DVCW-YOLO for Printed Circuit Board Surface Defect Detection by Pei Shi, Yuyang Zhang, Yunqin Cao, Jiadong Sun, Deji Chen, Liang Kuang

“…To address these challenges, this paper proposes a novel PCB surface defect detection algorithm, named DVCW-YOLO. First, all standard convolutions in the backbone and neck networks of YOLOv8n are replaced with lightweight DWConv convolutions. …”
Get full text

The prognostic significance of epoxide hydrolases in colorectal cancer by Lichao Cao, Ying Ba, Fang Chen, Dandan Li, Shenrui Zhang, Hezi Zhang

“…The Kaplan–Meier method, correlation analysis and random forest algorithm were used to evaluate the prognostic value of EPHX family members for CRC. …”
Get full text

Deep learning techniques for sentiment analysis in code-switched Hausa-English tweets by Yusuf Aliyu, Aliza Sarlan, Kamaluddeen Usman Danyaro, Abdullahi Sani abd Rahman, Aminu Aminu Muazu, Mustapha Yusuf Abubakar

“…This paper proposes an efficient hyperparameter tuning framework and a novel stemming algorithm for the Hausa language. The framework leverages word embeddings to determine the polarity scores of code-mixed tweets and enhances the accuracy of sentiment analysis models in low-resource language. …”
Get full text

Can artificial intelligence and contrast-enhanced mammography be of value in the assessment and characterization of breast lesions? by Lamiaa Mohamed Bassam Hashem, Heba Monir Azzam, Ghadeer Saad Abd El-Shakour El-Gamal, MennatAllah Mohamed Hanafy

“…We aimed to evaluate the accuracy of AI software algorithms in the assessment and characterization of breast lesions compared to CEM. …”
Get full text

On the Choice of System Strength Metrics for the Allocation and Sizing of Synchronous Condensers in Power Grids by Shereefdeen Oladapo Sanni, Olatunji Obalowu Mohammed, Suprava Chakraborty, Ayodele Isqeel Abdullateef, Abdulrahaman Okino Otuoze, Olumoroti Ikotun, Ephraim Bonah Agyekum

“…This study compares two approaches for optimizing SC placement and sizing: SCR-based and network-response short-circuit ratio (NRSCR)-based, a metric that captures dynamic IBG interactions. Applying a genetic algorithm (GA) to the Nigerian power grid as a case study, the SCR-based approach identified two critical points of interconnection (PoIs) requiring 68 MVA of SC capacity, while the NRSCR-based method identified four PoIs, requiring a total of 674 MVA. …”
Get full text

Exploring interconnections among atoms, brain, society, and cosmos with network science and explainable machine learning by Daniele Caligiore, Daniele Caligiore, Anna Monreale, Anna Monreale, Giulio Rossetti, Angela Bongiorno, Giuseppe Fisicaro

“…The parallels between neural and social networks could deepen our understanding of human behavior, while studying cosmic and social systems may reveal shared dynamics in large-scale, interconnected structures. …”
Get full text

Comparing the accuracy of machine learning methods for classifying wild red deer behavior based on accelerometer data by Benjamin Bar-Gera, Pia Anderwald, Alina L. Evans, Thomas Rempfler, Claudio Signer

“…Results We found significant differences in the models’ performances depending on which algorithm, transformation method and combination of input variables was used. …”
Get full text

Skill decay following Basic Life Support training: a systematic review protocol by Andrew Owen, Joseph Alderman, Emily Beesley, Jonathan Hulme, Benjamin Stanley, Thomas Burton, Harriet Percival, Nicholas Coffin

“…Bystander cardiopulmonary resuscitation (CPR) is associated with increased rates of survival to hospital discharge following OHCA, prompting the introduction of several initiatives by the UK government to increase rates of bystander CPR, including the inclusion of Basic Life Support (BLS) teaching within the English national curriculum. While there is clear benefit in this, increasing evidence suggests poor retention of skills following BLS teaching. …”
Get full text

Data-driven prediction of rate of penetration (ROP) in drilling operations using advanced machine learning models by Guoli Huang, Sarah Kanaan Hamzah, Pinank Patel, T. Ramachandran, Aman Shankhyan, A. Karthikeyan, Dhirendra Nath Thatoi, Deepak Gupta, S. AbdulAmeer, Mariem Alwan, Zahraa Saad Abdulali, Mahmood Jasem Jawad, Hiba Mushtaq, Mohammad Mahtab Alam, Hojjat Abbasi

“…Among the models tested, the Random Forest algorithm demonstrated outstanding performance, achieving an R2 of 0.955, a Mean Squared Error (MSE) of 0.119, and an Average Absolute Relative Error (AARE%) of 7.683, highlighting its reliability and robustness in predicting ROP. …”
Get full text

