Class and Data-Incremental Learning Framework for Baggage Threat Segmentation via Knowledge Distillation by Ammara Nasim, Saad Mazhar Khan, Anum Abdul Salam, Arslan Shaukat, Taimur Hassan, Adeel M. Syed, Muhammad Usman Akram

“…Researchers have proposed multiple automated threat detection systems to enhance security screening efficiency; however, automated baggage threat segmentation remains a complex task, especially in the context of multi-class threat detection across diverse datasets. …”
Get full text

A Multivariable Probability Density-Based Auto-Reconstruction Bi-LSTM Soft Sensor for Predicting Effluent BOD in Wastewater Treatment Plants by Wenting Li, Yonggang Li, Dong Li, Jiayi Zhou

“…To address this issue, this paper proposed a multivariable probability density-based auto-reconstruction bidirectional long short-term memory (MPDAR-Bi-LSTM) soft sensor for predicting effluent BOD, enhancing the prediction accuracy and efficiency. Firstly, the selection of appropriate auxiliary variables for soft-sensor modeling is determined through the calculation of k-nearest-neighbor mutual information (KNN-MI) values between the global process variables and effluent BOD. …”
Get full text

Brain functional connectivity analysis of fMRI-based Alzheimer's disease data by Maitha S. Alarjani, Badar A. Almarri

“…Feeding ELM with MVPA features yield decent outcomes given a generalizable and computationally-efficient model. This study underscores the effectiveness of the proposed approach in accurately distinguishing AD stages, offering potential improvements in AD and AD stages detection.…”
Get full text

Flow modeling of high-viscosity fluids in pipeline infrastructure of oil and gas enterprises by Ilia Beloglazov, Valentin Morenov, Ekaterina Leusheva

“…The proposed solutions and tasks for predicting changes in the viscosity-temperature characteristics of the flow for blends of different oil types are especially relevant in the current conditions of an increase in the share of oil production with complex rheological characteristics. Results of the presented investigations may be used for planning the measures of efficient transportation of high-viscosity and heavy oils.…”
Get full text

Research on Numerical Calculation Methods for Modelling the Dynamics of Diesel Engine Crankshaft System Substructures by Zhongxu Tian, Zengbin Sun, Yun Zhou, You Zhou

“…These complexities present challenges in achieving comprehensive and efficient dynamic modelling and analysis. …”
Get full text

Critical Role of Surface Properties in Passive Interstitial Fluid Extraction Using Polymeric Hollow Microneedles for Wearable Diagnostics by Ipek Atay, Emel Yilgör, Gürdeniz Neşer, Taher Abbasiasl, M. Baris Yagci, Iskender Yilgör, Levent Beker

“…Abstract Efficient sampling of dermal interstitial fluid (ISF) is essential for continuous monitoring of biomarkers for early detection and management of chronic diseases. …”
Get full text

Multifunctional Hierarchical Metamaterials: Synergizing Visible-Laser-Infrared Camouflage with Thermal Management by Shenglan Wu, Hao Huang, Zhenyong Huang, Chunhui Tian, Lina Guo, Yong Liu, Shuang Liu

“…Furthermore, the RSHM demonstrates exceptional incident angle and polarization stability, maintaining robust performances even under complex detection conditions. This design is easy to expand relative to other frequency bands of the electromagnetic spectrum and holds significant potential for applications in military camouflage, energy-efficient buildings, and optical devices.…”
Get full text

Attribute-based lightweight reconfigurable access control policy by Rongna XIE, Hui LI, Guozhen SHI, Yunchuan GUO

“…Aiming at the severe challenges of access control policy redundancy and conflict detection,the efficiency of access control policy evaluation in complex network environment,an attribute-based lightweight reconfigurable access control policy was proposed.Taking the attribute-based access control policy as an example,the attribute-based access control policy was divided into multiple disjoint atomic access control rules according to the operation type,subject attribute,object attribute,and environment attribute in the access control policy.Complex access control policies were constructed through atomic access control rules and an algebraic expression formed by AND,OR logical relationships.A method for redundancy and collision detection of atomic access control rules was proposed.A method was proposed for decompose a complex access control policy into equivalent atomic access control rules and an algebraic expression.The method for redundancy and collision detection of complex access control policies were proposed through redundancy and collision detection of equivalent atomic access control rules and algebraic expressions.From time complexity and space complexity,the efficiency of the equivalent transformation access control policy was evaluated.It showes that the reconstruction method for access control policy greatly reduces the number,size and complexity of access control policy,improves the efficiency of access control policy redundancy and collision detection,and the efficiency of access control evaluation.…”
Get full text

An enhanced fruit fly optimization algorithm with random spare and double adaptive weight strategies for oil and gas production optimization by Xu Wang, Jingfu Shan

“…As a promising alternative, evolutionary algorithms—rooted in the principles of natural selection—have demonstrated strong potential for addressing complex optimization problems due to their gradient-free nature and inherent suitability for parallel computation. …”
Get full text

