Article
Chemistry, Analytical
Sebastian-Alexandru Arghirescu, Maria Dragan, Octavian Fratu
Summary: This paper discusses a microcontroller-based architecture for a mobile laboratory control system, aiming to improve the autonomy of robotic vectors and reduce the required space.
Article
Automation & Control Systems
XinJiang Lu, Xiangbo Cui
Summary: The article proposes a novel spatiotemporal neural network method to model the nonlinear dynamics of distributed parameter systems, integrating temporal neural network model and spatial distribution function to consider both nonlinear temporal dynamics and spatial relationships. The two-step solving approach developed effectively learns the model and shows superior modeling performance compared to commonly used methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Robotics
Matteo Santilli, Mauro Franceschelli, Andrea Gasparri
Summary: The article investigates the dynamic resilient containment control problem for continuous-time multirobot systems, developing a local interaction protocol to successfully drive followers towards a target region. Under specific conditions, the influence of adversarial robots does not allow the followers to escape the containment area.
IEEE TRANSACTIONS ON ROBOTICS
(2022)
Article
Automation & Control Systems
Manuel Castellano-Quero, Manuel Castillo-Lopez, Juan-Antonio Fernandez-Madrigal, Vicente Arevalo-Espejo, Holger Voos, Alfonso Garcia-Cerezo
Summary: In order for mobile robots to operate autonomously and safely, they need to be able to perceive their environment effectively despite challenging or unpredictable conditions in their sensory apparatus. This paper proposes a novel probabilistic inference architecture based on Bayesian Networks to detect, diagnose, and recover from diverse and multiple sensory failures in robotic systems. Real-time performance is achieved through the compilation of these BNs into feedforward neural networks.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Yun-Kai Li, Qing-Hao Meng, Tian-Hao Yang, Ya-Xin Wang, Hui-Rang Hou
Summary: Touch is an essential means of conveying emotions and intentions in human communication. This study focuses on the recognition of touch gestures and emotions by social robots, using a pressure sensor array to build a dataset. The proposed method utilizes a decomposed spatiotemporal convolution for feature representation, which improves the nonlinear expression ability of the model and reduces computation cost. Experimental results demonstrate the effectiveness of the proposed method and verify the feasibility of robot perceiving human emotions through touch.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Computer Science, Information Systems
Oxana Shamilyan, Ievgen Kabin, Zoya Dyka, Oleksandr Sudakov, Andrii Cherninskyi, Marcin Brzozowski, Peter Langendoerfer
Summary: Many technical solutions are bio-inspired, such as octopus-inspired robotic arms. These arms belong to continuum robots used in minimally invasive surgery or for restoring technical systems in difficult-to-access areas. The robots' motion is controlled by humans via wireless communication, but autonomy is required in case of a lost connection. Distributed control and decision-making based on artificial intelligence could be a promising solution, although further investigation is needed. This paper explores the mechanisms of Distributed Artificial Intelligence to improve the resilience of complex systems, using a physical continuum robot prototype for experimental investigations.
Article
Engineering, Electrical & Electronic
Carmen Aracil, Gabor Sziebig, Peter Korondi, Sehoon Oh, Zhichao Tan, Michael Ruderman, Wangli He, Lei Ding, Hao Luo, Shen Yin, Adel Haghani
Summary: The field of industrial electronics has undergone a profound transformation in recent decades, with advancements in smart systems enabling robots to perform tasks, sensors to extract data accurately, and motion control systems to adapt to harsh conditions. These changes have led to increased efficiency and tighter data interconnectivity in industrial processes.
