Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208007
Thanh Trung LE, K. Abed-Meraim, P. Ravier, O. Buttelli
Block-term decomposition (BTD), which factorizes a tensor (aka a multiway array) into block components of low rank, has been a powerful processing tool for multivariate and high-dimensional data analysis. In this paper, we propose a novel tensor tracking method called SBTD for factorizing tensors derived from multidimensional data streams under the BTD format. Thanks to the alternating optimization framework, SBTD first applies a regularized least-squares solver to estimate the temporal factor of the underlying streaming tensor. Then, SBTD adopts an adaptive filter to track the non-temporal tensor factors over time by minimizing a weighted least-squares cost function. Numerical experiments indicate that SBTD is capable of tensor tracking with competitive performance compared to the state-of-the-art BTD algorithms.
{"title":"A Novel Tensor Tracking Algorithm for Block-Term Decomposition of Streaming Tensors","authors":"Thanh Trung LE, K. Abed-Meraim, P. Ravier, O. Buttelli","doi":"10.1109/SSP53291.2023.10208007","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208007","url":null,"abstract":"Block-term decomposition (BTD), which factorizes a tensor (aka a multiway array) into block components of low rank, has been a powerful processing tool for multivariate and high-dimensional data analysis. In this paper, we propose a novel tensor tracking method called SBTD for factorizing tensors derived from multidimensional data streams under the BTD format. Thanks to the alternating optimization framework, SBTD first applies a regularized least-squares solver to estimate the temporal factor of the underlying streaming tensor. Then, SBTD adopts an adaptive filter to track the non-temporal tensor factors over time by minimizing a weighted least-squares cost function. Numerical experiments indicate that SBTD is capable of tensor tracking with competitive performance compared to the state-of-the-art BTD algorithms.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133055528","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208054
Thien Huynh-The, Viet Quoc Pham, Thai-Hoc Vu, D. B. D. Costa, Van‐Phuc Hoang
The paper presents an intelligent spectrum sensing approach for next-generation wireless networks by exploiting deep learning, in which we develop a deep convolutional network (ConvNet) to automatically identify Fifth Generation New Radio (5G NR) and Long-Term Evolution (LTE) signals under standards-specified channel models with diversified RF impairments. In particular, we design a semantic segmentation ConvNet to detect and localize the spectral content of 5G NR and LTE in a synthetic signal featured by spectrum occupancy. A received signal is first converted by a short-time Fourier transform and represented as a wideband spectrogram image which is then passed through the ConvNet, incorporated by DeepLabv3+ and ResNet18 to improve the accuracy of pixel-wise segmentation to further increase the accuracy of signal identification. In the simulations, our ConvNet achieves around 95% mean accuracy and 91% mean intersection-over-union (IoU) at medium SNR level and demonstrates robustness under various practical channel impairments.
{"title":"Intelligent Spectrum Sensing with ConvNet for 5G and LTE Signals Identification","authors":"Thien Huynh-The, Viet Quoc Pham, Thai-Hoc Vu, D. B. D. Costa, Van‐Phuc Hoang","doi":"10.1109/SSP53291.2023.10208054","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208054","url":null,"abstract":"The paper presents an intelligent spectrum sensing approach for next-generation wireless networks by exploiting deep learning, in which we develop a deep convolutional network (ConvNet) to automatically identify Fifth Generation New Radio (5G NR) and Long-Term Evolution (LTE) signals under standards-specified channel models with diversified RF impairments. In particular, we design a semantic segmentation ConvNet to detect and localize the spectral content of 5G NR and LTE in a synthetic signal featured by spectrum occupancy. A received signal is first converted by a short-time Fourier transform and represented as a wideband spectrogram image which is then passed through the ConvNet, incorporated by DeepLabv3+ and ResNet18 to improve the accuracy of pixel-wise segmentation to further increase the accuracy of signal identification. In the simulations, our ConvNet achieves around 95% mean accuracy and 91% mean intersection-over-union (IoU) at medium SNR level and demonstrates robustness under various practical channel impairments.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129130475","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208024
Ehsan Lari, Vinay Chakravarthi Gogineni, R. Arablouei, Stefan Werner
The effectiveness of federated learning (FL) in leveraging distributed datasets is highly contingent upon the accuracy of model exchanges between clients and servers. Communication errors caused by noisy links can negatively impact learning accuracy. To address this issue, we present an FL algorithm that is robust to communication errors while reducing the communication load on clients. To derive the proposed algorithm, we consider a weighted least-squares regression problem as a motivating example. We cast the considered problem as a distributed optimization problem over a federated network, which employs random scheduling to enhance communication efficiency, and solve it using the alternating direction method of multipliers. To improve robustness, we eliminate the local dual parameters and reduce the number of global model exchanges via a change of variable. We analyze the mean convergence of our proposed algorithm and demonstrate its effectiveness compared with related existing algorithms via simulations.
