Classification of imbalanced datasets has become one of the most challenging problems in big data mining. Because the number of positive samples is far less than the negative samples, low accuracy and poor generalization performance and some other defects always go with learning process of traditional algorithms. Ensemble construction algorithm is an important method to handle this problem. Especially, the ensemble construction algorithm based on random under-sampling or clustering can effectively improve the performance of classification. However, the former causes information loss easily and the latter increases complexity. In this paper, we propose ACUS, an improved ensemble algorithm based on automatic clustering and under-sampling. ACUS conducts clustering first according to the weight of samples, and then it constructs balanced-distributed dataset which consists of a certain percentage of the majority class and all of the minority class from each cluster. With Adaboost algorithm construction, these datasets are used to get an ensemble classifier. Experimental results demonstrate the advantages of our proposed algorithm in terms of accuracy, simplicity and high stability.
Current wireless capsule endoscopy (WCE) is limited in the long examination time and low flexibility since the capsule is passively moved by the natural peristalsis. Efforts have been made to facilitate the active locomotion of WCE using magnetic actuation and localization technologies. This work focuses on the motion control of the robotic capsule under magnetic actuation in a complex gastrointestinal (GI) tract environment in order to improve the efficiency and accuracy of its motion in dynamic, complex environments. Specifically, a magnetic actuation system based on a four-electromagnetic coil module is designed, and a control strategy for the system is proposed. In particular, the proportional–integral–derivative (PID) control parameters and current values are optimized online and in real time using the adaptive particle swarm optimization (APSO) algorithm. In this paper, both simulations and real-world experiments were conducted using acrylic plates with irregular shapes to simulate the GI tract environment for evaluation. The results demonstrate the potential of the proposed control methods to realize the accurate and efficient inspection of the intestine using active WCE. The methods presented in this paper can be integrated with current WCE to improve the diagnostic accuracy and efficiency of the GI tract.
30 September 2024 in IEEE Transactions on Instrumentation and Measurement
This paper introduces a novel technique for accurately positioning a toroidal permanent magnet (PM) in a magnetically-driven surgical laser ablation end-effector, taking into account the effects of electromagnetic interference (EMI). A novel hybrid optimization algorithm is proposed that designs the initial search direction and step size of the algorithm by analyzing the error function in the iteration. Moreover, the algorithm establishes the boundary value when the hybrid algorithm is initiated, thus facilitating a more effective integration of the global search capabilities of the tree seed algorithm (TSA) and the local search capabilities of the Levenberg-Marquardt algorithm (LM). Furthermore, precise tracking of the permanent magnet in the context of coil-controlled permanent magnet motion is accomplished through the use of an accurate coil model and a real-time EMI subtraction algorithm. In the real-time tracking task with an update rate of 25Hz, the mean absolute error (MAE) and root mean square error (RMSE) of the position error of the hybrid optimization algorithm incorporating the proposed model are 0.0809mm and 0.1085mm, respectively. The MAE and RMSE percentages are 1.84% and 2.17%, respectively. In the laser target tracking experiments, the MAE and RMSE of the tracking error are 0.1339mm and 0.1668mm, respectively, with MAE and RMSE percentages of 2.23% and 2.78%, respectively.