This anniversary article re-presents and reinterprets the 2007 International Journal of Semantic Computing article on SIOX, Simple Interactive Object Extraction [9]. The historical contribution was a practical foreground-extraction tool for images and videos: a user supplied a small amount of semantic supervision in the form of foreground and background examples; the system mapped pixels into a perceptually meaningful color space; compressed the examples into color signatures; classified the remaining pixels by distance to those signatures; and refined the resulting confidence matrix. Twenty years later, this pipeline reads less like an isolated image-processing trick than like a transparent miniature of a broader pattern in artificial intelligence and semantic computing: representation, compression, separation, and action. We therefore preserve much of the original article, revise the related-work discussion as a 2026 retrospective, and argue that twenty years of semantic-computing applications now call for a more explicit unifying theory.
Lower Urinary Tract Symptoms (LUTS) are commonly evaluated using clinician judgment and nomogram-based methods derived from limited physiological parameters. However, these approaches may not generalize across patient subgroups and may not fully capture patient-specific variability. we develop Machine Learning (ML) models to predict the necessity of medical intervention using uroflowmetry and clinical features. Unlike prior work focusing on symptom clustering or parameter-based analysis, the proposed approach models physician-assessed decisions and enables a direct comparison with established clinical nomograms. Multiple ML models, including Support Vector Machines (SVM), Random Forest (RF), and gradient boosting methods, as well as neural network architectures, are evaluated on a clinically collected dataset using stratified analysis across age and sex groups. Experimental results show that ML-based models achieve higher overall classification accuracy than Liverpool and Siroky nomograms, particularly in male subgroups. Reduced performance in female subgroups highlights the impact of data imbalance and suggests the need for more representative datasets. These findings suggest that ML-based approaches can provide more flexible and data-driven decision support compared to nomogram methods.
Immersive formats such as 360° and 6DoF point cloud videos require high bandwidth and low latency, posing challenges for real-time AR/VR streaming. This work focuses on reducing bandwidth consumption and encryption/decryption delay, two key contributors to overall latency. We design a system that downsamples point cloud content at the origin server and applies partial encryption. At the client, the content is decrypted and upscaled using an ML-based super-resolution model. We integrate this pipeline into an adaptive bitrate (ABR) streaming client, which enables the system to dynamically select among multiple resolution levels and apply Super-Resolution (SR) to enhance delivered quality. We evaluate our approach through a full streaming deployment on CloudLab where we compare SR-aided ABR streaming against a standard ABR baseline under varying cache configurations. Our results show that the SR-aided approach raises the average delivered resolution from approximately 18% to 31% of full density under constrained network conditions, a 76% relative improvement over the ABR-only baseline. Additionally, we demonstrate a nearly linear reduction in bandwidth consumption and encryption/decryption overhead with lower downsampling resolutions while maintaining the ability to effectively reconstruct the original full-resolution point clouds with inference times as low as 68 ms for a 157K-point frame.
When analyzing networks, Betweenness Centrality is a method of measurement that can be used to find the frequency at which a node is accessed when calculating the shortest path between various nodes. The more often a node is accessed, the greater the node’s Betweenness Centrality score becomes. This metric allows for numerous practical applications, from gene identification for diseases to analyzing the movement of data through informational infrastructures. With modern day computing power, we are able to utilize Large Language Models (LLMs) to calculate Betweenness Centrality on large-scale networks. However, the performance of LLMs may not be quick nor accurate when presenting a response for Betweenness Centrality graph problems. Therefore, we propose a GPS-BC module that has the capability to formulate accurate solutions for Betweenness Centrality problems using tailored algorithms. The problems contain several combinations of the constraints on (A) node color, (B) edge/path weights, and (C) node degree. For all the constrained problems, GPT-5.2 was observed to have an average accuracy of 62% when reporting Betweenness Centrality scores. The accuracy decreases when increasing the complexity of the constraints imposed on a problem. Additionally, GPS-BC algorithms were found to be, on average, [Formula: see text] faster than the observed processing time for GPT-5.2. Through this approach of using validated algorithms in our GPS-BC module, we are able to process Betweenness Centrality calculations with efficiency and ensured accuracy.
