检索结果-内蒙古大学图书馆

31st Conference on Electronics Circuits and Systems

作者： Pelayo, Kenn Danielle C. Alvarez, Anastacia B. Chua, Adelson N. Galapon, Fredrick Angelo R. Tan, Allen Jason A. Quizon, Lawrence Roman A. Univ Philippines Diliman Elect & Elect Engn Inst Quezon City Philippines

ISBN: (纸本)9798350377217;9798350377200

Recent trends in machine learning algorithms have shifted from computer vision applications to near-sensor intelligent data analytics, such as wireless sensor nodes, which are considered as ultra-low power devices. This shift presents new challenges in energy consumption, throughput, and area budgets. This work implements and optimizes Bit fusion, a 2D-scalable divide-and-conquer (D&C) MAC architecture with precision-scaling from 8 to 2 bits, through bitwidth optimizations and by trading-off complexity overheads that are not aligned with the target MobileNet-v2 model. The designs are synthesized using 22-nm FD-SOI CMOS technology. It was determined that the throughput trade-offs of 1-level architectures in 2bx2b mode for 17.37% less energy per operation and 26.84% more throughput per area would be preferred. Architecture variations were also explored wherein sum-together (ST) architectures outperformed sum-apart (SA) architectures with 21.03% reduction in energy per operation and 33.32% increase in throughput per area.

关键词： ASIC deep neural networks digital accelerators multiply-accumulate MAC precision-scalable circuits energy-quality scalable circuits

来源：评论

学校读者我要写书评

暂无评论

Accuracy and cross-sensitivity analysis of the PMS5003 formaldehyde sensor 27

Accuracy and cross-sensitivity analysis of the PMS5003 forma...

引用

27th IEEE Signal Processing: algorithms, architectures, Arrangements, and applications, SPA 2024

作者： Bronczyk, Karolina Adamski, Michal Dabrowska, Agata Konieczka, Adam Dabrowski, Adam Adam Mickiewicz University Faculty of Chemistry Department of Trace Analysis Poznań Poland Poznan University of Technology Division of Electronic Systems and Signal Processing Institute of Automatic Control and Robotics Poznań Poland

ISBN: (纸本)9788362065486

Measurement data produced with the PMS5003 electrochemical sensor, allegedly selective for formaldehyde, were analyzed. The amounts of formaldehyde released from heated standard solutions were measured. At the same time, samples were sorbed into sorption tubes with an XAD-2 cartridge, which enabled chromatographic analysis - gas chromatography coupled with an electron capture detector (GC-ECD). A susceptibility of the PMS5003 sensor to cross-sensitivity associated with the presence of other low-molecular-weight carbonyl compounds, such as acetaldehyde and acetone in the sample, was also tested. The conducted research clearly indicates poor selectivity/accuracy of the PMS5003 sensor in relation to formaldehyde and its sensitivity to the presence of other carbonyl compounds in the sample, with a structure similar to formaldehyde. © 2024 Division of Signal Processing and Electronic Systems, Poznan University of Technology (DSPES PUT).

关键词： Acetone

来源：评论

学校读者我要写书评

暂无评论

Deep learning for plant stress detection: A comprehensive review of technologies, challenges, and future directions

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2025年 229卷

作者： Paul, Nijhum Sunil, G. C. Horvath, David Sun, Xin North Dakota State Univ Dept Agr & Biosyst Engn Fargo ND 58108 USA North Dakota State Univ Genom Phen & Bioinformat Program Fargo ND 58108 USA USDA ARS ETSARC Weed & insect Biol unit Fargo ND 58102 USA

Deep learning (DL)-based systems have emerged as powerful methods for the diagnosis and treatment of plant stress, offering high accuracy and efficiency in analyzing imagery data. This review paper aims to present a thorough overview of the state-of-the-art DL technologies for plant stress detection. For this purpose, a systematic literature review was conducted to identify relevant articles for highlighting the technologies and approaches currently employed in the development of a DL-based plant stress detection system, specifically the advancement of image-based data collection systems, image preprocessing techniques, and deep learning algorithms and their applications in plant stress classification, disease detection, and segmentation tasks. Additionally, this review emphasizes the challenges and future directions in collecting and preprocessing image data, model development, and deployment in real-world agricultural settings. Some of the key findings from this review paper are: Training data: (i) Most plant stress detection models have been trained on Red Green Blue (RGB) images;(ii) Data augmentation can increase both the quantity and variation of training data;(iii) Handling multimodal inputs (e. g., image, temperature, humidity) allows the model to leverage information from diverse sources, which can improve prediction accuracy;Model Design and Efficiency: (i) Self-supervised learning (SSL) and Few-shot learning (FSL)-based methods may be better than transfer learning (TL)-based models for classifying plant stress when the number of labeled training images are scarce;(ii) Custom designed DL architectures for a specific stress and plant type can have better performance than the state-of-the-art DL architectures in terms of efficiency, overfitting, and accuracy;(iii) The multi-task learning DL structure reuses most of the network architecture while performing multiple tasks (e.g., estimate stress type and severity) simultaneously, which makes the learning much

