Future Digital Technologies and Artificial Intelligence

The application of artificial intelligence in large-scale high-end equipment manufacturing projects: the moderating effect on the relationship between corporate culture, advertising investment, and strategic management of Shandong SMEs

2026-03-28T04:21:08+00:00

In view of the rapid development and penetration of artificial intelligence (AI) into the field of manufacturing, the strategic management of small and medium-sized enterprises (SMEs) in large-scale high-end equipment projects is undergoing a new transformation, yet previous studies have not taken artificial intelligence adoption as a boundary condition to examine the influence of corporate culture and advertising investment on strategic management effectiveness. Based on the Resource-Based View (RBV) and Contingency Theory, this study proposes a moderation model and tests it empirically. Questionnaires were distributed to 323 SME managers in Shandong Province, and hierarchical regression analysis and 5,000-resample bootstrapping were used to test the proposed model. The results show that all four hypotheses proposed in this study were verified. Corporate culture and advertising investment positively influence the effectiveness of strategic management. Artificial intelligence adoption plays a significant role in moderating these two relationships, and corporate culture is more important than advertising investment in this regard, since the interaction effect of corporate culture and artificial intelligence adoption on strategic management effectiveness is greater than that of advertising investment and artificial intelligence adoption. Under high levels of artificial intelligence adoption, the slope coefficient of corporate culture on strategic management effectiveness is 2.8 times that of low levels of artificial intelligence adoption. The study provides a new framework for strategic artificial intelligence management that integrates the RBV and Contingency Theory.

Optimization of multi-echelon multi-product supply chains using discrete event simulation

2026-07-01T19:32:12+00:00

This study details the application of a novel multi-echelon, multi-product hybrid supply chain optimization framework known as the Optimizing Known Warehouses (OKW) framework, which consists of mathematical and computer simulation models, to analyze the effects of changes in inventory policies for products delivered by two (2) different case-study manufacturing supply chains. The methods used are the Bayesian optimization algorithm and linear programming to optimize inventory and routing in the supply chains. Furthermore, Arena software was used to develop a discrete event simulation model to compare the current and optimized scenarios of the supply chains. The results show that the optimization framework effectively reduces backorders and increases order fulfillment within the manufacturing supply chains analyzed, and can be easily applied to other Fast-Moving Consumer Goods (FMCG) manufacturing supply chains. For the water bottling supply chain, the optimal inventory policies reduced backorders of the 50cl, 75cl, and 150cl bottled water products by 8.7%, 18.7%, and 34.7%, respectively. For the noodles manufacturing supply chain, backorders for the 70g, 100g, 120g, 180g, and 280g noodle products were reduced by 3.5%, 12%, 20.6%, 7.1%, and 11.9%, respectively. This study provides a procedure for inventory and routing optimization using Bayesian optimization and linear programming, respectively, and a Discrete Event Simulation model for analyzing various supply chain configurations.

Intelligent visual perception beyond classification: a survey of deep learning and foundation models

2026-10-01T15:53:58+00:00

Intelligent visual perception has advanced from traditional image classification to thorough comprehension of objects, scenes, relations, spatial context, and semantic information. This paper surveys the development of intelligent visual perception, particularly focusing on DL and foundation models. This section provides a comprehensive overview of visual recognition, detection, segmentation, and scene understanding, including key methods such as convolutional neural networks, recurrent neural networks, attention mechanisms, encoder-decoder architectures, generative models, and Vision Transformers. The study also explores feature attribution, visual attention, visual reasoning, and multimodal vision-language models, which combine visual and text information for tasks such as visual question answering, captioning, and visual generation. This study examines recent foundation models incorporating vision-language architectures for their transferability, contextual understanding, and generalized perception capabilities. The study also discusses challenges related to computational efficiency, environmental variability, data requirements, robustness, explainability, and real-time deployment. Finally, it contrasts current developments to identify new approaches to scalable, interpretable, multimodal, and human-centric visual intelligence systems.

Comparative evaluation of milling machine tooling fixtures using finite geometry and finite element methods

2026-10-03T09:39:06+00:00

Fixture layout directly affects workpiece stability during milling, but checking several possible locator arrangements with finite element analysis can be time-consuming, especially at the initial design stage. This study examines a milling machine angle plate fixture using a two-stage Finite Geometry (FG) and Finite Element Analysis (FEA) procedure based on the 3–2–1 locating principle. Three locator configurations were developed from the fixture geometry and first assessed using finite geometry. The Effective Support Area and Kinematic Stability Index (KSI) were used to assess the geometric stability of each arrangement, with MATLAB used to carry out the required geometric calculations. The KSI values obtained for Configurations 1, 2, and 3 were 0.01214, 0.01033, and 0.00772, respectively. Configuration 3 was consequently selected for structural assessment. The selected configuration was then analyzed in ANSYS Mechanical under a 10 kN distributed machining load. A maximum von Mises stress of 48.322 MPa and a maximum deformation of 0.015394 mm were obtained. The results show that the geometric assessment provided a means of screening the three locator arrangements before the more detailed finite element analysis was carried out. The study therefore demonstrates the use of FG as a preliminary assessment stage, followed by FEA for structural verification of the selected fixture configuration.

Performance comparison of ML algorithms for liver disease prediction

2026-10-12T14:59:07+00:00

Liver disease is a leading cause of mortality throughout the world. Numerous lives may be saved if it can be detected in its early stages. Therefore, early detection of liver disease is crucial. This study aims to find a reliable ML model that can predict liver disease development using demographic and clinical data. This research explores several ML methods and introduces the most promising ones, Random Forest (RF) and Light Gradient Boosting Machine (LightGBM), for classification. The Indian Liver Patient Dataset (ILPD) is preprocessed by encoding categorical data, imputing missing values, removing duplicates and noise, applying Min-Max scaling, and balancing the data with SMOTE; this yields a dataset of 583 cases with 11 clinical and demographic characteristics. Models are assessed using F1-score, recall, accuracy, and precision, with an 80:20 stratified train-test split. While the proposed LightGBM model achieves a 99.8% ACC rate, a 99.9% PRE rate, a 99.5% REC rate, and a 99.8% F1-score (F1), the experimental results show that the RF model achieves a 99.6% PRE rate, a 99.7% REC rate, and a 99.6% F1-score (F1). The findings confirm that the proposed models achieved high ACC and reliability in predicting liver disease, with LightGBM delivering the highest ACC and PRE.