Celal Ceken

Selecting and deploying an appropriate wireless sensor network (WSN) is an important challenge in IoT system design. Evaluating different WSN configurations through physical deployment can be costly and time-consuming. This study proposes a simulation-driven framework that integrates a simulated WSN with an MQTT-based IoT communication infrastructure to enable network-aware performance evaluation prior to physical deployment. An SDN-WISE-based WSN was implemented using the Cooja simulator, and the generated sensor traffic was forwarded to a Mosquitto-based MQTT cluster via a socket-based integration mechanism. Unlike conventional approaches that use independent traffic generators, the MQTT workload in the proposed framework originates directly from the simulated WSN. Experiments with 24-, 36-, and 48-node scenarios showed that average end-to- end delay increased from 37.51 ms to 138.01 ms, while total application throughput increased from 142.51 bps to 281.12 bps. Packet delivery remained effectively near 100% across all scenarios. The proposed approach provides a controlled, repeatable environment for evaluating various WSN configurations and can reduce the need for multiple physical deployments in the early stages of IoT system design.

This study presents a scalable decision support system (DSS) framework designed to meet the growing demands of instant data-driven decision-making environments. The architecture integrates key technologies, including Apache Kafka for parallel data streaming, a Python-based data analytics module for distributed processing, JWT-based secure user authentication, and WebSocket communication for instantaneous prediction delivery. The system performs mitochondrial localization in electron microscopy (EM) images using multiple versions of the YOLO (You Only Look Once) object detection model. The publicly available CA1 Hippocampus dataset was used for detection evaluation. Among the evaluated models, YOLOv10x achieved the highest detection performance, yielding a mean average precision (mAP) score of 95.2%. Experimental evaluations of the DSS were conducted under simulated load conditions using the Artillery tool to assess the system’s scalability and responsiveness. Empirical results indicate consistent low-latency performance across varying consumer group sizes, confirming the architecture’s ability to scale the analytics module horizontally without compromising responsiveness. These findings validate the system’s suitability for just-in-time decision support applications. In particular, the system may support clinicians in the task of mitochondrial analysis, where structural abnormalities can be indicative of pathological conditions, including cancer. By enabling early detection of such abnormalities, the proposed framework has the potential to contribute to the timely diagnosis of diseases such as cancer. The proposed study differs from existing studies by combining deep learning with real-time scalable data processing technologies, such as Kafka and WebSocket, in a web-based DSS application for mitochondria detection.

Decision Support Systems facilitate timely and informed decision-making by integrating heterogeneous data sources, analytical models, and user interfaces into cohesive systems. This study introduces a general-purpose and scalable Decision Support System framework that supports just-in-time, data-driven decision-making processes across diverse application domains. The proposed system architecture incorporates essential technologies, including Apache Kafka for parallel data streaming, a Python-based distributed data analytics module, a role-based access control system for authentication and authorization, and a WebSocket interface to deliver predictions in real-time. The Iris dataset was utilized for model validation, with logistic regression employed as the predictive model. Experimental evaluations were conducted under simulated load conditions using the Artillery tool to assess system scalability and responsiveness. Results demonstrate significant performance improvements when utilizing Apache Kafka consumer group with associated worker modules for parallel processing, achieving lower mean, median, P95, and P99 latencies. These findings highlight the effectiveness of the proposed architecture in enabling highly scalable and responsive Decision Support System applications that support just-in-time decision-making.

Anxiety and depression are prevalent psychological disorders that can occur throughout life, with a notably higher prevalence among women during the perinatal period, encompassing pregnancy and the postpartum phase. The early detection and monitoring of these conditions are crucial for timely intervention and improved patient outcomes. Although healthcare analytics has progressed considerably, the extraction of actionable insights from large-scale patient data remains computationally intensive, especially under instant processing constraints. Furthermore, conventional healthcare infrastructures frequently lack the scalability, computational efficiency, and architectural flexibility required to integrate machine learning models into clinical workflows effectively. To address these challenges, the proposed distributed computing framework employs Apache Kafka for instant data streaming, Apache Spark for efficient in-memory machine learning–based analytics, and Kubernetes for orchestrating scalable, fault-tolerant deployment. This architectural configuration facilitates continuous data ingestion, accelerates analytical processing, and ensures system resilience, thereby enabling the timely identification of psychological conditions such as anxiety and depression during the perinatal period. Unlike schematic or batch-only prior work, we provide a production-ready, streaming-first clinical deployment and an empirical scaling analysis linking executors to end-to-end diagnostic latency and resource efficiency. Performance evaluations demonstrate the efficiency and scalability of the proposed system, highlighting its potential for real-world applications in healthcare analytics.

