Pub Date : 2019-04-16DOI: 10.1109/CISS.2019.8692935
Henri Hentila, V. Koivunen, H. Poor, Rick S. Blum
A secret key generation scheme is proposed for generating keys to be used for one-time pad encryption. This type of encryption is suitable for e.g., short packet communication in distributed inference in IoT. The scheme exploits the phase of the channel fading coefficient in a Rayleigh fading channel to extract highly correlated key bits at two legitimate parties. Compared to other existing methods, the proposed scheme trades off higher bit error probabilities in the keys for lower error correction communication requirements. The bit error of generated keys is characterized via an approximate upper bound, which is shown to be fairly tight for reasonable signal-to-noise ratios.
{"title":"Secure Key Generation for Distributed Inference in IoT Invited Presentation","authors":"Henri Hentila, V. Koivunen, H. Poor, Rick S. Blum","doi":"10.1109/CISS.2019.8692935","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692935","url":null,"abstract":"A secret key generation scheme is proposed for generating keys to be used for one-time pad encryption. This type of encryption is suitable for e.g., short packet communication in distributed inference in IoT. The scheme exploits the phase of the channel fading coefficient in a Rayleigh fading channel to extract highly correlated key bits at two legitimate parties. Compared to other existing methods, the proposed scheme trades off higher bit error probabilities in the keys for lower error correction communication requirements. The bit error of generated keys is characterized via an approximate upper bound, which is shown to be fairly tight for reasonable signal-to-noise ratios.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124437902","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 : 2019-04-16DOI: 10.1109/CISS.2019.8692864
Derek Allman, Fabrizio R. Assis, J. Chrispin, M. Bell
Catheter guidance is typically performed with fluoroscopy, which requires patient and operator exposure to ionizing radiation. Our group is exploring robotic photoacoustic imaging as an alternative to fluoroscopy to track catheter tips. However, the catheter tip segmentation step in the photoacoustic-based robotic visual servoing algorithm is limited by the presence of confusing photoacoustic artifacts. We previously demonstrated that a deep neural network is capable of detecting photoacoustic sources in the presence of artifacts in simulated, phantom, and in vivo data. This paper directly compares the in vivo results obtained with linear and phased ultrasound receiver arrays. Two convolutional neural networks (CNNs) were trained to detect point sources in simulated photoacoustic channel data and tested with in vivo images from a swine catheterization procedure. The CNN trained with a linear array receiver model correctly classified 88.8% of sources, and the CNN trained with a phased array receiver model correctly classified 91.4% of sources. These results demonstrate that a deep learning approach to photoacoustic image formation is capable of detecting catheter tips during interventional procedures. Therefore, the proposed approach is a promising replacement to the segmentation step in photoacoustic-based robotic visual servoing algorithms.
{"title":"Deep learning to detect catheter tips in vivo during photoacoustic-guided catheter interventions : Invited Presentation","authors":"Derek Allman, Fabrizio R. Assis, J. Chrispin, M. Bell","doi":"10.1109/CISS.2019.8692864","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692864","url":null,"abstract":"Catheter guidance is typically performed with fluoroscopy, which requires patient and operator exposure to ionizing radiation. Our group is exploring robotic photoacoustic imaging as an alternative to fluoroscopy to track catheter tips. However, the catheter tip segmentation step in the photoacoustic-based robotic visual servoing algorithm is limited by the presence of confusing photoacoustic artifacts. We previously demonstrated that a deep neural network is capable of detecting photoacoustic sources in the presence of artifacts in simulated, phantom, and in vivo data. This paper directly compares the in vivo results obtained with linear and phased ultrasound receiver arrays. Two convolutional neural networks (CNNs) were trained to detect point sources in simulated photoacoustic channel data and tested with in vivo images from a swine catheterization procedure. The CNN trained with a linear array receiver model correctly classified 88.8% of sources, and the CNN trained with a phased array receiver model correctly classified 91.4% of sources. These results demonstrate that a deep learning approach to photoacoustic image formation is capable of detecting catheter tips during interventional procedures. Therefore, the proposed approach is a promising replacement to the segmentation step in photoacoustic-based robotic visual servoing algorithms.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128903612","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 : 2019-04-16DOI: 10.1109/CISS.2019.8692847
A. Garnaev, W. Trappe
In this paper, we consider how subjectivity affects the problem of reliable communication. To model subjective factor we formulate a prospect theoretical (PT) extension of a zero sum game involving a primary user (PU) that must communicate with one of n users, while avoiding being jammed by an adversary. We prove that the PT equilibrium strategies, which are generalizations of the Nash equilibrium, exist for any probability weighting functions that models the corresponding subjective factors. Moreover, the PT-equilibrium strategy for the adversary is unique, and it can be found in water-filling form. We establish conditions for the PT-equilibrium of the PU to be unique. If PT-equilibrium of the PU is not unique, then a continuum of PT-equilibria arise. All of the PT-equilibria are found in water-filling form, and a hierarchical relationship between the derived water-filling equations is established. Finally, the sensitivity of the PT equilibrium strategies to environmental parameters is theoretically proven and numerically illustrated.
