In today's AI-driven era, deep learning (DL) algorithms play a crucial role in automatically detecting life-threatening skin cancers, thereby significantly enhancing survival rates. It makes skin cancer detection ...
详细信息
An Intelligent data processing is essential to create a large amount of data in Internet of things. We progress the consistent smooth and computerized uses of artificial intelligence, machinelearning, deep learning. ...
详细信息
Human activity recognition (HAR) has developed rapidly in recent years due to its widespread applications in motion analysis, mobile health monitoring, security, and rehabilitation. However, due to missing sensor data...
详细信息
ISBN:
(纸本)9798400710582
Human activity recognition (HAR) has developed rapidly in recent years due to its widespread applications in motion analysis, mobile health monitoring, security, and rehabilitation. However, due to missing sensor data, complex application scenarios, poor model robustness, existing HAR algorithms still cannot meet application requirements. In this context, the Sussex-Huawei Locomotion (SHL) recognition challenge provides a dataset for improving HAR algorithms. In this study, our team (SIAT-BIT) proposes a three-branch convolutional neural network framework for SHL recognition challenge. Firstly, the data is preprocessed for feature extraction, and then three classifiers are trained in parallel using three cross-entropy loss functions. The experimental results show that the proposed model achieves the best performance with the least model parameters. In addition, we further improved the performance through post-smoothing. Finally, we get an average accuracy of 0.9274 on the validation dataset.
data augmentation is a commonly used method for training networks in deep learning. For object detection tasks, data augmentation methods include random flip, random crop, etc. For semantic segmentation tasks, data en...
详细信息
The frequency of potholes and speed bumps on the roads has linearly increased due to ageing, inadequate maintenance, and a growth in the number of vehicles. We have discussed a prototype for the identification of poth...
详细信息
Discovering symbolic models is growing in popularity with the increasing interest in interpretable machinelearning. Symbolic regression is the task of learning an analytical form of underlying models in data. Two mac...
详细信息
ISBN:
(纸本)9783031283499;9783031283505
Discovering symbolic models is growing in popularity with the increasing interest in interpretable machinelearning. Symbolic regression is the task of learning an analytical form of underlying models in data. Two machinelearning techniques have proven their effectiveness: reinforce trick and transformer neural network. This paper discusses in detail the two techniques and presents the application of symbolic regression on a simulated data set that describes a high-energy physics process.
This paper motivates the concept of urban monitoring in a decision-making framework for emergency responses to technical systems that support various types of urban performance, and discussed its conceptual and techni...
详细信息
Nowadays, the MOBA game is the game type with the most audiences and players around the world. Recently, the League of Legends has become an official sport as an e-sport among 37 events in the 2022 Asia Games held in ...
详细信息
Unsupervised multiplex graph representation learning (UMGRL) has received increasing interest, but few works simultaneously focused on the common and private information extraction. In this paper, we argue that it is ...
详细信息
Unsupervised multiplex graph representation learning (UMGRL) has received increasing interest, but few works simultaneously focused on the common and private information extraction. In this paper, we argue that it is essential for conducting effective and robust UMGRL to extract complete and clean common information, as well as more-complementarity and less-noise private information. To achieve this, we first investigate disentangled representation learning for the multiplex graph to capture complete and clean common information, as well as design a contrastive constraint to preserve the complementarity and remove the noise in the private information. Moreover, we theoretically analyze that the common and private representations learned by our method are provably disentangled and contain more task-relevant and less task-irrelevant information to benefit downstream tasks. Extensive experiments verify the superiority of the proposed method in terms of different downstream tasks.
Land Use and Land Cover (LULC) change refer to the loss of natural areas, particularly forests, agricultural areas, or water bodies, to urban or exurban development. Understanding how LULC will impact the district of ...
详细信息
ISBN:
(纸本)9789819774661
Land Use and Land Cover (LULC) change refer to the loss of natural areas, particularly forests, agricultural areas, or water bodies, to urban or exurban development. Understanding how LULC will impact the district of Hanamkonda’s water resource availability is crucial. In order to conduct tasks like change detection analysis and theme mapping, baseline data on land cover must be determined. Expanding urban areas affects natural resources and makes them vulnerable. As it is observed that rapid changes are occurring in LULC around the water bodies, this will badly affect the quantity and quality of water resources, increasing the pressure on water availability in urban areas. It also creates flood hazards in the surrounding areas of the water bodies due to not protecting the boundaries of the water bodies. Any loss in the water surface area will also impact the groundwater resources in the region. The Hanamkonda district of Telangana state, India, has many water bodies. Over the period, the surroundings of some of the water bodies are highly urbanised, causing stress on water resource availability and flood-related problems during monsoon season. The land use and land cover changes for the four lake systems in the Hanamkonda district over a ten-year period, from 2013 to 2022, are presented in this paper using machinelearning algorithms in the Google Earth Engine site. The accuracy assessment is used to compare the performance of the two machinelearning algorithms such as Random Forest (RF) and Support Vector machine (SVM) in the classification of LULC. For the years 2013, 2016, 2019, and 2022, Landsat-8 data is used, and the major LULC classes are ‘water bodies’, ‘urban’, ‘vegetation’, and ‘barren’. The average overall accuracy of RF and SVM classifiers is 88.47% and 91.92%, respectively. The results suggest that the support vector machine classifier outperforms the random forest classifier in terms of accuracy. The findings revealed that from 2013 to 2022, water bo
暂无评论