Convergence in key month of phenology-based mangrove species classification using sentinel-2 imagery data: insights from structural and physiological indices by Yangcan Bao, Xiaofeng Lin, Mingming Jia, Zhongyong Xiao, Cuiping Wang, Jiangfu Liao, Yinghui Zhang

“…In this study, a random forest algorithm (RF) and Sentinel-2 time series data were applied using the Google Earth Engine platform. …”
Get full text

Signatures of Six Autophagy‐Related Genes as Diagnostic Markers of Thyroid‐Associated Ophthalmopathy and Their Correlation With Immune Infiltration by Qintao Ma, Yuanping Hai, Jie Shen

“…Six DSGs were identified by three algorithms. They were validated in another independent validation dataset. …”
Get full text

Track Classification and Characteristics Analysis of Northeast China Cold Vortex During the Warm Season by Jin Tong, Yueming Yu, Qiuping Wang, Xulin Ma, Zhaorong Zhuang

“…This study employed ERA5 reanalysis data over 2012–2022 and the optimized K-means clustering algorithm to classify NCCV tracks into five types: (A) eastward-moving dissipative, (B) eastward-moving retrogressive, (C) short-range eastward-moving offshore, (D) long-range eastward-moving offshore, and (E) long-range southeastward-moving offshore. …”
Get full text

Simulation and Spatio-Temporal Analysis of Soil Erosion in the Source Region of the Yellow River Using Machine Learning Method by Jinxi Su, Rong Tang, Huilong Lin

“…By leveraging soil erosion data measured by ¹³⁷Cs from 521 locations and employing the random forest (RF) algorithm, a new soil erosion model was formulated. …”
Get full text

A Hybrid Deep Learning and Improved SVM Framework for Real-Time Railroad Construction Personnel Detection with Multi-Scale Feature Optimization by Jianqiu Chen, Huan Xiong, Shixuan Zhou, Xiang Wang, Benxiao Lou, Longtang Ning, Qingwei Hu, Yang Tang, Guobin Gu

“…This paper proposes a railway worker detection method based on improved support vector machines (ISVM), while using non-local mean noise reduction and histogram equalisation pre-processing techniques to optimise image quality to improve detection efficiency and accuracy. …”
Get full text

A multi-robot collaborative manipulation framework for dynamic and obstacle-dense environments: integration of deep learning for real-time task execution by Afnan Ahmed Adil, Saber Sakhrieh, Jinane Mounsef, Noel Maalouf

“…Path planning is achieved through a sampling-based algorithm that is integrated with the LiDAR data to facilitate precise obstacle avoidance and localization. …”
Get full text

Utilizing Sentinel-2 Remote Sensing for Water Quality Monitoring in Deran Lake, Bosnia and Herzegovina by A. Batina, A. Šiljeg, G. Pedić, M. Parać

“…Chl-a concentrations confirmed oligotrophic conditions, while TSS patterns aligned with known hydrodynamic features such as inflow zones and sediment resuspension areas. …”
Get full text

Chemical Composition, Chemometric Analysis, and Sensory Profile of <i>Santolina chamaecyparissus L.</i> (<i>Asteraceae</i>) Essential Oil: Insights from a Case Study in Serbia and... by Biljana Lončar, Mirjana Cvetković, Milica Rat, Jovana Stanković Jeremić, Jelena Filipović, Lato Pezo, Milica Aćimović

“…Gas Chromatography–Mass Spectrometry (GC–MS) was employed for identifying the essential oil composition, while chemometric techniques like the genetic algorithm (GA), quantitative structure–retention relationship (QSRR) analysis, artificial neural network (ANN), and molecular descriptors were applied to ensure accurate and reliable results for authenticating the oil. …”
Get full text

Enhancement in dynamic range for dual-rotating retarder Mueller matrix polarimetry by Jiongying Lv, Shuan Yao, Nan Zeng, Caizhong Guan, Honghui He

“…In this study, we propose a novel method to generate high dynamic range (HDR) MM images based on a multi-exposure fusion algorithm. By employing an optimal exposure selection strategy for transmission imaging and a multi-exposure weighted averaging strategy for backscattering imaging, the method expands the dynamic range while accurately preserving the polarization information of the samples. …”
Get full text

Federated learning for digital twin applications: a privacy-preserving and low-latency approach by Jie Li, Dong Wang

“…To address these security and privacy threats, this paper proposes the FL-FedDT scheme—a privacy-preserving and low-latency FL method that employs an enhanced Paillier homomorphic encryption algorithm to safeguard the privacy of local device parameters without transmitting data to the server. …”
Get full text

Integrated optimization and coordination of cascaded reservoir operations: Balancing flood control, sediment transport and ecosystem service by Xinmiao Cao, Teng Lin, Jiahui Li, Ting Zhou

“…To address the optimization model, an elite mutation‐based multi‐objective particle swarm optimization (MOPSO) algorithm that integrates genetic algorithms (GA) is developed. …”
Get full text