To address the challenge of inaccurate volleyball height detection and localization due to complex environments and low image resolution during volleyball bobble assessments, a refined detection algorithm, YOLOv8n-SPD...
详细信息
ISBN:
(数字)9798350349252
ISBN:
(纸本)9798350349269
To address the challenge of inaccurate volleyball height detection and localization due to complex environments and low image resolution during volleyball bobble assessments, a refined detection algorithm, YOLOv8n-SPD, is proposed. This algorithm enhances the YOLOv8n model by incorporating several key improvements. Firstly, a meticulously labeled dataset of volleyball bobble images is created. The algorithm integrates a Spatial Depth Convolution module (SPD-Conv), which preprocesses images prior to their entry into the neural network. By eliminating the max-pooling layer, redundant pixel information is reduced. Secondly, the activation function Mish is employed instead of SiLU to diminish the interdependence of parameters and enhance the adaptability of the network. Additionally, the DIoU replaces the original CIoU loss function, aiming to better align the predicted and actual bounding boxes. Experimental results show that YOLOv8n-SPD improves the mAP@0.5 metric from 99.3% to 99.4% and the mAP@0.5-0.95 metric from 86.5% to 87.6%, with an increase in GFLOPS from 8.1 to 11.5. This algorithm not only enhances accuracy but also improves real-time performance and stability in complex scenarios.
Wireless sensor networks (WSN) are increasingly used to support critical applications - especially in enterprise settings. If the sensor data collected through the network is incorrect, such applications cannot run re...
详细信息
ISBN:
(纸本)9781467351461
Wireless sensor networks (WSN) are increasingly used to support critical applications - especially in enterprise settings. If the sensor data collected through the network is incorrect, such applications cannot run reliably. Thus, detecting the occurrence of abnormal sensor values is crucial. In this paper we develop three decentralized, lightweight data anomaly detection mechanisms that can be run directly on sensor nodes. These algorithms are evaluated with a real dataset to which we added plausible attacks. Further, they are compared to standard centralized anomaly detection mechanisms.
In recent years, the evolution of online social networks has become an important research topic in online social network analysis. An important approach to this problem is to detect community evolution events so as to...
详细信息
In recent years, the evolution of online social networks has become an important research topic in online social network analysis. An important approach to this problem is to detect community evolution events so as to understand the evolution of the whole network. Considering the huge amount of data in large social networks, an efficient and scalable community evolution detection algorithm is necessary. In this paper, we focus on community evolution events detection in dynamic social networks. First, we divide the Facebook and DBLP data set into a series of snapshots and apply the Louvain algorithm to find the communities in each snapshot. Then, we propose a light weight evolution events detection algorithm to find the community evolution patterns between adjacent snapshots, which statistically show the evolution trend of the entire network. Simulation results show that our algorithm can effectively detect the community evolution events in online social networks.
A small leak will sink a great ship. The existence of various cracks poses a huge threat to the quality and safety of engineering construction. For manual inspection of cracks, various complex cracks have high false d...
详细信息
ISBN:
(纸本)9781665402682
A small leak will sink a great ship. The existence of various cracks poses a huge threat to the quality and safety of engineering construction. For manual inspection of cracks, various complex cracks have high false detections or missed detections. Therefore, we proposed a crack detection algorithm based on attention mechanism to automatically locate cracks to improve the safety of the engineering construction. By improving the CSP layer in the backbone of YOLOv5, it introduces an attention mechanism called pyramid split attention (PSA) to focus on the importance of different channels to make the network better learn the crack features. In addition, during the testing process, we use TTA to synthesize the network detection performances at different scales to get the final detection results more accurately. Finally, the F1 score of our network reached a high level on the RDDC2020 dataset.
An article is dedicated to creation of locally-optimal robust algorithm of non-Gaussian signal detection on the base of sampling statistical analysis and to investigation of the algorithm effectiveness.
An article is dedicated to creation of locally-optimal robust algorithm of non-Gaussian signal detection on the base of sampling statistical analysis and to investigation of the algorithm effectiveness.
