Samhita Roy, U. L. Dang, Jakob Kneissl, G. Kilian, R. Meyer, F. Obernosterer
{"title":"Time Variant Doppler Compensation for TS-UNB","authors":"Samhita Roy, U. L. Dang, Jakob Kneissl, G. Kilian, R. Meyer, F. Obernosterer","doi":"10.1109/ICASSPW59220.2023.10192999","DOIUrl":"https://doi.org/10.1109/ICASSPW59220.2023.10192999","url":null,"abstract":"This paper extends a terrestrial Internet of Things (IoT) solution to the satellite communication scenario. The IoT solution considered for this paper, uses the Telegram Splitting Ultra Narrow Band (TS-UNB) protocol. TS-UNB is standardized as a technical specification in the European Telecommunications Standards Institute (ETSI) specifications for Low Throughput Networks. This framework describes the impact of Low Earth Orbit (LEO) satellite channel, specifically the time varying Doppler shift on a TS-UNB receiver. Traditionally the TS-UNB receiver is equipped to handle the Doppler impairments that are typically observed in terrestrial scenarios. However for mitigating the high Doppler drifts introduced by a LEO satellite, the paper proposes a solution that can be applied to any TS-UNB based receiver.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123724711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Next-Generation IoT Networks: Integrated Sensing Communication and Computation","authors":"Kunwar Pritiraj Rajput, Linlong Wu, B. Shankar","doi":"10.1109/ICASSPW59220.2023.10193000","DOIUrl":"https://doi.org/10.1109/ICASSPW59220.2023.10193000","url":null,"abstract":"To enable the exponential expansion of Internet of Things (IoT) applications, IoT devices must gather and transmit massive amounts of data to the server for further processing. By employing the same signals for both radar sensing and data transmission, the integrated sensing and communication (ISAC) approach provides simultaneous data gathering and delivery in the physical layer. Over-the-air computation (AirComp), which leverages the analog-wave addition property in multi-access channels, is a communication method that also supports function computation. In order to leverage the individual benefits of ISAC and AirComp, this work focuses on Integrated Sensing Communication and Computation (ISCCO) framework for the IoT network. Since the IoT sensors are small size low cost devices and each is equipped with single antenna, and hence to make the processing of received echo simple this work assume that the waveform transmitted by each sensor is orthogonal to each other. Furthermore, joint optimal power allocation for each sensor in the IoT network and the combining vector at the EC is designed such that the signal-to-noise (SNR) ratio at the EC is maximized. However, the design challenge lies in the non-convex joint optimal power allocation for each IoT device and the combining vector at the server. To address this, an iterative algorithm is proposed which provides closed-form solution for each quantity in each iteration. Results show that the proposed optimal power allocation and orthogonal waveform design scheme outperforms the equal power allocation-based design.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121469897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Improving Few-Shot Performance of DST Model Through Multitask to Better Serve Language-Impaired People","authors":"Mingyang Sun, QiXiang Gao, Yutao Mou, Guanting Dong, Ruifang Liu, Wenbin Guo","doi":"10.1109/ICASSPW59220.2023.10193387","DOIUrl":"https://doi.org/10.1109/ICASSPW59220.2023.10193387","url":null,"abstract":"Artificial intelligence-based virtual assistants make people’s daily life more convenient. However, the utterances of language-impaired people are limited and different in characteristics and domains from that of ordinary people. So it is difficult for language-impaired people to benefit from standard data-driven artificial intelligence algorithms. In this paper, we propose a multi-task training method for the dialogue state tracking (DST) task in dialogue systems that make up virtual assistants, improving the performance of T5 on the few-shot cross-domain DST task. Specifically, we consider two ways of handling DST task: predicting the dialogue state from the beginning or updating the dialogue state every turn, and accordingly design the main task and auxiliary task for the model. Experiments show that our method outperforms most previous works on the MultiWOZ 2.0 and 2.1 datasets for the few-shot cross-domain DST task. For the artificial-crafted language-impaired dataset, our method can effectively improve the few-shot cross-domain performance of the model. Additionally, we analyzed the possible reason why this multitasking approach works well.