{"title":"A Prospect Theoretical Extension of a Communication Game Under Jamming","authors":"A. Garnaev, W. Trappe","doi":"10.1109/CISS.2019.8692847","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692847","url":null,"abstract":"In this paper, we consider how subjectivity affects the problem of reliable communication. To model subjective factor we formulate a prospect theoretical (PT) extension of a zero sum game involving a primary user (PU) that must communicate with one of n users, while avoiding being jammed by an adversary. We prove that the PT equilibrium strategies, which are generalizations of the Nash equilibrium, exist for any probability weighting functions that models the corresponding subjective factors. Moreover, the PT-equilibrium strategy for the adversary is unique, and it can be found in water-filling form. We establish conditions for the PT-equilibrium of the PU to be unique. If PT-equilibrium of the PU is not unique, then a continuum of PT-equilibria arise. All of the PT-equilibria are found in water-filling form, and a hierarchical relationship between the derived water-filling equations is established. Finally, the sensitivity of the PT equilibrium strategies to environmental parameters is theoretically proven and numerically illustrated.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114102495","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 : 2019-04-16DOI: 10.1109/CISS.2019.8693055
Annan Dong, O. Simeone, A. Haimovich, J. Dabin
Radio frequency sources are observed at a fusion center via sensor measurements made over slow unknown flat-fading channels. The number of sources may be larger than the number of sensors, but their activity is sparse and intermittent with bursty transmission patterns accounted by hidden Markov models. The problem of blind source estimation in the absence of channel state information is tackled via a novel algorithm, consisting of a dictionary learning (DL) stage and a per-source stochastic filtering (PSF) stage. To this end, smooth LASSO is integrated with DL, while the forward-backward algorithm is leveraged for PSF. It is shown that the proposed algorithm can enhance the detection performance of the sources.
{"title":"Sparse Dictionary Learning and Per-source Filtering for Blind Radio Source Separation","authors":"Annan Dong, O. Simeone, A. Haimovich, J. Dabin","doi":"10.1109/CISS.2019.8693055","DOIUrl":"https://doi.org/10.1109/CISS.2019.8693055","url":null,"abstract":"Radio frequency sources are observed at a fusion center via sensor measurements made over slow unknown flat-fading channels. The number of sources may be larger than the number of sensors, but their activity is sparse and intermittent with bursty transmission patterns accounted by hidden Markov models. The problem of blind source estimation in the absence of channel state information is tackled via a novel algorithm, consisting of a dictionary learning (DL) stage and a per-source stochastic filtering (PSF) stage. To this end, smooth LASSO is integrated with DL, while the forward-backward algorithm is leveraged for PSF. It is shown that the proposed algorithm can enhance the detection performance of the sources.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130021216","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 : 2019-04-16DOI: 10.1109/CISS.2019.8692938
S. Hirasawa, H. Yagi, Manabu Kobayashi, M. Kasahara
Performance of block codes constructed by unit memory (UM) trellis codes is discussed from random coding arguments. There are three methods to obtain block codes from trellis codes, i.e., those of (a) Tail Termination (TT), (b) Direct Truncation (DT), and (c) Tail Biting (TB). In this paper, we derive exponential error bounds and decoding complexity for block codes constructed by the UM trellis codes of branch length two based on the above three methods to uniformly discuss their performance. For the UM trellis codes of branch length two, the error exponent of the tail biting unit memory (TB-UM) trellis codes is shown to be larger than or equal to those of the ordinary block codes, the tail termination unit memory (TT-UM) and the direct truncation unit memory (DT-UM) trellis codes for all rates less than the capacity. Decoding complexity for the TB-UM trellis codes of branch length two exhibits interesting property since their trellis diagrams become simple. Taking into account of the asymptotic decoding complexity, the TB-UM trellis codes are also shown to have a smaller upper bound on the probability of decoding error compared to the ordinary block codes for the same rate with the same decoding complexity.