关键词： Plant stress Computer vision Deep learning Image processing Imaging sensor Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Data stream fusion for accurate quantile tracking and analysis

引用

INFORMATION fusion 2023年 89卷 155-165页

作者： Cafaro, Massimo Melle, Catiuscia Epicoco, Italo Pulimeno, Marco Univ Salento Lecce Italy

UDDSketch is a recent algorithm for accurate tracking of quantiles in data streams, derived from the DDSketch algorithm. UDDSketch provides accuracy guarantees covering the full range of quantiles independently of the input distribution and greatly improves the accuracy with regard to DDSketch. In this paper we show how to compress and fuse two or more data streams (or datasets) by leveraging the mergeability of the UDDSketch data summaries. In general, two summaries on two data streams are said to be mergeable if there exists an algorithm that allows combining the two summaries into a single one related to the union of the two datasets, simultaneously preserving the error and size guarantees. The property of mergeability of a sketch enables the parallel and distributed processing of big volume data streams that can be compressed and fused by means of such mergeable data structures. Among the applications strictly related to accurate tracking of quantiles, requiring parallel and/or distributed processing we recall here estimating the latency of a web site, database query optimizers and the need of succinctly summarizing the distribution of values occurring over a sensor network. We prove that UDDSketch is fully mergeable and introduce PUDDSketch, a parallel version of UDDSketch suitable for message-passing based architectures. We formally prove its correctness and compare it to a parallel version of DDSketch, showing through extensive experimental results that our parallel algorithm almost always outperforms the parallel DDSketch algorithm with regard to the overall accuracy in determining the quantiles. Moreover, we also design and implement parallel versions of both the state of the art KLL and REQ sequential algorithms in order to compare and contrast PUDDSketch versus the corresponding parallel algorithms. Our experiments clearly show that PUDDSketch is faster or on par with regard to parallel running time, whilst providing simultaneously greater accuracy.

关键词： Quantiles Sketches Message-passing

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning on Multimodal sensor Data for Wireless Communication: From mmWave Beamforming to Digital Twins

Leveraging Deep Learning on Multimodal Sensor Data for Wirel...

引用

作者： Salehihikouei, Batool Northeastern University

学位级别：Ph.D., Doctor of Philosophy

With the widespread Internet of Things (IoT) devices, a wide variety of sensors are now present in different environments. For example, self-driving vehicles and automated warehouses depend on sensor information for navigation and management of the robots, respectively. In this dissertation, we present methods, where these sensors are re-purposed to assist network management in wireless communication, especially when classic approaches fall short to provide the required quality of service (QoS). This thesis presents data-driven and AI-based methods, where the multimodal sensor information is used for two applications: (i) beamforming at the mmWave band and (ii) joint optimization of the navigation and network management in warehouse environments. In the first part, we study multimodal beamforming methods for mmWave vehicular networks. First, we present deep learning fusion algorithms, where the inputs from a multitude of sensor modalities such as GPS (Global Positioning System), camera, and LiDAR (Light Detection and Ranging) are combined towards predicting the optimum beam at the mmWave band. We prove that fusing the multimodal sensor data improves the prediction accuracy, compared to using single modalities. Second, we study the trade-off between the accuracy and cost of different learning strategies and demonstrate that federated learning is the most successful learning strategy, with respect to the communication overhead. Third, we propose algorithms to further optimize the communication overhead by incorporating a pruning strategy tailored to the disturbed nature of the federated learning systems. Fourth, we propose a modality-agnostic deep learning paradigm that operates on any possible combination of sensor modalities. In part two, we propose using digital twins to overcome the challenges of scarcity of data and close-world assumption in deep learning algorithms. A digital twin is a replica of a real world entity, which is typically used for studying the impa

关键词： Network resource management Reinforcement learning Deep learning algorithms sensor modalities Federated learning systems

