ACM-TURC

As existing works on federated learning (FL) have not typically shared their implementations as open-source, and existing open-source FL frameworks fell short of evaluating FL mechanisms appropriately, in the past two years, we have designed and ...

In causality-based trustworthy machine learning, finding mechanisms from data-driven correlation analysis to causal inference and constructing a machine learning framework from correlation-driven to causality-driven are two significant challenges. To ...

In addition to a physical comprehension of the world, humans possess a high social intelligence—the intelligence that senses social events infers the mental states of others, and facilitates social interaction. We believe that Artificial Social ...

Pretrained visual-language models (VLMs) have made progress in developing multimodal models to improve various tasks. However, they lack reasoning and in-context learning ability. Building on the success of large language models (LLMs) in general-...

In this poster, we present ASGaze, a new gaze tracking system designed using the common RGB camera from mobile phones. In addition to improving the accuracy of existing RGB camera-based gaze tracker methods, a novelty of ASGaze is that it can track ...

In light of the increasing occurrence of building collapse tragedies, such as the recent Florida condo collapse, there is a growing recognition of the need for long-term and persistent structural health monitoring (SHM) in civilian buildings. However, ...

The rapid growth of the Internet of Vehicles (IoV) has highlighted the need for effective secret key establishment, as the dynamic and ad-hoc nature of IoV communication remains a security challenge. Physical layer key generation offers a lightweight, ...

In FL, participants cooperatively train a global model with their local data. The participants, however, may be heterogeneous in terms of data distribution. In such cases, FL might produce a biased global model that is not optimal for each participant. ...

Camera-equipped devices and deep learning advancements have driven the development of intelligent mobile video apps. These apps require on-device processing of video streams for real-time, high-quality services while addressing privacy and robustness. ...

The vision of decoupled software and hardware for wireless communications has prompted the application of Open-Radio-Access-Networks (O-RANs) and Software Defined Radios (SDRs). Such a structure is beneficial to operators for flexible and low-cost ...

The grouping protocol in RFID systems is to label tags according to a given partition so that tags in the identical group hold the same group ID, which makes multi-cast transmissions or aggregate queries possible and thereby improves time efficiency. ...

Fine-tuning pre-trained models for downstream tasks often requires private data, for which federated learning is the de-facto approach (i.e., FedNLP). However, FedNLP is prohibitively slow due to the large model sizes and the resultant high network/...

We propose a task scheduling system for Multi-modal Industrial Internet of Things (IIoT). The system is based on the improvement of Kubernetes and the parsing of task. Furthermore, it can dynamically select the appropriate nodes to parallelly process ...

Industrial Internet of Things (IIoT) play an important role in the new round of industrial revolution. However, the isolation of Information Technology (IT) networks and Operational Technology (OT) networks impedes the innovations, developments, and ...

Ubiquitous wireless sensing makes use of wireless RF signals in the environment, such as WiFi, 4G/5G, LoRa, UWB, etc. The sensing of information such as the location and state of the sensing target can be achieved by modeling and analyzing the effects ...

WiFi sensing has emerged as a promising technology for smart services, including gesture recognition and trajectory tracking. One of the key challenges in these applications is accurately extracting velocity from WiFi signals. In this paper, we report ...

Cross-Technology Communication (CTC) technique enables direct interconnection among heterogeneous devices, which provides new technical routes for IoT’s heterogeneous interconnection. However, existing CTC methods have a great dependence on the ...

The increasing demand for edge computing has led to the deployment of artificial intelligence (AI) models on IoT devices. However, due to data privacy and communication cost concerns, AI models are often offloaded from the cloud to the edge or device ...

We design and implement DPMS (Distributed Persistent Memory Storage System) based on persistent memory and RDMA, which unifies the memory, file system and key-value interface in a single system. DPMS is designed upon pDSM, a unified distributed ...

With the recent advancement of multilayer convolutional neural networks (CNN), deep learning has achieved amazing success in many areas, especially in visual content understanding and classification. To improve the performance and energy-efficiency of ...

Recent point cloud recognition (PCR) tasks tend to utilize deep neural network (DNN) for better accuracy. Still, the computational intensity of DNN makes them far from real-time processing, given the fast-increasing number of points that need to be ...

Federated Learning (FL) enables potentially a large number of clients to collaboratively train a global model with the coordination of a central cloud server without exposing client raw data. However, the FL model convergence performance, often ...

This poster proposes a low-latency deterministic forwarding technology for multi-modal data based on time-sensitive networks. It presents the design and implementation of an FPGA-based switch that can handle data frames of different protocols, ...

In this article, we proposed a two-stage deep reinforcement learning (DRL) based deterministic scheduling architecture for computing and networking convergence, named as DetCNCS. By designing DRL algorithms for task offloading and global resource ...