Pub Date : 2025-09-11DOI: 10.1109/TMBMC.2025.3601476
{"title":"IEEE Communications Society Information","authors":"","doi":"10.1109/TMBMC.2025.3601476","DOIUrl":"https://doi.org/10.1109/TMBMC.2025.3601476","url":null,"abstract":"","PeriodicalId":36530,"journal":{"name":"IEEE Transactions on Molecular, Biological, and Multi-Scale Communications","volume":"11 3","pages":"C3-C3"},"PeriodicalIF":2.3,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11159540","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-10DOI: 10.1109/TMBMC.2025.3608500
Michael Gattringer;Stefan Angerbauer;Andreas Springer;Werner Haselmayr
In this paper, we propose a novel distributed scheduling algorithm for time-division multiple access (TDMA) in diffusion-based molecular communication systems. We consider a receiver nano device (ND) surrounded by randomly distributed transmitter NDs. The goal of the proposed scheduling algorithm is to arrange transmissions of the different transmitter NDs in order to mitigate inter-user interferences (IUI). Each ND follows the scheduling algorithm, which only requires listening to the channel and measuring time, but no synchronization. We provide a theoretical foundation and verify the functionality of the algorithm with a particle-based simulation (PBS). Furthermore, we compare the performance of the algorithm in terms of temporal channel utilization with an ideal (centralized) scheduling algorithm, which shows similar results for large packet lengths.
{"title":"A Distributed Scheduling Algorithm for TDMA in Diffusion-Based Molecular Communication","authors":"Michael Gattringer;Stefan Angerbauer;Andreas Springer;Werner Haselmayr","doi":"10.1109/TMBMC.2025.3608500","DOIUrl":"https://doi.org/10.1109/TMBMC.2025.3608500","url":null,"abstract":"In this paper, we propose a novel distributed scheduling algorithm for time-division multiple access (TDMA) in diffusion-based molecular communication systems. We consider a receiver nano device (ND) surrounded by randomly distributed transmitter NDs. The goal of the proposed scheduling algorithm is to arrange transmissions of the different transmitter NDs in order to mitigate inter-user interferences (IUI). Each ND follows the scheduling algorithm, which only requires listening to the channel and measuring time, but no synchronization. We provide a theoretical foundation and verify the functionality of the algorithm with a particle-based simulation (PBS). Furthermore, we compare the performance of the algorithm in terms of temporal channel utilization with an ideal (centralized) scheduling algorithm, which shows similar results for large packet lengths.","PeriodicalId":36530,"journal":{"name":"IEEE Transactions on Molecular, Biological, and Multi-Scale Communications","volume":"11 4","pages":"506-512"},"PeriodicalIF":2.3,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11157763","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-10DOI: 10.1109/TMBMC.2025.3608558
Luiz C. P. Wille;Christof Pfannenmüller;Jens Kirchner
The interplay of particle propagation due to fluid convection has been subject to extensive research in the areas of molecular communication (MC) and magnetic drug targeting (MDT). Although a lot of models have been developed already, often the time-varying nature of the background flow and the elasticity of the channel walls have been neglected. We propose a simulation-based analysis of particle propagation in the radial artery under pulsatile flow in comparison to classical laminar flow. The effect of elastic channel walls compared to rigid walls is investigated. Our results reveal that in the case of pulsatile flow, the channel impulse response (CIR) is formed by a series of sharp peaks synchronous to the cardiac cycle instead of the long-tailed shape of laminar flow. In particular, 70% of particle movement occurs in the first 30% of each cardiac cycle. The results indicate a strong impact of pulsatile flow on inter-symbol interference and thus the design of demodulation algorithms in MC as well as on the design of steering approaches in MDT.
