Skip to Content

1,675 Results Found

  • Article
  • Open Access
3 Citations
4,906 Views
24 Pages

Robotic Motion Intelligence Using Vector Symbolic Architectures and Blockchain-Based Smart Contracts

  • Daswin De Silva,
  • Sudheera Withanage,
  • Vidura Sumanasena,
  • Lakshitha Gunasekara and ,
  • Harsha Moraliyage,
  • Nishan Mills and
  • Milos Manic
  • + 2 authors+ 0 author

28 March 2025

The rapid adoption of artificial intelligence (AI) systems, such as predictive AI, generative AI, and explainable AI, is in contrast to the slower development and uptake of robotic AI systems. Dynamic environments, sensory processing, mechanical move...

(This article belongs to the Section AI in Robotics)
  • Article
  • Open Access
4 Citations
5,254 Views
18 Pages

Design of an ASIC Vector Engine for a RISC-V Architecture

  • Miguel Bucio-Macías,
  • Luis Pizano-Escalante and
  • Omar Longoria-Gandara

5 August 2025

Nowadays, Graphical Processor Units (GPUs) are a great technology to implement Artificial Intelligence (AI) processes; however, a challenge arises when the inclusion of a GPU is not feasible due to the cost, power consumption, or the size of the hard...

  • Article
  • Open Access
4 Citations
3,435 Views
24 Pages

A Two-Layer Self-Organizing Map with Vector Symbolic Architecture for Spatiotemporal Sequence Learning and Prediction

  • Thimal Kempitiya,
  • Damminda Alahakoon,
  • Evgeny Osipov,
  • Sachin Kahawala and
  • Daswin De Silva

We propose a new nature- and neuro-science-inspired algorithm for spatiotemporal learning and prediction based on sequential recall and vector symbolic architecture. A key novelty is the learning of spatial and temporal patterns as decoupled concepts...

(This article belongs to the Special Issue Nature-Inspired Computer Algorithms: 2nd Edition)
  • Article
  • Open Access
739 Views
23 Pages

While the Triton compiler has revolutionized GPU kernel development, its deployment on general-purpose CPUs struggles to fully utilize the underlying hardware capabilities. This is primarily due to the semantic gap between Triton’s SPMD executi...

  • Article
  • Open Access
1 Citations
2,352 Views
15 Pages

SRB-ELL: A Vector-Friendly Sparse Matrix Format for SpMV on Scratchpad-Augmented Architectures

  • Sheng Zhang,
  • Wuqiang Bai,
  • Zongmao Zhang,
  • Xuchao Xie and
  • Xuebin Tang

7 September 2025

Sparse Matrix–Vector Multiplication (SpMV) is a critical computational kernel in high-performance computing (HPC) and artificial intelligence (AI). However, its irregular memory access patterns lead to frequent cache misses on multi-level cache...

(This article belongs to the Special Issue Intelligent Data Processing and Management: Technologies and Applications)
  • Article
  • Open Access
455 Views
28 Pages

Symbolic Disentangled Representations for Images

  • Alexandr V. Korchemnyi,
  • Alexey K. Kovalev and
  • Aleksandr I. Panov

The idea of disentangled representations is to reduce the data to a set of generative factors that produce it. Typically, such representations are vectors in latent space, where each coordinate corresponds to one of the generative factors. The object...

(This article belongs to the Special Issue Artificial Intelligence Models and Cognitive Computing: Innovations from Algorithms to Intelligent Systems)
  • Proceeding Paper
  • Open Access
56 Views
9 Pages

5 November 2026

Generative artificial intelligence-based chatbot systems are increasingly used to support information provision and customer service processes; however, their reliability strongly depends on the underlying architecture and the availability of domain-...

(This article belongs to the Proceedings of The Sustainable Mobility and Transportation Symposium 2026)
  • Article
  • Open Access
6 Citations
8,678 Views
13 Pages

Optimization of Finite-Differencing Kernels for Numerical Relativity Applications

  • Roberto Alfieri,
  • Sebastiano Bernuzzi,
  • Albino Perego and
  • David Radice

A simple optimization strategy for the computation of 3D finite-differencing kernels on many-cores architectures is proposed. The 3D finite-differencing computation is split direction-by-direction and exploits two level of parallelism: in-core vector...

