检索结果-内蒙古大学图书馆

Adaptive cache policy optimization through deep reinforcement learning in dynamic cellular networks

Intelligent and Converged Networks 2024年第2期5卷 81-99页

作者： Ashvin Srinivasan Mohsen Amidzadeh Junshan Zhang Olav Tirkkonen Department of Information and Communications Engineering Aalto UniversityEspoo 02150Finland Department of Electrical and Computer Engineering University of CaliforniaDavisCA 95616USA

We explore the use of caching both at the network edge and within User Equipment(UE)to alleviate traffic load of wireless *** develop a joint cache placement and delivery policy that maximizes the Quality of Service(QoS)while simultaneously minimizing backhaul load and UE power consumption,in the presence of an unknown time-variant file *** file requests in a time slot being affected by download success in the previous slot,the caching system becomes a non-stationary Partial Observable Markov Decision Process(POMDP).We solve the problem in a deep reinforcement learning framework based on the Advantageous Actor-Critic(A2C)algorithm,comparing Feed Forward Neural Networks(FFNN)with a Long Short-Term Memory(LSTM)approach specifically designed to exploit the correlation of file popularity distribution across time *** results show that using LSTM-based A2C outperforms FFNN-based A2C in terms of sample efficiency and optimality,demonstrating superior performance for the non-stationary POMDP *** caching at the UEs,we provide a distributed algorithm that reaches the objectives dictated by the agent controlling the network,with minimum energy consumption at the UEs,and minimum communication overhead.

关键词： wireless caching deep reinforcement learning advantageous actor critic long short term memory non-stationary Partial Observable Markov Decision Process(POMDP)

来源：评论

学校读者我要写书评

暂无评论

Motion Saliency Based Human Action Recognition in RGBD Videos 20

Motion Saliency Based Human Action Recognition in RGBD Video...

引用

20th IEEE International Conference on Intelligent computer Communication and Processing Conference, ICCP 2024

作者： Gutev, Alexander Debono, Carl James University of Malta Department of Communications and Computer Engineering Msida Malta

ISBN: (纸本)9798331539979

Human action recognition (HAR) systems need to process large volumes of data posing several challenges including, but not limited to, accurately identifying the actions and classifying them in near real time. Most of the state of the art solutions rely on machine learning techniques where a substantial amount of time is required both for the training and the inference phases. Existing solutions try to reduce the size of the data that is processed by the HAR classifier by constructing a spatio-temporal region of interest (ST-ROI) based on skeleton data, such as the model-based multimodal network (MMNet). However, the performance of these solutions depends on the accuracy of the skeleton data. This paper presents a novel solution to reduce the size of the data that is processed during classification by constructing an ST-ROI using regions identified as motion salient. The results show that the classification accuracy of the proposed solution is comparable to existing solutions such as MMNet but with a training time that is drastically lower. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Gen-Power: Anomaly Detection in IoT Devices Utilizing Generated Power Waveforms

Gen-Power: Anomaly Detection in IoT Devices Utilizing Genera...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Hisafuru, Kota Togawa, Nozomu Waseda University Department of Computer Science and Communications Engineering Japan

ISBN: (纸本)9798350324136

Recently, IoT (Internet-of-Things) devices are very widely used in consumer electronics areas and their design and manufacturing are often outsourced to third parties to make them at a low cost. Meanwhile, malfunctions may be inserted into them intentionally by malicious third parties. Utilizing power waveforms measured from IoT devices is one of the effective ways to detect its anomalous behaviors. Most IoT devices regularly consume steady-state power due to the operating system and/or hardware components. However, the existing methods manually or semi-manually find out the steady-state power in the IoT device and extract pre-determined features from the application power waveform. Hence, they cannot well detect its anomalous behaviors automatically. In this paper, we propose a method, called Gen-Power, to detect anomalous behaviors in IoT devices utilizing the generative machine-learning model. The proposed method generates application power waveforms by inferring the steady-state power by machine learning from the observed total power waveform. Then, the anomalous application behaviors are detected by automatically extracting the latent features from the generative application power waveform. Experimental evaluations show that Gen-Power detects anomalous application behaviors successfully, while the recent state-of-The-Art method cannot detect them. © 2024 IEEE.

关键词： anomaly detection generated power waveform generative machine learning IoT device power analysis side-channel analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning with Clustering and Experience Sharing 28th

Multi-Agent Reinforcement Learning with Clustering and Exper...

