| 1. |
- Jiang, Meng, et al.
(författare)
-
Performance Comparison of Omni and Cardioid Directional Microphones for Indoor Angle of Arrival Sound Source Localization
- 2022
-
Ingår i: Conference Record - IEEE Instrumentation and Measurement Technology Conference. - : IEEE. - 9781665483605
-
Konferensbidrag (refereegranskat)abstract
- The sound source localization technology brings the possibility of mapping the sound source positions. In this paper, angle-of-arrival (AOA) has been chosen as the method for achieving sound source localization in an indoor enclosed environment. The dynamic environment and reverberations bring a challenge for AOA-based systems for such applications. By the acknowledgement of microphone directionality, the cardioid-directional microphone systems have been chosen for the localization performance comparison with omni-directional microphone systems, in order to investigate which microphone is superior in AOA indoor sound source localization. To reduce the hardware complexity, the number of microphones used during the experiment has been limited to 4. A localization improvement has been proposed with a weighting factor. The comparison has been done for both types of microphones with 3 different array manifolds under the same system setup. The comparison shows that the cardioid-directional microphone system has an overall higher accuracy.
|
|
| 2. |
- Lv, Zhihan, Dr. 1984-, et al.
(författare)
-
Traffic Safety Detection System by Digital Twins and Virtual Reality Technology
- 2022
-
Ingår i: 2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC 2022). - : IEEE. - 9781665483605 - 9781665483612
-
Konferensbidrag (refereegranskat)abstract
- The present work studies the prediction of vehicle driving states to enhance the accuracy of traffic safety detection under new technologies. Firstly, the vehicle simulator and environment virtual system are built based on vehicle dynamics through virtual reality (VR) technology. Secondly, the vehicle Digital Twins (DTs) model is constructed based on various sensors and the Gaussian process algorithm. Besides, the vehicle simulator uses the Adams-Moulton-2 algorithm in CarSim software for numerical calculation. Finally, the background subtraction method is introduced to monitor and predict the vehicle motion state. The simulation results indicate that the engine of the vehicle DTs system constructed here changes with the rotational speed by the actual value. Besides, the maximum prediction error of the Gaussian process reported here is 2. 55, and the maximum error of the deep neural convolutional network is 4.29, indicating high prediction accuracy of the Gaussian process. Moreover, the background subtraction method selected in the present work has a high detection rate and low false alarm rate. The present work provides a reference for the development of DTs technology and VR technology in the field of transportation.
|
|
| 3. |
- Nie, Yali, et al.
(författare)
-
Skin Cancer Classification based on Cosine Cyclical Learning Rate with Deep Learning
- 2022
-
Ingår i: Conference Record - IEEE Instrumentation and Measurement Technology Conference. - : IEEE. - 9781665483605
-
Konferensbidrag (refereegranskat)abstract
- Since early-stage skin cancer identification can improve melanoma prognosis and significantly reduce treatment costs, AI-based diagnosis systems might greatly benefit patients suffering from suspicious skin lesions. The study proposes a cosine cyclical learning rate with a skin cancer classification model to improve melanoma prediction. The contributions of models involve three critical CNNs, which are standard deep feature extraction modules for the skin cancer classification in this study (Vgg19, ResNet101 and InceptionV3). Each CNN model applies three different learning rates: fixed learning rate(LR), Cosine Annealing LR, and Cosine Annealing with WarmRestarts. HAM10000 is a large collection of publicly available dermoscopic images dataset used for our experiments. The performance of the proposed approach was appraised through comparative experiments. The outcome has indicated that the proposed method has high efficiency in diagnosing skin lesions with a cosine cyclical learning rate.
|
|