  • Article
  • Open Access
4 Citations
6,935 Views
19 Pages

Symmetry Extraction in High Sensitivity Melanoma Diagnosis

  • Elyoenai Guerra-Segura,
  • Carlos M. Travieso-González,
  • Jesús B. Alonso-Hernández,
  • Antonio G. Ravelo-García and
  • Gregorio Carretero

15 June 2015

Melanoma diagnosis depends on the experience of doctors. Symmetry is one of the most important factors to measure, since asymmetry shows an uncontrolled growth of cells, leading to melanoma cancer. A system for melanoma detection in diagnosing melano...

  • Article
  • Open Access
28 Citations
6,604 Views
36 Pages

Machine learning is becoming the cornerstones of smart and autonomous systems. Machine learning algorithms can be categorized into supervised learning (classification) and unsupervised learning (clustering). Among many classification algorithms, the...

(This article belongs to the Section Artificial Intelligence Circuits and Systems (AICAS))
  • Feature Paper
  • Article
  • Open Access
4 Citations
3,157 Views
11 Pages

Kernel Mapping Methods of Convolutional Neural Network in 3D NAND Flash Architecture

  • Min Suk Song,
  • Hwiho Hwang,
  • Geun Ho Lee,
  • Suhyeon Ahn and ,
  • Sungmin Hwang and
  • Hyungjin Kim
  • + 1 author+ 0 author

27 November 2023

A flash memory is a non-volatile memory that has a large memory window, high cell density, and reliable switching characteristics and can be used as a synaptic device in a neuromorphic system based on 3D NAND flash architecture. We fabricated a TiN/A...

(This article belongs to the Section Semiconductor Devices)
  • Article
  • Open Access
376 Views
17 Pages

Construction-Period Classification of Traditional Dwellings in the Guanzhong Region Based on Support Vector Machine

  • Yujia Liu,
  • Chenyu Guo,
  • Yingtao Qi,
  • Jiahe Xian and ,
  • Yujun Yang and
  • Dian Zhou
  • + 1 author+ 0 author

1 August 2026

Construction period is a core item of information for the heritage conservation of traditional dwellings, supporting building archive compilation, historical character zoning, conservation grading, and restoration strategy formulation in traditional...

(This article belongs to the Special Issue Universal and Age-Friendly Design in Urban and Rural Built Environment Creation)
  • Article
  • Open Access
3,628 Views
23 Pages

A large number of architectural drawings have historically existed in paper form or as non-editable raster images, which makes them difficult to directly support information reuse and digital management, while manual CAD reconstruction is time-consum...

(This article belongs to the Topic Application of Smart Technologies in Buildings)
  • Article
  • Open Access
1,371 Views
27 Pages

Hybrid Method of Organizing Information Search in Logistics Systems Based on Vector-Graph Structure and Large Language Models

  • Vadim Voloshchuk,
  • Yaroslav Melnik,
  • Irina Safronenkova,
  • Egor Lishchenko and ,
  • Oleg Kartashov and
  • Alexander Kozlovskiy
  • + 1 author+ 0 author

In logistics systems, the organization of information retrieval plays a key role in human interaction with technical systems to ensure decision-making speed, route optimization, planning, and resource allocation. At the same time, the efficiency of t...

  • Article
  • Open Access
36 Citations
5,822 Views
16 Pages

26 June 2019

Water quality data cleaning is important for the management of water environments. A framework for water quality time series cleaning is proposed in this paper. Considering the nonlinear relationships among water quality indicators, support vector re...