引用

28th International Conference on Knowledge Based and Intelligent information and engineering Systems, KES 2024

作者： Inokuchi, Kaname Sugawara, Toshiharu Department of Computer Science and Communications Engineering Waseda University Japan

We propose a training method for a heterogeneous multi-agent system to improve the learning efficiency in sparse-reward environments. Although extensive research on multi-agent deep reinforcement learning are conducted actively, these studies often assume that all agents are homogeneous to share/utilize learning parameters in their networks. Unfortunately, this is not always the case in real-world applications where heterogeneous autonomous agents, i.e., those with different capabilities and perspectives, must properly cooperate and coordinate with each other. In our learning method, which is an extension of the shared experience actor-critic (SEAC) for a heterogeneous agent environment, agents are classified depending on their features (such as trajectories of the observations, actions and received rewards) using variational autoencoder, and share their experience among agents within each cluster to train their individual agents for improving the learning efficiency in a sparse-reward environment. Our experimental evaluation shows that the proposed method is capable of more efficient cooperative/coordinated behaviors than the baselines while remaining the advantages of SEAC. © 2024 The Authors.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Carrying-Mode-Free Stair Ascent and Descent Estimation using Smartphones

Carrying-Mode-Free Stair Ascent and Descent Estimation using...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Kajimoto, Dai Saeki, Etsushi Bao, Siya Togawa, Nozomu Waseda University Department of Computer Science and Communications Engineering Japan

ISBN: (纸本)9798350324136

This paper proposes a smartphone-based pedestrian dead reckoning to track stair ascent and descent. By using accelerometer and barometer information, pedestrians' gait patterns are collected under different carrying modes to detect the stair ascent and descent motions. Also, weather influences are considered to eliminate the barometer measurement errors. We evaluate the proposed method in a seven-floor environment, and we compare our method with a conventional method without multiple carrying modes and weather considerations. The minimal error rate of the proposed method is only 4.2% when ascending or descending seven floors, and at most 14.4% error are reduced compared with the conventional method. © 2024 IEEE.

关键词： indoor localization PDR smartphone stair ascent/descent

来源：评论

学校读者我要写书评

暂无评论

Random Frame: a Data Augmentation for Glass Detection 27th

Random Frame: a Data Augmentation for Glass Detection

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Liang, Yiming Ishikawa, Hiroshi Department of Computer Science and Communications Engineering Waseda University Tokyo Japan

ISBN: (纸本)9783031801358

Glass, though ubiquitous, is difficult to recognize in an image due to its transparency. Fine-grained low-level features indicating the presence of glass, such as refraction and reflection, are weak and subtle. This causes difficulties for existing glass detection models in learning those features, pushing them to rely on more overt cues, especially the frame surrounding the glass. Consequently, they can be fooled easily by frame-like objects. Here, we propose a simple data augmentation scheme called Random Frame to address this problem. Random Frame inserts a frame into an image to create an area with a frame but no glass. The model will receive a penalty if it only relies on the frame. The performances of existing models on various datasets improve when Random Frame is applied while being trained. Our comprehensive experiments demonstrate that our data augmentation can make models utilize more low-level features with more confidence in their predictions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Overlap-Free Pattern Formation Method Using Particle Swarm Optimization 28th

Overlap-Free Pattern Formation Method Using Particle Swarm O...

引用

28th International Conference on Knowledge Based and Intelligent information and engineering Systems, KES 2024

作者： Yamada, Kotaro Sugawara, Toshiharu Department of Computer Science and Communications Engineering Waseda University Japan

We propose a method based on particle swarm optimization (PSO) for the multi-agent pattern formation problem (MAPFP), which allows agents to form formation patterns with a high completion rate without overlaps. MAPFP is a problem in which a large number of agents autonomously move to appropriate locations to fill in a target pattern, such as line drawings, letters, and geometric figure, in a cooperative manner. They are used in several applications such as route planning and object exploration. Although some studies consider the pattern-formation problem using swarm intelligence (SI), including PSO, they do not often consider conflicts such as collisions and overlaps of particles, and thus cannot be used in real-world applications. Our proposed method, based on PSO, an SI algorithm, allows agents to act independently, while avoiding overlaps, to form a pattern by introducing a local field of view to each particle and secreting pheromones to their neighbor points to attract other agents that have not yet found places to stay. Through experimental evaluation, we show that the proposed method not only eliminates overlaps during movement and unwanted overlaps on a target pattern but also improves the pattern completion rate compared to the baseline. © 2024 The Authors.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Ensemble Learning Models for Hardware-Trojan Identification at Gate-level Netlists

