arXiv subjects

Haoxin Wang

Publications and source records attributed to Haoxin Wang.

At least 37 records · Page 2Linked to original sources

arXiv2024

CSformer: Combining Channel Independence and Mixing for Robust Multivariate Time Series Forecasting

In the domain of multivariate time series analysis, the concept of channel independence has been increasingly adopted, demonstrating excellent performance due to its ability to eliminate noise and the influence of irrelevant variables. However, such a concept often simplifies the complex interactions among channels, potentially leading to information loss. To address this challenge, we propose a strategy of channel independence followed by mixing. Based on this strategy, we introduce CSformer, a novel framework featuring a two-stage multiheaded self-attention mechanism. This mechanism is designed to extract and integrate both channel-specific and sequence-specific information. Distinctively, CSformer employs parameter sharing to enhance the cooperative effects between these two types of information. Moreover, our framework effectively incorporates sequence and channel adapters, significantly improving the model's ability to identify important information across various dimensions. Extensive experiments on several real-world datasets demonstrate that CSformer achieves state-of-the-art results in terms of overall performance.

cs.LG↗

arXiv2024

Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices

Today, deep learning optimization is primarily driven by research focused on achieving high inference accuracy and reducing latency. However, the energy efficiency aspect is often overlooked, possibly due to a lack of sustainability mindset in the field and the absence of a holistic energy dataset. In this paper, we conduct a threefold study, including energy measurement, prediction, and efficiency scoring, with an objective to foster transparency in power and energy consumption within deep learning across various edge devices. Firstly, we present a detailed, first-of-its-kind measurement study that uncovers the energy consumption characteristics of on-device deep learning. This study results in the creation of three extensive energy datasets for edge devices, covering a wide range of kernels, state-of-the-art DNN models, and popular AI applications. Secondly, we design and implement the first kernel-level energy predictors for edge devices based on our kernel-level energy dataset. Evaluation results demonstrate the ability of our predictors to provide consistent and accurate energy estimations on unseen DNN models. Lastly, we introduce two scoring metrics, PCS and IECS, developed to convert complex power and energy consumption data of an edge device into an easily understandable manner for edge device end-users. We hope our work can help shift the mindset of both end-users and the research community towards sustainability in edge computing, a principle that drives our research. Find data, code, and more up-to-date information at https://amai-gsu.github.io/DeepEn2023.

cs.NI↗

arXiv2024

CarbonCP: Carbon-Aware DNN Partitioning with Conformal Prediction for Sustainable Edge Intelligence

This paper presents a solution to address carbon emission mitigation for end-to-end edge computing systems, including the computing at battery-powered edge devices and servers, as well as the communications between them. We design and implement, CarbonCP, a context-adaptive, carbon-aware, and uncertainty-aware AI inference framework built upon conformal prediction theory, which balances operational carbon emissions, end-to-end latency, and battery consumption of edge devices through DNN partitioning under varying system processing contexts and carbon intensity. Our experimental results demonstrate that CarbonCP is effective in substantially reducing operational carbon emissions, up to 58.8%, while maintaining key user-centric performance metrics with only 9.9% error rate.

cs.NI↗

arXiv2024

Analyzing and Overcoming Local Optima in Complex Multi-Objective Optimization by Decomposition-Based Evolutionary Algorithms

When addressing the challenge of complex multi-objective optimization problems, particularly those with non-convex and non-uniform Pareto fronts, Decomposition-based Multi-Objective Evolutionary Algorithms (MOEADs) often converge to local optima, thereby limiting solution diversity. Despite its significance, this issue has received limited theoretical exploration. Through a comprehensive geometric analysis, we identify that the traditional method of Reference Point (RP) selection fundamentally contributes to this challenge. In response, we introduce an innovative RP selection strategy, the Weight Vector-Guided and Gaussian-Hybrid method, designed to overcome the local optima issue. This approach employs a novel RP type that aligns with weight vector directions and integrates a Gaussian distribution to combine three distinct RP categories. Our research comprises two main experimental components: an ablation study involving 14 algorithms within the MOEADs framework, spanning from 2014 to 2022, to validate our theoretical framework, and a series of empirical tests to evaluate the effectiveness of our proposed method against both traditional and cutting-edge alternatives. Results demonstrate that our method achieves remarkable improvements in both population diversity and convergence.