{"title":"From Steady to Pulsatile Flow in Molecular Communication: Propagation of Nanoparticles in Mid-Sized Arteries","authors":"Luiz C. P. Wille;Christof Pfannenmüller;Jens Kirchner","doi":"10.1109/TMBMC.2025.3608558","DOIUrl":"https://doi.org/10.1109/TMBMC.2025.3608558","url":null,"abstract":"The interplay of particle propagation due to fluid convection has been subject to extensive research in the areas of molecular communication (MC) and magnetic drug targeting (MDT). Although a lot of models have been developed already, often the time-varying nature of the background flow and the elasticity of the channel walls have been neglected. We propose a simulation-based analysis of particle propagation in the radial artery under pulsatile flow in comparison to classical laminar flow. The effect of elastic channel walls compared to rigid walls is investigated. Our results reveal that in the case of pulsatile flow, the channel impulse response (CIR) is formed by a series of sharp peaks synchronous to the cardiac cycle instead of the long-tailed shape of laminar flow. In particular, 70% of particle movement occurs in the first 30% of each cardiac cycle. The results indicate a strong impact of pulsatile flow on inter-symbol interference and thus the design of demodulation algorithms in MC as well as on the design of steering approaches in MDT.","PeriodicalId":36530,"journal":{"name":"IEEE Transactions on Molecular, Biological, and Multi-Scale Communications","volume":"11 4","pages":"531-536"},"PeriodicalIF":2.3,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11157771","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-05DOI: 10.1109/TMBMC.2025.3606625
Zhuoqun Jin;Huiyu Luo;Boyu Jiang;Yao Chen;Lin Lin
Transmitting information in engineered neural communication systems is a promising solution to delay-sensitive applications for the Internet of bio-nano Things (IoBNT). As widely used in wired and wireless communication systems, multiplexing could improve channel transmission efficiency in the neural communication system. In this article, we model a neural communication system and propose a neural signal multiplexing scheme based on code division multiplexing (CDM) principle. The whole system including channel modeling, neural coding, multiplexing scheme, and decoding method is presented. The optimal threshold and computational complexity are analyzed. The performance of the proposed scheme is evaluated in terms of bit error rate (BER) and mutual information rate in comparison with our previous methods. The work can help researchers better understand the underlying mechanism of neural multiplexing and pave the way for the implementation of IoBNT applications.
在工程神经通信系统中传输信息是生物纳米物联网（IoBNT）延迟敏感应用的一个有前途的解决方案。多路复用技术广泛应用于有线和无线通信系统中，可以提高神经通信系统的信道传输效率。在本文中，我们建立了一个神经通信系统模型，并提出了一种基于码分复用（CDM）原理的神经信号复用方案。介绍了整个系统，包括信道建模、神经编码、多路复用方案和解码方法。分析了最优阈值和计算复杂度。在误码率（BER）和互信息率（mutual information rate）方面对该方案的性能进行了评估，并与我们之前的方法进行了比较。这项工作可以帮助研究人员更好地理解神经多路复用的潜在机制，并为实现IoBNT应用铺平道路。
{"title":"An Engineered Neural Communication System Based on CDM Scheme for the Internet of Bio-Nano Things","authors":"Zhuoqun Jin;Huiyu Luo;Boyu Jiang;Yao Chen;Lin Lin","doi":"10.1109/TMBMC.2025.3606625","DOIUrl":"https://doi.org/10.1109/TMBMC.2025.3606625","url":null,"abstract":"Transmitting information in engineered neural communication systems is a promising solution to delay-sensitive applications for the Internet of bio-nano Things (IoBNT). As widely used in wired and wireless communication systems, multiplexing could improve channel transmission efficiency in the neural communication system. In this article, we model a neural communication system and propose a neural signal multiplexing scheme based on code division multiplexing (CDM) principle. The whole system including channel modeling, neural coding, multiplexing scheme, and decoding method is presented. The optimal threshold and computational complexity are analyzed. The performance of the proposed scheme is evaluated in terms of bit error rate (BER) and mutual information rate in comparison with our previous methods. The work can help researchers better understand the underlying mechanism of neural multiplexing and pave the way for the implementation of IoBNT applications.","PeriodicalId":36530,"journal":{"name":"IEEE Transactions on Molecular, Biological, and Multi-Scale Communications","volume":"12 ","pages":"1-10"},"PeriodicalIF":2.3,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145859873","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 : 2025-09-03DOI: 10.1109/TMBMC.2025.3605771
Eren Akyol;Aysa Azmoudeh;Iman Mokari Bolhassan;Pelin Kubra Isgor;Murat Kuscu
Droplet-based communications has been investigated as a more robust alternative to diffusion-based molecular communications (MC), yet most existing demonstrations employ large “plug-like” droplets or simple T-junction designs for droplet generation, restricting modulation strategies and achievable data rates. Here, we report a microfluidic communication system that encodes information via the generation rate of sub-$100~mu $ m water-in-oil microdroplets using a microfabricated flow focusing architecture. By precisely tuning the flow rate of the dispersed-phase (water) via a pressure-regulated flow controller, we implement frequency shift keying modulation with four symbols (4-FSK). A high-speed optical detection and video processing setup serves as the receiver, tracking system response in the microfluidic channel across different symbol durations (20 s and 12 s) and quantifying error performance. Despite the miniaturized device and channel architecture, our experiments demonstrate programmable and reliable data transmission with minimal symbol errors. Beyond water-in-oil systems, the same encoding principles can be extended to other compartmentalized carriers (e.g., giant unilamellar vesicles, polymersomes) that can also be synthesized via flow focusing techniques, paving the way for biocompatible, robust, and high-capacity communication in intrabody networks and the emerging Internet of Bio-Nano Things.
