Periodic, wave-like modifications of 2D shape contours are often applied to convey quantitative data via images. However, to the best of our knowledge, there has been no in-depth investigation of the perceptual uniformity and legibility of these kind...
Vision–language models (VLMs) are increasingly deployed in resource-constrained environments, yet efficient fine-tuning remains challenging because post-training quantization often degrades the effectiveness of low-rank adaptation. This paper r...
In the realm of product design and development, efficient retrieval and reuse of 3D CAD models are vital for optimizing workflows and minimizing redundant efforts. Manual labeling of CAD models, while traditional, is labor-intensive and prone to inco...
With the rapid growth of sensor technology and computer vision, efficient deep learning models are essential for real-time image feature extraction in resource-constrained environments. However, most existing quantized deep neural networks (DNNs) are...
In this paper, an improved model-free adaptive predictive control method is presented for unknown nonlinear systems with quantization to handle the limited network transmission capacity and denial of service (DoS) attacks. Firstly, to reduce the impa...
Low-precision floating-point computation has become central to efficient artificial intelligence, yet its behavior for compact transformer-based hyperspectral imaging (HSI) models remains underexplored. In this work, we present a controlled comparati...
The deployment of transformer-based language models on resource-constrained edge devices presents fundamental challenges in computational efficiency and memory utilization. We introduce SQ-LoRA (Stable-rank Quantized Low-Rank Adaptation), a theoretic...
In this paper, the problem of model-free adaptive predictive control (MFAPC) under denial-of-service attacks and quantization effects for high-speed trains with unknown models is investigated. Since the system model of the high-speed train is unknown...
The development of non-invasive blood pressure monitoring systems remains a critical challenge, particularly in resource-constrained settings. This study proposes an efficient deep learning framework integrating Edge Artificial Intelligence for conti...
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...
This expository paper provides a unified and pedagogical introduction to optimal quantization for probability measures supported on spherical curves and discrete subsets of the sphere, emphasizing both continuous and discrete settings. We first prese...
Quantized large language models are large language models (LLMs) optimized for model size while preserving their efficacy. They can be executed on consumer-grade computers without the powerful features of dedicated servers needed to execute regular (...
Network quantization becomes a crucial step when deploying deep models to the edge devices as it is hardware-friendly, offers memory and computational advantages, but it also suffers performance degradation as the result of limited representation cap...
In this paper, quantized residual preference is proposed to represent the hypotheses and the points for model selection and inlier segmentation in multi-structure geometric model fitting. First, a quantized residual preference is proposed to represen...
Outliers significantly impact the accuracy of geometric model fitting. Previous approaches to handling outliers have involved threshold selection and scale estimation. However, many scale estimators assume that the inlier distribution follows a Gauss...
We present RoBaseLM-S (125 M) and RoBaseLM-M (260 M), two compact Romanian decoder-only language models trained from scratch on a 4.3 B-token curated corpus. Architecturally, they follow a modern LLaMA-style recipe with pre-norm RMSNorm, rotary posit...
Quantization reduces the precision of neural network parameters to accelerate inference and lower power consumption, but it often causes noticeable accuracy degradation. We propose a differentiable quantization framework that replaces the non-differe...
Multimodal Emotion Recognition in Conversation (ERC) has attracted attention as a key technology in human–computer interaction, mental healthcare, and intelligent services. However, deploying ERC in real-world settings remains challenging due t...
Deep learning models are applied in precision agriculture for site-specific weed management by identifying weeds in farmlands. Unfortunately, because deep learning models are usually large, they are rarely adopted in resource-constrained devices (lik...
This study proposed an event-triggered quantized model predictive control (ETQMPC) method for the dynamic docking of unmanned underwater vehicles (UUVs) and human-occupied vehicles (HOVs). The proposed strategy employed a non-periodic control approac...
Due to their simplicity and ease of visualization, lattice models can be useful to illustrate basic concepts in thermodynamics. The recipe to obtain classical thermodynamic expressions from lattice models is usually based on invoking the thermodynami...
Artificial intelligence (AI) plays a critical role in the operation of robot vacuum cleaners, enabling them to intelligently navigate to clean and avoid indoor obstacles. Due to limited computational resources, manufacturers must balance performance...
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...
A toy model (suggested by Klauder) was analyzed from the perspective of first-class and second-class Dirac constrained systems. First-class constraints are often associated with the existence of important gauge symmetries in a system. A comparison wa...
The autonomous landing of an unmanned aerial vehicle (UAV) on a moving platform is an essential functionality in various UAV-based applications. It can be added to a teleoperation UAV system or part of an autonomous UAV control system. Various robust...
