Skip to Content

781 Results Found

  • Article
  • Open Access
154 Views
25 Pages

A Data Compression Method for Mechanical Vibration Wireless Sensor Networks Based on Data Segmentation and Non-Uniform Quantization

  • Yi Huang,
  • Jiaquan Zhang,
  • Xiaojing Mu,
  • Dongmei Tian and ,
  • Rongtao Mu and
  • Tianhong Luo
  • + 1 author+ 0 author

20 October 2026

High-frequency sampling in mechanical vibration wireless sensor networks (WSNs) generates large volumes of raw data, imposing substantial demands on transmission bandwidth and node energy consumption. To address this problem, this paper proposes a tw...

(This article belongs to the Special Issue Information-Theoretic Methods in Data Analytics, 2nd Edition)
  • Article
  • Open Access
12 Citations
4,864 Views
17 Pages

Design of Hardware Accelerators for Optimized and Quantized Neural Networks to Detect Atrial Fibrillation in Patch ECG Device with RISC-V

  • Ingo Hoyer,
  • Alexander Utz,
  • André Lüdecke,
  • Holger Kappert and ,
  • Maurice Rohr,
  • Christoph Hoog Antink and
  • Karsten Seidl
  • + 2 authors+ 0 author

1 March 2023

Atrial Fibrillation (AF) is one of the most common heart arrhythmias. It is known to cause up to 15% of all strokes. In current times, modern detection systems for arrhythmias, such as single-use patch electrocardiogram (ECG) devices, have to be ener...

(This article belongs to the Section Biomedical Sensors)
  • Article
  • Open Access
3 Citations
1,682 Views
18 Pages

7 September 2023

This paper considers the fixed-time synchronization of complex-valued coupled networks (CVCNs) with hybrid perturbations (nonlinear bounded external perturbations and stochastic perturbations). To accomplish the target of fixed-time synchronization,...

(This article belongs to the Special Issue Mathematic Control and Artificial Intelligence)
  • Article
  • Open Access
9 Citations
6,572 Views
17 Pages

Blockwise reconstruction with adaptive rounding helps achieve acceptable 4-bit post-training quantization accuracy. However, adaptive rounding is time intensive, and the optimization space of weight elements is constrained to a binary set, thus limit...

  • Article
  • Open Access
1 Citations
927 Views
26 Pages

Real-Time Low-Cost Traffic Monitoring Based on Quantized Convolutional Neural Networks for the CNOSSOS-EU Noise Model

  • Domenico Profumo,
  • Gonzalo de León,
  • Alessandro Monticelli,
  • Luca Fredianelli and
  • Gaetano Licitra

9 March 2026

Accurate urban noise mapping requires granular traffic flow characterization aligned with specific acoustic models, such as CNOSSOS-EU. Existing monitoring solutions often lack the specific categorization capabilities, cost-effectiveness, or flexibil...

(This article belongs to the Special Issue Advanced Environmental Sensing Towards Acoustic Monitoring and Modeling: Applications and Challenges)
  • Article
  • Open Access
7 Citations
5,910 Views
17 Pages

Source number estimation plays an important role in successful blind signal separation. At present, the application of machine learning allows the processing of signals without the time-consuming and complex work of manual feature extraction. However...

(This article belongs to the Special Issue Advanced Technologies of Artificial Intelligence in Signal Processing)
  • Article
  • Open Access
6 Citations
3,026 Views
22 Pages

12 December 2022

Embedded computing platforms such as neural network accelerators deploying neural network models need to quantize the values into low-bit integers through quantization operations. However, most current embedded computing platforms with a fixed-point...

(This article belongs to the Special Issue Virtual Reality, Digital Twins and Metaverse)
  • Article
  • Open Access
4 Citations
3,163 Views
21 Pages

Two Novel Non-Uniform Quantizers with Application in Post-Training Quantization

  • Zoran Perić,
  • Danijela Aleksić,
  • Jelena Nikolić and
  • Stefan Tomić

21 September 2022

With increased network downsizing and cost minimization in deployment of neural network (NN) models, the utilization of edge computing takes a significant place in modern artificial intelligence today. To bridge the memory constraints of less-capable...