{"title":"Microdroplet-Based Communications With Frequency Shift Keying Modulation","authors":"Eren Akyol;Aysa Azmoudeh;Iman Mokari Bolhassan;Pelin Kubra Isgor;Murat Kuscu","doi":"10.1109/TMBMC.2025.3605771","DOIUrl":"https://doi.org/10.1109/TMBMC.2025.3605771","url":null,"abstract":"Droplet-based communications has been investigated as a more robust alternative to diffusion-based molecular communications (MC), yet most existing demonstrations employ large “plug-like” droplets or simple T-junction designs for droplet generation, restricting modulation strategies and achievable data rates. Here, we report a microfluidic communication system that encodes information via the generation rate of sub-<inline-formula> <tex-math>$100~mu $ </tex-math></inline-formula> m water-in-oil microdroplets using a microfabricated flow focusing architecture. By precisely tuning the flow rate of the dispersed-phase (water) via a pressure-regulated flow controller, we implement frequency shift keying modulation with four symbols (4-FSK). A high-speed optical detection and video processing setup serves as the receiver, tracking system response in the microfluidic channel across different symbol durations (20 s and 12 s) and quantifying error performance. Despite the miniaturized device and channel architecture, our experiments demonstrate programmable and reliable data transmission with minimal symbol errors. Beyond water-in-oil systems, the same encoding principles can be extended to other compartmentalized carriers (e.g., giant unilamellar vesicles, polymersomes) that can also be synthesized via flow focusing techniques, paving the way for biocompatible, robust, and high-capacity communication in intrabody networks and the emerging Internet of Bio-Nano Things.","PeriodicalId":36530,"journal":{"name":"IEEE Transactions on Molecular, Biological, and Multi-Scale Communications","volume":"11 4","pages":"513-517"},"PeriodicalIF":2.3,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760910","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}
Ultrasonic intra-body communication (IBC) has essential application prospects in personalized medicine. However, due to the limitations of complex biological tissues in the human body, signal transmission faces challenges such as significant attenuation, multipath effect, and noise interference. In this paper, we propose an adaptive parallel transmission with code-indexed modulation and differential chaos shift keying (A-PT-CIM-DCSK), aiming to achieve the optimal data rate and system robustness in complex channel environments. To balance the data rate and bit error rate (BER), the number of parallel bit blocks is adaptively adjusted according to the channel state information. The proposed scheme extends the conventional DCSK dual time slot structure to realize the parallel transmission of multiple quasi-orthogonal chaotic sequences, using longer Walsh codes, which further improves the resistance to multipath effects in fading channels. In addition, this paper designs a new q-value search algorithm by adopting three classical diversity combining strategies. The theoretical BER of A-PT-CIM-DCSK over the generalized Nakagami fading channel is also derived. The simulation results verify the theoretical derivation and show that the proposed A-PT-CIM-DCSK scheme significantly improves the performance compared with the conventional CIM-DCSK and PT-CIM-DCSK systems while maintaining a lower BER for ultrasonic IBCs.
