Articles in this Volume

Research Article Open Access
A Survey on Resource Scheduling and Optimization for Space‑Air‑Ground Integrated Communication‑Sensing‑Computation Networks
Article thumbnail
The development of sixth generation (6G) communications is aimed at achieving global connectivity, covering oceans and remote areas with limited ground infrastructure. With the integration of sensing, communication and computing (ISCC) technology, the space-air-ground integrated network (SAGIN) is evolving from a simple data transmission channel to an intelligent task processing platform. This paper uses a narrative review method to analyze the evolution path of resource orchestration technology in heterogeneous environments, and focuses on mathematical programming and data-driven intelligent methods to optimize resources. The existing research is classified according to the method system. This paper also examines the architecture paradigm, multi-dimensional resource modeling and algorithm system. Studies have shown that static methods such as Lagrangian dual decomposition and block coordinate descent provide the necessary performance benchmarks, and deep reinforcement learning can achieve fast response in high mobility links. In addition, this paper discusses the potential of large language model (LLM) as a semantic interpreter, which can accelerate the process of parsing task requirements into technical constraints in specific applications. This study provides a methodological reference for achieving task-centered connectivity, and believes that a hybrid framework that combines the accuracy of deterministic methods and the adaptability of learning methods is a feasible development direction for future space infrastructure.
Show more
Read Article PDF
Cite
Research Article Open Access
Deep Learning-Based Channel Equalization for Visible Light Communication Systems
Visible light communication (VLC) gets increasing attention with the continuous advancement of technology. In contrast to conventional wireless networks, VLC possesses numerous innovative advantages. It has an abundant optical spectrum with immunity to radio-frequency interference. More importantly, its compatibility with existing lighting infrastructure demonstrates its broad applicability. However, high-speed VLC systems still need to address numerous challenges during communication such as limited LED bandwidth, inter-symbol interference, device nonlinearity, and receiver noise. Due to the above-mentioned factors, the channel equalization becomes an important physical-layer function. This paper aims to clarify the strengths and limitations of different deep learning-based channel equalization methods with cross-method comparison. Meanwhile, finds suitable application scenarios for different VLC systems. This review explores neural-network architectures including artificial neural networks, convolutional neural networks, long short-term memory networks, and hybrid/model-driven structures. Finally, it also illustrates the importance of lightweight designs. The analysis shows that no single architecture is optimal for all VLC conditions. ANN is effective for nonlinear mapping, CNN is suitable for local feature extraction, while LSTM performs better for channel memory and inter-symbol interference.
Show more
Read Article PDF
Cite
Research Article Open Access
Design of an Automated SQL Injection Detection Tool for Web Applications
Article thumbnail
World Wide Web (Web) applications have become an important interface for network services. However, the direct connection among user input, business logic, and database operations has also increased security risks. SQL injection vulnerabilities remain an important issue affecting Web application security. To address the low efficiency and repetitive nature of traditional manual detection, this paper designs an automated SQL injection vulnerability detection tool for Web applications. By analyzing the principles of SQL injection and common attack types, a detection process consisting of parameter extraction, payload construction, request transmission, response analysis, and vulnerability confirmation is established. The tool is tested in experimental environments involving MySQL, a Content Management System (CMS), and Damn Vulnerable Web Application (DVWA). Experimental results show that the tool can identify different types of SQL injection vulnerabilities based on characteristics such as page content, error messages, response length, and response time. It can improve vulnerability detection efficiency and the consistency of result interpretation, providing a useful reference for Web application security testing.
Show more
Read Article PDF
Cite
Research Article Open Access
A Data-Driven Analysis of Housing Consumption Patterns: Evidence from King County
Article thumbnail
Housing is one of the biggest expenses for most households, so changes in how people consume housing can tell us a lot about broader trends in consumption and upgrading. This paper uses a dataset of housing sales in King County, Washington, to explore what factors influence housing prices and what these patterns say about consumer behaviour. The analysis uses descriptive statistics, correlation analysis, and multiple linear regression to identify the key drivers of housing prices. The results show that living area (r = 0.702) and waterfront status are the strongest predictors of price, followed by property grade and view quality. However, the year the house was built does not have a strong effect on price once other factors are accounted for, which suggests that consumers care more about quality and location than about whether a property is brand new. These findings suggest that housing consumption upgrading is less about buying newer houses and more about buying better houses, which has more space, better views, and higher quality construction.
Show more
Read Article PDF
Cite
Research Article Open Access
In Her Purse: Designing a Benefits Navigation Platform for Incomplete and Sensitive Disclosures
Article thumbnail
Public assistance is organized by program, while people seeking help often describe overlapping needs without knowing which agency or eligibility category applies. In Her Purse is a deployed web platform that accepts a plain-language description and optional profile information to search approximately 4,489 official U.S. assistance listings. This paper examines its Eligibility Matcher as a design for navigation across housing, income, education, employment, and other support domains. The matcher combines semantic retrieval with language-model analysis, presents criteria that appear satisfied separately from those requiring clarification, and requires neither an account nor a complete profile. A descriptive evaluation used thirty written personas situated in economic abuse, including five Spanish- or Chinese-language inputs. The system returned 297 listing instances representing 131 distinct programs, with a reported mean of 3.9 need domains per persona. The evaluation also exposed organizational funding notices among individual-facing results and lower confidence labels for incomplete and non-English inputs. These results establish output coverage in the tested scenarios, not eligibility accuracy, user benefit, or safety. The paper contributes an implemented navigation approach and an account of the design problems that remain when broad program retrieval must support decisions made with limited information.