{"title":"Exponential Error Bounds and Decoding Complexity for Block Codes Constructed by Unit Memory Trellis Codes of Branch Length Two","authors":"S. Hirasawa, H. Yagi, Manabu Kobayashi, M. Kasahara","doi":"10.1109/CISS.2019.8692938","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692938","url":null,"abstract":"Performance of block codes constructed by unit memory (UM) trellis codes is discussed from random coding arguments. There are three methods to obtain block codes from trellis codes, i.e., those of (a) Tail Termination (TT), (b) Direct Truncation (DT), and (c) Tail Biting (TB). In this paper, we derive exponential error bounds and decoding complexity for block codes constructed by the UM trellis codes of branch length two based on the above three methods to uniformly discuss their performance. For the UM trellis codes of branch length two, the error exponent of the tail biting unit memory (TB-UM) trellis codes is shown to be larger than or equal to those of the ordinary block codes, the tail termination unit memory (TT-UM) and the direct truncation unit memory (DT-UM) trellis codes for all rates less than the capacity. Decoding complexity for the TB-UM trellis codes of branch length two exhibits interesting property since their trellis diagrams become simple. Taking into account of the asymptotic decoding complexity, the TB-UM trellis codes are also shown to have a smaller upper bound on the probability of decoding error compared to the ordinary block codes for the same rate with the same decoding complexity.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126838701","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 : 2019-04-16DOI: 10.1109/CISS.2019.8692925
A. Jalilzadeh, U. Shanbhag
We consider the development of first-order algorithms for convex stochastic optimization problems with expectation constraints. By recasting the problem as a solution to a monotone stochastic variational inequality problem, we note that a solution to this problem can be obtained as a solution to an unconstrained nonsmooth convex stochastic optimization problem. We utilize a variance-reduced smoothed first-order scheme for resolving such a problem and derive rate statements for such a scheme.
{"title":"Smoothed First-order Algorithms for Expectation-valued Constrained Problems","authors":"A. Jalilzadeh, U. Shanbhag","doi":"10.1109/CISS.2019.8692925","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692925","url":null,"abstract":"We consider the development of first-order algorithms for convex stochastic optimization problems with expectation constraints. By recasting the problem as a solution to a monotone stochastic variational inequality problem, we note that a solution to this problem can be obtained as a solution to an unconstrained nonsmooth convex stochastic optimization problem. We utilize a variance-reduced smoothed first-order scheme for resolving such a problem and derive rate statements for such a scheme.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121297873","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 : 2019-03-20DOI: 10.1109/CISS.2019.8693053
Wei Zhou, M. Lentmaier
We present a CRC-aided LDPC coding scheme that can outperform the underlying LDPC code under ordered statistic decoding (OSD). In this scheme, the CRC is used jointly with the LDPC code to construct a candidate list, instead of conventionally being regarded as a detection code to prune the list generated by the LDPC code alone. As an example we consider a (128,64)5 G LDPC code with BP decoding, which we can outperform by 2 dB using a (128,72) LDPC code in combination with a 8-bit CRC under OSD of order t=3. The proposed decoding scheme for CRC-aided LDPC codes also achieves a better performance than the conventional scheme where the CRC is used to prune the list. A manageable complexity can be achieved with iterative reliability based OSD, which is demonstrated to perform well with a small OSD order.
