Advances in image editing models have enabled intelligent, rapid fashion customization. Vision-guided editing models, in particular, offer more precise and flexible control over fine-grained garment attributes. However, existing methods are limited to coarse-grained edits and fail to achieve attribute-level manipulation, thereby restricting the flexibility and composability required in fashion customization. To address these issues, this paper proposes a Vision-Guided Fashion Fine-Grained Attribute Editing (VFFAE) framework, which leverages visual references to achieve customized editing of both style and structure in fine-grained garment regions. The VFFAE framework involves three key components: (1) a text-driven fashion fine-grained attribute segmenter that incorporates garment keypoints as spatial priors and applies deformable attention to enhance spatial perception, with CLIP-based multimodal alignment for accurate segmentation; (2) a clothing attribute disentanglement module based on orthogonal subspace projection of CLIP embeddings, enabling zero-shot explicit separation of style and structure attributes; and (3) a conditional diffusion pipeline that leverages disentangled representations of segmented regions to fine-tune a pretrained Stable Diffusion model under classifier-free guidance, enabling controllable attribute editing. Experiments on multiple public datasets show that VFFAE surpasses state-of-the-art methods, and ablation analyses confirm the effectiveness of its segmentation and disentanglement modules, establishing it as a practical solution for high-fidelity attribute-level fashion customization.

Enhancing large language models (LLMs) with external knowledge base retrieval in the fashion manufacturing industry can provide more reliable technical support and decision-making assistance, significantly improving process control and boosting intelligent production efficiency. However, the field of fashion manufacturing involves highly specialized terminology, logically complex technical knowledge, and intricate query tasks. Existing simple query-matching techniques often return a large number of contextually loose and redundant document chunks, severely impacting the model's understanding and response quality. To address this issue, this article proposes a retrieval optimization framework based on a dynamic capsule routing network with embedded semantic graph (SGDCR), which models semantic relations among multiple retrieved documents by simulating a team collaboration mechanism. Specifically, the framework consists of two steps: filtering and reranking. First, a capsule routing mechanism embedded in a semantic association graph dynamically captures complex contextual relationships among coarse-grained document blocks, learns contribution scores for multiple documents, and filters irrelevant or redundant documents based on ranking. Subsequently, the filtered documents are matched with the query through deep semantic similarity measurement, and the documents are reranked by integrating relevance scores and contribution scores and generating efficient, accurate, and contextually coherent document prompts. Experimental results on publicly available dense open-domain QA datasets and a constructed fashion manufacturing process QA dataset demonstrate the effectiveness and superiority of the proposed method over existing reranking approaches in the fashion manufacturing knowledge QA system.

Production logistics (PL) is essential for linking manufacturing activities through the timely transportation of work-in-progress items. However, increasing product customization, a broader range of materials, and more complex spatial-temporal constraints among resources have made PL orchestration significantly more challenging. To address these issues, we propose the cyber-physical computer (CPC), an intelligent edge terminal designed to coordinate operators, vehicles, robots, and materials involved in PL tasks. The CPC continuously collects Internet of Things (IoT) signals and extracts semantic-level relationships among PL resources, constructing a resource semantic graph that forms the basis for cyber-physical twinning. Upon receiving a new resource request, the CPC identifies relevant nodes to generate a corresponding spatial-temporal subgraph and performs subgraph reasoning by integrating contextual information with its local knowledge memory. Informed by task-specific insights distilled from prior expert decisions, the CPC recommends a prioritized allocation plan to the manager and enables interactive refinement using a large language model. To validate the proposed approach, we conduct comparative experiments across four simulated environments representing typical PL scenarios with varying degrees of dynamicity, along with a real-world case study at an air conditioning equipment manufacturer. Results demonstrate that the CPC, empowered by subgraph reasoning, outperforms existing methods in punctuality rate and delivery distance.

With increasing pressure from customized demands, discrete manufacturing systems face challenges due to fluctuating resource requirements. These challenges hinder the synchronization of production logistics (PL), which is essential for coordinating resources and ensuring smooth production. Poor synchronization will result in resources waiting on each other, leading to delays and idle time. Accordingly, this paper proposes ChatSync, a framework leveraging large language model (LLM) and spatial-temporal knowledge reasoning to optimize resource allocation, delivery, and monitoring in industrial applications, particularly within the Industrial Internet of Things (IIoT) environment. First, the resource spatial-temporal graph (RSTG) is constructed by integrating real-time IIoT data and expert operational experience, enhancing the knowledge base of LLM through cross-domain knowledge fusion. Second, graph-based reasoning optimization is presented, incorporating spatial-temporal, contextual, and relational reasoning mechanisms, enabling LLM to achieve credible and responsible analysis and decision-making. Third, the PL-oriented ChatSync framework with knowledge and reasoning engines is proposed, supporting chat-based interactions for resilient resource allocation, personalized suggestion, and precise traceability. A case study in air conditioning manufacturing demonstrates that ChatSync outperforms existing benchmark methods in various PL phases, achieving a delivery punctuality rate of 91.2%.