{"title":"Adaptive Parallel Transmission With Code Index Modulation and DCSK Over Ultrasonic Intra-Body Fading Channels","authors":"Qianqian Wang;Weidong Wang;Quansheng Guan;Mangang Xie;Xiangdong Jia;Julian Cheng","doi":"10.1109/TMBMC.2025.3605775","DOIUrl":"https://doi.org/10.1109/TMBMC.2025.3605775","url":null,"abstract":"Ultrasonic intra-body communication (IBC) has essential application prospects in personalized medicine. However, due to the limitations of complex biological tissues in the human body, signal transmission faces challenges such as significant attenuation, multipath effect, and noise interference. In this paper, we propose an adaptive parallel transmission with code-indexed modulation and differential chaos shift keying (A-PT-CIM-DCSK), aiming to achieve the optimal data rate and system robustness in complex channel environments. To balance the data rate and bit error rate (BER), the number of parallel bit blocks is adaptively adjusted according to the channel state information. The proposed scheme extends the conventional DCSK dual time slot structure to realize the parallel transmission of multiple quasi-orthogonal chaotic sequences, using longer Walsh codes, which further improves the resistance to multipath effects in fading channels. In addition, this paper designs a new q-value search algorithm by adopting three classical diversity combining strategies. The theoretical BER of A-PT-CIM-DCSK over the generalized Nakagami fading channel is also derived. The simulation results verify the theoretical derivation and show that the proposed A-PT-CIM-DCSK scheme significantly improves the performance compared with the conventional CIM-DCSK and PT-CIM-DCSK systems while maintaining a lower BER for ultrasonic IBCs.","PeriodicalId":36530,"journal":{"name":"IEEE Transactions on Molecular, Biological, and Multi-Scale Communications","volume":"12 ","pages":"197-207"},"PeriodicalIF":2.3,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929462","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 : 2025-09-03DOI: 10.1109/TMBMC.2025.3605779
Huiyu Luo;Kun Deng;Zhe Yuan;Ying Qin;Junfang Zhang;Saied M. Abd El-Atty;Lin Lin
Advances in molecular communication and the Internet of Nanothings (IoNT) have opened new possibilities for in-body nanodevice networks in medicine. As a promising approach for transmitting information from IoNT to external devices, neural communication leverages the nervous system as a data transmission interface. However, reliable transmission depends on accurate channel parameter estimation and research in this area remains limited. To address this, we take pH as the primary channel parameter and experimentally propose channel parameter estimation schemes using the bullfrog sciatic nerve as the neural communication channel. Here, compound action potentials (CAPs), which are the electrical responses of the nerve channel, are employed to characterize the channel. To establish the relationship between CAPs and pH values, we develop an experimental platform to collect CAPs at different pH values. Then, we design regression models including the random forest (RF) and long short-term memory (LSTM) methods, and further propose an enhanced LSTM model to address their limitations. The enhanced model uses convolutional layers to extract local spatial features from raw CAPs waveforms, followed by LSTM layers for temporal modeling, and concludes with MLP layers for continuous pH prediction. Experimental results reveal that the corresponding pH value can be accurately detected when new CAPs are fed into the trained models, with the enhanced LSTM model demonstrating superior accuracy. This study paves the way for conducting experimental research to ensure reliable data transmission from in-vivo IoNT to external networks.
{"title":"Channel Parameter Estimation in Neural Communication Based on Bullfrog Sciatic Nerve","authors":"Huiyu Luo;Kun Deng;Zhe Yuan;Ying Qin;Junfang Zhang;Saied M. Abd El-Atty;Lin Lin","doi":"10.1109/TMBMC.2025.3605779","DOIUrl":"https://doi.org/10.1109/TMBMC.2025.3605779","url":null,"abstract":"Advances in molecular communication and the Internet of Nanothings (IoNT) have opened new possibilities for in-body nanodevice networks in medicine. As a promising approach for transmitting information from IoNT to external devices, neural communication leverages the nervous system as a data transmission interface. However, reliable transmission depends on accurate channel parameter estimation and research in this area remains limited. To address this, we take pH as the primary channel parameter and experimentally propose channel parameter estimation schemes using the bullfrog sciatic nerve as the neural communication channel. Here, compound action potentials (CAPs), which are the electrical responses of the nerve channel, are employed to characterize the channel. To establish the relationship between CAPs and pH values, we develop an experimental platform to collect CAPs at different pH values. Then, we design regression models including the random forest (RF) and long short-term memory (LSTM) methods, and further propose an enhanced LSTM model to address their limitations. The enhanced model uses convolutional layers to extract local spatial features from raw CAPs waveforms, followed by LSTM layers for temporal modeling, and concludes with MLP layers for continuous pH prediction. Experimental results reveal that the corresponding pH value can be accurately detected when new CAPs are fed into the trained models, with the enhanced LSTM model demonstrating superior accuracy. This study paves the way for conducting experimental research to ensure reliable data transmission from in-vivo IoNT to external networks.","PeriodicalId":36530,"journal":{"name":"IEEE Transactions on Molecular, Biological, and Multi-Scale Communications","volume":"12 ","pages":"185-196"},"PeriodicalIF":2.3,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929460","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 : 2025-09-03DOI: 10.1109/TMBMC.2025.3605778
