Le Wang¹, Bing Xu^1,*, Peng Liu², En Yuan¹

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.070794

Abstract Deep learning has been recognized as an effective method for indoor positioning. However, most existing real-valued neural networks (RVNNs) treat the two constituent components of complex-valued channel state information (CSI) as real-valued inputs, potentially discarding useful information embedded in the original CSI. In addition, existing positioning models generally face the contradiction between computational complexity and positioning accuracy. To address these issues, we combine graph neural network (GNN) with complex-valued neural network (CVNN) to construct a lightweight indoor positioning model named CGNet. CGNet employs complex-valued convolution operation to directly process the original CSI data, fully exploiting… More >

Yunhao Yu¹, Boda Zhang¹, Meiling Dizha¹, Ruibin Wen¹, Fuhua Luo¹, Xiang Guo¹, Zhenyong Zhang^2,*

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.070577

Abstract Load frequency control (LFC) is a critical function to balance the power consumption and generation. The grid frequency is a crucial indicator for maintaining balance. However, the widely used information and communication infrastructure for LFC increases the risk of being attacked by malicious actors. The dynamic load altering attack (DLAA) is a typical attack that can destabilize the power system, causing the grid frequency to deviate from its nominal value. Therefore, in this paper, we mathematically analyze the impact of DLAA on the stability of the grid frequency and propose the network parameter regulation (NPR)… More >

Abdullah Alourani¹, Mehtab Alam^2,*, Ashraf Ali³, Ihtiram Raza Khan⁴, Chandra Kanta Samal²

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.070161

Abstract The evolution of cities into digitally managed environments requires computational systems that can operate in real time while supporting predictive and adaptive infrastructure management. Earlier approaches have often advanced one dimension—such as Internet of Things (IoT)-based data acquisition, Artificial Intelligence (AI)-driven analytics, or digital twin visualization—without fully integrating these strands into a single operational loop. As a result, many existing solutions encounter bottlenecks in responsiveness, interoperability, and scalability, while also leaving concerns about data privacy unresolved. This research introduces a hybrid AI–IoT–Digital Twin framework that combines continuous sensing, distributed intelligence, and simulation-based decision support. The… More >

Moneerah Alotaibi^*

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.069195

Abstract Advanced traffic monitoring systems encounter substantial challenges in vehicle detection and classification due to the limitations of conventional methods, which often demand extensive computational resources and struggle with diverse data acquisition techniques. This research presents a novel approach for vehicle classification and recognition in aerial image sequences, integrating multiple advanced techniques to enhance detection accuracy. The proposed model begins with preprocessing using Multiscale Retinex (MSR) to enhance image quality, followed by Expectation-Maximization (EM) Segmentation for precise foreground object identification. Vehicle detection is performed using the state-of-the-art YOLOv10 framework, while feature extraction incorporates Maximally Stable Extremal… More >

Kwok Tai Chui^1,*, Varsha Arya¹, Brij B. Gupta^2,3,4,*, Miguel Torres-Ruiz⁵, Razaz Waheeb Attar⁶

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.068842

Abstract Parkinson’s disease (PD) is a debilitating neurological disorder affecting over 10 million people worldwide. PD classification models using voice signals as input are common in the literature. It is believed that using deep learning algorithms further enhances performance; nevertheless, it is challenging due to the nature of small-scale and imbalanced PD datasets. This paper proposed a convolutional neural network-based deep support vector machine (CNN-DSVM) to automate the feature extraction process using CNN and extend the conventional SVM to a DSVM for better classification performance in small-scale PD datasets. A customized kernel function reduces the impact… More >