{"title":"Improving Short-Length LDPC Codes with a CRC and Iterative Ordered Statistic Decoding : (Invited Paper)","authors":"Wei Zhou, M. Lentmaier","doi":"10.1109/CISS.2019.8693053","DOIUrl":"https://doi.org/10.1109/CISS.2019.8693053","url":null,"abstract":"We present a CRC-aided LDPC coding scheme that can outperform the underlying LDPC code under ordered statistic decoding (OSD). In this scheme, the CRC is used jointly with the LDPC code to construct a candidate list, instead of conventionally being regarded as a detection code to prune the list generated by the LDPC code alone. As an example we consider a (128,64)5 G LDPC code with BP decoding, which we can outperform by 2 dB using a (128,72) LDPC code in combination with a 8-bit CRC under OSD of order t=3. The proposed decoding scheme for CRC-aided LDPC codes also achieves a better performance than the conventional scheme where the CRC is used to prune the list. A manageable complexity can be achieved with iterative reliability based OSD, which is demonstrated to perform well with a small OSD order.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129984477","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 : 2019-03-20DOI: 10.1109/CISS.2019.8692790
Syed S. Rizvi, Jarrett Imler, Luke Ritchey, M. Tokar
In most produced modern vehicles, Passive Keyless Entry and Start System (PKES), a newer form of an entry access system, is becoming more and more popular. The PKES system allows the consumer to enter within a certain range and have the vehicle’s doors unlock automatically without pressing any buttons on the key. This technology increases the overall convenience to the consumer; however, it is vulnerable to attacks known as relay and amplified relay attacks. A relay attack consists of placing a device near the vehicle and a device near the key to relay the signal between the key and the vehicle. On the other hand, an amplified relay attack uses only a singular amplifier to increase the range of the vehicle sensors to reach the key. By exploiting these two different vulnerabilities within the PKES system, an attacker can gain unauthorized access to the vehicle, leading to damage or even stolen property. To minimize both vulnerabilities, we propose a coordinate tracing system with an additional Bluetooth communication channel. The coordinate tracing system, or PKES Forcefield, traces the authorized key’s longitude and latitude in real time using two proposed algorithms, known as the Key Bearing algorithm and the Longitude and Latitude Key (LLK) algorithm. To further add security, a Bluetooth communication channel will be implemented. With an additional channel established, a second frequency can be traced within a secondary PKES Forcefield. The LLK Algorithm computes both locations of frequencies and analyzes the results to form a pattern. Furthermore, the PKES Forcefield movement-tracing allows a vehicle to understand when an attacker attempts to transmit an unauthenticated signal and blocks any signal from being amplified over a fixed range.