(This article belongs to the Special Issue Artificial Intelligence and Mathematical Methods)
  • Article
  • Open Access
3 Citations
2,866 Views
17 Pages

Bit-Weight Adjustment for Bridging Uniform and Non-Uniform Quantization to Build Efficient Image Classifiers

  • Xichuan Zhou,
  • Yunmo Duan,
  • Rui Ding,
  • Qianchuan Wang and ,
  • Qi Wang,
  • Jian Qin and
  • Haijun Liu
  • + 2 authors+ 0 author

18 December 2023

Network quantization, which strives to reduce the precision of model parameters and/or features, is one of the most efficient ways to accelerate model inference and reduce memory consumption, particularly for deep models when performing a variety of...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
15 Citations
4,600 Views
17 Pages

Neuron-by-Neuron Quantization for Efficient Low-Bit QNN Training

  • Artem Sher,
  • Anton Trusov,
  • Elena Limonova,
  • Dmitry Nikolaev and
  • Vladimir V. Arlazarov

29 April 2023

Quantized neural networks (QNNs) are widely used to achieve computationally efficient solutions to recognition problems. Overall, eight-bit QNNs have almost the same accuracy as full-precision networks, but working several times faster. However, the...

(This article belongs to the Special Issue Application of Machine Learning in Image Processing and Computer Vision)
  • Article
  • Open Access
5 Citations
4,485 Views
24 Pages

Although optimizing deep neural networks is becoming crucial for deploying the networks on edge AI devices, it faces increasing challenges due to scarce hardware resources in modern IoT and mobile devices. This study proposes a quantization method th...

(This article belongs to the Special Issue Deep and Machine Learning for Image Processing: Medical and Non-medical Applications)
  • Article
  • Open Access
2 Citations
2,537 Views
12 Pages

23 April 2023

Among various network compression methods, network quantization has developed rapidly due to its superior compression performance. However, trivial activation quantization schemes limit the compression performance of network quantization. Most conven...

(This article belongs to the Special Issue Artificial Intelligence Applications in Complex Networks)
  • Article
  • Open Access
5 Citations
4,202 Views
16 Pages

31 March 2022

Recurrent neural networks (RNNs) are neural networks (NN) designed for time-series applications. There is a growing interest in running RNNs to support these applications on edge devices. However, RNNs have large memory and computational demands that...

(This article belongs to the Special Issue Artificial Intelligence on the Edge)
  • Article
  • Open Access
18 Citations
5,055 Views
19 Pages

7 November 2017

Target tracking is one of the broad applications of underwater wireless sensor networks (UWSNs). However, as a result of the temporal and spatial variability of acoustic channels, underwater acoustic communications suffer from an extremely limited ba...

(This article belongs to the Special Issue Advances and Challenges in Underwater Sensor Networks)
  • Article
  • Open Access
10 Citations
4,571 Views
28 Pages

Whether the Support Region of Three-Bit Uniform Quantizer Has a Strong Impact on Post-Training Quantization for MNIST Dataset?

  • Jelena Nikolić,
  • Zoran Perić,
  • Danijela Aleksić,
  • Stefan Tomić and
  • Aleksandra Jovanović

20 December 2021

Driven by the need for the compression of weights in neural networks (NNs), which is especially beneficial for edge devices with a constrained resource, and by the need to utilize the simplest possible quantization model, in this paper, we study the...

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing)
  • Article
  • Open Access
15 Citations
4,091 Views
18 Pages

Design and Analysis of Binary Scalar Quantizer of Laplacian Source with Applications

  • Zoran Peric,
  • Bojan Denic,
  • Milan Savic and
  • Vladimir Despotovic

27 October 2020

A compression method based on non-uniform binary scalar quantization, designed for the memoryless Laplacian source with zero-mean and unit variance, is analyzed in this paper. Two quantizer design approaches are presented that investigate the effect...

(This article belongs to the Special Issue Signal Processing and Machine Learning)
  • Article
  • Open Access
4 Citations
2,993 Views
21 Pages

GradFreeBits: Gradient-Free Bit Allocation for Mixed-Precision Neural Networks

  • Benjamin Jacob Bodner,
  • Gil Ben-Shalom and
  • Eran Treister

13 December 2022

Quantized neural networks (QNNs) are among the main approaches for deploying deep neural networks on low-resource edge devices. Training QNNs using different levels of precision throughout the network (mixed-precision quantization) typically achieves...

