This research article presents an enhanced YOLOv8 model with an additional feature extraction layer integrated into the traditional YOLOv8 architecture to improve fault detection performance in smart additive manufacturing, specifically for FDM 3D printers. Hyperparameter optimization techniques are employed to ensure the model is trained with optimal input and batch size configurations. The findings demonstrate that the additional module successfully enhances the model’s performance in detecting faults during the FDM 3D printing process. The best results are achieved using the YOLOv8s model with an image input size of 640 and a batch size of 16, achieving a mAP _val (50-95) of 89.7%. Despite the increased complexity from additional layers, there is a favorable trade-off between performance and complexity. Furthermore, a testbed implementation is conducted to validate the model’s performance in a real-world setting, showing that the fault detection latency remains insignificant even with multiple Raspberry Pi clients. Overall, this research provides insights into improving fault detection in smart additive manufacturing and highlights the effectiveness of the proposed YOLOv8 model with additional extraction layers.

With the rapid advancement of wireless communication, sensors, and battery technologies, Swarm Unmanned Aerial Vehicles (UAVs) have been widely used for traffic surveillance, and military application. Swarm UAVs, however, need to plan paths through the atmosphere, effectively preventing any collision that can occur when flying a multiple UAV simultaneously. This study proposes to design an anti-collision and a path planning system of swarm UAVs by using Artificial Bee Colony (ABC) algorithm. The ABC algorithm is an optimization method inspired by the foraging behavior of honeybees. The self-organization trait of honeybees enables them to coordinate themselves to create a global and local optimum. The proposed system, however, uses the ABC algorithm to optimize UAV's velocity, i.e., to reach its destination efficiently in the shortest path while avoiding collision among drones. The establishment of a constraint of a minimum acceptable distance among UAVs enables the algorithm to search for an alternative path in avoiding a collision. The simulation, however, reveals a successful convergence of a swarm UAVs towards a destination with no collision. During the trial with 12 and 20 drones, for instance, all UAVs successfully arrive at their goals with 0 potential collisions. However, during the test with 50 drones, there are 12 possible collisions. Once swarm drones reach their goal position at rest, the cluster will not overlap with other agents, as demonstrated in the visualization. Therefore, the ABC algorithm has satisfied the success criteria for this project and is suitable for swarm drone applications.

This paper introduces PureFed, an innovative Federated Learning (FL) framework designed for efficiency, collaboration, and trustworthiness. In the background of FL research, it was observed that previous frameworks often neglected participant privacy, a critical aspect not aligned with the core FL concept. Additionally, there was room for improving the efficiency of existing frameworks. PureFed addresses these shortcomings by offering participants the flexibility to initiate FL tasks or join existing ones without sharing any private data and removing unnecessary actions that led to an inefficient system. Leveraging blockchain technology, it employs smart contracts to ensure traceability and immutability, enhancing the security of the framework. Additionally, PureFed employs symmetric key encryption and dual digital signature mechanisms using ECDSA to guarantee the confidentiality and integrity of shared models. To expedite model convergence, PureFed incorporates a dynamic aggregation scheme, selecting the most suitable model from three distinct techniques: FedAvg, accuracy-based, and loss-based. Furthermore, the framework introduces a dynamic incentive and punishment mechanism to incentivize collaboration and maintain trust. Extensive performance evaluations reveal PureFed’s significant advantages. It outperforms its counterparts by 63.39% and 67.72% in terms of smart contract deployment and interaction gas costs, respectively. Lastly, scalability analyses indicate PureFed’s ability to adapt efficiently, achieving target accuracy in fewer rounds.

Every Knowledge Based System has their own knowledge formalism depends on the problem to be solved, goal to be achieved, and proposed solution. This means every knowledge contained in the system will differ from one system to another. This was also meant that this knowledge cannot be used by other system, which in return makes every system must start with a learning phase from the start. One of the solutions to overcome this problem is by providing a unified model that can accept all type of knowledge which guarantees automatic interaction between Knowledge Based System. Interaction in this paper is defined as knowledge sharing, integration, and transfer from one system to another. This research provides the model and conducts the test on interaction capability. This research contributes for accelerating a new Knowledge Based System establishment because it does not need a knowledge initialization.

Every enterprise provides business processes to ensure information is delivered to the senior leaders, either automatically by system or by manual process. When this delivery is done by system, information is usually provided through an executive dashboard. Using executive dashboard, senior leaders can view company's vital information that related to business goal and make a quick decision based on this information. An executive dashboard is the tool to provide such information, however it usually designed with no flexibility so when there is a change in the information report, they will need to call the developer to change it. This research is aimed to design and implement an executive dashboard that provides flexibility, which can be configured by anyone without programming background. This research also pro-poses a mechanism on how to create an executive dashboard that supports a knowledge discovery capability.

Indonesian academic institutions commonly use direct marketing strategy, such as visiting high schools to find potential candidate for students, however, only few institutions use social media as an alternative for marketing channel and as the source of information. Social CRM as a social media extension can gives benefits where direct marketing cannot, for example, marketing team can profile their potential candidate to provide a better proposal. To do this, social CRM must have a feature like web mining where a crawler engine gather information from social media for a specific customer, for example high school students and/or parents, and create better segmentation using clustering algorithm. This research proposes a model and implementation of web mining extension part for social CRM, especially for Indonesian academic institution. This model and web mining part can focus marketing strategy by segmenting potential candidates.