Yuankun Tang;Qianqian Wang;Zhanjun Hao;Zhongyu Ma;Weidong Gao;Lie-Liang Yang
The Internet of Bio-Nano Things (IoBNT) is expected to play a pivotal role in the future healthcare systems. This paper proposes a molecular code index modulation (MCIM) scheme to achieve reliable information transmission for molecular communication (MC), which may find applications in micro/nano scale networks, including the IoBNT. The MCIM system, making use of two distinct types of molecules, encodes information into the indices of both spreading codes and molecular types. At the receiver, the concentration differences between the molecules of two types with respect to all chips of a code are exploited for information detection. Correspondingly, two low-complexity detectors dispensing with channel state information, namely joint detector and stepwise detector, are proposed based on the correlation detection principles. Furthermore, to mitigate the inter-symbol interference (ISI) caused by the MC channel and specifically structured spreading code, an enhanced stepwise detector is developed to improve the performance of the stepwise detector. The bit error rate (BER) upper bound of the MCIM systems with joint detection, as well as the throughput and the computational complexity of MCIM systems with any detection schemes are analyzed. Our studies demonstrate that the proposed MCIM scheme has the potential to achieve the superior BER and throughput performance at low computational complexity, when compared with the existing modulation schemes employing two molecular types, such as molecular shift keying and molecular type permutation shift keying schemes.
{"title":"Molecular Code Index Modulation: Signaling, Detection, and Performance Analysis","authors":"Yuankun Tang;Qianqian Wang;Zhanjun Hao;Zhongyu Ma;Weidong Gao;Lie-Liang Yang","doi":"10.1109/TMBMC.2025.3605778","DOIUrl":"https://doi.org/10.1109/TMBMC.2025.3605778","url":null,"abstract":"The Internet of Bio-Nano Things (IoBNT) is expected to play a pivotal role in the future healthcare systems. This paper proposes a molecular code index modulation (MCIM) scheme to achieve reliable information transmission for molecular communication (MC), which may find applications in micro/nano scale networks, including the IoBNT. The MCIM system, making use of two distinct types of molecules, encodes information into the indices of both spreading codes and molecular types. At the receiver, the concentration differences between the molecules of two types with respect to all chips of a code are exploited for information detection. Correspondingly, two low-complexity detectors dispensing with channel state information, namely joint detector and stepwise detector, are proposed based on the correlation detection principles. Furthermore, to mitigate the inter-symbol interference (ISI) caused by the MC channel and specifically structured spreading code, an enhanced stepwise detector is developed to improve the performance of the stepwise detector. The bit error rate (BER) upper bound of the MCIM systems with joint detection, as well as the throughput and the computational complexity of MCIM systems with any detection schemes are analyzed. Our studies demonstrate that the proposed MCIM scheme has the potential to achieve the superior BER and throughput performance at low computational complexity, when compared with the existing modulation schemes employing two molecular types, such as molecular shift keying and molecular type permutation shift keying schemes.","PeriodicalId":36530,"journal":{"name":"IEEE Transactions on Molecular, Biological, and Multi-Scale Communications","volume":"12 ","pages":"208-217"},"PeriodicalIF":2.3,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929466","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}
In vivo localization of infection sources is essential for effective diagnosis and targeted disease treatment. In this work, we leverage machine learning models to associate the temporal dynamics of biomarkers detected at static gateway positions with different infection source locations. In particular, we introduce a simulation that models infection sources, the release of biomarkers, and their decay as they flow through the bloodstream. From this, we extract time-series biomarker data with varying decay rates to capture temporal patterns from different infection sources at specific gateway positions. We then train a stacked ensemble model using LightGBM and BernoulliNB to analyze biomarker time-series data for classification. Our results reveal that higher biomarker degradation rates significantly reduce the localization accuracy by limiting the biomarker signal detected at the gateways. A fivefold increase in decay rate lowers the mean cross-validation accuracy from $sim {mathrm {92~%}}$ to $sim {mathrm {66~%}}$ . This effect is more pronounced for infection sources located farther from the gateways, e.g., the kidneys. Due to the longer distance, more biomarkers degrade before reaching the wrist-located gateways, leading to a substantial decline in classification performance.
