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...
Deep learning has achieved outstanding results in various tasks in machine learning under the background of rapid increase in equipment’s computing capacity. However, while achieving higher performance and effects, model size is larger, training and...
Increasing the efficiency of transmitters, as the largest consumers of energy, is relevant for any wireless communication devices. For higher efficiency, a number of methods are used, including envelope tracking and envelope elimination and restorati...
This paper investigates the event-triggered robust dissipative filtering problem for discrete-time networked nonlinear systems subject to dynamic quantization and stochastic cyber attacks. The networked nonlinear system under consideration is represe...
This article discusses the quantization of linear Hamiltonian systems, a historically rich but under explored line of research. The key idea is that a classical linear Hamiltonian system induces on its phase space a compatible complex structure and s...
The quantization problem aims to find the best possible approximation of probability measures on
This paper investigates the cooperative formation trajectory tracking problem for heterogeneous unmanned aerial vehicle (UAV) and multiple unmanned surface vessel (USV) systems with input quantization performance. Firstly, at the kinematic level, a d...
It is challenging to design an efficient lossy compression scheme for complicated sources based on block codes, especially to approach the theoretical distortion-rate limit. In this paper, a lossy compression scheme is proposed for Gaussian and Lapla...
Recent advances in deep learning have led to a proliferation of AI services for the general public. Consequently, constructing trustworthy AI systems that operate on personal devices has become a crucial challenge. While on-device processing is criti...
This paper presents a fixed-time fault-tolerant control strategy based on an improved long short-term memory network for dynamic positioning of unmanned marine vehicles subject to signal quantization, disturbances, and input saturation. Firstly, an i...
We focus on quantization of the metric of a black hole restricted to the Killing horizon with universal radius r0. After imposing spherical symmetry and after restriction to the Killing horizon, the metric is quantized employing the chiral currents f...
The exciton states and their influence on the optical absorption spectrum of CdSe and PbS nanoplatelets (NPLs) are considered theoretically in this paper. The problem is discussed in cases of strong, intermediate, and weak size quantization regimes o...
Since the number of acquired images and their size have the tendency to increase, their lossy compression is widely applied for their storage, transfer, and dissemination. Simultaneously with providing a relatively large compression ratio, lossy comp...
This paper designs an online adjustment strategy for dynamic quantizer parameters and investigates the sliding mode control (SMC) problem for uncertain switched systems under a limited network communication bandwidth. Due to the limitation of the cod...
Digital watermarking has become an essential and important tool for copyright protection, authentication, and security of multimedia contents. It is the process of embedding a watermark in the multimedia content and its extraction. Block-based discre...
This paper proposes a novel adaptive finite-time controller for a quadrotor unmanned aerial vehicle (UAV) model with stochastic perturbations and parameter-unknown terms, under the constraints of a state-constrained system. The controller is designed...
The preservation of relevant mutual information under compression is the fundamental challenge of the information bottleneck method. It has many applications in machine learning and in communications. The recent literature describes successful applic...
This paper presents a method for simplifying and quantizing a deep neural network (DNN)-based object detector to embed it into a real-time edge device. For network simplification, this paper compares five methods for applying channel pruning to a res...
This work presents the first RFI detection and mitigation algorithm for the interferometric radiometers that will be implemented in its correlator unit. The algorithm operates in the time and frequency domains, applying polarimetric and statistical t...
The outputs of deep hash network (DHN) are binary codes, so DHN has high retrieval efficiency in matching phase and can be used for high-speed palmprint recognition, which is a promising biometric modality. In this paper, the templates and network pa...
The functional Schrödinger representation of a nonlinear scalar quantum field theory in curved space-time is shown to emerge as a singular limit from the formulation based on precanonical quantization. The previously established relationship bet...
In the field of embedded and edge devices, efforts have been made to make deep neural network models smaller due to the limited size of the available memory and the low computational efficiency. Typical model footprints are under 100 KB. However, for...
Deep convolutional neural networks have a large number of parameters and require a significant number of floating-point operations during computation, which limits their deployment in situations where the storage space is limited and computational re...
We investigate a quantum walk on a ring represented by a directed triangle graph with complex edge weights and monitored at a constant rate until the quantum walker is detected. To this end, the first hitting time statistics are recorded using unitar...