Instant object detection is a critical capability in modern applications where timely decision-making is essential, such as in emergency medicine, autonomous systems, and intelligent surveillance. Efficiently handling high-throughput image streams with minimal delay presents significant challenges, particularly under demanding conditions. This study presents a scalable object detection pipeline that integrates YOLO models with Apache Kafka, a distributed streaming platform, to support just-in-time inference. The proposed architecture leverages Kafka’s partitioning and consumer group mechanisms to enable parallel processing, ensuring high throughput without requiring complex load-balancing logic. The system is deployed on a Virtual Private Server to demonstrate practical implementation. Two configurations are presented to illustrate Kafka’s native scalability: one with a single partition and a single consumer, and another with five partitions and five consumers. These setups visually demonstrate how Kafka efficiently distributes workloads across multiple consumers. Although specific latency or throughput metrics are not reported, the architecture effectively showcases how Kafka’s design enables prompt responses to high-volume input. This pipeline is well-suited for time-sensitive object detection tasks and can be extended to a wide range of instant analytics applications where rapid feedback is critical.

Digital transformation is crucial for organizations to survive, be competitive, and grow in the modern age. IoT is the key to enabling this transformation by connecting devices and optimizing processes. This paper presents the design and implementation of a generic IoT-based real-time environmental monitoring and alarm system. The platform is validated by applying it to a manufacturing plant scenario, where various sensors simulate industrial conditions. Scalable message distribution systems such as MQTT and Apache Kafka facilitate reliable data transmission. A microservice architecture is constructed for the backend services to ensure uninterrupted and high throughput services in the application domain. Instead of deploying a real WSN, traffic generation services were chosen to minimize costs, provide greater control and flexibility, and facilitate faster, scalable testing in a controlled environment. The platform also features an integrated alarm system with an event definition module, which allows users to define custom action rules. This flexible, scalable, and resilient architecture can be used across a wide range of application domains that require digital transformation. The experimental study demonstrates the platform's capabilities and great potential for broader IoT applications.

KSII Transactions on Internet and Information Systems TIIS Paper Details

Introduction and purpose: With the development of technology, new applications have started to deliver health services. These applications, which are described as mobile health applications, provide a systematic approach to managing chronic wounds and increase patients' quality of life and their compliance with treatment. In this direction, the study was carried out to develop an application that can be used by patients and healthcare professionals in chronic wound management. Material and Method: To develop the application, first of all, the user panels and their contents were drafted, and the servers and infrastructure works were started. Interfaces were developed based on the page designs created, and separate pages were designed for patients and healthcare personnel. After the development of the main operation and management platform, the definition of services, the editing of image processing features, and the security tests, the mobile application was made ready for use. In the pilot study, eight patients with diabetic foot wounds were followed up with the application used on Android systems via web browsers, both tablets, and smartphones, via mobile application. Results: In the study, it was determined that both the patients followed by the wound tracking system and the health personnel using the system were satisfied with the application. Conclusion: Using mobile applications in the long-term treatment process of chronic wounds increases the patients' follow-up outside the hospital, their compliance with the treatment, and their comfort. In terms of health personnel, it also reduces the intensity and workload in the hospital and ensures that patient records are kept regularly. Patients with chronic wounds with no indication for hospitalization can be followed up with the mobile application

One of the forces driving science and industry is machine learning, but the proliferation of Big Data necessitates paradigm shifts from conventional approaches in applying machine learning techniques to this massive amount of data with varying velocity. Computers are now capable of accurately diagnosing a variety of medical conditions thanks to the availability of immense healthcare datasets and advancements in machine learning techniques. The study’s primary aim is to identify the most compelling questions on anxiety and depression in pregnant women by extracting features through performance-optimized algorithms. In this way, it is aimed to reach the result in a shorter time with fewer questions. The next goal of this work is to create an instant remote health status prediction system for depression and anxiety in pregnant women based on the Apache Spark Big Data processing engine, which concentrates on using machine learning models on streaming Big Data. In this scalable system, the application receives data from pregnant women to forecast the patient’s health condition. It then applies the machine learning algorithm that produces the best results for this dataset. With the assistance of this big data platform, the time-consuming anxiety and depression detection procedure in a pregnant woman can be replaced with a computer-based technique that works in an instant with a respectable amount of accuracy.