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive Human-Machine Interface (HMI) Systems With Hybrid On-Body sensors for Controlling Upper-Limb Prosthesis: A Review

引用

IEEE sensorS JOURNAL 2022年第11期22卷 10292-10307页

作者： Zhou, Hao Alici, Gursel Univ Wollongong ARC Ctr Excellence Electromat Sci Sch Mech Mat Mechatron & Biomed Engn Wollongong NSW 2522 Australia

In this work, we present a systematic review on non-invasive HMIs employing hybrid wearable sensor modalities for recognition of upper limb intentions. Different combinations of the sensors are investigated. As sEMG is dominant in the applications of externally powered prosthetic hands, it is involved in most hybrid sensor combinations. The combined use of sEMG and IMU is most studied in the literature as IMU is easy to be integrated. Though limited, the investigation on other hybrid modalities has been drawing more and more research attention and efforts, especially those with FMG and NIRS. For all the reported hybrid sensors, it is verified that this strategy can enrich the information of user intention and help the pattern recognition and/or intensity regulation of robotic hand/arm prosthesis. Though it is the trend, the development of these hybrid-sensor-based HMIs are still at the preliminary stage. More dedicated sensor fusion models and system architectures as well as new hybrid features and algorithms need to be developed to make the best use of each sensing modality's strength to achieve robust and stable user intention recognition, which is essential for the progress and user acceptance of upper limb prosthesis.

关键词： sensors Muscles Robot sensing systems Robustness Electroencephalography Biosensors sensor systems Human-machine-interface HMI upper limb prosthesis hybrid modalities multi-modal sensor fusion sEMG plus MMG sEMG plus FMG sEMG plus SMG sEMG plus NIRS robustness adaptive learning

来源：评论

学校读者我要写书评

暂无评论

Three-Axis Attitude Determination of a Nanosatellite Using Optimized TRIAD algorithms 2nd

Three-Axis Attitude Determination of a Nanosatellite Using O...

引用

2nd International Conference on Information Technologies and Their applications

作者： Kirci, Orhan Hajiyev, Chingiz Istanbul Tech Univ Fac Aeronaut & Astronaut TR-34469 Istanbul Turkiye

ISBN: (纸本)9783031734199;9783031734205

This paper aims to develop a comprehensive approach for determining the attitude of a nanosatellite. Accurate determination of these parameters is essential for the proper operation of the nanosatellite and its successful mission completion. To achieve this goal, a detailed simulation of the magnetometer and sun sensor measurements in the body and orbital frame of the nanosatellite is conducted. These measurements are critical for determining the attitude of the nanosatellite and ensuring that it is pointing in the right direction. The attitude determination process is carried out using the Three-Axis Attitude Determination (TRIAD) algorithm, which is a popular and effective approach for estimating the attitude of a nanosatellite. The optimization of TRIAD with three different approaches is analyzed to ensure high accuracy and efficiency in determining the attitude of the nanosatellite. A covariance analysis is performed to evaluate the accuracy and reliability of the attitude determination process. The analysis provides valuable insights into the error sources and uncertainties associated with the measurements and estimation process. This information is used to improve the performance of the system and enhance the accuracy of the results. Overall, the results of this paper are expected to contribute significantly to the development of efficient and accurate methods for determining the attitude of a nanosatellite.

关键词： nanosatellite attitude determination Euler angles optimized TRIAD data fusion sun sensor magnetometer

来源：评论

学校读者我要写书评

暂无评论

Unlocking High Performance with Low-Bit NPUs and CPUs for Highly Optimized HPL-MxP on Cloud Brain ii 24

Unlocking High Performance with Low-Bit NPUs and CPUs for Hi...

引用

2024 International Conference for High Performance Computing, Networking, Storage and Analysis

作者： Xue, Weicheng Yang, Kai Liu, Yongxiang Fan, Dengdong Xu, Pengxiang Tian, Yonghong Pengcheng Lab Shenzhen 518055 Guangdong Peoples R China