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...
Researchers have resorted to model quantization to compress and accelerate graph neural networks (GNNs). Nevertheless, several challenges remain: (1) quantization functions overlook outliers in the distribution, leading to increased quantization erro...
Deep neural network quantization is a widely used method in the deployment of mobile or edge devices to effectively reduce memory overhead and speed up inference. However, quantization inevitably leads to a reduction in the performance and equivalenc...
TinyStressNet is a compact neural classifier for three-class academic stress estimation (low, medium, high) from three physiological features (galvanic skin response, heart rate, and skin temperature) designed for low-cost educational sensing. We eva...
Compared with traditional artificial neural networks (ANNs), spiking neural networks (SNNs) have lower computational complexity, lower energy consumption, and faster inference speed, making them more promising for practical deployment on edge devices...
With the increasing demand for implementing deep-learning models on devices on resource-constrained devices, the development of power-efficient neural networks has become imperative. This paper introduces HADQ-Net, a novel framework for optimizing de...
Ecohydrological models vary in their sensitivity to forcing data and use available information to different extents. We focus on the impact of forcing precision on ecohydrological model behavior particularly by quantizing, or binning, time-series for...
This work focuses on developing and applying Encrypted Lyapunov-based Model Predictive Control (LMPC) in a nonlinear chemical process network for Ethylbenzene production. The network, governed by a nonlinear dynamic model, comprises two continuously...
This study presents a comprehensive analysis of utilizing TensorFlow Lite on mobile phones for the on-edge medical diagnosis of lung diseases. This paper focuses on the technical deployment of various deep learning architectures to classify nine resp...
Nowadays, networked control systems (NCSs) are being widely implemented in many applications. However, several problems negatively affect and compromise the design of practical NCSs. One of them is the performance degradation of the system due to qua...
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...
The deployment of machine learning models on mobile platforms has ushered in a new era of innovation across diverse sectors, including agriculture, where such applications hold immense promise for empowering farmers with cutting-edge technologies. In...
This research addresses the optimization and deployment of convolutional neural networks for eyeglasses detection on low-power edge devices. Multiple convolutional neural network architectures were trained and evaluated using the FFHQ dataset, which...
Uniform quantization is widely taken as an efficient compression method in practical applications. Despite its merit of having a low computational overhead, uniform quantization fails to preserve sensitive components in neural networks when applied w...
The usual full- and half-harmonic oscillators are turned into field theories, and that behavior is examined using canonical and affine quantization. The result leads to a valid affine quantization of the half harmonic oscillator field theory, which p...
Machine learning deployment on edge devices has faced challenges such as computational costs and privacy issues. Membership inference attack (MIA) refers to the attack where the adversary aims to infer whether a data sample belongs to the training se...
We quantized the interaction of gravity with Yang–Mills and spinor fields; hence, offering a quantum theory incorporating all four fundamental forces of nature. Let us abbreviate the spatial Hamilton functions of the standard model by
The application of extremum seeking control is investigated to mitigate the spread of the COVID-19 pandemic, maximizing social distancing while limiting the number of infections. The procedure does not rely on the accurate knowledge of an epidemiolog...
This work investigates the effectiveness of block transform coding (BTC) as a lightweight, training-free quantization strategy for compressing the weights of pretrained deep neural networks. The proposed method applies a rule-based block transform wi...
Despite the emergence of mobile health and the success of deep learning (DL), deploying production-ready DL models to resource-limited devices remains challenging. Especially, during inference time, the speed of DL models becomes relevant. We aimed t...
This paper is devoted to the problem of prescribed performance trajectory tracking control for symmetrical underactuated unmanned surface vessels (USVs) in the presence of model uncertainties and input quantization. By combining backstepping filter m...
Real-time visual inference on resource-constrained hardware remains a core challenge for edge computing and embedded artificial intelligence systems. Recent deep learning architectures, particularly Vision Transformers (ViTs) and Detection Transforme...
Multiple sclerosis (MS) is a chronic demyelinating condition characterized by plaques in the white matter of the central nervous system that can be detected using magnetic resonance imaging (MRI). Many deep learning models for automated MS detection...
The advancement of artificial intelligence (AI) demands significant data and computational resources that have an adverse impact on the environment. To address this issue, a novel computing architecture that is both energy efficient and eco-friendly...
As the technology scales down, two-dimensional (2D) NAND flash memory has reached its bottleneck. Three-dimensional (3D) NAND flash memory was proposed to further increase the storage capacity by vertically stacking multiple layers. However, the new...
of 23