cs.NE↗

arXiv2024

Pre-insertion resistors temperature prediction based on improved WOA-SVR

The pre-insertion resistors (PIR) within high-voltage circuit breakers are critical components and warm up by generating Joule heat when an electric current flows through them. Elevated temperature can lead to temporary closure failure and, in severe cases, the rupture of PIR. To accurately predict the temperature of PIR, this study combines finite element simulation techniques with Support Vector Regression (SVR) optimized by an Improved Whale Optimization Algorithm (IWOA) approach. The IWOA includes Tent mapping, a convergence factor based on the sigmoid function, and the Ornstein-Uhlenbeck variation strategy. The IWOA-SVR model is compared with the SSA-SVR and WOA-SVR. The results reveal that the prediction accuracies of the IWOA-SVR model were 90.2% and 81.5% (above 100$^\circ$C) in the 3$^\circ$C temperature deviation range and 96.3% and 93.4% (above 100$^\circ$C) in the 4$^\circ$C temperature deviation range, surpassing the performance of the comparative models. This research demonstrates the method proposed can realize the online monitoring of the temperature of the PIR, which can effectively prevent thermal faults PIR and provide a basis for the opening and closing of the circuit breaker within a short period.

cs.LG↗

arXiv2023

DeepEn2023: Energy Datasets for Edge Artificial Intelligence

Climate change poses one of the most significant challenges to humanity. As a result of these climatic changes, the frequency of weather, climate, and water-related disasters has multiplied fivefold over the past 50 years, resulting in over 2 million deaths and losses exceeding $3.64 trillion USD. Leveraging AI-powered technologies for sustainable development and combating climate change is a promising avenue. Numerous significant publications are dedicated to using AI to improve renewable energy forecasting, enhance waste management, and monitor environmental changes in real time. However, very few research studies focus on making AI itself environmentally sustainable. This oversight regarding the sustainability of AI within the field might be attributed to a mindset gap and the absence of comprehensive energy datasets. In addition, with the ubiquity of edge AI systems and applications, especially on-device learning, there is a pressing need to measure, analyze, and optimize their environmental sustainability, such as energy efficiency. To this end, in this paper, we propose large-scale energy datasets for edge AI, named DeepEn2023, covering a wide range of kernels, state-of-the-art deep neural network models, and popular edge AI applications. We anticipate that DeepEn2023 will improve transparency in sustainability in on-device deep learning across a range of edge AI systems and applications. For more information, including access to the dataset and code, please visit https://amai-gsu.github.io/DeepEn2023.

cs.LG↗

arXiv2023

TimeSQL: Improving Multivariate Time Series Forecasting with Multi-Scale Patching and Smooth Quadratic Loss

Time series is a special type of sequence data, a sequence of real-valued random variables collected at even intervals of time. The real-world multivariate time series comes with noises and contains complicated local and global temporal dynamics, making it difficult to forecast the future time series given the historical observations. This work proposes a simple and effective framework, coined as TimeSQL, which leverages multi-scale patching and smooth quadratic loss (SQL) to tackle the above challenges. The multi-scale patching transforms the time series into two-dimensional patches with different length scales, facilitating the perception of both locality and long-term correlations in time series. SQL is derived from the rational quadratic kernel and can dynamically adjust the gradients to avoid overfitting to the noises and outliers. Theoretical analysis demonstrates that, under mild conditions, the effect of the noises on the model with SQL is always smaller than that with MSE. Based on the two modules, TimeSQL achieves new state-of-the-art performance on the eight real-world benchmark datasets. Further ablation studies indicate that the key modules in TimeSQL could also enhance the results of other models for multivariate time series forecasting, standing as plug-and-play techniques.

cs.LG↗

arXiv2023

Poster: Real-Time Object Substitution for Mobile Diminished Reality with Edge Computing

Diminished Reality (DR) is considered as the conceptual counterpart to Augmented Reality (AR), and has recently gained increasing attention from both industry and academia. Unlike AR which adds virtual objects to the real world, DR allows users to remove physical content from the real world. When combined with object replacement technology, it presents an further exciting avenue for exploration within the metaverse. Although a few researches have been conducted on the intersection of object substitution and DR, there is no real-time object substitution for mobile diminished reality architecture with high quality. In this paper, we propose an end-to-end architecture to facilitate immersive and real-time scene construction for mobile devices with edge computing.

cs.CV↗

arXiv2023

Visualization of Mobility Digital Twin: Framework Design, Case Study, and Future Challenges

A Mobility Digital Twin is an emerging implementation of digital twin technology in the transportation domain, which creates digital replicas for various physical mobility entities, such as vehicles, drivers, and pedestrians. Although a few work have investigated the applications of mobility digital twin recently, the extent to which it can facilitate safer autonomous vehicles remains insufficiently explored. In this paper, we first propose visualization of mobility digital twin, which aims to augment the existing perception systems in connected and autonomous vehicles through twinning high-fidelity and manipulable geometry representations for causal traffic participants, such as surrounding pedestrians and vehicles, in the digital space. An end-to-end system framework, including image data crowdsourcing, preprocessing, offloading, and edge-assisted 3D geometry reconstruction, is designed to enable real-world development of the proposed visualization of mobility digital twin. We implement the proposed system framework and conduct a case study to assess the twinning fidelity and physical-to-digital synchronicity within different image sampling scenarios and wireless network conditions. Based on the case study, future challenges of the proposed visualization of mobility digital twin are discussed toward the end of the paper.