(This article belongs to the Section Hydrology)
  • Article
  • Open Access
3 Citations
3,408 Views
12 Pages

Wordline Input Bias Scheme for Neural Network Implementation in 3D-NAND Flash

  • Hwiho Hwang,
  • Gyeonghae Kim,
  • Dayeon Yu and
  • Hyungjin Kim

In this study, we propose a neuromorphic computing system based on a 3D-NAND flash architecture that utilizes analog input voltages applied through wordlines (WLs). The approach leverages the velocity saturation effect in short-channel MOSFETs, which...

(This article belongs to the Section Bioinspired Sensorics, Information Processing and Control)
  • Article
  • Open Access
3 Citations
1,535 Views
24 Pages

A Feasibility Study of IoT-Based Classification of Residential Water-Use Activities in Storage Tank Systems: A Comparative Analysis of Decision Trees, Random Forest, SVM, KNN, and Neural Networks

  • Iván Neftalí Chávez-Flores,
  • Héctor A. Guerrero-Osuna,
  • Jesuś Antonio Nava-Pintor,
  • Fabián García-Vázquez and ,
  • Luis F. Luque-Vega,
  • Rocío Carrasco-Navarro,
  • Marcela E. Mata-Romero,
  • Jorge A. Lizarraga and
  • Salvador Castro-Tapia
  • + 4 authors+ 0 author

The increasing scarcity of urban water resources, particularly in regions with intermittent supply and household water storage tanks, demands monitoring approaches capable of identifying end-use consumption patterns beyond aggregated volume measureme...

(This article belongs to the Special Issue AI for Smart Engineering Systems)
  • Article
  • Open Access
302 Views
19 Pages

11 August 2026

Abnormally overpressured helium-rich natural gas occurs in dolomite reservoirs beneath gypsum-bearing strata of the Middle Triassic Zhouchongcun Formation in WWY1 Well, Wuwei Depression. Resolving the vertical arrangement of dolomite, gypsum, and sha...

(This article belongs to the Special Issue Advancements in Mineral Resource Characterization Using Machine Learning)
  • Article
  • Open Access
14 Citations
6,656 Views
19 Pages

30 October 2019

The Internet Protocol (IP) address lookup is one of the most challenging tasks for Internet routers, since it requires to perform packet forwarding at wire-speed for tens of millions of incomming packets per second. Efficient IP address lookup algori...

(This article belongs to the Section Electrical, Electronics and Communications Engineering)
  • Article
  • Open Access
1 Citations
3,505 Views
19 Pages

14 June 2021

The vector tracking loop (VTL) has high tracking accuracy and a superior ability to track weak signals in GNSS. However, traditional VTL architecture is established on continuous Code Division Multiple Access (CDMA) signal and is incompatible with ps...

(This article belongs to the Topic GNSS Measurement Technique in Aerial Navigation)
  • Systematic Review
  • Open Access
14 Citations
3,689 Views
16 Pages

Urban, Architectural, and Socioeconomic Factors Contributing to the Concentration of Potential Arbovirus Vectors and Arbovirosis in Urban Environments from a One Health Perspective: A Systematic Review

  • Luigi Cofone,
  • Marise Sabato,
  • Carolina Di Paolo,
  • Stefano Di Giovanni and ,
  • Maria Assunta Donato and
  • Lorenzo Paglione
  • + 1 author+ 0 author

30 April 2025

Today, urbanisation and environmental changes are increasingly influencing the social and biological landscape of our planet. This systematic review aims to assess the relationship between urban–architectural and socioeconomic factors and vecto...

  • Review
  • Open Access
53 Citations
10,967 Views
42 Pages

18 September 2024

Gene therapy is the technique of inserting foreign genetic elements into host cells to achieve a therapeutic effect. Although gene therapy was initially formulated as a potential remedy for specific genetic problems, it currently offers solutions for...

(This article belongs to the Special Issue Biopolymer-Based Materials in Medical Applications)
  • Article
  • Open Access
75 Citations
7,095 Views
16 Pages

9 July 2021

Recently, digital pathology is an essential application for clinical practice and medical research. Due to the lack of large annotated datasets, the deep transfer learning technique is often used to classify histopathology images. A softmax classifie...