Unveiling Performance and Genetic Estimates of Tongil-Type Rice Genotypes for Yield Improvement and Breeding by Barnabas Justo Sitta, Lupakisyo Mwakyusa, William Titus Suvi, Fatma Suleiman Ally, Mbaraka Abbakari Batare, Sophia Kashenge-Killenga, Sang-Bok Lee

“…However, owing to its complex genetic basis, selecting for yield alone is often insufficient. …”
Get full text

Integrating Deep Transfer Learning and Image Enhancement for Enhancing Defective Photovoltaic Cells Classification in Electroluminescence Images by Hanim Suraya Mohd Mokhtar, Aimi Salihah Abdul Nasir, Mohammad Faridun Naim Tajuddin, Muhammad Hafeez Abdul Nasir, Kumuthawathe Ananda Rao

“…The rapid growth of photovoltaic (PV) systems has highlighted the need for efficient and reliable defect detection to maintain system performance. …”
Get full text

Autonomous vehicle surveillance through fuzzy C-means segmentation and DeepSORT on aerial images by Asifa Mehmood Qureshi, Moneerah Alotaibi, Sultan Refa Alotaibi, Dina Abdulaziz AlHammadi, Muhammad Asif Jamal, Ahmad Jalal, Bumshik Lee

“…After segmentation, we employed the YOLOv4 deep learning algorithm, which is efficient in detecting small-sized objects in vehicle detection. …”
Get full text

Bolt Anchorage Quality Levels Classification Method Based on HO‐VMD‐CNN‐BiLSTM by Fan Kesong, Zhang Can, Liu Shaowei, Feng Mengyin, Yan Ao, Fu Mengxiong, He Deyin, Nie Zhibin

“…The model accurately identifies internal defects in bolts through precise signal decomposition and feature extraction, achieving a high classification accuracy of 96.78% even in a complex noise environment. The model incorporates the Logistic‐Tent chaotic mapping optimization algorithm, which enhances global search capability, improves feature extraction, and increases detection efficiency and accuracy. …”
Get full text

Acoustic virtual sensors for industrial process monitoring using non-negative matrix factorization by Clara Luzon-Alvarez, Maximo Cobos, Jesus Lopez-Ballester, Ana M. Torres-Aranda, Francesc J. Ferri

“…Abstract In modern industrial environments, efficient and non-invasive monitoring of machinery operations is crucial for ensuring process optimization and early fault detection. …”
Get full text

Algorithm for pixel-level concrete pavement crack segmentation based on an improved U-Net model by Zixuan Zhang, Yike He, Di Hu, Qiang Jin, Manxu Zhou, Zongwei Liu, Hongli Chen, He Wang, Xinchen Xiang

“…Among the seven comparison models, U-Net-FML has the strongest overall performance, highlighting its engineering value for precise detection and efficient analysis of cracks.…”
Get full text

On the Usage of Deep Learning Techniques for Unmanned Aerial Vehicle-Based Citrus Crop Health Assessment by Ana I. Gálvez-Gutiérrez, Frederico Afonso, Juana M. Martínez-Heredia

“…This work proposes an end-to-end solution for leaf segmentation, disease detection, and damage quantification, specifically focusing on citrus crops. …”
Get full text

An intelligent prediction method for rock core integrity based on deep learning by Zhaoxia Hu, Hua Mei, Lei Yu

“…In IDA-RCF, a two-branch feature extraction network is firstly proposed, in which branch one is used to fully extract the complex and variable local detail fissure features by Deformable convolution, and branch two is used to capture the global context information of the rock core images by EfficientViT network based on the self-attention. …”
Get full text

Automated multi-class MRI brain tumor classification and segmentation using deformable attention and saliency mapping by Erfan Zarenia, Amirhossein Akhlaghi Far, Khosro Rezaee

“…This study presents a highly promising approach for the automated classification and segmentation of brain tumors in medical imaging, offering significant advancements for diagnostic imaging clinics and paving the way for more efficient, accurate, and scalable tumor detection methodologies.…”
Get full text

Indoor Mobile Localization in Mixed Environment with RSS Measurements by Zhengguo Cai, Lin Shang, Dan Gao, Kang Zhao, Yingguan Wang

“…This paper proposes an indoor mobile localization scheme with RSS measurements in a mixed LOS and NLOS environment. First, a new efficient composite measurement model is induced and validated, which approximates the complex effects of LOS and NLOS channels. …”
Get full text

Tomato Yield Estimation Using an Improved Lightweight YOLO11n Network and an Optimized Region Tracking-Counting Method by Aichen Wang, Yuanzhi Xu, Dong Hu, Liyuan Zhang, Ao Li, Qingzhen Zhu, Jizhan Liu

“…Accurate and effective fruit tracking and counting are crucial for estimating tomato yield. In complex field environments, occlusion and overlap of tomato fruits and leaves often lead to inaccurate counting. …”
Get full text