Xiusen Wang^1,*, Zheng Fang², Jie Chen^2,*

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.088952 - 15 September 2026

Abstract Complex networks in cyber–physical, transportation, and information infrastructures operate under topology variations, unmeasured disturbances, and limited actuation. This paper proposes robust disturbance-aware data-driven decision control (R-D3C), which couples a sliding-window graph-regularized estimator, disturbance-envelope adaptation, sparse intervention allocation, receding-horizon optimization, and a robust safety projection. The theory directly bounds the dynamic prediction regret of the implemented sliding-window estimator. A checkable sufficient condition for safety-filter feasibility is coupled with an explicit slack-and-backup fallback when the strict projection is infeasible. Practical input-to-state stability and sparse-allocation risk reduction are established. The nominal comparison uses 30 paired runs with standard More >

Xiaolei Yin, Zihan Wang, Sanfeng Zhang^*, Shouwei Li^*

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.088083 - 15 September 2026

Abstract On-chain risky address identification is an important task in blockchain security analysis and digital asset risk management. In practical on-chain risk control, however, risky addresses are usually far fewer than benign ones. Fund flows also follow complex propagation paths and strict temporal orders, which makes it difficult for existing methods to handle class imbalance, structural semantic modeling, and information leakage under temporal split settings at the same time. To address these challenges, this paper proposes AMLHunter, an on-chain risky address identification method based on temporally consistent transaction semantic constraints and generative graph augmentation. AMLHunter first… More >

Long Yu^1,2,3, Ma Zhu^1,2,3,*, Xu Wang^1,2,3, Yang Pei^1,2,3, Chunfang Yang^1,2,3

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.087636 - 15 September 2026

Abstract Cross-view geo-localization (CVGL) estimates the location of a street-level image by retrieving its matching GPS-tagged satellite tile. Semi-supervised methods reduce the need for dense annotations by mining pseudo labels, but most of them keep only one positive reference for each query. In real-world galleries, several overlapping satellite tiles may cover the same ground location. As a result, valid matches can be discarded as negatives, which gives the model conflicting supervision. To address this problem, we propose DMP-Geo, a semi-supervised cross-view geo-localization method that mines multiple positives for each query from unlabeled data. A bird’s-eye fusion More >

Hao Sun, Xiaohong Ding^*, Min Xiong, Heng Zhang

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.087308 - 15 September 2026

Abstract Designing two-dimensional anisotropic mechanical metamaterial unit cells from prescribed effective properties remains a challenging inverse problem, particularly when directional stiffness and material usage need to be controlled simultaneously. In this work, a data-driven conditional diffusion framework is developed for generating unit-cell structures with target effective elastic moduli and volume fractions. A structure–property database containing 57,000 binary unit-cell images is first established through a random target-property-driven inverse homogenization method. The effective elastic moduli in the x and y directions, together with the volume fraction, are used as conditional labels, denoted as (E_x, E_y, V). A conditional denoising diffusion probabilistic… More >

Weijia Liu¹, Junwen Deng², Hao Li³, Zhenyong Zhang^3,*

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.086022 - 15 September 2026

Abstract With the rapid development of artificial intelligence technologies in machine learning-as-a-service (MLaaS), deep learning-based intelligent models have demonstrated high value in applications such as trend prediction and risk assessment. However, MLaaS data are typically highly sensitive and contain private information. In cross-institutional collaborative modeling scenarios, different departments and local centers often hold partial, heterogeneous data resources on MLaaS platforms. Given data security, privacy, and compliance requirements, raw data are difficult to share directly, which makes it challenging to apply centralized model training methods. This paper proposes FedE, a multi-precision, multi-source, heterogeneous privacy-preserving federated learning training More >

Yusra Mansoor¹, Huma Jamshed^1,*, Mohammed Khouj², Muhammad I. Masud^2,*, Urooj Waheed¹, Abdul Wahid Memon³, Najeeb Ur Rehman Malik^4,*, Touqeer Ahmed Jumani⁵