cs.NI↗

arXiv2023

Confidence-based federated distillation for vision-based lane-centering

A fundamental challenge of autonomous driving is maintaining the vehicle in the center of the lane by adjusting the steering angle. Recent advances leverage deep neural networks to predict steering decisions directly from images captured by the car cameras. Machine learning-based steering angle prediction needs to consider the vehicle's limitation in uploading large amounts of potentially private data for model training. Federated learning can address these constraints by enabling multiple vehicles to collaboratively train a global model without sharing their private data, but it is difficult to achieve good accuracy as the data distribution is often non-i.i.d. across the vehicles. This paper presents a new confidence-based federated distillation method to improve the performance of federated learning for steering angle prediction. Specifically, it proposes the novel use of entropy to determine the predictive confidence of each local model, and then selects the most confident local model as the teacher to guide the learning of the global model. A comprehensive evaluation of vision-based lane centering shows that the proposed approach can outperform FedAvg and FedDF by 11.3% and 9%, respectively.

cs.CV↗

arXiv2023

EPAM: A Predictive Energy Model for Mobile AI

Artificial intelligence (AI) has enabled a new paradigm of smart applications -- changing our way of living entirely. Many of these AI-enabled applications have very stringent latency requirements, especially for applications on mobile devices (e.g., smartphones, wearable devices, and vehicles). Hence, smaller and quantized deep neural network (DNN) models are developed for mobile devices, which provide faster and more energy-efficient computation for mobile AI applications. However, how AI models consume energy in a mobile device is still unexplored. Predicting the energy consumption of these models, along with their different applications, such as vision and non-vision, requires a thorough investigation of their behavior using various processing sources. In this paper, we introduce a comprehensive study of mobile AI applications considering different DNN models and processing sources, focusing on computational resource utilization, delay, and energy consumption. We measure the latency, energy consumption, and memory usage of all the models using four processing sources through extensive experiments. We explain the challenges in such investigations and how we propose to overcome them. Our study highlights important insights, such as how mobile AI behaves in different applications (vision and non-vision) using CPU, GPU, and NNAPI. Finally, we propose a novel Gaussian process regression-based general predictive energy model based on DNN structures, computation resources, and processors, which can predict the energy for each complete application cycle irrespective of device configuration and application. This study provides crucial facts and an energy prediction mechanism to the AI research community to help bring energy efficiency to mobile AI applications.

cs.LG↗

arXiv2023

Metamobility: Connecting Future Mobility with Metaverse

A Metaverse is a perpetual, immersive, and shared digital universe that is linked to but beyond the physical reality, and this emerging technology is attracting enormous attention from different industries. In this article, we define the first holistic realization of the metaverse in the mobility domain, coined as ``metamobility". We present our vision of what metamobility will be and describe its basic architecture. We also propose two use cases, tactile live maps and meta-empowered advanced driver-assistance systems (ADAS), to demonstrate how the metamobility will benefit and reshape future mobility systems. Each use case is discussed from the perspective of the technology evolution, future vision, and critical research challenges, respectively. Finally, we identify multiple concrete open research issues for the development and deployment of the metamobility.

cs.NI↗

arXiv2022

FAIR: Towards Impartial Resource Allocation for Intelligent Vehicles with Automotive Edge Computing

The emerging vehicular connected applications, such as cooperative automated driving and intersection collision warning, show great potentials to improve the driving safety, where vehicles can share the data collected by a variety of on-board sensors with surrounding vehicles and roadside infrastructures. Transmitting and processing this huge amount of sensory data introduces new challenges for automotive edge computing with traditional wireless communication networks. In this work, we address the problem of traditional asymmetrical network resource allocation for uplink and downlink connections that can significantly degrade the performance of vehicular connected applications. An end-to-end automotive edge networking system, FAIR, is proposed to provide fast, scalable, and impartial connected services for intelligent vehicles with edge computing, which can be applied to any traffic scenes and road topology. The core of FAIR is our proposed symmetrical network resource allocation algorithm deployed at edge servers and service adaptation algorithm equipped on intelligent vehicles. Extensive simulations are conducted to validate our proposed FAIR by leveraging real-world traffic dataset. Simulation results demonstrate that FAIR outperforms existing solutions in a variety of traffic scenes and road topology.