(This article belongs to the Section Internet of Things)
  • Article
  • Open Access
17 Citations
6,064 Views
21 Pages

A Hardware-Friendly Low-Bit Power-of-Two Quantization Method for CNNs and Its FPGA Implementation

  • Xuefu Sui,
  • Qunbo Lv,
  • Yang Bai,
  • Baoyu Zhu and ,
  • Liangjie Zhi,
  • Yuanbo Yang and
  • Zheng Tan
  • + 2 authors+ 0 author

1 September 2022

To address the problems of convolutional neural networks (CNNs) consuming more hardware resources (such as DSPs and RAMs on FPGAs) and their accuracy, efficiency, and resources being difficult to balance, meaning they cannot meet the requirements of...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
8 Citations
8,320 Views
25 Pages

17 November 2021

Quantization of neural networks has been one of the most popular techniques to compress models for embedded (IoT) hardware platforms with highly constrained latency, storage, memory-bandwidth, and energy specifications. Limiting the number of bits pe...

(This article belongs to the Section Computer Science & Engineering)
  • Letter
  • Open Access
2,667 Views
16 Pages

17 July 2020

In this paper, we investigate a trajectory control problem for Euler-Lagrange systems with unknown quantization on the actuator channel. To address such a challenge, we proposed a quantization-mitigation-based trajectory control method, wherein adapt...

(This article belongs to the Special Issue Data Analysis for Smart Sensor Systems)
  • Article
  • Open Access
16 Citations
3,609 Views
29 Pages

This paper studies the containment control problem for a class of fractional order nonlinear multiagent systems in the presence of arbitrary switchings, unmeasured states, and quantized input signals by a hysteresis quantizer. Under the framework of...

(This article belongs to the Topic Fractional Calculus: Theory and Applications)
  • Feature Paper
  • Article
  • Open Access
1 Citations
2,244 Views
14 Pages

Network Splitting Techniques and Their Optimization for Lightweight Ternary Neural Networks

  • Hasna Nur Karimah,
  • Novi Prihatiningrum,
  • Young-Ho Gong,
  • Jonghoon Jin and
  • Yeongkyo Seo

15 September 2025

To run a high-performing deep convolutional neural network (CNN), substantial memory and computational resources are typically required. To address this, we propose an optimization method of a ternary neural network (TNN) by applying network splittin...

(This article belongs to the Special Issue Convolutional Neural Networks and Vision Applications, 4th Edition)
  • Article
  • Open Access
7 Citations
6,153 Views
11 Pages

11 August 2015

We examine a distributed detection problem in a wireless sensor network, where sensor nodes collaborate to detect a Gaussian signal with an unknown change of power, i.e., a scale parameter. Due to power/bandwidth constraints, we consider the case whe...

(This article belongs to the Special Issue Algorithms for Sensor Networks)
  • Article
  • Open Access
6 Citations
1,740 Views
26 Pages

5 May 2026

Automated mobile microscopy in Internet of Things (IoT) networks is essential for scaling malaria screening in resource-constrained environments. Deploying standard convolutional architectures here introduces severe adversarial vulnerabilities. Post-...

(This article belongs to the Special Issue AI-Enabled Sensing Technology for Smart Healthcare and Precision Diagnosis)
  • Article
  • Open Access
6 Citations
2,708 Views
13 Pages

Study of Weight Quantization Associations over a Weight Range for Application in Memristor Devices

  • Yerim Kim,
  • Hee Yeon Noh,
  • Gyogwon Koo,
  • Hyunki Lee and ,
  • Sanghan Lee,
  • Rock-Hyun Choi,
  • Shinbuhm Lee,
  • Myoung-Jae Lee and
  • Hyeon-Jun Lee
  • + 4 authors+ 0 author

15 October 2024

The development of hardware-based cognitive computing systems critically hinges upon the integration of memristor devices capable of versatile weight expression across a spectrum of resistance levels while preserving consistent electrical properties....