Evaluation of Ensemble Learning Models for Hardware-Trojan I...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Negishi, Ryotaro Togawa, Nozomu Waseda University Department of Computer Science and Communications Engineering Japan

ISBN: (纸本)9798350324136

IoT (Internet-of-Things) devices are tremendously widespread in our daily lives and these devices are very often outsourced to third-party companies to save cost. However, it is pointed out that the risk to insert malicious circuitry, called hardware Trojans (HTs), much increases there. The methods using machine learning for detecting HTs at gate-level netlists have been proposed, and those based on ensemble learning models are considered the most effective among them. This paper evaluates the performance of HT detection at gate-level netlists using various machine learning models based on ensemble learning, including random forest, XGBoost, LightGBM, and CatBoost. In particular, we optimize HT features for each machine-learning model and perform HT detection for various gate-level netlists, including intellectual property core netlists. The detailed HT detection results are thoroughly summarized and compared. © 2024 IEEE.

关键词： ensemble learning hardware security hardware Trojan machine learning netlist

来源：评论

学校读者我要写书评

暂无评论

QoS aware Joint Radar Communication Optimization via Backtrack based Training Network 100

QoS aware Joint Radar Communication Optimization via Backtra...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Wang, Junlong Pan, Zhenni Shimamoto, Shigeru Waseda University Department of Communications and Computer Engineering Tokyo Japan

ISBN: (纸本)9798331517786

Joint Radar Communication (JRC) system achieves radar detection and communication transmission using a shared hardware platform, making it more suitable for integration, miniaturization, and efficient spectrum utilization compared to traditional standalone radar or communication devices. Due to the mutual interference between the two subsystems, there is growing interest in reducing negative impacts and optimizing the overall performance of JRC systems. Among various approaches, optimizing resource scheduling strategies within JRC systems to balance the performance of each subsystem in different environments and enhance system Quality of Services (QoS) values has become a significant research direction. In this paper, we propose a deep learning-based optimization framework tailored for JRC systems. By analyzing the current application environment of JRC systems, the proposed method dynamically adjusts the energy resource allocation strategy within the JRC system. This approach aims to balance the subsystems' performance concerning the current system environment and demands, achieving self-optimization to adapt to the current application scenarios. Simulation results indicates that our proposal could improved the JRC average performance under different application scenarios. © 2024 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Passersby-Anonymizer: Safeguard the Privacy of Passersby in Social Videos 18

Passersby-Anonymizer: Safeguard the Privacy of Passersby in ...

引用

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Ma, Jingzhe Luo, Haoyu Huang, Zixu Jin, Dongyang Wang, Rui Briffa, Johann A. Poh, Norman Yu, Shiqi Southern University of Science and Technology Department of Computer Science and Engineering China University of Malta Department of Communications and Computer Engineering Malta

ISBN: (纸本)9798350364132

In the current era of pervasive short video content, the exposure of passersby's data frequently raises privacy concerns. Traditional anonymization techniques for passersby, like blurring and mosaicing, are often used before uploading such videos. However, these methods tend to degrade the informational richness of the visual content, markedly reducing the quality of the anonymized videos. Recent advancements of diffusion models have paved the way for text-guided image and video synthesis, yet applying these models to the anonymization of passersby poses three main challenges: i) bridging the domain gap between specific passersby data and high-quality image/video datasets that are used for pre-training diffusion models, ii) ensuring temporal consistency in the anonymized videos, and iii) preserving the integrity of video subjects' content while exclusively anonymizing passersby-related information. To address these challenges, we propose the Passersby-Anonymizer, a novel diffusion-based framework for anonymizing identity-specific attributes in video content. At its core, our model introduces a spatial content adapter (SCA) to adapt to the visual patterns of passersby image datasets. We introduce a Temporal Content Stabilizer (TCS) to maintain the temporal consistency of the anonymized videos. Furthermore, we design a mask-aware training strategy that specifically targets the anonymization of the mask region while preserving the integrity of other contents. Our experimental evaluations demonstrate that our model effectively addresses the challenge of anonymizing passersby without compromising the informational integrity of the social videos. The source code is available at https://***/HappyDeepLearning/Passersby-Anonymizer. © 2024 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：