cs.NI↗

arXiv2022

LEAF + AIO: Edge-Assisted Energy-Aware Object Detection for Mobile Augmented Reality

Today very few deep learning-based mobile augmented reality (MAR) applications are applied in mobile devices because they are significantly energy-guzzling. In this paper, we design an edge-based energy-aware MAR system that enables MAR devices to dynamically change their configurations, such as CPU frequency, computation model size, and image offloading frequency based on user preferences, camera sampling rates, and available radio resources. Our proposed dynamic MAR configuration adaptations can minimize the per frame energy consumption of multiple MAR clients without degrading their preferred MAR performance metrics, such as latency and detection accuracy. To thoroughly analyze the interactions among MAR configurations, user preferences, camera sampling rate, and energy consumption, we propose, to the best of our knowledge, the first comprehensive analytical energy model for MAR devices. Based on the proposed analytical model, we design a LEAF optimization algorithm to guide the MAR configuration adaptation and server radio resource allocation. An image offloading frequency orchestrator, coordinating with the LEAF, is developed to adaptively regulate the edge-based object detection invocations and to further improve the energy efficiency of MAR devices. Extensive evaluations are conducted to validate the performance of the proposed analytical model and algorithms.

cs.CV↗

arXiv2022

A theoretical framework and some promising findings of grey wolf optimizer, part I: analytical model of sampling distribution and stability analysis

This paper proposes a theoretical framework of the grey wolf optimizer (GWO) based on several interesting theoretical findings, involving sampling distribution, order-1 and order-2 stability, and global convergence analysis. In the part I of the paper, the characteristics of the sampling distribution of the new solution and the probabilistic stability of the GWO are carefully discussed based on the well-known stagnation assumption for simplification purposes. Firstly, the characteristics of the sampling distribution of the new solution, mainly related to the shape of the joint probability density function (PDF), are discussed under the assumption that the original solution before updating is constant. Then, the assumption that the original solution is constant is eliminated to perform the sampling distribution analysis, based on which several characteristics of the new solution are provided, containing the shape of the joint PDF and central moments of any positive integer order. Finally, the order-1 and order-2 stability of the GWO under stagnation assumption is introduced and proved as the inference of conclusions above, which are all verified by numerical simulations.

math.OC↗

arXiv2022

A theoretical framework and some promising findings of grey wolf optimizer, part II: global convergence analysis

This paper proposes a theoretical framework of the grey wolf optimizer (GWO) based on several interesting theoretical findings, involving sampling distribution, order-1 and order-2 stability, and global convergence analysis. In the part II of the paper, the global convergence analysis is carried out based on the well-known stagnation assumption for simplification purposes. Firstly, the global convergence property of the GWO under stagnation assumption is abstracted and modelled into two propositions, corresponding to global searching ability analysis and probability-1 global convergence analysis. Then, the global searching ability analysis is carried out. Next, based on a characteristic of the central moments of the new solution of the GWO under stagnation assumption, the probability-1 global convergence property of the GWO under stagnation assumption is proved. Finally, all conclusions are verified by numerical simulations, and the corresponding discussions that the global convergence property can still be guaranteed in the original GWO without stagnation assumption are given.

math.OC↗

arXiv2022

EdgeMap: CrowdSourcing High Definition Map in Automotive Edge Computing

High definition (HD) map needs to be updated frequently to capture road changes, which is constrained by limited specialized collection vehicles. To maintain an up-to-date map, we explore crowdsourcing data from connected vehicles. Updating the map collaboratively is, however, challenging under constrained transmission and computation resources in dynamic networks. In this paper, we propose EdgeMap, a crowdsourcing HD map to minimize the usage of network resources while maintaining the latency requirements. We design a DATE algorithm to adaptively offload vehicular data on a small time scale and reserve network resources on a large time scale, by leveraging the multi-agent deep reinforcement learning and Gaussian process regression. We evaluate the performance of EdgeMap with extensive network simulations in a time-driven end-to-end simulator. The results show that EdgeMap reduces more than 30% resource usage as compared to state-of-the-art solutions.

cs.LG↗

arXiv2021

A Bare Bones Grey Wolf Optimizer for Global Numerical Optimization

In order to better understand and analyze the currently widely used population-based metaheuristic optimization algorithms, , this paper proposes a novel computational intelligence algorithm called bare bones grey wolf optimizer (BBGWO) inspired by a bare bones mechanism. In the BBGWO, the complex updating mechanism of solutions is replaced by a random vector that obeys a normal distribution, whose mean and variance are derived by theoretically studying the probability distribution of the new solution of the original GWO. The corresponding theoretical analysis and simulation results verify the good optimization performance of the proposed BBGWO algorithm.

math.OC↗