Özgür Gültekin

Hepatitis C Virus (HCV) is a common blood-borne pathogen and a leading contributor to chronic liver disease worldwide, including cirrhosis and hepatocellular carcinoma. Early and accurate diagnosis is essential to halt progression and improve outcomes, yet conventional approaches can be invasive and costly, highlighting the need for accessible, non-invasive decision support. This study examines whether representing routine clinical information as relational structure can enhance classification using the publicly available UCI Hepatitis C Virus (HCV) dataset, which contains standard biochemical and demographic variables. Rather than treating each patient independently, patients with similar laboratory profiles were connected through a patient–patient similarity graph, and a graph-based learning approach (GraphSAGE) was applied to leverage these relationships. For context and fairness, widely used non-graph machine learning methods were also evaluated on the same splits. Across repeated runs, the graph-based model achieves very high and stable performance (99.51% for both accuracy and macro-F1) and remains consistently competitive with, and in many cases slightly superior to, traditional models. Because the relational structure is derived directly from routine laboratory values, the learned representations reflect clinically meaningful similarity patterns without requiring additional inputs. Taken together, the findings suggest that reframing standard HCV data as a patient–patient network is a practical and effective strategy for non-invasive computer-aided diagnosis, complementing established baselines while offering a flexible path toward robust, clinically plausible deployment.

Early fault detection and real-time condition monitoring systems have become quite significant for today’s modern industrial systems. In a high volume of manufacturing facilities, fleets of equipment are expected to operate uninterrupted for days or weeks. Any unplanned interruptions to equipment uptime could jeopardize manufacturers’ cycle time, capacity, and, most significantly, credibility for their customers. With the help of smart manufacturing technologies, companies have started to develop and integrate fault detection and classification systems where end-to-end constant monitoring of equipment is facilitated, and smart algorithms are adapted for the early generation of fault alarms and classification. This paper proposes a generic real-time fault diagnosis and condition monitoring system utilizing edge artificial intelligence (edge AI) and a data distributor open source middleware platform called FIWARE. The implemented system architecture is flexible and includes interfaces that can be easily expanded for various devices. This work demonstrates it for condition monitoring of autonomous transfer vehicle (ATV) equipment targeting a smart factory use case. The system is verified in a designated industrial model environment in a lab with a single ATV operation. The anomaly conditions of the ATV are diagnosed by a deep learning-based fault diagnosis method performed in the Edge AI unit, and the results are transferred to the data storage via a data pipeline setup. The proposed system’s Edge AI solution for the ATV use case provides significant real-time performance. The network bandwidth requirement and total elapsed data transfer time have been reduced by 43 and 37 times, respectively. The proposed system successfully enables real-time monitoring of ATV fault conditions and expands to a fleet of equipment in a real manufacturing facility.