Streaming data are present all around us. From traditional radio systems streaming audio to today’s connected end-user devices constantly sending information or accessing services, data are flowing constantly between nodes across various networks. The demand for appropriate outlier detection (OD) methods in the fields of fault detection, special events detection, and malicious activities detection and prevention is not only persistent over time but increasing, especially with the recent developments in Telecommunication systems such as Fifth Generation (5G) networks facilitating the expansion of the Internet of Things (IoT). The process of selecting a computationally efficient OD method, adapted for a specific field and accounting for the existence of empirical data, or lack thereof, is non-trivial. This paper presents a thorough survey of OD methods, categorized by the applications they are implemented in, the basic assumptions that they use according to the characteristics of the streaming data, and a summary of the emerging challenges, such as the evolving structure and nature of the data and their dimensionality and temporality. A categorization of commonly used datasets in the context of streaming data is produced to aid data source identification for researchers in this field. Based on this, guidelines for OD method selection are defined, which consider flexibility and sample size requirements and facilitate the design of such algorithms in Telecommunications and other industries.

INTRODUCTION: Africa is the least motorized populated continent, yet it experiences the highest traffic fatality rate. Despite laws mandating helmet and seatbelt use, data on protective gear use among Cameroonian road traffic injury (RTI) patients remains sparse. METHODS: We extracted Cameroon Trauma Registry data prospectively collected from 10 hospitals during July 2022 to December 2023. Protective gear users wore helmets in motorcycle and seatbelts/car seats in vehicle crashes. We categorized patients into five economic clusters based on ownership of durable goods using parallel distance matrix computation. We analyzed associations between continuous variables with Wilcoxon rank-sum and categorical variables with χ² and multivariate logistic regression. Our primary outcome was in-hospital death or major disability at discharge. RESULTS: Among 3,554 RTI patients, 303 (9%) used protective gear. A larger proportion of patients who did not use protective gear were designated as majorly disabled or dead (20% vs. 16%, p < 0.001). The greatest percentage of protective gear users belonged to the richest cluster, while the poorest cluster patients comprised the smallest proportion of protective gear users (13% vs. 3%, p < 0.001). The richest cluster demonstrated the smallest percentage of major disability or death (13%), while the poorest cluster had the greatest percentage (28%, p < 0.001). When controlling for age, protective gear use, and injury severity, the three poorest clusters showed the greatest odds of major disability or death (cluster 3: adjusted odds ratio [AOR], 2.34; 95% confidence interval [CI], 1.58–3.46; cluster 4: AOR, 2.09; 95% CI, 1.59–2.74; cluster 5: AOR, 2.38; 95% CI, 1.24–4.58). CONCLUSION: Greater economic status is associated with increased protective gear use during RTIs in Cameroon. Despite suffering the most severe outcomes, the poorest patients remain less likely to use protective gear. Enforcement of protective gear laws and economic incentives such as price subsidies for helmets and seatbelts would particularly benefit the most vulnerable population. LEVEL OF EVIDENCE: Prognostic and Epidemiological; Level IV.

Mobile networks have advanced significantly, providing high-throughput voice, video, and integrated data access to support connectivity through various services to facilitate high user density. This traffic growth has also increased the complexity of outlier detection (OD) for fraudster identification, fault detection, and protecting network infrastructure and its users against cybersecurity threats. Autoencoder (AE) models are widely used for outlier detection (OD) on unlabeled and temporal data; however, they rely on fixed anomaly thresholds and anomaly-free training data, which are both difficult to obtain in practice. This paper introduces statistical masking in the encoder to enhance learning from nearly normal data by flagging potential outliers. It also proposes a quasidynamic threshold mechanism that adapts to reconstruction errors, improving detection by up to 3% median area under the receiver operating characteristic (AUROC) compared to the standard 95% threshold used in base AE models. Extensive experiments on the Milan Human Telecommunications Interaction (HTA) dataset validate the performance of the proposed methods. Combined, these two techniques yield a 31% improvement in AUROC and a 34% lower computational complexity when compared to baseline AE, long short-term memory AE (LSTM-AE), and seasonal auto-regressive integrated moving average (SARIMA), enabling efficient OD in modern cellular networks.

The number of Internet of Things (IoT) devices has been growing rapidly, driven by the demand for low-cost and low-power devices across a wide range of industrial and consumer applications. This expansion has broadened the attack surface exposed to cyber threats, making the detection of malicious activity in the IoT infrastructure a pressing research challenge. Most existing approaches are limited to binary anomaly detection, rely on a single data modality, or incur a computational overhead incompatible with realistic deployment on the edge. This paper introduces the Multi-modal Universal Informer Convolutional Neural Network (MUI-CNN) Classifier, a distributed architecture for multi-class attack detection across heterogeneous IoT sensor and network environments. It combines four components - a multi-modal universal data embedding layer that unifies numerical, categorical, and temporal features into a shared spatio-temporal representation, a CNN local pattern recognition layer, an encoder-only classifier for long-term temporal dependencies, and an optional statistical masking layer for greater sensitivity to low-amplitude signatures. The model is evaluated on the Telecommunication Operating Systems (OS) and Network Internet of Things (TON-IoT) dataset covering eight sensor types and ten attack classes. Results demonstrate F1 above 88% on all IoT sensors and up to 94.85% on the network sensor, confirming that each architectural component contributes a measurable and distinct improvement over partial baselines.