The effects of the conformal deformation of physical parameters on the measurement, Berry phase, and resonance of a spin are investigated. We first construct a form-invariant yet measurement-tunable representation of a spinor from the deformed parame...
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 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...
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...
In recent years, the expansion of large-model parameters has substantially increased storage and inference overhead. Consequently, post-training quantization has become a key technique for reducing model size and inference-time energy consumption. Ho...
Private document question answering (QA) requires language models to answer from local evidence while abstaining when the supplied context is insufficient. This study evaluates quantized parameter-efficient adaptation for private email QA using Enron...
In previous work, we investigated thermodynamic processes in systems at the mesoscopic level where traditional thermodynamic descriptions (macroscopic or microscopic) may not be fully adequate. The key result is that entropy in such systems does not...
Binarized Neural Network (BNN) is a quantized Convolutional Neural Network (CNN), reducing the precision of network parameters for a much smaller model size. In BNNs, the Batch Normalisation (BN) layer is essential. When running BN on edge devices, f...
We present a filtering technique that allows estimating the time derivative of slowly changing temperature measured via quantized sensor output in real time. Due to quantization, the output may appear constant for several minutes in a row with the te...
The utilization of broadband quantization data increases the possibility of practical applications for fish target recognition based on the acoustic scattering theory. However, the quantification of broadband data is more complex than that of narrowb...
We propose a new extended theory of Hořava gravity based on the following three conditions: (i) power-counting renormalizable, (ii) healthy IR behavior and (iii) a stable vacuum state in a quantized version of the theory. Compared with other extended...
A model for generating synthetic time series data using pre-trained large language models is proposed. Starting with the Google T5-base model, which employs an encoder–decoder transformer architecture, the model underwent pre-training on divers...
Concrete surface crack detection plays a crucial role in infrastructure maintenance and safety. Deep learning-based methods have shown great potential in this task. However, under real-world conditions such as poor image quality, environmental interf...
Rice, as one of the significant grain products across the world, features a wide range of varieties in terms of usability and efficiency. It may be known with various varieties and regional names depending on the specific locations. To specify a part...
This study presents a lightweight RGB vision-based express-parcel detection framework for complex logistics environments. An Express Parcel Recognition (EPR) dataset is first constructed from RGB images acquired through multi-source data collection,...
This paper presents the hardware aspects of a Hjorth-parameter deep neural network (DNN)-based cardiac fibrillation diagnosis pipeline targeting low-power Internet of Medical Things (IoMT) devices and ASIC implementations. Building on earlier edge-to...
The measured signals of internal leakage detection of the large-diameter pipeline ball valve in natural gas pipeline systems usually contain background noise, which will affect the accuracy of internal leakage detection and sound localization of inte...
This paper proposes a novel autoencoder-based neural network for compressing and reconstructing underwater acoustic signals collected by Directional Frequency Analysis and Recording sonobuoys. To improve both signal compression rates and reconstructi...
In this work, an adaptive dynamic surface control law for a type of strict-feedback fractional-order nonlinear system is proposed. The considered system contained input quantization and unknown external disturbances. The virtual control law is presen...
In this paper, the problem of distributed adaptive consensus tracking control for second-order nonlinear heterogeneous multi-agent systems (MASs) with input quantization is considered. A distributed output feedback control scheme based on a K-filter...
The interplay between topology and soliton is a central topic in nonlinear topological physics. So far, most studies have been confined to conservative settings. Here, we explore Thouless pumping of dissipative temporal solitons in a nonconservative...
The hardware power-aware keyword spotting (KWS) implementation requires small memory footprint, low-complex computation, and high accuracy performances. Binary neural networks (BNNs) naturally satisfy these constraints. They quantize both weights and...
Sigma-delta modulators use a noise-shaping technique to curtail the noise power in the band of interest during digital-to-analog conversion. Error feedback modulator employs an efficient noise transfer function for time varying inputs than any other...
Autonomous systems operating in embedded environments require robust scene understanding under computational constraints. Multi-task learning offers a compact alternative to deploying multiple task-specific models by jointly solving dense prediction...
The current neural networks for tomato leaf disease recognition have problems such as large model parameters, long training time, and low model accuracy. To solve these problems, a lightweight convolutional neural network (LBFNet) is proposed in this...
Vehicle classification is an important part of intelligent transportation. Owing to the development of deep learning, better vehicle classification can be achieved compared to traditional methods. Contemporary deep network models have huge computatio...
of 10