{"title":"Resource-Efficient Federated Learning Robust to Communication Errors","authors":"Ehsan Lari, Vinay Chakravarthi Gogineni, R. Arablouei, Stefan Werner","doi":"10.1109/SSP53291.2023.10208024","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208024","url":null,"abstract":"The effectiveness of federated learning (FL) in leveraging distributed datasets is highly contingent upon the accuracy of model exchanges between clients and servers. Communication errors caused by noisy links can negatively impact learning accuracy. To address this issue, we present an FL algorithm that is robust to communication errors while reducing the communication load on clients. To derive the proposed algorithm, we consider a weighted least-squares regression problem as a motivating example. We cast the considered problem as a distributed optimization problem over a federated network, which employs random scheduling to enhance communication efficiency, and solve it using the alternating direction method of multipliers. To improve robustness, we eliminate the local dual parameters and reduce the number of global model exchanges via a change of variable. We analyze the mean convergence of our proposed algorithm and demonstrate its effectiveness compared with related existing algorithms via simulations.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131557684","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10207972
A. Falcon-Caro, M. Frîncu, S. Sanei
In this paper, for the first time a brain connectivity-enhanced diffusion adaptation is introduced and applied to an electroencephalogram (EEG) hyperscanning brain-computer interfacing scenario where the EEGs from two brains are recorded during the performance of a collaborative task. In the diffusion adaptation formulation for modeling, the link between one brain (under rehabilitation) which follows the other (healthy) brain, the combination weights are replaced by the connectivity estimates and the corresponding EEG channels of the healthy subject are used as the targets for the adaptation algorithm. The outcome can be used as a new rehabilitation platform where the state of the patient under rehabilitation depends on how well his/her brain signals can follow the target brain signals.
{"title":"A Diffusion Adaptation Approach to model Brain Responses in an EEG-based Hyperscanning Study","authors":"A. Falcon-Caro, M. Frîncu, S. Sanei","doi":"10.1109/SSP53291.2023.10207972","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10207972","url":null,"abstract":"In this paper, for the first time a brain connectivity-enhanced diffusion adaptation is introduced and applied to an electroencephalogram (EEG) hyperscanning brain-computer interfacing scenario where the EEGs from two brains are recorded during the performance of a collaborative task. In the diffusion adaptation formulation for modeling, the link between one brain (under rehabilitation) which follows the other (healthy) brain, the combination weights are replaced by the connectivity estimates and the corresponding EEG channels of the healthy subject are used as the targets for the adaptation algorithm. The outcome can be used as a new rehabilitation platform where the state of the patient under rehabilitation depends on how well his/her brain signals can follow the target brain signals.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134158643","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10207957
Jasin Machkour, Michael Muma, D. Palomar
Genomics biobanks are information treasure troves with thousands of phenotypes (e.g., diseases, traits) and millions of single nucleotide polymorphisms (SNPs). The development of methodologies that provide reproducible discoveries is essential for the understanding of complex diseases and precision drug development. Without statistical reproducibility guarantees, valuable efforts are spent on researching false positives. Therefore, scalable multivariate and high-dimensional false discovery rate (FDR)-controlling variable selection methods are urgently needed, especially, for complex polygenic diseases and traits. In this work, we propose the Screen-T-Rex selector, a fast FDR-controlling method based on the recently developed T-Rex selector. The method is tailored to screening large-scale biobanks and it does not require choosing additional parameters (sparsity parameter, target FDR level, etc). Numerical simulations and a real-world HIV-1 drug resistance example demonstrate that the performance of the Screen-T-Rex selector is superior, and its computation time is multiple orders of magnitude lower compared to current benchmark knockoff methods.