ISBN: (数字)9798350352917

ISBN: (纸本)9798350352924;9798350352917

Mix-precision computation is crucial for artificial intelligence and scientific computing applications. However, as novel chips with innovative architectures emerge, harnessing their computational capabilities presents significant challenges. While existing algorithms for the HPL-MxP LU factorization excel on homogeneous systems, they often encounter difficulties on specialized heterogeneous architectures. This deficiency arises from inadequate optimization for computation, memory access, and communication, hindering effective mixed-precision acceleration. This work introduces an algorithm-hardware co-optimization approach for LU factorization on specialized NPUs and CPUs, leveraging their unique architectures. A novel multi-iteration fusion method for general matrix multiplication is proposed, strategically designed to maximize on-chip L1 buffer utilization, effectively overcoming the notorious "memory wall". Additionally, a multi-stage, multi-level heterogeneous pipeline for LU factorization in an accelerator-CPU cloud environment is presented, where compute-intensive matrix multiplications are offloaded to NPUs while CPUs handle the remaining tasks. The co-optimization approach fosters deep collaboration between CPUs and accelerators, thereby unlocking enhanced performance.

关键词： Scientific computing High performance computing Pipelines AI accelerators Collaboration Computer architecture Heterogeneous networks System-on-chip Optimization

来源：评论

学校读者我要写书评

暂无评论

Grayscale And Event-Based sensor fusion for Robust Steering Prediction for Self-Driving Cars 18

Grayscale And Event-Based Sensor Fusion for Robust Steering ...

引用

18th IEEE sensors applications Symposium (SAS)

作者： Pascarella, Luca Magno, Michele Swiss Fed Inst Technol Zurich Switzerland

ISBN: (纸本)9798350323078

Event-based vision, led by a dynamic vision sensor (DVS), is a bio-inspired vision model that leverages timestamped pixel-level brightness changes of non-static scenes. Thus, DVS's architecture captures the dynamics of a scene and filters static information out. Although machine learning algorithms based on DVS inputs overcome active pixel sensors (APS), they still struggle in challenging conditions. For example, DVS-based models outperform APS-based ones in high-dynamic scenes but suffer in static landscapes. In this paper, we present GEFU (Grayscale and Event-based FUsor), an approach that opens to sensor fusion by combining grayscale and event-based inputs. In particular, we evaluate GEFU's performance on a practical task: predicting a vehicle's steering angle in a realistic driving condition. GEFU is built on top of a consolidated convolutional neural network and trained with realistic driving conditions. Our approach outperforms solo DVS- or APS-based models on non-trivial driving cases, such as the static scenes for the former and the suboptimal light exposure for the latter approach. Our results show that GEFU (i) reduces the root-mean-squared error to similar to 2 degrees and (ii) although the magnitude of the steering angle does not always match the ground truth, the steering direction left/right is always predicted correctly.

关键词： sensor Vision Machine Learning sensor fusion

来源：评论

学校读者我要写书评

暂无评论

FieldHAR: A Fully Integrated End-to-end RTL Framework for Human Activity Recognition with Neural Networks from Heterogeneous sensors 34

FieldHAR: A Fully Integrated End-to-end RTL Framework for Hu...

引用

34th IEEE International Conference on Application-Specific Systems, architectures and Processors (ASAP)

作者： Liu, Mengxi Zhou, Bo Zhao, Zimin Hong, Hyeonseok Kim, Hyun Suh, Sungho Rey, Vitor Fortes Lukowicz, Paul German Res Ctr Artificial Intelligence DFKI Kaiserslautern Germany RPTU Kaiserslautern Landau Dept Comp Sci Kaiserslautern Germany Seoul Natl Univ Sci & Technol Dept Elect & Informat Engn Seoul South Korea

ISBN: (纸本)9798350346855

In this work, we propose an open-source scalable end-to-end RTL framework FieldHAR, for complex human activity recognition (HAR) from heterogeneous sensors using artificial neural networks (ANN) optimized for FPGA or ASIC integration. FieldHAR aims to address the lack of apparatus to transform complex HAR methodologies often limited to offline evaluation to efficient run-time edge applications. The framework uses parallel sensor interfaces and integer-based multi-branch convolutional neural networks (CNNs) to support flexible modality extensions with synchronous sampling at the maximum rate of each sensor. To validate the framework, we used a sensor-rich kitchen scenario HAR application which was demonstrated in a previous offline study. Through resource-aware optimizations, with FieldHAR the entire RTL solution was created from data acquisition to ANN inference taking as low as 25% logic elements and 2% memory bits of a low-end Cyclone IV FPGA and less than 1% accuracy loss from the original FP32 precision offline study. The RTL implementation also shows advantages over MCU-based solutions, including superior data acquisition performance and virtually eliminating ANN inference bottleneck.

关键词： FPGA sensor fusion Human Activity Recognition Neural Networks

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：