(This article belongs to the Special Issue Thin Film Microelectronic Devices and Circuits)
  • Article
  • Open Access
4,789 Views
26 Pages

Adaptive Global Power-of-Two Ternary Quantization Algorithm Based on Unfixed Boundary Thresholds

  • Xuefu Sui,
  • Qunbo Lv,
  • Changjun Ke,
  • Mingshan Li and ,
  • Mingjin Zhuang,
  • Haiyang Yu and
  • Zheng Tan
  • + 2 authors+ 0 author

28 December 2023

In the field of edge computing, quantizing convolutional neural networks (CNNs) using extremely low bit widths can significantly alleviate the associated storage and computational burdens in embedded hardware, thereby improving computational efficien...

(This article belongs to the Section Industrial Sensors)
  • Article
  • Open Access
2 Citations
2,558 Views
14 Pages

1 April 2021

In this paper, we investigate the adaptive state-quantized control problem of uncertain lower-triangular systems with input delay. It is assumed that all state variables are quantized for the feedback control design. The error transformation method u...

  • Article
  • Open Access
4 Citations
2,941 Views
18 Pages

25 August 2018

This paper considers the active detection of a stealth target with aspect dependent reflection (e.g., submarine, aircraft, etc.) using wireless sensor networks (WSNs). When the target is detected, its localization is also of interest. Due to stringen...

(This article belongs to the Section Sensor Networks)
  • Communication
  • Open Access
3 Citations
4,661 Views
15 Pages

Ultra-High-Speed Accelerator Architecture for Convolutional Neural Network Based on Processing-in-Memory Using Resistive Random Access Memory

  • Hongzhe Wang,
  • Junjie Wang,
  • Hao Hu,
  • Guo Li and ,
  • Shaogang Hu,
  • Qi Yu,
  • Zhen Liu,
  • Tupei Chen,
  • Shijie Zhou and
  • Yang Liu
  • + 5 authors+ 0 author

21 February 2023

Processing-in-Memory (PIM) based on Resistive Random Access Memory (RRAM) is an emerging acceleration architecture for artificial neural networks. This paper proposes an RRAM PIM accelerator architecture that does not use Analog-to-Digital Converters...

(This article belongs to the Section Electronic Sensors)
  • Article
  • Open Access
5 Citations
1,987 Views
17 Pages

19 September 2024

An adaptive predefined-time quantized control issue is considered for strict-feedback systems with actuator quantization. To handle the unknown nonlinearities of a system, the neural networks are first applied to model them. To analyze the predefined...

(This article belongs to the Special Issue Neural Networks-Based Modeling and Control for Uncertain Dynamical Systems)
  • Article
  • Open Access
1 Citations
2,307 Views
17 Pages

29 July 2020

This paper considers a downlink cellular network where multi-antenna base stations (BSs) simultaneously serve their associated multi-antenna users. Each BS is distributed according to a homogeneous Poisson point process and uses zero-forcing beamform...

(This article belongs to the Section Sensor Networks)
  • Article
  • Open Access
22 Citations
4,830 Views
17 Pages

Speaker Recognition Using Constrained Convolutional Neural Networks in Emotional Speech

  • Nikola Simić,
  • Siniša Suzić,
  • Tijana Nosek,
  • Mia Vujović and ,
  • Zoran Perić,
  • Milan Savić and
  • Vlado Delić
  • + 2 authors+ 0 author

16 March 2022

Speaker recognition is an important classification task, which can be solved using several approaches. Although building a speaker recognition model on a closed set of speakers under neutral speaking conditions is a well-researched task and there are...

(This article belongs to the Special Issue Methods in Artificial Intelligence and Information Processing)
  • Article
  • Open Access
19 Citations
8,120 Views
37 Pages

A Survey of Computationally Efficient Graph Neural Networks for Reconfigurable Systems

  • Habib Taha Kose,
  • Jose Nunez-Yanez,
  • Robert Piechocki and
  • James Pope

28 June 2024

Graph neural networks (GNNs) are powerful models capable of managing intricate connections in non-Euclidean data, such as social networks, physical systems, chemical structures, and communication networks. Despite their effectiveness, the large-scale...