Show more
Read Article PDF
Cite
Research Article Open Access
Supervised Contrastive Learning for Cross-Load Bearing Fault Diagnosis with Limited Training Labels
Article thumbnail
Vibration-based fault diagnosis requires annotated examples that may not be easy to come by in service. This paper compares the effectiveness of supervised contrastive pretraining to cross-entropy training using the same compact convolutional encoder and 40 recordings of bearings from Case Western Reserve University. Motor load data with 0 and 1 hp load provided the training set, 2 hp provided the validation data, and 3 hp the test set. Five random seeds were evaluated at three training budgets of 5, 10 and 20 examples per class. A separate fixed validation set with 944 labeled windows was used to select checkpoints and was excluded from the budgets above. Linear classification on contrastively pretrained embeddings resulted in higher mean test accuracy and macro-F1 score compared to cross-entropy training at all three budgets. The biggest improvement came at a budget of 10 windows/class: accuracy increased from 84.81% to 89.22% and macro-F1 score from 84.62% to 89.24%. Recall for ball faults was primarily responsible for the increase. These results support the effectiveness of complete contrastive training based on this cross-load test scheme but do not isolate the effect of the loss or establish performance on other machines.
Show more
Read Article PDF
Cite
Research Article Open Access
An Interpretable Uplift Modeling Framework for Customer Churn Intervention Decision-Making
Article thumbnail
Customer churn challenges subscription-based industries, especially telecommunications. Traditional churn prediction identifies high-risk customers but cannot determine who will respond to retention campaigns. This paper proposes an interpretable decision support framework integrating predictive modeling, SHapley Additive exPlanations (SHAP) interpretation, and causal uplift analysis. An XGBoost classifier predicts churn probability on the public Telco dataset, while SHAP reveals tenure, contract type, and monthly charges as key drivers with nonlinear and interaction effects. Four uplift models—S-Learner, T-Learner, X-Learner, and Uplift Random Forest—are compared on a held-out test set using the Area Under the Uplift Curve (AUUC). The X-Learner performs best, achieving an AUUC of 0.724. A cost-sensitive simulation shows that targeting customers with high uplift scores improves expected profit substantially over treating all at-risk customers. The framework is implemented in a Streamlit dashboard, offering managers an actionable tool for churn prevention and shifting churn management from reactive prediction to proactive decision-making.
Show more
Read Article PDF
Cite
Research Article Open Access
From "Birds of a Feather" to Data Insights: The Principles, Methods and Applications of Hierarchical Clustering Algorithms
Article thumbnail
Cluster analysis aims to group similar objects into the same cluster. Hierarchical clustering, as an important method, does not produce a single grouping result but instead constructs a clustering tree that simultaneously presents the grouping structure of the data at different levels of granularity. This paper focuses on hierarchical clustering algorithms. Using a literature review approach, it outlines the basic principles of hierarchical clustering, its two construction approaches, the algorithmic workflow exemplified by AGNES, and linking methods such as single linkage, complete linkage, average linkage, and Ward's method. It also reviews their applications in fields such as bioinformatics, image segmentation, text clustering, and business analytics. The results indicate that hierarchical clustering does not require a predefined number of clusters and offers high interpretability, however, it is computationally complex, its merging decisions are irreversible, and it is sensitive to noise. Integrating hierarchical clustering with partitioning methods such as K-means, or with improved hierarchical algorithms such as BIRCH and CURE, represents an important direction.
Show more
Read Article PDF
Cite
Research Article Open Access
Security Indexing Coding under the Eavesdropper Model: A Review of Capacity Boundaries and Secure Indexing Methods
With 5G and Internet technology developing quickly, broadcast and multicast communications are widely applied in many scenarios such as the Internet of Vehicles, edge distributed networks and group transmission for the Internet. Wireless broadcast channels are open, but transmitted signals are easy to intercept and pose a risk of data leakage. This study focuses on a survey of secure index encoding. This work defines the secure index encoding model, adversary model, strong security and weak security. Based on the above, it discusses how to use and where to use linear coding and random linear coding. Through analysis, this paper find that secure index encoding also have some troubles, like inaccurate minimum rank, difficulty in solving optimal coding solution and hard to achievement. This paper reviews the theoretical framework of secure index encoding based on existing research, which can provide a reference for more in-depth research in the future.
Show more
Read Article PDF
Cite
Research Article Open Access
Variable Step-Size LMS-Based Anti-Jamming Algorithm for Industrial IoT Communications over 2.4 GHz ISM Band
Article thumbnail
Industrial Internet of Things (IIoT) systems deployed in factory environments face severe narrowband interference in the 2.4 GHz ISM band, where ZigBee-based sensor networks coexist with Wi-Fi and Bluetooth devices operating under strong electromagnetic interference from industrial machinery. Conventional adaptive filters employing fixed step-size Least Mean Squares (LMS) algorithms fail under high Jammer-to-Noise Ratio (JNR) conditions, exhibiting numerical instability and bit error rates (BER) approaching 0.5. This paper proposes a Variable Step-Size LMS (VS-LMS) algorithm integrated with Direct Sequence Spread Spectrum (DSSS) modulation to address this limitation. The proposed step-size update rule adaptively scales the learning rate according to instantaneous filter error: μ(n)=μ min +(μ max -μ min ) · exp(-α·e 2 (n)) , enabling large step-sizes during convergence and small step-sizes under strong interference to maintain numerical stability. Python-based simulations under AWGN plus sinusoidal narrowband interference (JNR=25 dB) demonstrate that the proposed VS-LMS scheme reduces BER by 76.1% compared to conventional fixed-step LMS, recovering communication quality (BER=0.12) in scenarios where fixed-step LMS completely fails. The results confirm that the proposed software-layer approach provides a practical, hardware-agnostic solution for reliable IIoT communications in electromagnetically hostile factory environments.
Show more
Read Article PDF
Cite