IEEE INDUSTRIAL ELECTRONICS MAGAZINE
(2021)
Article
Automation & Control Systems
Bowen Xu, Hai-Tao Zhang, Haofei Meng, Binbin Hu, Duxin Chen, Guanrong Chen
Summary: This article proposes a two-stage surrounding control algorithm for hunting a moving target. By utilizing algebraic graph theory and low gain feedback technique, distributed controllers are designed to effectively drive multiple agents to encircle the moving target. The effectiveness of the proposed control algorithm is validated through numerical simulations and experiments.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Chao Liu, Kin Gwn Lore, Zhanhong Jiang, Soumik Sarkar
Summary: This paper introduces a data-driven framework for root-cause analysis in complex CPSs based on symbolic dynamics, with S-3 and A(3) approaches showing high accuracy and versatility in fault scenarios.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Automation & Control Systems
Xinjiang Lu, Du Xu, Wenbo Liu
Summary: The article introduces a novel spatiotemporal recurrent neural network method for modeling distributed parameter systems. By representing spatial dynamics in hidden layers, this method integrates spatial and temporal dynamics without the need for model reduction.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Engineering, Mechanical
Bowen Xu, Xinjiang Lu
Summary: A data-driven spatiotemporal model predictive control (MPC) strategy is proposed for nonlinear distributed parameter systems (DPSs) with strongly nonlinear spatiotemporal dynamics, unknown parameters, and complex boundary conditions. It develops a low-order nonlinear spatiotemporal model using kernel principal component analysis to better preserve the spatial nonlinearity. A new objective function is constructed with consideration of errors on both time and space, overcoming the shortcomings of traditional MPC. The stability and effectiveness of the proposed spatiotemporal control strategy are demonstrated through mathematical stability and comparative case studies.
NONLINEAR DYNAMICS
(2022)
Article
Engineering, Electrical & Electronic
Dila Turkmen, Merve Acer Kalafat
Summary: This paper introduces a new method for improved integrated angle sensing in foldable robot joints using low-cost inkjet printed sensors and a novel physical intelligence based compensation approach. By printing silver nanoparticle angle sensors on a flexible PET substrate, the sensors are implemented as part of a rigid experimental setup, resulting in combined signals that greatly improve the individual sensor responses. This approach shows promise in overcoming limitations in using printed sensors in flexible hinges and allows for the development of reliable and fully integrated foldable robots.
SENSORS AND ACTUATORS A-PHYSICAL
(2022)
Article
Engineering, Electrical & Electronic
Yun-Kai Li, Qing-Hao Meng, Hong-Wei Zhang
Summary: The article introduces a novel method for touch gesture recognition, which utilizes time-frequency features and spatiotemporal fusion features to extract representations of touch gestures. Experimental results show that this method outperforms existing techniques and that spatiotemporal fusion features effectively enhance the performance of touch gesture recognition.
IEEE SENSORS JOURNAL
(2022)
Article
Engineering, Mechanical
Bowen Xu, Xinjiang Lu
Summary: This article proposes a data-driven inverse control method for complex distributed parameter systems (DPSs) using spatiotemporal least squares support vector machine (LS-SVM) model and spatial fuzzy strategy, effectively tracking the dynamics of DPSs. The efficacy and stability of this method are demonstrated through actual experiments.
NONLINEAR DYNAMICS
(2023)
Article
Robotics
Malintha Fernando, Ransalu Senanayake, Martin Swany
Summary: We propose a novel framework for real-time communication-aware coverage control in networked robot swarms. Our framework integrates robot dynamics with network-level message-routing to achieve consensus on swarm formations in the presence of communication uncertainties by leveraging local information. The proposed approach was experimentally validated in a mobile ad-hoc wireless network scenario, demonstrating its capability to provide wireless coverage to stationary and mobile devices under realistic network conditions.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Computer Science, Hardware & Architecture
Mohammad Reza Nosouhi, Shui Yu, Keshav Sood, Marthie Grobler, Raja Jurdak, Ali Dorri, Shigen Shen
Summary: In this article, a secure mix-based approach called UCoin is proposed to address the issues in preserving privacy of users in cryptocurrencies. It breaks the link between input and output addresses in transactions, utilizes a secure shuffling protocol, and achieves higher performance and compatibility with the existing cryptocurrency architecture.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Siddique Latif, Rajib Rana, Sara Khalifa, Raja Jurdak, Junaid Qadir, Bjorn Schuller
Summary: Traditionally, speech emotion recognition (SER) relied on manual feature engineering, but this approach requires significant manual effort and impedes innovation. Representation learning techniques have been adopted to automatically learn intermediate representations without manual engineering, leading to improved SER performance and rapid innovation. Deep learning further enhances the effectiveness of representation learning by enabling the automatic learning of hierarchical representations. This article presents a comprehensive survey on deep representation learning for SER, highlighting techniques, challenges, and future research areas.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Review
Energy & Fuels
Samuel Karumba, Subbu Sethuvenkatraman, Volkan Dedeoglu, Raja Jurdak, Salil S. Kanhere
Summary: The increasing adoption of clean energy technologies has led to the evolution of traditional electricity markets into Distributed Energy Trading (DET) systems. Blockchain technology has the potential to provide decentralised trust, immutability, security, and transparency in DET systems. However, the integration of blockchain in DET systems faces technical, administrative, standardisation, and economic barriers, which need to be addressed.
