This paper presents a complete approach for automatic detection and classification of pulmonary nodules through applying several techniques on chest CT images. The proposed approach starts by multi segmentation techniques followed by nodule extraction and then classification of the extracted features. The first step of is the preprocessing by converting the pixel values into Hounsfield units, and then applying a region growing technique to isolate the human body from other items. After that, the lung segmentation process takes place, which initially starts by thresholding the image followed by Hessian method for vascular tree segmentation. The application of multi segmentation methods allowed the precise extraction of the nodule features, which facilitate the classification. After this stage, several classifiers with their combination had been applied to perform the classification of malignant nodule and benign. The combination of these classifiers are used to evaluate and then enhance the classification accuracy of malignant nodule and benign. CT study of 200 patients, each with 150 to 500 images, is used to evaluate the proposed technique. The results are promising and achieved 98% classification accuracy.

Most navigation systems of unmanned surface vehicles (USVs) are based on global position system (GPS)/inertial navigation system (INS) integrated methods to improve the accuracy of the navigation system. But in some places on the Earth’s surface, the GPS signal suffers from outages, interferences, and weakness, which affect the performance of the whole USV navigation system. This paper provides a continuous and accurate navigation solution via integrated GPS with micro-electro-mechanical (MEMS)-INS smartphone sensors and reduced-aided visual odometry (RAVO) using centralized Kalman filter (CKF) data fusion. The proposed RAVO is used to correct USV navigation system errors during GPS outages. It is based on integrated visual odometry (VO) with MEMS-INS smartphone sensors, the Doppler velocity log (DVL), depth and compass sensors. The DVL/depth/compass/MEMS-INS smartphone integrated solution is used to improve the performance of a VO system before data fusion processing using a CKF. The CKF is used as data fusion processing to estimate and correct USV navigation system errors. The efficiency of the USV navigation system is tested on a surface reference trajectory called Kur-Mukalla in Mukalla City, Yemen. During GPS outage for 83 s, the proposed method based on the GPS/RAVO/MEMS-INS smartphone integrated CKF method could provide a reliable USV navigation solution; it reduced the position error to 82.32% compared to the traditional GPS/MEMS-INS CKF method, and to about 70.72% compared to the GPS/Pure-VO/MEMS-INS CKF integrated method.

The design of the robotic arm's trajectory is based on inverse kinematics problem solving, with additional refinements of certain criteria. One common design issue is the trajectory optimization of the robotic arm. Due to the difficulty of the work in the past, many of the suggested ways only resulted in a marginal improvement. This paper introduces two approaches to solve the problem of achieving robotic arm trajectory control while maintaining the minimum reachability time. These two approaches are based on rule-based optimization and a genetic algorithm. The way we addressed the problem here is based on the robot’s forward and inverse kinematics and takes into account the minimization of operating time throughout the operation cycle. The proposed techniques were validated, and all recommended criteria were compared on the trajectory optimization of the KUKA KR 4 R600 six-degree-of-freedom robot. As a conclusion, the genetic based algorithm behaves better than the rule-based one in terms of achieving a minimal trip time. We found that solutions generated by the Genetic based algorithm are approximately 3 times faster than the other solutions generated by the rule-based algorithm to the same paths. We argue that as the rule-based algorithm produces its solutions after discovering all the problem’s searching space which is time consuming, and it is not the case as per the genetic based algorithm.

Trajectory optimal control for a robotic arm with a high degree of freedom (DOF) is challenging. The design space for that problem is complex and the search for an optimal solution is demanding. The design of a robotic arm's trajectory is based on solving the inverse kinematics problem, considering additional refinements influenced by factors like total rotating angle, reachability time, minimum execution time, obstacle avoidance, and energy consumption minimization. Due to the complexity of the design space, in this paper, genetic algorithm (GA) optimization and whale optimization algorithm (WOA) have been used to achieve robotic arm trajectory control while maintaining a minimum reachability time. To validate the suggested techniques, a case study was conducted on a 6 DOF KUKA KR 4 R600 robot arm to control subject to its constraints. Sets of consecutive points forming four different paths were inputted to the algorithms. The goal was to reach all these points, in order, with a minimum total reachability time. As a result of this paper, we shown that the whale optimization algorithm provides better performance than the genetic algorithm with a factor of more than 2.5 while satisfying the reachability constraints.

Numerous classification and regression problems have extensively used Support Vector Machines (SVMs). However, the SVM approach is less practical for large datasets because of its processing cost. This is primarily due to the requirement of optimizing a quadratic programming problem to determine the decision boundary during training. As a result, methods for selecting data instances that have a better likelihood of being chosen as support vectors by the SVM algorithm have been developed to help minimize the bulk of training data. This paper presents a density-based method, called Density-based Border Identification (DBI), in addition to four different variations of the method, for the lessening of the SVM training data through the extraction of a layer of border instances. For higher-dimensional datasets, the extraction is performed on lower-dimensional embeddings obtained by Uniform Manifold Approximation and Projection (UMAP), and the resulting subset can be repetitively used for SVM training in higher dimensions. Experimental findings on different datasets, such as Banana, USPS, and Adult9a, have shown that the best-performing variations of the proposed method effectively reduced the size of the training data and achieved acceptable training and prediction speedups while maintaining an adequate classification accuracy compared to training on the original dataset. These results, as well as comparisons to a selection of related state-of-the-art methods from the literature, such as Border Point extraction based on Locality-Sensitive Hashing (BPLSH), Clustering-Based Convex Hull (CBCH), and Shell Extraction (SE), suggest that our proposed methods are effective and potentially useful.