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114727105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Covid-19 Detection From X-Rays Images Using Deep Learning Methods","authors":"G. Sapountzakis, P. Theofilou, P. Tzouveli","doi":"10.1109/ICASSPW59220.2023.10193312","DOIUrl":"https://doi.org/10.1109/ICASSPW59220.2023.10193312","url":null,"abstract":"COVID-19 is a serious and highly contagious disease that causes infection of the respiratory system. Its severity varies from person to person. Many times patients’ health deteriorates rapidly and they need specialized medical care. For this reason, its early and reliable detection is important. Chest X-ray (CXR) imaging is widely used as an easy, accessible, economical and valid mean of COVID-19 diagnosis. In this work, using the COVID-QU-Ex dataset, which is the largest dataset of such images, we aim to build a deep learning system to produce efficient and reliable predictions in the detection problem of the disease COVID-19. Therefore, we focus on the study and comparison of state-of-the-art Deep Convolutional Neural Networks (DCNNs) for classification of CXR images and we use Grad-CAM to test their explainability.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"AES-14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126531952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Opportunistic Rainfall Measurements from Dual Channel KU-Band Receiver","authors":"F. Mercier-Tigrine, L. Barthès, C. Mallet","doi":"10.1109/ICASSPW59220.2023.10193748","DOIUrl":"https://doi.org/10.1109/ICASSPW59220.2023.10193748","url":null,"abstract":"We focus in this paper on the use of satellite attenuation in Ku-frequency band for measuring rainfall, using low-cost sensors allowing to measure only the total received power. This implies that the measured powers are not only composed of the satellite signal, but also include a radiometric contribution, which is the atmospheric radiation and the receiving system noise. In case of heavy rainfall, while the satellite signal weakens, the atmospheric radiation becomes more important and neglecting it can lead to a significant underestimation of rainfall. In this paper, we introduce the theoretical framework of these measurements, and derive a simple method for correcting this underestimation, based on the measurements of the received power on two channels (different frequencies and / or polarizations), one with strong satellite signal and the other one with no or weak satellite signal. Then we do a preliminary assessment of this method in Abidjan, Ivory Coast, where such a sensor has been deployed during 9 months close to a rain gauge. These preliminary results show that this method seems to lead to rainfall assessments better than using a single-channel approach, but only after a calibration phase to assess the difference in the gain of the system between the two channels we use.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115930831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Texture Quality Criteria Comparison","authors":"M. Haindl, Nahidbanu Shaikh","doi":"10.1109/ICASSPW59220.2023.10193606","DOIUrl":"https://doi.org/10.1109/ICASSPW59220.2023.10193606","url":null,"abstract":"Visual scene recognition or modeling predominantly uses visual textures representing an object’s material properties. However, the single material texture varies in scale and illumination angles due to mapping an object’s shape. We present a comparative study of thirteen possible texture quality criteria and show the superior performance of two multispectral measures derived from the Markovian descriptive model.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130221055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Julius Polz, Luca Glawion, Maximilian Graf, Nico Blettner, Elżbieta Lasota, Lennart Schmidt, H. Kunstmann, C. Chwala