(This article belongs to the Special Issue Artificial Intelligence on the Edge)
  • Article
  • Open Access
12 Citations
3,598 Views
13 Pages

31 October 2022

In the field of computer vision technology, deep learning of image processing has become an emerging research area. The semantic segmentation of an image is among the utmost essential and significant tasks in image-processing research, offering a wid...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
101 Views
36 Pages

A Lightweight Multi-Branch Network for Double JPEG Compression Detection

  • Muhammed Uhudhan Ateş,
  • Emin Ölmez,
  • Ekin Ekinci and
  • Orhan Akbulut

11 November 2026

Double JPEG compression detection is a key forensic tool for identifying image tampering, yet existing convolutional architectures often achieve robustness to real-world quantization-table diversity at the cost of increased model size. Recent approac...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
9 Citations
4,589 Views
11 Pages

Training and Inference of Optical Neural Networks with Noise and Low-Bits Control

  • Danni Zhang,
  • Yejin Zhang,
  • Ye Zhang,
  • Yanmei Su and ,
  • Junkai Yi,
  • Pengfei Wang,
  • Ruiting Wang,
  • Guangzhen Luo,
  • Xuliang Zhou and
  • Jiaoqing Pan
  • + 5 authors+ 0 author

20 April 2021

Optical neural networks (ONNs) are getting more and more attention due to their advantages such as high-speed and low power consumption. However, in a non-ideal environment, the noise and low-bits control may heavily lead to a decrease in the accurac...

(This article belongs to the Collection Optical Design and Engineering)
  • Article
  • Open Access
14 Citations
5,245 Views
18 Pages

7 December 2024

This paper presents a hardware implementation of a one-dimensional convolutional neural network using depthwise separable convolution (DSC) on the VC707 FPGA development board. The design processes the one-dimensional rolling bearing current signal d...

(This article belongs to the Special Issue Feature Papers in Physical Sensors 2024)
  • Article
  • Open Access
13 Citations
4,107 Views
14 Pages

To solve the problem of water management subsystem fault diagnosis in a proton exchange membrane fuel cell (PEMFC) system, a novel approach based on learning vector quantization neural network (LVQNN) and kernel principal component analysis (KPCA) is...

(This article belongs to the Special Issue Towards Intelligent E-Mobility—Selected Papers from The 34th International Electric Vehicles Symposium and Exhibition (Nanjing, China))
  • Article
  • Open Access
7 Citations
5,079 Views
21 Pages

An SSD-MobileNet Acceleration Strategy for FPGAs Based on Network Compression and Subgraph Fusion

  • Shoutao Tan,
  • Zhanfeng Fang,
  • Yanyi Liu,
  • Zhe Wu and ,
  • Hang Du,
  • Renjie Xu and
  • Yunfei Liu
  • + 2 authors+ 0 author

27 December 2022

Over the last decade, various deep neural network models have achieved great success in image recognition and classification tasks. The vast majority of high-performing deep neural network models have a huge number of parameters and often require sac...

(This article belongs to the Section Natural Hazards and Risk Management)
  • Article
  • Open Access
549 Views
18 Pages

High-Throughput and Low-Latency DrDoS Detection Using Quantized ONNX Models

  • Salih Eren,
  • Alperen Gültekin,
  • Ömer Özkan and
  • İlker Özçelik

14 July 2026

Distributed Reflection Denial-of-Service (DrDoS) attacks, such as DNS Amplification, exploit inherent asymmetries in standard network protocols to generate devastating traffic volumes. To restore defense-side balance against these asymmetric threats,...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
5 Citations
2,725 Views
19 Pages

Intelligent Fault Diagnosis Method Based on Neural Network Compression for Rolling Bearings

  • Xinren Wang,
  • Dongming Hu,
  • Xueqi Fan,
  • Huiyi Liu and
  • Chenbin Yang

4 November 2024

Rolling bearings are often exposed to high speeds and pressures, leading to the symmetry in their rotating structure being disrupted, which can lead to serious failures. Intelligent rolling bearing fault diagnosis is a critical part of ensuring opera...