This paper explores the application of Cyber-physical Internet (CPI) in prefabricated construction logistics to enhance module shipment efficiency through a new scheduling framework. Drawing parallels between the TCP/IP model’s data transmission process and the physical shipment of construction modules, the study identifies inefficiencies in current logistics practices, including obstructed information sharing and collaboration among practitioners. To address these challenges, the paper proposes a suite of CPI protocols, like the internet protocols, to standardize information sharing, scheduling & routing rules among logistics practitioners and nodes. Based on the CPI protocols, a hierarchical and decentralized shipment decision framework is proposed to govern how the routing decisions and shipment scheduling decisions are made at each logistics node. A set of numerical experiments is conducted based on a real-life shipment case of construction modules in the Greater Bay Area to exhibit the great efficiency and resilience of the proposed protocol-based decision framework. And a case study is designed to show how the proposed protocols influence the decision process. The study’s contributions are threefold: demonstrating CPI application in a logistics scenario, developing protocols for efficient information sharing, and proposing a new decision framework for resilient and timely scheduling in complex logistics networks.

Unsupervised domain adaptation (UDA) assumes a labeled source domain and an unlabeled target domain. It aims to train a target domain model by transferring the knowledge from source domain to target domain. With the same goal, source-free domain adaptation (SFDA) only uses the trained source model and target domain data for target model training, which is beneficial for data transmission and data privacy protection etc. Existing SFDA methods suffer from domain shift, resulting in unsatisfactory results. Different from existing methods, we eliminate the domain shift from the domain style perspective. Specifically, we propose a novel method named Adapting to the Enhanced Style (AES). We first increase the diversity of target domain style by style enhancement, then a contrastive loss is used to adapt to the diverse generated styles by requiring consistent feature representations. This process forces our classification model adapting to target domain style, thus increasing the robustness of the model. We conduct extensive experiments on standard benchmarks, and the results show the superiority of our method.

In perishable supply chain logistics, even a small departure from the required storage conditions at any distribution link can compromise the quality of transported products, such as food, pharmaceuticals, and other bioproducts, resulting in big losses for the businesses involved or even threats to public health. To enhance quality management (QM) and consumer confidence, an edge-cloud blockchain and Internet of Everything (IoE)-enabled QM platform is proposed to achieve low delay and rapid response for sensor data acquisition, authentication, consistency, and transparency in cold supply chain logistics. Then, we design an adaptive data smoothing and compression (ADSC) mechanism to reduce IoE data size, and analyze and store those data in the edge gateways with limited computation and storage capacity for correctly characterizing logistics operations and transactions. Moreover, to ensure the data integrity during last-mile delivery, the mobile edge gateway is adopted when the goods are temporarily off the communication range of the fixed edge gateway in the truck. Then, we propose a synchronization engine with a formal workflow applied at mobile and fixed edge gateways where data blocks are generated, validated, and synchronized with the cloud. Finally, a real-life case study on vaccine logistics is introduced to verify our proposed approach with results presented.

Acquiring the real-time spatial–temporal information of manufacturing resources holds the promise to enable efficient operation in factory logistics. This article proposes a system architecture using industrial Internet of Things and digital twin technologies to fulfill spatial–temporal traceability and visibility with seamless cyber-physical synchronization for finished goods logistics in the workshop. A long short-term memory network-enabled genetic indoor-tracking algorithm (GITA) is developed to locate product trolleys via a bluetooth low energy technology, with ultra-wideband applied to sample labeling in the training stage. It is enlightened by genetics to achieve self-adapting online for the long-term performance. A feature selection method based on received signal strength indicator is designed to deal with signal multipath fading and streamline the learning process. In addition, the spatial–temporal information obtained is leveraged to activate location-based services that can help promote operational efficiency. Moreover, a real-life case study is carried out in a world-leading computer manufacturer’s factory to illustrate the viability and practicality of the system and methods proposed, with hardware and software developed. By comparison, the GITA shows superiority over existing approaches despite various noises under the manufacturing scenario, attaining a location precision of about 2 m with a 98.12% accuracy.

The communication infrastructure is an important part to provide the reliability for energy management in the smart grid environment. With the aim of reducing the infrastructure cost for residential energy management, this article introduces a more complex multihop wireless remote metering network model. A novel evolutionary aggregation algorithm (EAA) is proposed to obtain the minimum number and locations of the local data centers (powerful nodes) in a 2-hop wireless remote metering network which has an arbitrary number of smart meters (ordinary nodes) with arbitrary transmission ranges. In the novel 2-hop EAA, the article designs and implements two novel adaptive operations (the switch operation and the shuffle operation) to improve the algorithm performance. Then the article extends the 2-hop EAA method to a more generic n-hop EAA which could obtain the optimal result in an n-hop (n > 2) smart meter network. Comprehensive case studies and numerical statistical analyses demonstrate that the EAA could efficiently achieve the optimal results in an n-hop (n> = 2) smart meter network environment; and the novel switch and shuffle operations could efficiently improve the performance of the evolutionary algorithm. The connectivity of the smart meter network could be fulfilled with the minimum number of the powerful nodes, from which the infrastructure cost for residential energy network could be minimized.

The order picking process has been considered as the most time-consuming and costly activity in warehouse management. Efficient location management, including product location management and storage location assignment management, serves as the key to reducing product searching time and traveling time during the process. This research is motivated by a real-life industrial case, which is from a forklift manufacturer that encountered the underperformance in warehouse management. Excessive time was consumed in searching and picking the forklift in finished product warehouse, which thus led to great waste in resources and even the postponement of delivery. To solve this problem, this paper first presents the details about the problem and related processes. A conceptual model of cloud forklifts and its life cycle oriented management platform is then proposed. Accordingly, a prototype system named cloud forklift warehouse management system (CFWMS) is built based on the proposed model. The suggested model and system architecture is designed and developed with the commonality for general warehousing processes, and therefore can be easily configured and applied to any general warehouse environment. Results and details of implementation for the real-life case are also provided to demonstrate the validity of the proposed model and CFWMS.