Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleAugust 2024JUST ACCEPTED
A2: Towards Accelerator Level Parallelism for Autonomous Micromobility Systems
ACM Transactions on Architecture and Code Optimization (TACO), Just Accepted https://doi.org/10.1145/3688611Autonomous micromobility systems (AMS) such as low-speed minicabs and robots are thriving. In AMS, multiple Deep Neural Networks execute in parallel on heterogeneous AI accelerators. An emerging paradigm called Accelerator Level Parallelism (ALP) suggests ...
- research-articleJune 2024
ChainStream: A Stream-based LLM Agent Framework for Continuous Context Sensing and Sharing
EdgeFM '24: Proceedings of the Workshop on Edge and Mobile Foundation ModelsJune 2024, Pages 18–23https://doi.org/10.1145/3662006.3662063This paper introduces ChainStream, an LLM-based framework for building and serving context-aware AI agents. Driven by the goal to enable context awareness of LLM agents and flexible information sharing between them, we adopt a stream-based design, in ...
- research-articleJune 2024
WASP: Efficient Power Management Enabling Workload-Aware, Self-Powered AIoT Devices
IEEE Transactions on Parallel and Distributed Systems (TPDS), Volume 35, Issue 8Aug. 2024, Pages 1400–1414https://doi.org/10.1109/TPDS.2024.3408167The wide adoption of edge AI has heightened the demand for various battery-less and maintenance-free smart systems. Nevertheless, emerging Artificial Intelligence of Things (AIoT) are complex workloads showing increased power demand, diversified power ...
- research-articleJuly 2024
From lab to orchard use for models of hand-held NIRS instrument: A case for navel orange quality assessment considering ambient light correction
- Xudong Sun,
- Fulong Guo,
- Jiacheng Liu,
- Zhaoxing Chen,
- Waleed Fouad Abobatta,
- Muhammad Azher Nawaz,
- Shaoran Feng
Computers and Electronics in Agriculture (COEA), Volume 219, Issue CApr 2024https://doi.org/10.1016/j.compag.2024.108797Highlights- EPO was recommended for sunlight correction.
- Results support use of hand-held NIRS with varying sunlight.
- Results support use of hand-held NIRS estimation of optimal harvest date.
The models for hand-held near infrared spectroscopy (NIRS) instrument calibrated in the laboratory are prone to failure during orchard application because of measurement conditions change especially on sunlight interference. The models transfer ...
- research-articleAugust 2024
Intelligent Driving Safety Monitoring Based on Machine Learning ——An Example of Students Research Training Program in the Context of New Engineering Disciplines
CAICE '24: Proceedings of the 3rd International Conference on Computer, Artificial Intelligence and Control EngineeringJanuary 2024, Pages 851–857https://doi.org/10.1145/3672758.3672899The development of new engineering technologies such as artificial intelligence, machine learning, and big data analysis has prompted engineering colleges to keep up with the times in their courses and introduce relevant knowledge to cultivate ...
-
- research-articleMay 2024
Conditional Transformation Diffusion for Object Placement
ICIGP '24: Proceedings of the 2024 7th International Conference on Image and Graphics ProcessingJanuary 2024, Pages 363–368https://doi.org/10.1145/3647649.3647706We propose a conditional transformation diffusion model for the object placement task in the field of image composition. Specifically, we design an object and background feature extractor (OBFE) to infuse information about object and background into the ...
- research-articleMay 2024
RainyTrack: Enhancing Object Tracking in Adverse Weather Conditions with Siamese Networks
ICIGP '24: Proceedings of the 2024 7th International Conference on Image and Graphics ProcessingJanuary 2024, Pages 308–315https://doi.org/10.1145/3647649.3647698Object tracking is a critical task in the field of computer vision, playing a significant role in many practical applications. However, in complex rainy conditions, existing object tracking methods often perform poorly. This is due to rain introducing ...
- research-articleDecember 2023
Practical Network Modeling Using Weak Supervision Signals for Human-Centric Networking in Metaverse
IEEE Journal on Selected Areas in Communications (JSAC), Volume 42, Issue 3March 2024, Pages 680–693https://doi.org/10.1109/JSAC.2023.3345391As the metaverse continues to expand, it becomes increasingly critical to have human-centric networks that are both efficient and high-performing to optimize the user experience. Network modeling plays a fundamental role in optimizing and allocating ...
- ArticleNovember 2023
A Novel Convolutional Neural Network with Large Kernel for Classification of Crash Test Photos
AbstractSince variation of car’s types, direction classification of crash test photos for multiple type of vehicles is a big challenge to office automation. Moreover, because of the similarity of images before and after crash test, semantic identification ...
- research-articleOctober 2023
A lightweight encoder–decoder network for automatic pavement crack detection
Computer-Aided Civil and Infrastructure Engineering (MICE), Volume 39, Issue 1215 June 2024, Pages 1743–1765https://doi.org/10.1111/mice.13103AbstractCracks are the most common damage type on the pavement surface. Usually, pavement cracks, especially small cracks, are difficult to be accurately identified due to background interference. Accurate and fast automatic road crack detection play a ...