INTERNATIONAL JOURNAL OF SUSTAINABLE ENERGY
(2023)
Article
Computer Science, Theory & Methods
Seyedehfaezeh Hosseininoorbin, Siamak Layeghy, Mohanad Sarhan, Raja Jurdak, Marius Portmann
Summary: This paper explores the implementation of a practical network intrusion detection system (NIDS) at the edge of IoT using Google's Edge TPU and a deep learning approach. It focuses on the computational and energy efficiency of deep learning-based NIDS at the IoT edge. The study uses various scaled model sizes of deep neural network architectures and compares the performance of Edge TPU-based implementation with an energy-efficient embedded CPU.
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Siddique Latif, Rajib Rana, Sara Khalifa, Raja Jurdak, Bjorn Schuller
Summary: Despite recent advancements in speech emotion recognition (SER) within a single corpus, the performance of these systems degrades significantly for cross-corpus and cross-language scenarios. This is due to the lack of generalization in SER systems towards unseen conditions. Adversarial methods have been used to address this issue, but many only focus on cross-corpus SER and ignore the cross-language performance degradation. This study proposes an adversarial dual discriminator (ADDi) network and a self-supervised ADDi (sADDi) network to improve cross-corpus and cross-language SER without requiring target data labels. Experimental results demonstrate improved performance compared to state-of-the-art methods.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Information Systems
Seyedehfaezeh Hosseininoorbin, Siamak Layeghy, Brano Kusy, Raja Jurdak, Marius Portmann
Summary: This paper examines the performance of Google's Edge TPU on feed-forward neural networks. It considers the Edge TPU as a hardware platform and explores different architectures of deep neural network classifiers, which have traditionally been challenging to run on resource-constrained edge devices. By utilizing a spectrogram data representation, the study examines the trade-off between classification performance and energy consumption for inference. The energy efficiency of the Edge TPU is compared to that of the widely-used embedded CPU ARM Cortex-A53. The results provide insights into the impact of neural network architecture on the performance of the Edge TPU and offer guidance for selecting the optimal operating point based on classification accuracy and energy consumption. Additionally, the evaluations highlight the performance crossover between the Edge TPU and Cortex-A53, depending on the neural network specifications. The analysis also provides a decision chart to assist in platform selection based on model parameters and context.
INTERNET OF THINGS
(2023)
Proceedings Paper
Computer Science, Information Systems
Guntur Dharma Putra, Volkan Dedeoglu, Salil S. Kanhere, Raja Jurdak
Summary: 6G-enabled IoT networks require effective resource allocation for massive scale network capacity. While blockchain-based resource sharing schemes lack trust monitoring, Trust and Reputation Management (TRM) can address this. However, changeable keys in blockchains may hinder TRM's usability. This paper proposes a privacy-preserving TRM using interconnected public-private blockchains, allowing nodes to use changeable keys and ensuring minimal overheads.
2023 IEEE INTERNATIONAL CONFERENCE ON BLOCKCHAIN AND CRYPTOCURRENCY, ICBC
(2023)
Proceedings Paper
Computer Science, Information Systems
Gowri Sankar Ramachandran, Thi Thuy Linh Tran, Raja Jurdak
Summary: Many real-world applications use web service frameworks to provide APIs to businesses and end-consumers. However, in applications like supply chain management, the organization running the web server may act dishonestly or the server may be compromised. To address this, we propose DeWS, a decentralized and Byzantine fault-tolerant web service framework that provides transparency and auditability through a blockchain ledger. Our proof-of-concept implementation shows that DeWS can tolerate Byzantine failures, although at the cost of high latency. This framework can support the shift towards more decentralized web services for safety-critical and mission-critical applications.
