognition systemthat identifies the volume and shipping information of parcels,and determines whether they are damaged;this method is intended for use in the actual parcel-transportation *** this purpose,1)the study acquired image data in an environment simulating the actual parcel-transportation process,and 2)the training dataset was expanded based on StyleGAN3 with adaptive discriminator ***,3)a preliminary distinction was made between the appearance of parcels and their damage status to enhance the performance of the parcel damage detection model and analyze the causes of parcel ***,using the dataset constructed based on the proposed method,a damage type detection model was trained,and its mean average precision was *** model can improve customer satisfaction and reduce return costs for parcel delivery companies.
暂无评论