(This article belongs to the Topic Applied Computer Vision and Pattern Recognition)
  • Article
  • Open Access
2 Citations
2,023 Views
17 Pages

13 January 2024

This study proposes an efficient method for computing State Vectors in Sequence-to-Sequence (SVSeq2Seq) architecture to improve the performance of sequence data forecasting, which associates each element with other elements instead of relying only on...

(This article belongs to the Special Issue New Trends in Computer Vision, Deep Learning and Artificial Intelligence)
  • Review
  • Open Access
5 Citations
7,826 Views
30 Pages

17 December 2014

Inovirus-associated vectors (IAVs) are engineered, non-lytic, filamentous bacteriophages that are assembled primarily from thousands of copies of the major coat protein gp8 and just five copies of each of the four minor coat proteins gp3, gp6, gp7...

(This article belongs to the Special Issue AIDS Vaccine 2014)
  • Article
  • Open Access
3,826 Views
15 Pages

A Collaborative CPU Vector Offloader: Putting Idle Vector Resources to Work on Commodity Processors

  • Youngbin Son,
  • Seokwon Kang,
  • Hongjun Um,
  • Seokho Lee and ,
  • Jonghyun Ham,
  • Donghyeon Kim and
  • Yongjun Park
  • + 2 authors+ 0 author

28 November 2021

Most modern processors contain a vector accelerator or internal vector units for the fast computation of large target workloads. However, accelerating applications using vector units is difficult because the underlying data parallelism should be unco...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
3 Citations
4,527 Views
37 Pages

This study presents a universal reconfigurable hardware accelerator for efficient processing of sparse decision trees, artificial neural networks and support vector machines. The main idea is to develop a hardware accelerator that will be able to dir...

(This article belongs to the Special Issue Energy-Efficient Processors, Systems, and Their Applications)
  • Article
  • Open Access
4 Citations
3,542 Views
20 Pages

Evaluation of Clustering Algorithms on HPC Platforms

  • Juan M. Cebrian,
  • Baldomero Imbernón,
  • Jesús Soto and
  • José M. Cecilia

4 September 2021

Clustering algorithms are one of the most widely used kernels to generate knowledge from large datasets. These algorithms group a set of data elements (i.e., images, points, patterns, etc.) into clusters to identify patterns or common features of a s...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
3 Citations
4,570 Views
15 Pages

23 October 2022

Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate between d...

(This article belongs to the Special Issue Artificial Intelligence and Machine Learning Based Methods and Applications)
  • Article
  • Open Access
2,232 Views
23 Pages

24 April 2025

Despite their unprecedented success, artificial neural networks suffer extreme opacity and weakness in learning general knowledge from limited experience. Some argue that the key to overcoming those limitations in artificial neural networks is effici...

(This article belongs to the Special Issue Optimization Algorithms and Their Applications)
  • Proceeding Paper
  • Open Access
378 Views
9 Pages

Automatic detection of retinal lesions is an important component of diabetic retinopathy screening. While classical image processing and machine learning approaches can achieve good performance on specific datasets, their ability to generalize across...

(This article belongs to the Proceedings of International Conference on Electromagnetic Fields, Signals and BioMedical Engineering (ICEMS-BIOMED))
  • Article
  • Open Access
2 Citations
1,834 Views
21 Pages

Model-Free Transformer Framework for 6-DoF Pose Estimation of Textureless Tableware Objects

  • Jungwoo Lee,
  • Hyogon Kim,
  • Ji-Wook Kwon,
  • Sung-Jo Yun and ,
  • Na-Hyun Lee,
  • Young-Ho Choi,
  • Goobong Chung and
  • Jinho Suh
  • + 3 authors+ 0 author

5 October 2025

Tableware objects such as plates, bowls, and cups are usually textureless, uniform in color, and vary widely in shape, making it difficult to apply conventional pose estimation methods that rely on texture cues or object-specific CAD models. These li...

(This article belongs to the Topic Transformer and Deep Learning Applications in Image Processing)
  • Article
  • Open Access
3 Citations
950 Views
37 Pages

13 February 2026

School buildings are important in terms of energy performance, and their energy demand varies significantly across different climates. Early design decisions strongly influence this demand; however, building energy simulations are computationally int...

