Stroke has been one of the leading causes of death. Recognizing its warning signs early can lessen its severity and maximize the effectiveness of its prevention. A highly effective data-driven predictive algorithm is needed for this, which can be done through various machine learning-based techniques. In this paper, Linear Support Vector Machines (linear-SVM), Radial Support Vector Machines (rbf-SVM), Logistic Regression, Decision Tree, Gaussian Naive Bayes, and Random Forests were used for stroke prediction. Among these models, linear-SVM, rbf-SVM, and Logistic Regression yielded the highest accuracy value of 95%. Cross-validation and boosting through ensembling were also conducted to further enhance the overall confidence of model prediction.

This study presents numerical simulations and analysis of rain power Pelton wheel turbine for a household application. The material used and compared in the simulation are ABS AND A390 Aluminum Alloy. An average rainfall data was used in the modeling simulation with different head height and number of buckets. Torque, RPM and Shaft Power were simulated using SolidWorks. Based on the simulation the 22 & 24 number of buckets at a height of 3 meter have a close result with the two dissimilar materials. In this research a rain power Pelton wheel turbine with different materials, varying height and number of buckets was simulated and analyzed.

The quest for alternative sustainable energy sources has led to innovative solutions, such as harnessing energy from rainwater. This study aims to evaluate the performance of a 3D printed pelton wheel turbine for a household rain gutter application with a height of 3m and 5m. The design and simulation were done via SolidWorks with varying number of buckets: 15, 18, and 20, evaluating the shaft power and rpm. Initial design parameters were calculated and simulated. The actual prototype and test were done. The results show an overall turbine efficiency of 71 percent and was able to produce an 8W power output. In this research, a 3D printed pelton turbine for a household application during rainy season was designed, simulated, fabricated, tested, and analyzed.

This paper presents the use of machine learning in predicting the symbiotic insights such as coefficient and carrying capacity of a given modular mobile robot configuration doing a cooperative load pushing task. The independent parameters were load and the number of modules. The actual experiment results from a DFRobot Maqueen mobile robot pushing a range of loads were used as dataset in the study. Various regression models were run as an ML algorithm to assess symbiotic relationship of a given configuration whether harmful, beneficial or has no effect and to yield the total distance that can be traversed given a set of input parameters. The researchers used python in running the ML model on Google Colab Notebook. Results show that Gradient Boosting performed best in the prediction of distance carrying capacity with 95.87% and Extra Trees for symbiotic coefficient with 93.75% accuracy which took about only 5 seconds training time on a T4 GPU device. The researchers were able to develop a custom trained ML regressor model that can immediately return a symbiotic insight on a cooperative pushing modular mobile robots.

Counting high volumes of product and packages is prone to human error and is time consuming especially on a fast-moving conveyor system. To address this issue, automated counting systems are typically operated, the performance of which is dependent on the reliability of instruments used such as the sensors and scanners. Technological advancements in machine vision are progressing exponentially, making it increasingly accessible, cheap, and dependable for solving and executing real-time image related problems. In this paper, a vision-based high speed counting system is proposed. YOLOv8 was utilized as the machine learning model and is executed via Roboflow. Soap and small parcel items were focused on as a dataset. The generated mean average precision (mAP), precision, and recall for combined items is 98.6%, 96.8%, 96.3% with an inference and prediction time of 1:3 and 1:1 ratio respectively.

This paper presents a decentralized and cooperative load lifting and transportation system using unmanned aerial vehicle quadcopters. The limitation of a single UAV to carry load is addressed in this study by creating a cooperative lifting system that can accommodate varying load weight. Cooperative, independent and scalable agents were implemented with decision making algorithm embedded in each agents. Decentralized sensing of load is done by the UAV and the group consensually decides if another UAV is needed to carry the load. The system can lift different weight by autonomously sending appropriate number of UAV depending on the load. Experiments were conducted to determine the responsiveness of the system in varying load weights. Experiment results showed that the developed system is robust and scalable.

This research proposes a method in order to classify vehicles in a highly congested roads , a robust technique for vehicle classification with low computational power must be used. So, a proposed solution is to embed an AKAZE feature matching extraction which is ran in an artificial neural network will be used. AKAZE was used because it is faster than SIFT. The features extracted from the AKAZE algorithm will be grouped according to the type of vehicle where it was used and be placed to an Artificial Neural Network (ANN) for the training of the network itself. The results yielded good for real-time Vehicle Classification.

In response to addressing the issue of pipe quality checking, the researchers developed an adaptive in-pipe inspection robot that is able to detect rust as well as map the rust on the pipe network. The robot is traversed in a pipe network of horizontal, vertical, elbow, and tee type with diameters of 8, 10 and 12 inches for all. Hence, the test features the versatility, adaptability, and robustness of the robot. The leg expansion of the robot is inspired by the scissors mechanism. On the other hand, rust detection was done through a per pixel classification via image processing. To effectively map the rust, checkpoints were used as a guide of the robot. Testing of the robot were supported in both simulation and actual testing, wherein it yields a 96.45% success rate on the site. Likewise, its rust detection program proved to be successful with a high percentage accuracy of 99.18%. The localization on the other hand yielded an accuracy of 85%. Given the obtained data and results, the researchers were able to go beyond their target objective of 70%.