{"title":"False Discovery Rate Control for Fast Screening of Large-Scale Genomics Biobanks","authors":"Jasin Machkour, Michael Muma, D. Palomar","doi":"10.1109/SSP53291.2023.10207957","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10207957","url":null,"abstract":"Genomics biobanks are information treasure troves with thousands of phenotypes (e.g., diseases, traits) and millions of single nucleotide polymorphisms (SNPs). The development of methodologies that provide reproducible discoveries is essential for the understanding of complex diseases and precision drug development. Without statistical reproducibility guarantees, valuable efforts are spent on researching false positives. Therefore, scalable multivariate and high-dimensional false discovery rate (FDR)-controlling variable selection methods are urgently needed, especially, for complex polygenic diseases and traits. In this work, we propose the Screen-T-Rex selector, a fast FDR-controlling method based on the recently developed T-Rex selector. The method is tailored to screening large-scale biobanks and it does not require choosing additional parameters (sparsity parameter, target FDR level, etc). Numerical simulations and a real-world HIV-1 drug resistance example demonstrate that the performance of the Screen-T-Rex selector is superior, and its computation time is multiple orders of magnitude lower compared to current benchmark knockoff methods.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131903535","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208071
Madison Lee, O. Haddadin, T. Javidi
In this paper, we consider the problem of black-box function optimization. We propose an FFT-based algorithm that adaptively updates the parameters of a bandlimited Gaussian process surrogate model for the function. Our algorithm uses these parameters to construct approximate upper confidence bounds that determine its sampling behavior. We show that when the underlying function can be extended as a periodic function whose bandwidth is sufficiently small relative to the evaluation budget, our models converge to a perfect reconstruction, allowing our algorithm to recover the true optimizer. For periodic bandlimited function spaces, our algorithm has reduced complexity compared to traditional GP-UCB-based algorithms and demonstrates improved robustness.
{"title":"FFT-Based Approximations for Black-Box Optimization","authors":"Madison Lee, O. Haddadin, T. Javidi","doi":"10.1109/SSP53291.2023.10208071","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208071","url":null,"abstract":"In this paper, we consider the problem of black-box function optimization. We propose an FFT-based algorithm that adaptively updates the parameters of a bandlimited Gaussian process surrogate model for the function. Our algorithm uses these parameters to construct approximate upper confidence bounds that determine its sampling behavior. We show that when the underlying function can be extended as a periodic function whose bandwidth is sufficiently small relative to the evaluation budget, our models converge to a perfect reconstruction, allowing our algorithm to recover the true optimizer. For periodic bandlimited function spaces, our algorithm has reduced complexity compared to traditional GP-UCB-based algorithms and demonstrates improved robustness.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133913090","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208067
Van-Tam Nguyen, Enzo Tartaglione, Tuan Dinh
Attention and working memory, which are two fundamental components of cognitive basis, can be improved through cognitive training. In addition, thanks to neuroplasticity, neurons are able to adapt quickly to the demands placed on them. By developing new neural networks and strengthening important connections, a cognitive training program can measurably and permanently improve brain activity. In this paper, we present a concept of AIoT based neural decoding and neurofeedback to accelerate cognitive training, the preliminary results and research directions. The proposed concept is to design adequate tiny machine learning to extract the relevant features and characteristics from physiological signals. A tiny ML performs classification or recognition of relevant patterns, based on which the neurofeedback system is appropriately designed for more effective cognitive training.
{"title":"AIoT-based Neural Decoding and Neurofeedback for Accelerated Cognitive Training: Vision, Directions and Preliminary Results","authors":"Van-Tam Nguyen, Enzo Tartaglione, Tuan Dinh","doi":"10.1109/SSP53291.2023.10208067","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208067","url":null,"abstract":"Attention and working memory, which are two fundamental components of cognitive basis, can be improved through cognitive training. In addition, thanks to neuroplasticity, neurons are able to adapt quickly to the demands placed on them. By developing new neural networks and strengthening important connections, a cognitive training program can measurably and permanently improve brain activity. In this paper, we present a concept of AIoT based neural decoding and neurofeedback to accelerate cognitive training, the preliminary results and research directions. The proposed concept is to design adequate tiny machine learning to extract the relevant features and characteristics from physiological signals. A tiny ML performs classification or recognition of relevant patterns, based on which the neurofeedback system is appropriately designed for more effective cognitive training.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133167996","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10207927
D. Tran, Ba Linh Vu, Xuan Nguyen Tien
In this paper, we propose an improved deterministic usage of the Elliptic Curve Digital Signature Algorithm (ECDSA) with the key derivation function scrypt. In particular, the scrypt function generates a batch of random bits where the random bits needed for the signing process are selected. As a certain number of bits is chosen from a bigger set, the reuse of the secret random number for each signing process is avoided, which is against fault and side-channel attacks. Numerical results are provided for five different-length messages and seventeen private keys considered as inputs for deterministic ECDSA and our proposed method. The random quality assessment using a statistical test suite of the National Institute of Standards and Technology (NIST) shows that our proposed method generates higher-quality random bit sequences, which can be seen clearly with one- and two-million-bit lengths respectively.