(This article belongs to the Section Building Energy, Physics, Environment, and Systems)
  • Article
  • Open Access
1,043 Views
33 Pages

26 August 2026

Artificial intelligence has increasingly been applied to residential floor plan generation, producing outputs in diverse forms such as semantic raster images, graph-structured layouts, and vector polygons. However, these outputs still require substan...

(This article belongs to the Section Construction Management, and Computers & Digitization)
  • Article
  • Open Access
1,750 Views
21 Pages

A Low-Power Mixed-Signal Differential In-Memory Matrix–Vector Computing Circuit Architecture with RISC-V Control for Edge AI

  • David Ng,
  • King Hang Lam,
  • Si Qi Bu,
  • Wen Chin Lo and ,
  • Chi Hong Chan,
  • Roy Ng,
  • Sunny Chan,
  • Matt Mak,
  • Hugo Wong and
  • Wai Ming To
  • + 9 authors+ 4 authors

Analog in-memory computing (AIMC) has emerged as a promising approach to mitigate the Von Neumann bottleneck in matrix operations, which are common in deep learning applications. However, the practical implementation of resistive crossbar arrays is l...

(This article belongs to the Topic Advanced Integrated Circuit Design and Application)
  • Article
  • Open Access
7 Citations
7,773 Views
25 Pages

10 May 2012

This paper presents a novel hardware architecture for principal component analysis. The architecture is based on the Generalized Hebbian Algorithm (GHA) because of its simplicity and effectiveness. The architecture is separated into three portions: t...

(This article belongs to the Section Physical Sensors)
  • Article
  • Open Access
3 Citations
6,411 Views
23 Pages

27 August 2012

A novel k-winners-take-all (k-WTA) competitive learning (CL) hardware architecture is presented for on-chip learning in this paper. The architecture is based on an efficient pipeline allowing k-WTA competition processes associated with different trai...

(This article belongs to the Section Physical Sensors)
  • Feature Paper
  • Article
  • Open Access
226 Views
21 Pages

16 October 2026

Extract, Transform, and Load (ETL) and Online Analytical Processing (OLAP) provide robust mechanisms for integrating structured data and supporting multidimensional analysis. Still, they offer limited support for semantic access to unstructured textu...

(This article belongs to the Special Issue International Database Engineered Applications Symposium, 2nd Edition)
  • Proceeding Paper
  • Open Access
222 Views
12 Pages

18 September 2026

Traditional Single-Vector embeddings for System Dynamics models suffer from an “Information Bottleneck”, where the specific characteristics of granular subsystems are diluted into a single dense representation. To address this limitation,...

(This article belongs to the Proceedings of The International Conference on Electronics, Engineering Physics and Earth Science (EEPES2026))
  • Article
  • Open Access
5 Citations
4,362 Views
21 Pages

A Parallel-Computing Approach for Vector Road-Network Matching Using GPU Architecture

  • Bo Wan,
  • Lin Yang,
  • Shunping Zhou,
  • Run Wang and ,
  • Dezhi Wang and
  • Wenjie Zhen
  • + 1 author+ 0 author

The road-network matching method is an effective tool for map integration, fusion, and update. Due to the complexity of road networks in the real world, matching methods often contain a series of complicated processes to identify homonymous roads and...

  • Article
  • Open Access
4 Citations
3,877 Views
21 Pages

Vectorization Programming Based on HR DSP Using SIMD

  • Chunhu Xie,
  • Huachun Wu and
  • Jian Zhou

Single instruction multiple data (SIMD) vector extension has become an essential feature of high-performance processors. Architectures such as x86, ARM, MIPS, and PowerPC have specific vector extension instruction sets and SIMD micro-architectures. U...

(This article belongs to the Special Issue High-Performance Computing and Its Applications)
  • Review
  • Open Access
9 Citations
4,263 Views
43 Pages

19 August 2025

Polymers and polymer composites offer versatile possibilities for engineering the physico-chemical properties of materials on micro- and macroscopic scales. This review provides an overview of polymeric and polymer-decorated particles that can serve...