- research-articleOctober 2023
INFER: Distilling knowledge from human-generated rules with uncertainty for STINs
Information Sciences: an International Journal (ISCI), Volume 645, Issue COct 2023https://doi.org/10.1016/j.ins.2023.119219AbstractAs a long-time wish, researchers always want to find a way to fuse human knowledge directly into machine models that can fulfill intelligent tasks. Existing researches attempted to approach this goal by manually labeling data or writing simple ...
Highlights- We propose a new paradigm INFER that can effectively use human intelligence.
- We model the uncertain rules that contain more informative knowledge.
- We design a new knowledge distillation algorithm to extract knowledge from the ...
- research-articleSeptember 2023
Delay-Optimal Cooperation Transmission in Remote Sensing Satellite Networks
IEEE Transactions on Mobile Computing (ITMV), Volume 22, Issue 9Sept. 2023, Pages 5109–5123https://doi.org/10.1109/TMC.2022.3172848Many remote sensing applications, such as the forest fire monitoring, need to send a large volume of data to the ground with low delay. Therefore, the <italic>cooperation transmission</italic>, which relies on cooperation among satellites to achieve ...
- ArticleAugust 2023
MMExit: Enabling Fast and Efficient Multi-modal DNN Inference with Adaptive Network Exits
Euro-Par 2023: Parallel ProcessingAug 2023, Pages 426–440https://doi.org/10.1007/978-3-031-39698-4_29AbstractMulti-modal DNNs have been demonstrated to outperform the best uni-modal DNNs by fusing information from different modalities. However, the performance improvement of multi-modal DNNs is always associated with an incredible increase in ...
- research-articleAugust 2023
Optimized Controller Provisioning in Software-Defined LEO Satellite Networks
IEEE Transactions on Mobile Computing (ITMV), Volume 22, Issue 8Aug. 2023, Pages 4850–4864https://doi.org/10.1109/TMC.2022.3155657The controller provisioning, which adjusts the number, locations, and members of satellite controllers adaptive to the dynamic network load and topology, fundamentally impacts the performance of software-defined satellite networks (SDSNs). An ideal ...
- research-articleJune 2023
Architecting Efficient Multi-modal AIoT Systems
ISCA '23: Proceedings of the 50th Annual International Symposium on Computer ArchitectureJune 2023, Article No.: 31, Pages 1–13https://doi.org/10.1145/3579371.3589066Multi-modal computing (M2C) has recently exhibited impressive accuracy improvements in numerous autonomous artificial intelligence of things (AIoT) systems. However, this accuracy gain is often tethered to an incredible increase in energy consumption. ...
- research-articleFebruary 2023
Time-Varying Resource Graph Based Processing on the Way for Space-Terrestrial Integrated Vehicle Networks
- Long Chen,
- Feilong Tang,
- Jiacheng Liu,
- Xu Li,
- Yanmin Zhu,
- Jiadi Yu,
- Laurence T. Yang,
- Zhetao Li,
- Bin Yao,
- Yichuan Yu
IEEE Transactions on Mobile Computing (ITMV), Volume 23, Issue 2Feb. 2024, Pages 1985–2002https://doi.org/10.1109/TMC.2023.3248376Desirable information processing in space-terrestrial integrated vehicle networks (STINs) handles data distributed in different satellites while transmitting, where efficient modeling time-varying resources is critical. Existing works are not applicable ...
- research-articleApril 2024
NATURALPROVER: grounded mathematical proof generation with language models
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsNovember 2022, Article No.: 355, Pages 4913–4927Theorem proving in natural mathematical language - the mixture of symbolic and natural language used by humans - plays a central role in mathematical advances and education, and tests aspects of reasoning that are core to intelligence. Yet it has ...
- research-articleJuly 2022
Characterizing and Understanding End-to-End Multi-Modal Neural Networks on GPUs
IEEE Computer Architecture Letters (ICAL), Volume 21, Issue 2July-Dec. 2022, Pages 125–128https://doi.org/10.1109/LCA.2022.3215718Multi-modal neural networks have become increasingly pervasive in many machine learning application domains due to their superior accuracy by fusing various modalities. However, they present many unique characteristics such as multi-stage execution, ...
- research-articleJune 2022
A parametric head geometry model accounting for variation among adolescent and young adult populations
Computer Methods and Programs in Biomedicine (CBIO), Volume 220, Issue CJun 2022https://doi.org/10.1016/j.cmpb.2022.106805Highlights- Head CT scans of 101 subjects between 14 and 25 years of age were used to develop a statistical head geometry model.
Modeling the size and shape of human skull and scalp is essential for head injury assessment, design of helmets and head-borne equipment, and many other safety applications. Finite element (FE) head ...
- research-articleJune 2022
WeAnimate: Motion-coherent animation generation from video data
Multimedia Tools and Applications (MTAA), Volume 81, Issue 15Jun 2022, Pages 20685–20703https://doi.org/10.1007/s11042-022-12359-4AbstractDue to the lack of easy-to-use tools, User-Generated-Animation (UGA) only has limited development compared with the rapid development of user participatory culture and the resulting User-Generated Contents (UGC). In this paper, we develop a ...