With the development of big data, artificial intelligence, and wearable technology, the data generated by learners in the learning process can be fully recorded and stored. Using these data to study the characteristic...
详细信息
Chronic Kidney Disease (CKD) is a major health condition that causes millions of deaths and billions of dollars in worldwide economic loss. The classical way of diagnosis and treatment of CKDs is through routine blood...
详细信息
Vehicular Ad-hoc Networks (VANETs) are dynamic networks formed among the vehicles travelling on road. They are prone to change in network topologies very quickly due to limited range of randomly moving vehicles. A veh...
详细信息
Each year Dengue infection causes havoc almost across the entire globe raising the death toll and thus becoming a global burden. With the absence of Global approved vaccine and its scope not limiting itself to tropica...
详细信息
Federated learning (FL) is an emerging technique used to collaboratively train a global machinelearning model while keeping the data localized on the user devices. The main obstacle to FL's practical implementati...
详细信息
ISBN:
(纸本)9798350320886
Federated learning (FL) is an emerging technique used to collaboratively train a global machinelearning model while keeping the data localized on the user devices. The main obstacle to FL's practical implementation is the Non-Independent and Identical (Non-IID) data distribution across users, which slows convergence and degrades performance. To tackle this fundamental issue, we propose a method (called ComFed) that enhances the whole training process on both the client and server sides. The key idea of ComFed is to simultaneously utilize clientvariance reduction techniques to facilitate server aggregation and global adaptive update techniques to accelerate learning. Our experiments show that ComFed can improve state-of-theart algorithms dedicated to Non-IID data.
We present a new data generation method to facilitate an automatic machine interpretation of 2D engineering part drawings. While such drawings are a common medium for clients to encode design and manufacturing require...
详细信息
ISBN:
(纸本)9780791886229
We present a new data generation method to facilitate an automatic machine interpretation of 2D engineering part drawings. While such drawings are a common medium for clients to encode design and manufacturing requirements, a lack of computer support to automatically interpret these drawings necessitates part manufacturers to resort to laborious manual approaches for interpretation which, in turn, severely limits processing capacity. Although recent advances in trainable computer vision methods may enable automatic machine interpretation, it remains challenging to apply such methods to engineering drawings due to a lack of labeled training data. As one step toward this challenge, we propose a constrained data synthesis method to generate an arbitrarily large set of synthetic training drawings using only a handful of labeled examples. Our method is based on the randomization of the dimension sets subject to two major constraints to ensure the validity of the synthetic drawings. The effectiveness of our method is demonstrated in the context of a binary component segmentation task with a proposed list of descriptors. An evaluation of several image segmentation methods trained on our synthetic dataset shows that our approach to new data generation can boost the segmentation accuracy and the generalizability of the machinelearning models to unseen drawings.
The paper introduces an interpretable machinelearning technique SHAP (SHapley Additive exPlanation) to analyze the vehicle yielding behaviors during pedestrian-vehicle interactions at unsignalized intersections. The ...
详细信息
ISBN:
(纸本)9798350399462
The paper introduces an interpretable machinelearning technique SHAP (SHapley Additive exPlanation) to analyze the vehicle yielding behaviors during pedestrian-vehicle interactions at unsignalized intersections. The study first extracts trajectory data from drone videos and then exploits machinelearning methods to construct the yielding classification model. The results indicate that Random Forest (RF) outperforms Support Vector machine (SVM), Gradient Boosting machine (GBM), and eXtreme Gradient Boosting (XGBoost), achieving the best classification performance with an area under the ROC curve (AUC) of 0.934. Finally, the SHAP algorithm is fused with RF to improve the model interpretability. The analysis reveals that the distances between vehicles and pedestrians make the most significant impact on vehicle yielding behavior. Furthermore, it is found that traffic-related variables exhibit non-linear and threshold effects on vehicle yielding.
Online reinforcement learning (RL) methods are often data-inefficient or unreliable, making them difficult to train on real robotic hardware, especially quadruped robots. So learning robotic tasks from pre-collected d...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
Online reinforcement learning (RL) methods are often data-inefficient or unreliable, making them difficult to train on real robotic hardware, especially quadruped robots. So learning robotic tasks from pre-collected data is a promising direction. Agile and stable legged locomotion remains an open issue in its general form. Analogous to the rapid progress of supervised learning in recent years, the combination of offline reinforcement learning (ORL) and realistic datasets has the potential to make breakthroughs in this challenging field. To facilitate the ORL research for real-world applications, we benchmark ten ORL algorithms in the realistic quadrupedal locomotion dataset. The dataset is collected by the classical model predictive control (MPC) method, rather than the online RL method commonly utilized by previous ORL benchmarks. Extensive experimental results show that the best-performing ORL algorithms can achieve competitive performance compared with the online RL, and even surpass it in some tasks. However, there is still a gap between the learning-based methods and classical MPC, especially in terms of stability and task response accuracy. Our benchmark can provide a fertile ground for future application-oriented ORL research.
Oversampling is a strategy employed in machinelearning to handle imbalanced datasets by creating copies of the minority class instances to balance the dataset, thus reducing bias and enhancing the accuracy of the mod...
详细信息
A computer system is trained to make right predictions by giving it data through a process known as machinelearning. The phrase 'cloud computing' refers to on-demand internet access to computer resources kept...
详细信息
暂无评论