(This article belongs to the Section Polymer Applications)
  • Article
  • Open Access
13 Citations
7,182 Views
20 Pages

The buffer generation algorithm is a fundamental function in GIS, identifying areas of a given distance surrounding geographic features. Past research largely focused on buffer generation algorithms generated in a stand-alone environment. Moreover, d...

(This article belongs to the Special Issue Geospatial Big Data and Urban Studies)
  • Article
  • Open Access
3 Citations
12,874 Views
22 Pages

Multidirectional Scanning Model, MUSCLE, to Vectorize Raster Images with Straight Lines

  • Ismail Rakip Karas,
  • Bulent Bayram,
  • Fatmagul Batuk,
  • Abdullah Emin Akay and
  • Ibrahim Baz

15 April 2008

This paper presents a new model, MUSCLE (Multidirectional Scanning for Line Extraction), for automatic vectorization of raster images with straight lines. The algorithm of the model implements the line thinning and the simple neighborhood methods to...

(This article belongs to the Special Issue Spatio-Temporal Modeling of Solar Radiation, Climate and Biogeochemical Cycles)
  • Article
  • Open Access
33 Citations
11,862 Views
28 Pages

30 July 2007

Wireless sensor networks (WSNs) are autonomous networks that have beenfrequently deployed to collaboratively perform target localization and classification tasks.Their autonomous and collaborative features resemble the characteristics of agents. Such...

(This article belongs to the Special Issue Energy Efficiency and Intelligent Signal Processing for Wireless Sensing)
  • Article
  • Open Access
6 Citations
9,859 Views
21 Pages

Thread-level and data-level parallel architectures have become the design of choice in many of today’s energy-efficient computing systems. However, these architectures put substantially higher requirements on the memory subsystem than scalar architec...

(This article belongs to the Special Issue Emerging Network-on-Chip Architectures for Low Power Embedded Systems)
  • Article
  • Open Access
18 Citations
3,442 Views
24 Pages

30 August 2021

Recently, deep metric learning (DML) has received widespread attention in the field of remote sensing image retrieval (RSIR), owing to its ability to extract discriminative features to represent images and then to measure the similarity between image...

  • Article
  • Open Access
6 Citations
9,173 Views
29 Pages

Vector Disparity Sensor with Vergence Control for Active Vision Systems

  • Francisco Barranco,
  • Javier Diaz,
  • Agostino Gibaldi,
  • Silvio P. Sabatini and
  • Eduardo Ros

9 February 2012

This paper presents an architecture for computing vector disparity for active vision systems as used on robotics applications. The control of the vergence angle of a binocular system allows us to efficiently explore dynamic environments, but requires...

(This article belongs to the Section Physical Sensors)
  • Article
  • Open Access
5 Citations
5,226 Views
13 Pages

Soft-Decision Low-Complexity Chase Decoders for the RS(255,239) Code

  • Vicente Torres,
  • Javier Valls,
  • Maria Jose Canet and
  • Francisco García-Herrero

In this work, we present a new architecture for soft-decision Reed–Solomon (RS) Low-Complexity Chase (LCC) decoding. The proposed architecture is scalable and can be used for a high number of test vectors. We propose a novel Multiplicity Assign...

(This article belongs to the Special Issue VLSI Architecture Design for Digital Signal Processing)
  • Article
  • Open Access
1 Citations
1,622 Views
10 Pages

safe Torque Vectoring function for an electric vehicle

  • Volker Scheuch,
  • Gerd Kaiser,
  • Matthias Korte,
  • Peter Grabs and ,
  • Fabian Kreft and
  • Frédéric Holzmann
  • + 1 author+ 0 author

27 September 2013

A safe Torque Vectoring function is applied to an electric vehicle with a two front motors drivetrain concept. The function has been embedded in a lean and scalable functional architecture adaptable to various drivetrain concepts. The Torque Vectorin...

of 34