This paper presents a comprehensive approach to predicting student engagement and learning behavior by analyzing eye-tracking data combined with behavioral analysis using camera-based recognition algorithms. The propo...
详细信息
ISBN:
(数字)9798331525439
ISBN:
(纸本)9798331525446
This paper presents a comprehensive approach to predicting student engagement and learning behavior by analyzing eye-tracking data combined with behavioral analysis using camera-based recognition algorithms. The proposed system leverages WebGazer for eye-tracking to monitor gaze patterns and uses computer vision algorithms to recognize behaviors and emotional states. Feelings like engagement, frustration, or perplexity are identified using facial expression analysis. The system aims to provide real-time, actionable insights to students and educators by relating to emotional and concentration states by combining different modalities, thereby improving personalized learning strategies and educational outcomes.
Industrial processes are becoming increasingly complex and larger in scale, which has resulted in a constantly growing demand for robust, scalable monitoring systems. Conventional monitoring strategies entail a huge q...
详细信息
ISBN:
(数字)9798331519582
ISBN:
(纸本)9798331519599
Industrial processes are becoming increasingly complex and larger in scale, which has resulted in a constantly growing demand for robust, scalable monitoring systems. Conventional monitoring strategies entail a huge quantity of sensors and steep infrastructure charges, main to excessive electricity intake and operational costs. Burkhard Theen, vice president at weather analytics company Iteris describes a smart monitoring device using IoT sensors and predictive algorithms for accurately tracking industrial processes on this track. The system is made using a low-voltage IoT sensor community at essential points within the process, which constantly collects and transmits statistics in real time. This data is then fed into the predictive algorithms that use machinelearning techniques to analyze and determine any anomalies in the system. The system helps to improve process performance and reduce power consumption by identifying & addressing potential issues at their early stages.
Challenges in target detection include significant variations in target size, insufficient detection accuracy on small, resource-constrained devices, and the high cost of fully annotating large datasets. To address th...
详细信息
ISBN:
(纸本)9798400713231
Challenges in target detection include significant variations in target size, insufficient detection accuracy on small, resource-constrained devices, and the high cost of fully annotating large datasets. To address these issues, a semi-supervised lightweight target detection method based on the improved YOLOv7-tiny algorithm is proposed. First, a new spatial pyramid pooling network, MSPP, is designed to address the problem of significant variations in target size. Then, a lightweight convolutional attention module, GC-SAM, is introduced, which generates stronger feature representations by combining channel and spatial attention mechanisms. Finally, a multi feature semi-supervised data filtering method is proposed, which enhances the model's ability to learn valuable information from unlabeled data, effectively improving detection accuracy. Experimental results show that the improved algorithm achieves a detection accuracy of 82.2% and 63.6% for mAP@50 on 30% of the KITTI and SODA1000 datasets, which is 5.4% and 2.7% higher than the original model, respectively. The model size is only 14.4 MB and the detection speed is 82.1 frames per second, confirming the effectiveness of the algorithm.
This paper proposes an artificial intelligence-based adaptive Quality of Service (QoS) optimization framework for Internet of Things (IoT) devices in healthcare networks. IoT devices, such wearable monitoring and remo...
详细信息
ISBN:
(数字)9798331525439
ISBN:
(纸本)9798331525446
This paper proposes an artificial intelligence-based adaptive Quality of Service (QoS) optimization framework for Internet of Things (IoT) devices in healthcare networks. IoT devices, such wearable monitoring and remote diagnostic tools, struggle to maintain optimal performance due to fluctuating network circumstances and hardware limitations. The suggested system uses machinelearning and deep learning techniques to dynamically update QoS settings in order to achieve consistent, low-latency, and energy-efficient data transport. The AI model forecasts congestion, distributes resources optimally, and enhances network performance by continuously learning from real-time data and network conditions. This customisable solution improves healthcare delivery by providing timely, continuous services, resulting in better patient outcomes and ensuring the long-term viability of IoT healthcare networks. The framework's adaptive nature addresses scalability and flexibility challenges in healthcare IoT systems by constantly learning and optimising performance as network conditions change. The simulation results demonstrate how well the proposed solution works to improve QoS, ensure seamless healthcare delivery, and improve patient outcomes in dynamic network situations. This study paves the way for AI-powered healthcare IoT networks that are more reliable, responsive, and intelligent.
In the field of Parkinson’s’ disease diagnosis and progression monitoring, functional and structural connection patterns in the brain, which can be observed by modalities such as functional magnetic resonance imagin...
详细信息
ISBN:
(数字)9798331525439
ISBN:
(纸本)9798331525446
In the field of Parkinson’s’ disease diagnosis and progression monitoring, functional and structural connection patterns in the brain, which can be observed by modalities such as functional magnetic resonance imaging (MRI) and electroencephalography (EEG) are becoming more recognized as promising bio markers. An innovative use of Graph Neural Network (GNNs) is proposed in this study for analyzing patterns of brain connectivity. By utilizing the graph structure of brain networks, the researchers identify disturbances that are unique to Parkinson’s disease conditions. In the proposed framework, brain regions are represented as nodes, and the edges of the graph correspond to functional or structural connections derived from either fMRI or EEG data, depending on the modality used for analysis. The investigation of the brain regions and the connection that are most pertinent to the diagnosis can be accomplished through the utilization of attention weights in feature importance analysis. In recognizing brain network changes in Parkinson’s disease, the findings indicates that the GNN perform much better than traditional machinelearning methods. Additionally, these research offers significant advancements into mechanism of neuronal degeneration leads attention to certain regions of the brain and connected throughout the brain that are impacted by Parkinson’s disease. This work contributes to a more comprehensive knowledge of neural network disruptions in neurodegenerative disease and enhances the potential of GNN as diagnostic tool.
With the advancement of modern Internet technology, email is widely used in people's daily lives and has become one of the common communication tools. However, at the same time, email-based spam has also been wide...
详细信息
The rigid registration of two point clouds is a fundamental task in many areas, such as 3D reconstruction and robot navigation. The Iterative Closest Point (ICP) algorithm has been widely for this task. The basic prin...
详细信息
We proposes a new kind of contrast learning method based on Temporal-Correlation characters of electroencephalogram (EEG) used in sleep staging. This method, called simple framework of temporal-correlation representat...
详细信息
The current single-target trackers cannot detect the categories of the targets, and multi-object trackers have low performances due to the missed and false detections. Most of these trackers do not have the capabiliti...
详细信息
The boundary recognition algorithm of self-walking agricultural machine based on vision was proposed in this paper, which combined 2D-gabor with uniform pattern of LBP to extract the texture features of boundary area....
详细信息
ISBN:
(纸本)9781450365307
The boundary recognition algorithm of self-walking agricultural machine based on vision was proposed in this paper, which combined 2D-gabor with uniform pattern of LBP to extract the texture features of boundary area. After that, an algorithm that fuzzy extreme learningmachine based on KFCM was presented to improve the accuracy of boundary recognition. The experiment result shows that the proposed method is effective in classifying the boundary of the working area in the process of self-walking agriculture tractor, and owns highaccuracy.
暂无评论