Yağmur Yılan, Ahad Beykent^*

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.068440

Abstract Accurate short-term electricity price forecasts are essential for market participants to optimize bidding strategies, hedge risk and plan generation schedules. By leveraging advanced data analytics and machine learning methods, accurate and reliable price forecasts can be achieved. This study forecasts day-ahead prices in Türkiye’s electricity market using eXtreme Gradient Boosting (XGBoost). We benchmark XGBoost against four alternatives—Support Vector Machines (SVM), Long Short-Term Memory (LSTM), Random Forest (RF), and Gradient Boosting (GBM)—using 8760 hourly observations from 2023 provided by Energy Exchange Istanbul (EXIST). All models were trained on an identical chronological 80/20 train–test split, with hyperparameters More >

John Hordines¹, Shirley Ge², Dima Raskolnikov¹, Alexander C. Small¹, Kara L. Watts^1,*

Canadian Journal of Urology, DOI:10.32604/cju.2025.065988

Abstract Background: The healthcare industry contributes nearly 5% of worldwide carbon emissions. In an effort to mitigate this impact, urology practices can take steps to reduce their carbon footprints. We conducted a systematic review which aimed to summarise the current literature on the environmental impact of urologic-related care. Methods: A systematic literature review evaluating the impact of urologic procedures, telehealth and conferences/interviews was conducted on PubMed and Cochrane databases using a Boolean search strategy and the following search terms: urology, planetary health, environmental impact, carbon emissions, carbon footprint, and waste. Full-text articles published in English were… More >

Zhonghao Wang^1,2, Xin Liu^1,2,*, Changhua Yue³, Haiwen Yuan⁴

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.071813

Abstract To address critical challenges in nighttime ship detection—high small-target missed detection (over 20%), insufficient lightweighting, and limited generalization due to scarce, low-quality datasets—this study proposes a systematic solution. First, a high-quality Night-Ships dataset is constructed via CycleGAN-based day-night transfer, combined with a dual-threshold cleaning strategy (Laplacian variance sharpness filtering and brightness-color deviation screening). Second, a Cross-stage Lightweight Fusion-You Only Look Once version 8 (CLF-YOLOv8) is proposed with key improvements: the Neck network is reconstructed by replacing Cross Stage Partial (CSP) structure with the Cross Stage Partial Multi-Scale Convolutional Block (CSP-MSCB) and integrating Bidirectional Feature Pyramid More >

Ruoxue Cai^1,#, Shuyi Hu^2,#, Feiyang Li², Huanhuan Sha^3,*, Guoren Zhou^2,*, Ying Fang³

Oncology Research, DOI:10.32604/or.2025.070893

Abstract Objective: To determine whether immunotherapy can bring new hope for patients with limited-stage small-cell lung cancer (LS-SCLC). We conducted this retrospective study to evaluate whether immunotherapy can achieve better efficacy in LS-SCLC patients. Methods: We evaluated 122 LS-SCLC patients who received concurrent chemoradiotherapy (CCRT) or sequential chemoradiotherapy (SCRT) (Group A) and immunotherapy combined with CCRT/SCRT followed by immunotherapy (Group B), to assess the objective response rate (ORR), disease control rate (DCR), and progression-free survival (PFS). Factors affecting prognosis were also explored using Cox analysis. The prognosis of patients with type 2 diabetes and patients with… More >

Lv Ling^1,#, Minying Lu^2,#, Ling Ye³, Yuanhang Chen², Sheng Lin², Jun Yang², Yu Rong^2,*, Guixiong Wu^4,*

Oncology Research, DOI:10.32604/or.2025.069889

Abstract Background: A significant proportion of patients still cannot benefit from existing targeted therapies and immunotherapies, making the search for new treatment strategies extremely urgent. In this study, we combined integrate public data analysis with experimental validation to identify novel prognostic biomarkers and therapeutic targets for lung adenocarcinoma (LUAD). Methods: We analyzed RNA and protein databases to assess the expression levels of cytochrome C oxidase 5B (COX5B) in LUAD. Several computational algorithms were employed to investigate the relationship between COX5B and immune infiltration in LUAD. To further elucidate the role of COX5B in LUAD, we utilized… More > Graphic Abstract