The paper proposes a novel method to detect fire and/or flame by processing the video data generated by an ordinary camera monitoring a scene. In addition to ordinary motion and color clues, flame and fire flicker are...
详细信息
The paper proposes a novel method to detect fire and/or flame by processing the video data generated by an ordinary camera monitoring a scene. In addition to ordinary motion and color clues, flame and fire flicker are detected by analyzing the video in the wavelet domain. Periodic behavior in flame boundaries is detected by performing a temporal wavelet transform. Color variations in fire are detected by computing the spatial wavelet transform of moving fire-colored regions. Other clues used in the fire detection algorithm include irregularity of the boundary of the fire-colored region and the growth of such regions in time. All of the above clues are combined to reach a final decision.
A new mark-detection algorithm for synchronous optical CDMA using modified prime sequence codes is proposed. Performance analysis shows that the bit error probability (BER) is significantly improved when using the mar...
详细信息
A new mark-detection algorithm for synchronous optical CDMA using modified prime sequence codes is proposed. Performance analysis shows that the bit error probability (BER) is significantly improved when using the mark-detection algorithm in the presence of avalanche photodiode (APD) noise, thermal noise and interference.
In this paper, to accurately establish sea clutter model, we propose a 3-partitioned random multiplicative mechanism using multifractal theory to tackle the high-frequency radar sea clutter, which could extract featur...
详细信息
ISBN:
(数字)9798350355895
ISBN:
(纸本)9798350355901
In this paper, to accurately establish sea clutter model, we propose a 3-partitioned random multiplicative mechanism using multifractal theory to tackle the high-frequency radar sea clutter, which could extract feature factors from sea clutter data and verifies the multifractal features. Furthermore, we present a clutter energy priority SVD-OP (CEP-SVD-OP) based detection algorithm. In which, echo signals of the selected distance units are combined into a signal space, and processed by orthogonal projection idea. Then, the clutter suppression is performed again for all the distance units on the individual pulses after orthogonal projection. The singular values are utilized to determine the signal subspace and clutter subspace. After eliminating the clutter subspace, the signal is reconstructed using the Hankel matrix, and the detection-flow can be achieved. Simulations has demonstrated that CEP-SVD-OP algorithm obtains some superior performance in sea clutter suppression and target detection.
Nowadays, automatic speech recognizers have become quite good in recognizing well prepared fluent speech (e.g. news readings). However, the recognition of unprepared or spontaneous speech is still problematic. Some im...
详细信息
Nowadays, automatic speech recognizers have become quite good in recognizing well prepared fluent speech (e.g. news readings). However, the recognition of unprepared or spontaneous speech is still problematic. Some important reasons for this are that spontaneous speech is less articulated, exhibits a high speaking rate and usually contains a lot of disfluencies. The latter occur when the speaker needs time to think about the continuation of his discourse, or when he needs to change/correct his last utterance. Although there are different types of disfluencies (interruptions, corrections, repetitions, etc.) the most common ones are filled pauses. They can take the form of an interjection like /uh/ or /uhm/, or an abnormal lengthening of one syllable of a word. In this paper we propose a new method for detecting such fillers prior to the speech recognition. Tests show that it is possible to improve the recognition accuracy by just removing the detected filled pauses from the recognizer input.
detection of anomalies in multivariate time series is an important data mining task with potential applications in medical diagnosis, ecosystem modeling, and network traffic monitoring. In this paper, we present a rob...
详细信息
detection of anomalies in multivariate time series is an important data mining task with potential applications in medical diagnosis, ecosystem modeling, and network traffic monitoring. In this paper, we present a robust graph-based algorithm for detecting anomalies in noisy multivariate time series data. A key feature of the algorithm is the alignment of kernel matrices constructed from the time series. The aligned kernel enables the algorithm to capture the dependence relationship between different time series and to support the discovery of different types of anomalies (including subsequence-based and local anomalies). We have performed extensive experiments to demonstrate the effectiveness of the proposed algorithm. We also present a case study that shows the utility of applying our algorithm to detect ecosystem disturbances in Earth science data.
暂无评论