Biomimetic and compliant robotic hands offer the potential for human-like dexterity, but controlling them is challenging due to high dimensionality, complex contact interactions, and uncertainties in state estimation....
详细信息
Poor sanitation and limited access to clean water are the main causes of increased risk of gastrointestinal diseases. In Indonesia, environmental hygiene problems are the main cause of digestive tract disorders, which...
详细信息
ISBN:
(数字)9798331505530
ISBN:
(纸本)9798331505547
Poor sanitation and limited access to clean water are the main causes of increased risk of gastrointestinal diseases. In Indonesia, environmental hygiene problems are the main cause of digestive tract disorders, which contribute to more than 25% of deaths each year according to data from the Ministry of Health. Digestive disease is one of the diseases that often appears due to Poor sanitation and limited access to clean water. The development of a digital stethoscope for early detection of problems in the digestive tract would be useful, especially in remote areas. The sound was recorded from a Mel Frequency Cepstral Coefficient (MFCC) technique. The resulting features extracted from the stethoscope sound signal, are used as the inputs for the machine learning which applied three types of method, they are Logistic Regression (LR), combination of Logistic Regression (LR) and K-Nearest Neighbors (KNN), combination of Logistic Regression (LR) and Support Vector Machine (SVM). The experiment of MFCC with three types of machine learning methods above, based the sound from a stethoscope. Experimental results show the combination of Logistic Regression (LR) and K-Nearest Neighbors (KNN) has exceeded results among other methods, with the training and testing accuracy of 90 % and 88 % respectively. They confirm the effectiveness of the proposed intelligent automatic stethoscope sound identification based on Mel-Frequency Cepstral Coefficient (MFCC) and Linear Regression. Furthermore, the system continuously saves and monitors the result of the patient.
There was an incident on a campus involving the casualty of students. It created social unrest and heightened concerns over campus security. Consequently, it becomes important to prevent such incidents. Thus, we devel...
详细信息
Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share si...
详细信息
ISBN:
(数字)9798350353006
ISBN:
(纸本)9798350353013
Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively.
A domain shift exists between the large-scale, internet data used to train a Vision-Language Model (VLM) and the raw image streams collected by a robot. Existing adaptation strategies require the definition of a close...
详细信息
Convolutional Neural network is state of the art of image recognition or image classification. However to build the robust model using CNN needs many parameters adjusted, and choosing the good combination hyperparamet...
详细信息
IoT technologies can facilitate machine-to-machine as well as human-to-machine interactions. Use of an automotive human-machine interface can help in exchanging information between vehicles and passengers or drivers. ...
详细信息
In this paper,region reaching controller is designed for fully actuated ocean surface vessels to reach a desired target region instead of a *** are not the requirements for both the pre-specified trajectory outside th...
详细信息
In this paper,region reaching controller is designed for fully actuated ocean surface vessels to reach a desired target region instead of a *** are not the requirements for both the pre-specified trajectory outside the desired region and the desired pinpoint position inside the desired *** controller design is based on the potential energy function,backstepping recursive design methodology,and the Lyapnov stability analysis *** the target region is specified arbitrarily small,the target region reduces to a point,and hence the region reaching control can be a generalisation of the setpoint *** results are presented to illustrate the performance of the proposed controller.
This research explores the use of Fuzzy K-Nearest Neighbor(F-KNN)and Artificial Neural Networks(ANN)for predicting heart stroke incidents,focusing on the impact of feature selection methods,specifically Chi-Square and...
详细信息
This research explores the use of Fuzzy K-Nearest Neighbor(F-KNN)and Artificial Neural Networks(ANN)for predicting heart stroke incidents,focusing on the impact of feature selection methods,specifically Chi-Square and Best First Search(BFS).The study demonstrates that BFS significantly enhances the performance of both *** BFS preprocessing,the ANN model achieved an impressive accuracy of 97.5%,precision and recall of 97.5%,and an Receiver Operating Characteristics(ROC)area of 97.9%,outperforming the Chi-Square-based ANN,which recorded an accuracy of 91.4%.Similarly,the F-KNN model with BFS achieved an accuracy of 96.3%,precision and recall of 96.3%,and a Receiver Operating Characteristics(ROC)area of 96.2%,surpassing the performance of the Chi-Square F-KNN model,which showed an accuracy of 95%.These results highlight that BFS improves the ability to select the most relevant features,contributing to more reliable and accurate stroke *** findings underscore the importance of using advanced feature selection methods like BFS to enhance the performance of machine learning models in healthcare applications,leading to better stroke risk management and improved patient outcomes.
The purpose of this study is to find out what makes Generation Z students accept and use Canva as a tool for making presentation materials. The conceptual framework of this study is the combination of "Technology...
详细信息
暂无评论