{"title":"Expert Flagging of Commercial Microwave Link Signal Anomalies: Effect on Rainfall Estimation and Ambiguity of Flagging","authors":"Julius Polz, Luca Glawion, Maximilian Graf, Nico Blettner, Elżbieta Lasota, Lennart Schmidt, H. Kunstmann, C. Chwala","doi":"10.1109/ICASSPW59220.2023.10193654","DOIUrl":"https://doi.org/10.1109/ICASSPW59220.2023.10193654","url":null,"abstract":"Accurate detection of signal anomalies in the attenuation time-series from commercial microwave links (CMLs) is crucial for high quality rainfall estimates. Example causes of such anomalies include dew or ice on the antenna and multipath propagation. In a first effort to catalog examples of CML signal anomalies, four experts flagged suspicious segments in the time-series of 20 CMLs in Germany. The results show that the agreement between experts depends on the definition of the anomaly class. Removing the flagged anomalies increased the Pearson correlation coefficient between CML and radar rainfall estimates from 0.61 to 0.70 and reduced the BIAS by 40%. An implication of our study is that expert uncertainty is an important factor for the quality control of environmental sensor data.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134361335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Simulation of Micro-Doppler Signatures of Drones","authors":"Megha Kataria, B. Lall","doi":"10.1109/ICASSPW59220.2023.10193632","DOIUrl":"https://doi.org/10.1109/ICASSPW59220.2023.10193632","url":null,"abstract":"Drones or Unmanned Aerial Vehicles (UAVs) usage has increased considerably over the past years. Drones are being increasingly used for malicious activities in the recent times. So, there is a need for a good Anti Drone System(ADS). Dataset is a big issue if we are using machine learning techniques for drone detection. In this paper we present an approach for emulating drone and drone trajectory characteristics as captured in micro-doppler format. Mostly, work on simulation of micro-doppler signatures has been done for stationary targets, but in this paper, we allow for the target to have translational and rotational velocity. Also, such simulations are available only for quadcopters. We extend the set by creating the simulations for the case hexacopters, tricopters and octacopters We have used MATLAB software for our simulations.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114723542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
C. Oikonomou, I. Karolos, S. Bitharis, C. Pikridas, H. Haralambous
{"title":"Performance of a Low-Cost Dual-Frequency GNSS Receiver for Near Real-Time Water Vapor Estimation","authors":"C. Oikonomou, I. Karolos, S. Bitharis, C. Pikridas, H. Haralambous","doi":"10.1109/ICASSPW59220.2023.10193342","DOIUrl":"https://doi.org/10.1109/ICASSPW59220.2023.10193342","url":null,"abstract":"Tropospheric remote sensing based on high-grade Global Navigation Satellite Systems (GNSS) is nowadays an established technique termed as GNSS-Meteorology. The GNSS signal propagation delay in the troposphere provides information to infer Integrated Water Vapor (IWV), comprising a valuable data source for Numerical Weather Prediction (NWP) models. This study is aimed at investigating the performance of a low-cost dual-frequency GNSS receiver in tropospheric monitoring. For this purpose, near real-time estimates of IWV and Zenith Total Delay (ZTD) from the low-cost, GNSS Receiver “PREWAM” (Precipitable Water Vapor Monitor) (developed by Cloudwater Ltd) based on a sino gnssK803 chip are compared with respective ones deriving from a collocated Leica GR30 high-grade geodetic receiver during a four-month winter period in Cyprus. It is shown that PREWAM has the potential to provide tropospheric estimates with comparable accuracy to a high-grade receiver.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116308709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sándor Gazdag, Dániel Pasztornicky, Zsolt Jankó, T. Szirányi, A. Majdik
{"title":"Collaborative Visual-Inertial Localization of Teams With Floorplan Extraction","authors":"Sándor Gazdag, Dániel Pasztornicky, Zsolt Jankó, T. Szirányi, A. Majdik","doi":"10.1109/ICASSPW59220.2023.10192967","DOIUrl":"https://doi.org/10.1109/ICASSPW59220.2023.10192967","url":null,"abstract":"This paper showcases a real-world example of a system that achieves collaborative localization and mapping of multiple agents within a building. The proposed system processes the odometry and 3D point cloud data collected by the agents moving around the building to automatically generate the building’s floorplan on which the agent trajectories are overlaid. The wearable hardware consists of a low-cost passive integrated sensor that includes both a camera and an IMU (Inertial Measurement Unit) and an embedded compute unit. The system’s capabilities are shown through real-world experiments.","PeriodicalId":158726,"journal":{"name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123531723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}