(This article belongs to the Topic Predictive Analytics and Fault Diagnosis of Machines with Machine Learning Techniques)
  • Article
  • Open Access
1 Citations
6,506 Views
19 Pages

8 June 2012

This paper is concerned with the reliable finite frequency filter design for networked control systems (NCSs) subject to quantization and data missing. Taking into account quantization, possible data missing and sensor stuck faults, NCSs are modeled...

(This article belongs to the Section Physical Sensors)
  • Article
  • Open Access
1 Citations
2,251 Views
14 Pages

Optimizing Artificial Neural Networks to Minimize Arithmetic Errors in Stochastic Computing Implementations

  • Christiam F. Frasser,
  • Alejandro Morán,
  • Vincent Canals,
  • Joan Font and ,
  • Eugeni Isern,
  • Miquel Roca and
  • Josep L. Rosselló
  • + 2 authors+ 0 author

Deploying modern neural networks on resource-constrained edge devices necessitates a series of optimizations to ready them for production. These optimizations typically involve pruning, quantization, and fixed-point conversion to compress the model s...

(This article belongs to the Section Circuit and Signal Processing)
  • Article
  • Open Access
9 Citations
4,033 Views
16 Pages

Flexible Quantization for Efficient Convolutional Neural Networks

  • Federico Giordano Zacchigna,
  • Sergio Lew and
  • Ariel Lutenberg

This work focuses on the efficient quantization of convolutional neural networks (CNNs). Specifically, we introduce a method called non-uniform uniform quantization (NUUQ), a novel quantization methodology that combines the benefits of non-uniform qu...

(This article belongs to the Special Issue FPGA-Based Deep Neural Network Accelerators Using Emerging Technologies)
  • Article
  • Open Access
13 Citations
2,407 Views
25 Pages

This paper focuses on a distributed cooperative time-varying formation maneuvering issue of under-actuated unmanned surface vehicles (USVs). A fleet of USVs is guided by a parameterized path with a time-varying formation while avoiding collisions and...

(This article belongs to the Special Issue Modeling and Control of Marine Craft)
  • Article
  • Open Access
15 Citations
4,157 Views
21 Pages

A Methodology to Design Quantized Deep Neural Networks for Automatic Modulation Recognition

  • David Góez,
  • Paola Soto,
  • Steven Latré,
  • Natalia Gaviria and
  • Miguel Camelo

22 November 2022

Next-generation communication systems will face new challenges related to efficiently managing the available resources, such as the radio spectrum. DL is one of the optimization approaches to address and solve these challenges. However, there is a ga...

(This article belongs to the Collection Parallel and Distributed Computing: Algorithms and Applications)
  • Article
  • Open Access
1,975 Views
17 Pages

11 November 2022

We present an efficient scheme based on a long short-term memory (LSTM) autoencoder for accurate seismic deconvolution in a multichannel setup. The technique is beneficial for compressing massive amounts of seismic data. The proposed robust estimatio...

(This article belongs to the Section Environmental Sensing)
  • Article
  • Open Access
6 Citations
7,741 Views
17 Pages

29 September 2020

Spiking neural networks (SNN) increasingly attract attention for their similarity to the biological neural system. Hardware implementation of spiking neural networks, however, remains a great challenge due to their excessive complexity and circuit si...

(This article belongs to the Special Issue Deep Learning Based Object Detection)
  • Article
  • Open Access
669 Views
15 Pages

Weight Standardization Fractional Binary Neural Network for Image Recognition in Edge Computing

  • Chih-Lung Lin,
  • Zi-Qing Liang,
  • Jui-Han Lin,
  • Chun-Chieh Lee and
  • Kuo-Chin Fan

In order to achieve better accuracy, modern models have become increasingly large, leading to an exponential increase in computational load, making it challenging to apply them to edge computing. Binary neural networks (BNNs) are models that quantize...

(This article belongs to the Special Issue Advances in Algorithm Optimization and Computational Intelligence)
  • Article
  • Open Access
14 Citations
5,257 Views
27 Pages

8 July 2019

In real-time onboard hyperspectral-image(HSI) anomalous targets detection, processing speed and accuracy are equivalently desirable which is hard to satisfy at the same time. To improve detection accuracy, deep learning based HSI anomaly detectors (A...

(This article belongs to the Section Remote Sensing Image Processing)

of 16