2023 IEEE INTERNATIONAL CONFERENCE ON BLOCKCHAIN AND CRYPTOCURRENCY, ICBC
(2023)
Proceedings Paper
Computer Science, Information Systems
Kealan Dunnett, Shantanu Pal, Zahra Jadidi, Raja Jurdak
Summary: This paper proposes a blockchain-based CTI sharing framework that utilizes trustless delegates for dynamic trust-based decision-making and decentralized trust evaluation. Unlike existing approaches, delegates within our framework facilitate direct sharing of CTI with consumers, enabling scalable CTI sharing.
2023 IEEE INTERNATIONAL CONFERENCE ON BLOCKCHAIN AND CRYPTOCURRENCY, ICBC
(2023)
Proceedings Paper
Computer Science, Information Systems
Jun Wook Heo, Gowri Ramachandran, Raja Jurdak
Summary: This paper proposes a decentralized Practical Proof of Storage (PPoS) solution for blockchain full nodes, which uses asymmetric latency for encryption and decryption, and introduces a chained architecture to detect attacks and reduce performance overhead. Experimental results demonstrate that this approach significantly reduces decryption time while maintaining a high degree of decentralization.
2023 IEEE INTERNATIONAL CONFERENCE ON BLOCKCHAIN AND CRYPTOCURRENCY, ICBC
(2023)
Proceedings Paper
Computer Science, Information Systems
Samuel Karumba, Raja Jurdak, Salil S. Kanhere, Subbu Sethuvenkatraman
Summary: Blockchain technology can revolutionize the energy sector by enabling peer-to-peer energy trading, demand-side flexibility trading, and renewable energy certificate trading, among other decentralised energy trading use cases. However, the lack of interoperability between blockchain networks and platforms is a significant challenge that leads to data and information silos. To address this challenge, a Blockchain Agnostic Interoperability Framework (BAILIF) is proposed, which provides a decentralized notary service and a cross-chain attestation and verification protocol. A proof of concept for a distributed energy trading application demonstrates the solution's feasibility, with BAILIF achieving a throughput of up to 666 transactions per second, indicating its potential to enable seamless data sharing across blockchain platforms and promote the adoption of renewable energy sources.
2023 IEEE INTERNATIONAL CONFERENCE ON BLOCKCHAIN AND CRYPTOCURRENCY, ICBC
(2023)
Article
Computer Science, Information Systems
Seyedehfaezeh Hosseininoorbin, Siamak Layeghy, Brano Kusy, Raja Jurdak, Marius Portmann
Summary: This study explores different joint time-frequency representations of sensor data and utilizes a Convolutional Neural Network (ConvNet) for activity classification based on wearable devices. The concurrent use of two different data representations in a cooperative bi-stream ConvNet configuration is also considered. The proposed method achieves high classification accuracy and F1 score on a real-world public HAR dataset, surpassing the state-of-the-art. Furthermore, the method is implemented on a resource-constrained edge device to evaluate the trade-off between energy consumption and classification performance in IoT applications.
INTERNET OF THINGS
(2023)
Proceedings Paper
Computer Science, Hardware & Architecture
Guntur Dharma Putra, Sidra Malik, Volkan Dedeoglu, Salil S. Kanhere, Raja Jurdak
Summary: In recent years, there has been a growing interest in integrating blockchain technology into the Internet of Things (IoT) to address issues such as data security and trust. However, using blockchain alone cannot guarantee the authenticity and accuracy of data from IoT devices. Trust and Reputation Management (TRM) is a viable solution, but designing TRM frameworks for blockchain-enabled IoT applications is challenging due to unique trust challenges and requirements. This paper presents experiences in designing TRM frameworks for various blockchain-enabled IoT applications, providing insights and highlighting research challenges for future opportunities.
2023 15TH INTERNATIONAL CONFERENCE ON COMMUNICATION SYSTEMS & NETWORKS, COMSNETS
(2023)
Article
Computer Science, Information Systems
Yanxiang Wang, Jiawei Hu, Hong Jia, Wen Hu, Mahbub Hassan, Ashraf Uddin, Brano Kusy, Moustafa Youssef
Summary: We investigate the impact of location on the spectral distribution of received light in indoor settings. Different locations exhibit slightly different spectral distribution due to reflections from their environment. Exploiting this, we propose Spectral-Loc, an indoor localization system that uses light spectral information. We prototype Spectral-Loc using a commercial light spectral sensor and benchmark its accuracy against conventional light intensity sensors.
PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT
(2023)