{"title":"Machine Learning-Driven Localization of Infection Sources in the Human Cardiovascular System","authors":"Saswati Pal;Jorge Torres Gómez;Lisa Y. Debus;Regine Wendt;Florian-Lennert Lau;Cyrus Khandanpour;Malte Sieren;Stefan Fischer;Falko Dressler","doi":"10.1109/TMBMC.2025.3605770","DOIUrl":"https://doi.org/10.1109/TMBMC.2025.3605770","url":null,"abstract":"In vivo localization of infection sources is essential for effective diagnosis and targeted disease treatment. In this work, we leverage machine learning models to associate the temporal dynamics of biomarkers detected at static gateway positions with different infection source locations. In particular, we introduce a simulation that models infection sources, the release of biomarkers, and their decay as they flow through the bloodstream. From this, we extract time-series biomarker data with varying decay rates to capture temporal patterns from different infection sources at specific gateway positions. We then train a stacked ensemble model using LightGBM and BernoulliNB to analyze biomarker time-series data for classification. Our results reveal that higher biomarker degradation rates significantly reduce the localization accuracy by limiting the biomarker signal detected at the gateways. A fivefold increase in decay rate lowers the mean cross-validation accuracy from <inline-formula> <tex-math>$sim {mathrm {92~%}}$ </tex-math></inline-formula> to <inline-formula> <tex-math>$sim {mathrm {66~%}}$ </tex-math></inline-formula>. This effect is more pronounced for infection sources located farther from the gateways, e.g., the kidneys. Due to the longer distance, more biomarkers degrade before reaching the wrist-located gateways, leading to a substantial decline in classification performance.","PeriodicalId":36530,"journal":{"name":"IEEE Transactions on Molecular, Biological, and Multi-Scale Communications","volume":"11 4","pages":"524-530"},"PeriodicalIF":2.3,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760898","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}
Molecular communications is an active research area developed in the last quarter of century, trying to combine communications theory results with biological and unconventional environments. The main characteristic of molecular communications is the use of molecules as information carriers instead of electromagnetic signals to implement communications between nanomachines, natural cells, or synthetic ones, able to transmit and receive these signals, which may be useful when electromagnetic communications are not possible or undesirable. However, this new application domain comes with significant issues when it is necessary to switch from design and/or simulation to practical experimentation. In this letter, we critically discuss the transition from design to testbed experimentation, using a practical case study as driving example. The case study is relevant to the application of molecular communications for building a monitoring device, able to detect with local and minimally invasive technology the condition of blood hyperviscosity for continuous patient monitoring. We present the issues arose during the experimentation that have an impact on testbed design, and identify potential, practical solutions to address them, thus providing contributions in the area of testbed and platform design. These methodologies have a general applicability beyond the scope of this specific application, thus offering insights for broader molecular communication applications.
{"title":"From Design to Experimentation in Molecular Communications: Discussion Through a Case Study","authors":"Mauro Femminella;Gianluca Reali;Federico Calì;Nunzio Tuccitto","doi":"10.1109/TMBMC.2025.3603412","DOIUrl":"https://doi.org/10.1109/TMBMC.2025.3603412","url":null,"abstract":"Molecular communications is an active research area developed in the last quarter of century, trying to combine communications theory results with biological and unconventional environments. The main characteristic of molecular communications is the use of molecules as information carriers instead of electromagnetic signals to implement communications between nanomachines, natural cells, or synthetic ones, able to transmit and receive these signals, which may be useful when electromagnetic communications are not possible or undesirable. However, this new application domain comes with significant issues when it is necessary to switch from design and/or simulation to practical experimentation. In this letter, we critically discuss the transition from design to testbed experimentation, using a practical case study as driving example. The case study is relevant to the application of molecular communications for building a monitoring device, able to detect with local and minimally invasive technology the condition of blood hyperviscosity for continuous patient monitoring. We present the issues arose during the experimentation that have an impact on testbed design, and identify potential, practical solutions to address them, thus providing contributions in the area of testbed and platform design. These methodologies have a general applicability beyond the scope of this specific application, thus offering insights for broader molecular communication applications.","PeriodicalId":36530,"journal":{"name":"IEEE Transactions on Molecular, Biological, and Multi-Scale Communications","volume":"11 4","pages":"500-505"},"PeriodicalIF":2.3,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145760892","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：