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.085975 - 15 September 2026

Abstract The increasing demand for sustainable and energy-aware agricultural practices due to climate change, limited natural resources, and increasing food requirements has accelerated the adoption of Internet of Things (IoT) and machine learning (ML) technologies in smart farming. This study proposes a solar-powered IoT and ML-based framework for energy-aware crop suitability prediction in precision agriculture. The system employs low-power IoT sensors to continuously monitor important environmental and soil parameters, including temperature, humidity, soil moisture, soil temperature, heat index, nitrogen (N), phosphorus (P), and potassium (K) levels. To reduce dependence on conventional energy sources, the framework is… More >

Chung-Pao Lin¹, Yi-You Hou^2,*, Teh-Lu Liao¹

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.085788 - 15 September 2026

Abstract Smart grids (SG) integrate multiple network entities to achieve automation, but their interconnected nature also exposes communication networks to various security threats, such as replay, tampering, and man-in-the-middle (MITM) attacks. Existing encryption frameworks for smart grid edge devices often suffer from high computational complexity or lack of dynamic key management, leading to key leakage risks and communication bottlenecks. To address these challenges, this research proposes a lightweight end-to-end secure communication architecture specifically designed for smart grid power monitoring. This framework employs the Message Queuing Telemetry Transport (MQTT) protocol as the asynchronous communication backbone, effectively alleviating… More >

Ziyong Li^1,*, Yusheng Xia¹, Junfei Li², Le Tian², Xinglong Pei²

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.085191 - 15 September 2026

Abstract Multipath load balancing can effectively improve network throughput and reliability by aggregating the available bandwidth of multiple paths. However, existing load balancing schemes including Equal-Cost Multi-Path forwarding (ECMP), Weighted-Cost Multi-Path forwarding (WCMP) or LetFlow may lead to significant performance degradation due to hash conflicts and only target fixed symmetric topologies (e.g., Fattree). Flowlet switching has been proven to be a fine-grained load balancing technique, but remains elusive for widespread deployment. The emergence of network programmability including the control plane and data plane provides a new insight for the management of multipath load balancing. To achieve… More >

Sheraz Ali Hassan¹, Hamid Masood Khan¹, Muhammad Javed¹, Mohd Faizal Bin Yusof², Jamil Abedalrahim Jamil Alsayaydeh^3,*, Fida Muhammad Khan⁴, Inam Ullah^5,*

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.084547 - 15 September 2026

Abstract The increasing frequency of natural and human-induced disasters has intensified the need for reliable methods to identify crisis-relevant information from Twitter/X streams. However, tweets are often short, noisy, informal, ambiguous, and context-dependent, making disaster-related tweet classification challenging. This study proposes a lightweight attention-enhanced hybrid deep learning framework for binary disaster-related tweet classification. The framework integrates CNN-based local feature extraction, recurrent contextual modeling, static pre-trained word embeddings, class weighting, training-only data augmentation, and learned neural attention. Two architectures, CNN–LSTM–Attention and CNN–BiGRU–Attention, are evaluated on the labeled Kaggle Disaster Tweets dataset using a leakage-aware protocol in which More >

Yong Zheng^*

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.084278 - 15 September 2026

Abstract Recommender systems can alleviate information overload by producing item recommendations tailored to user preferences. The performance usually relies on rich user-item interaction data; however, missing entries introduce sparsity that substantially degrades performance. Early work primarily treated rating imputation as a preprocessing mechanism for mitigating sparsity and alleviating cold-start issues through explicit matrix completion. More recently, missing-data estimation has evolved beyond static preprocessing toward broader inference-oriented paradigms, including pseudo-label estimation, counterfactual inference, and debiasing mechanisms integrated directly into the learning objective. In this paper, we present a structured review of rating imputation and inference-oriented missing-data estimation… More >