{"title":"Securing PKES against Relay Attacks using Coordinate Tracing and Multi-Factor Authentication","authors":"Syed S. Rizvi, Jarrett Imler, Luke Ritchey, M. Tokar","doi":"10.1109/CISS.2019.8692790","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692790","url":null,"abstract":"In most produced modern vehicles, Passive Keyless Entry and Start System (PKES), a newer form of an entry access system, is becoming more and more popular. The PKES system allows the consumer to enter within a certain range and have the vehicle’s doors unlock automatically without pressing any buttons on the key. This technology increases the overall convenience to the consumer; however, it is vulnerable to attacks known as relay and amplified relay attacks. A relay attack consists of placing a device near the vehicle and a device near the key to relay the signal between the key and the vehicle. On the other hand, an amplified relay attack uses only a singular amplifier to increase the range of the vehicle sensors to reach the key. By exploiting these two different vulnerabilities within the PKES system, an attacker can gain unauthorized access to the vehicle, leading to damage or even stolen property. To minimize both vulnerabilities, we propose a coordinate tracing system with an additional Bluetooth communication channel. The coordinate tracing system, or PKES Forcefield, traces the authorized key’s longitude and latitude in real time using two proposed algorithms, known as the Key Bearing algorithm and the Longitude and Latitude Key (LLK) algorithm. To further add security, a Bluetooth communication channel will be implemented. With an additional channel established, a second frequency can be traced within a secondary PKES Forcefield. The LLK Algorithm computes both locations of frequencies and analyzes the results to form a pattern. Furthermore, the PKES Forcefield movement-tracing allows a vehicle to understand when an attacker attempts to transmit an unauthenticated signal and blocks any signal from being amplified over a fixed range.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133281223","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 : 2019-03-20DOI: 10.1109/CISS.2019.8692928
John Franklin, A. Cooper
Under sparse channel assumptions, channel state information for the massive MIMO uplink can be effectively estimated without sampling every antenna. Assuming a slow flat fading multipath channel, orthogonal pilot signals, and a uniform rectangular array, channel estimation is performed by leveraging sparsity in the spatial and pilot code domains to reconstruct the channel to all antennas. Results of sampling from 25 percent of a 32 by 64 element massive MIMO array during the uplink piloting phase are presented. The sum rate achieved by using compressed sensing and sparse recovery channel estimates exceeds that achieved with the least squares channel estimate for the same number of sampled antennas.
{"title":"Compressive Sensing for Indoor Millimeter Wave Massive MIMO : (Invited Paper)","authors":"John Franklin, A. Cooper","doi":"10.1109/CISS.2019.8692928","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692928","url":null,"abstract":"Under sparse channel assumptions, channel state information for the massive MIMO uplink can be effectively estimated without sampling every antenna. Assuming a slow flat fading multipath channel, orthogonal pilot signals, and a uniform rectangular array, channel estimation is performed by leveraging sparsity in the spatial and pilot code domains to reconstruct the channel to all antennas. Results of sampling from 25 percent of a 32 by 64 element massive MIMO array during the uplink piloting phase are presented. The sum rate achieved by using compressed sensing and sparse recovery channel estimates exceeds that achieved with the least squares channel estimate for the same number of sampled antennas.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132742915","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 : 2019-03-20DOI: 10.1109/CISS.2019.8692945
Kate D. Fischl, Adam B. Cellon, T. Stewart, T. Horiuchi, A. Andreou
Social robotics is a highly useful field that is rapidly growing. Advances in embedded systems and fields like neuromorphic computing provide hardware solutions for the computationally complex models needed to produce realistic, pro-social socio-emotional robots. This work details a robot which executes a simplified amygdala model to determine an emotional state from visual input and a subsequent behavioral response. Each nuclei of this model is processed on a different neuromorphic platform, including the SpiNNaker, Loihi, and Braindrop chips. Although simplified, this robot and its underlying model illustrate a proof of concept for more complicated and biologically-plausible socio-emotional robots.
{"title":"Socio-Emotional Robot with Distributed Multi-Platform Neuromorphic Processing : (Invited Presentation)","authors":"Kate D. Fischl, Adam B. Cellon, T. Stewart, T. Horiuchi, A. Andreou","doi":"10.1109/CISS.2019.8692945","DOIUrl":"https://doi.org/10.1109/CISS.2019.8692945","url":null,"abstract":"Social robotics is a highly useful field that is rapidly growing. Advances in embedded systems and fields like neuromorphic computing provide hardware solutions for the computationally complex models needed to produce realistic, pro-social socio-emotional robots. This work details a robot which executes a simplified amygdala model to determine an emotional state from visual input and a subsequent behavioral response. Each nuclei of this model is processed on a different neuromorphic platform, including the SpiNNaker, Loihi, and Braindrop chips. Although simplified, this robot and its underlying model illustrate a proof of concept for more complicated and biologically-plausible socio-emotional robots.","PeriodicalId":123696,"journal":{"name":"2019 53rd Annual Conference on Information Sciences and Systems (CISS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131897916","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：