{"title":"Improved Deterministic Usage of the Elliptic Curve Digital Signature Algorithm with Scrypt","authors":"D. Tran, Ba Linh Vu, Xuan Nguyen Tien","doi":"10.1109/SSP53291.2023.10207927","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10207927","url":null,"abstract":"In this paper, we propose an improved deterministic usage of the Elliptic Curve Digital Signature Algorithm (ECDSA) with the key derivation function scrypt. In particular, the scrypt function generates a batch of random bits where the random bits needed for the signing process are selected. As a certain number of bits is chosen from a bigger set, the reuse of the secret random number for each signing process is avoided, which is against fault and side-channel attacks. Numerical results are provided for five different-length messages and seventeen private keys considered as inputs for deterministic ECDSA and our proposed method. The random quality assessment using a statistical test suite of the National Institute of Standards and Technology (NIST) shows that our proposed method generates higher-quality random bit sequences, which can be seen clearly with one- and two-million-bit lengths respectively.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132775037","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10208073
Maharaj Faawwaz A Yusran, Tengku Siti Aisha Tengku Mohd Azzman, S. Saw, Zati Hakim Azizul Hasan
Approximately 10% of neonates require assistance transitioning from intrauterine to extrauterine environments. Applying these interventions requires accurate monitoring of vitals such as heart and respiratory rates. However, the current methods of these vital measurements require many devices to be attached to the neonates, resulting in rather intrusive methods that could even harm the neonates if not administered properly. This pilot study investigates the possibility of applying signal processing along with automated machine learning and deep learning models to estimate heart rate from respiratory signals recorded using inductance bands. The best machine learning model can get an average MAE of 10.15 BPM, and the best deep learning model at 10.88 BPM. The advantage of applying such a method would be reducing devices attached to neonates while preserving estimation accuracy.
{"title":"Machine Learning Methods for Neonatal Heart Rate Prediction using Respiratory Signals","authors":"Maharaj Faawwaz A Yusran, Tengku Siti Aisha Tengku Mohd Azzman, S. Saw, Zati Hakim Azizul Hasan","doi":"10.1109/SSP53291.2023.10208073","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10208073","url":null,"abstract":"Approximately 10% of neonates require assistance transitioning from intrauterine to extrauterine environments. Applying these interventions requires accurate monitoring of vitals such as heart and respiratory rates. However, the current methods of these vital measurements require many devices to be attached to the neonates, resulting in rather intrusive methods that could even harm the neonates if not administered properly. This pilot study investigates the possibility of applying signal processing along with automated machine learning and deep learning models to estimate heart rate from respiratory signals recorded using inductance bands. The best machine learning model can get an average MAE of 10.15 BPM, and the best deep learning model at 10.88 BPM. The advantage of applying such a method would be reducing devices attached to neonates while preserving estimation accuracy.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"441 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125781394","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}
Pub Date : 2023-07-02DOI: 10.1109/SSP53291.2023.10207939
Somaya Sadik, Mohamed Et-tolba, B. Nsiri
Nowadays, conventional statistical approaches to stock price forecasting fail to provide accurate predictions because financial data are affected by noise from different sources. To deal with this issue, we propose to apply Bayesian compressed sensing (BCS) for noise removal before performing any prediction. This results in a hybrid forecasting model combining BCS, denoising, and a prediction technique. The BCS approach was chosen instead of the traditional compressed sensing (CS) due to its superiority in terms of signal recovery accuracy. In the prediction step, we consider three models namely, autoregressive integrated moving average (ARIMA), long short-term memory (LSTM), and forward neural networks (FNN). The Standard & Poor 500 index (SP500), the Hang Seng index (HSI), and the Euro Stock 50 index (EU50) series are used as sample data for validation. In terms of accuracy, numerical results show that the proposed BCS-based hybrid models provide better performance compared to their single counterparts.
{"title":"Bayesian Compressed Sensing-Based Hybrid Models for Stock Price Forecasting","authors":"Somaya Sadik, Mohamed Et-tolba, B. Nsiri","doi":"10.1109/SSP53291.2023.10207939","DOIUrl":"https://doi.org/10.1109/SSP53291.2023.10207939","url":null,"abstract":"Nowadays, conventional statistical approaches to stock price forecasting fail to provide accurate predictions because financial data are affected by noise from different sources. To deal with this issue, we propose to apply Bayesian compressed sensing (BCS) for noise removal before performing any prediction. This results in a hybrid forecasting model combining BCS, denoising, and a prediction technique. The BCS approach was chosen instead of the traditional compressed sensing (CS) due to its superiority in terms of signal recovery accuracy. In the prediction step, we consider three models namely, autoregressive integrated moving average (ARIMA), long short-term memory (LSTM), and forward neural networks (FNN). The Standard & Poor 500 index (SP500), the Hang Seng index (HSI), and the Euro Stock 50 index (EU50) series are used as sample data for validation. In terms of accuracy, numerical results show that the proposed BCS-based hybrid models provide better performance compared to their single counterparts.","PeriodicalId":296346,"journal":{"name":"2023 IEEE Statistical Signal Processing Workshop (SSP)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127543657","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：