Search

Digital Twin (DT) technology has recently emerged as a powerful tool with the potential to revolutionize wireless systems as it enables accurate simulations, better decision-making, and tangible operational improvements. Prior studies on DT within the context of next generation wireless technologies have primarily focused on identifying potential use cases, application scenarios, standardization challenges, and conceptual implementation steps. However, the existing research is limited in translating theoretical ideas into real-world applications. Our research, in this paper, contributes to the practical realization of DT technology in the context of 6G wireless networks, demonstrating its potential impact on network planning, performance, and user experience. In particular, we explore the construction, validation, and applications of DT utilizing an indoor over-the-air (OTA) 5G NR testbed powered by an in-house developed Next Generation Radio Access Network (NG-RAN) that is fully compliant with 3rd Generation Partnership Project (3GPP) and Open RAN standards. First, we explain the integration and implementation steps followed to integrate Qualcomm EdgewiseTM Suite and Service Management and Orchestration (SMO) tools into the NG-RAN architecture, that will eventually enable the applicability of DT for wireless network operations. We then describe our procedure to construct and validate a high-fidelity DT of our OTA testbed modeling both Radio Frequency (RF) environment and system components. We demonstrate two pre-deployment use cases by describing our extensive coverage estimation and network capacity planning tests in OTA. Lastly, we explore how DT enables practical machine learning solutions for post-deployment use cases and share our comprehensive OTA performance results, highlighting that our proposed mobility and positioning techniques outperform the classical approaches in terms of throughput, number of undesired handovers, and positioning accuracy.

Electrocardiogram (ECG) data’s high dimensionality challenges real-time arrhythmia classification. Our approach employs functional approximation to condense ECG recordings into a compact feature set for simpler classification using Chebyshev polynomials. These polynomials, with 200 time points and 80 coefficients, accurately represent arrhythmias in an $81 \times 1$ feature vector. We prove Chebyshev polynomials act as implicit low-pass filters on input signals. Using MIT-BIH Arrhythmia and MIT-BIH Supraventricular Arrhythmia datasets, we introduce classifiers that achieve significant accuracy. A three-layered Artificial Neural Network yields high F1-scores (0.99, 0.90, 0.93, and 0.76 for classes N, S, V, and F) with minimal parameters (20,964), surpassing existing models. Furthermore, our proposed ECG classification system exhibits minimal computational demands, requiring only 0.1 MIPS per beat. We also propose efficient signal reconstruction methods, with the iterative approach showcasing accurate reconstruction with negligible error. This approach accommodates various data sampling types and determines optimal Chebyshev coefficients for capturing signal bandwidth.

In SDN-based networks, contextual understanding of network behaviour and safe execution of operational decisions are important as part of the network management process. Digital Twin Network (DTN) is a promising concept which creates a virtual twin of a live SDN-based network to monitor the network from different angles with various granularities and enables it to verify an operational change without disturbing the live one. However, modelling the arbitrary decisions by an SDN Controller to form a DTN and managing the contextual information in a DTN are challenging tasks in various aspects. This paper proposes a data representation based DTN architecture integrating Knowledge Graph (KG) for data modelling and storage and Template as the context description approach. The combination of KG and Template can make the DTN management scalable with the flexibility of defining the contextual information with the relationships between network entities. It also enables efficient querying of the data storage and provides the reusability of functions and data storage for the DTN applications development. The proposed DTN architecture was implemented using an ONOS-based SDN Controller and Neo4j-based KG with built-in DTN applications for practical use. The PoC implementation exhibited short query response time and high query throughput in reading from and updating a KG, though the initial creation of a KG incurs a considerable delay which increases with its size.

This paper presents a comparison of several artificial intelligence (AI) based binary classifiers for detecting the integrity of data obtained from Internet of Things (IoT) enabled wearable sensors. Detecting the integrity of data at the network edge facilitates the elimination of corrupted or unusable data, which translates to a lower amount of data stored and transmitted. This reduces the storage and power requirements of IoT devices without a reduction in functionality. In this work, we explore several machine learning-based classifiers to check the integrity of electrocardiogram (ECG) data. The feature vectors are derived from low complexity kurtosis and skewness based Signal Quality Indices (SQIs). From the experiments, it is found that a bagged ensemble of 3 neural networks achieves the highest detection accuracy of 99.47%. We also estimated the complexity and power consumed by the various classifier implementations and classifier fusion implementations. The energy consumed by the ensemble classifier was estimated to be around 0.039 nJ.

This paper aims to reduce the power consumption of electrocardiography based wearable healthcare devices, by introducing power reduction approaches and considerations at system level design, where we have the highest potential to influence power. It focuses, in particular, on algorithm design and implementation, data acquisition, and transmission under constrained resources. A thorough investigation of the suitability of nine existing algorithms for on-sensor QRS feature detection is conducted, with respect to metrics such as sensitivity, positive predictivity, power consumption, parameter choice and time delay. Optimisation of data acquisition on CPU-based IoT systems is performed, and the current consumption is reduced by a factor of 3 using a combination of direct memory access (DMA) list approach and low-level register manipulations for task delegation. The acquisition data rate, sampling rate, buffer and batch size are also optimised. To reduce the power consumption by data transmission, the effect of on-sensor versus off-sensor processing is investigated. While focusing on CPU-based systems with experiments performed on a generic low-power wearable platform, the design optimisation and considerations proposed in this work could be extended to custom designs and allow further investigation into QRS detection algorithm optimisation for wearable devices.

Stroke is widely considered as the second most common cause of mortality. The adverse consequences of stroke have led to global interest and work for improving the management and diagnosis of stroke. Various techniques for data mining have been used globally for accurate prediction of occurrence of stroke based on the risk factors that are associated with the electronic health care records (EHRs) of the patients. In particular, EHRs routinely contain several thousands of features and most of them are redundant and irrelevant that need to be discarded to enhance the prediction accuracy. The choice of feature-selection methods can help in improving the prediction accuracy of the model and efficient data management of the archived input features. In this paper, we systematically analyze the various features in EHR records for the detection of stroke. We propose a novel rough-set based technique for ranking the importance of the various EHR records in detecting stroke. Unlike the conventional rough-set techniques, our proposed technique can be applied on any dataset that comprises binary feature sets. stroke. We evaluated our proposed method in a publicly available dataset of EHR, and concluded that age, average glucose level, heart disease, and hypertension were the most essential attributes for detecting stroke in patients. Furthermore, we benchmarked the proposed technique with other popular feature-selection techniques. We obtained the best performance in ranking the importance of individual features in detecting stroke.

This special section presents seven state-of-the-art design techniques for AI hardware accelerators that lead to substantial improvements on energy efficiency, reconfigurability, and resource utilization.

Gamakas are the musical embellishments used in Karnatic Music. Predicting them from the musical notations plays an important part in applications like automatic synthesis and composition of Karnatic Music. Since there are no well-defined rules governing the use of gamakas, predicting them is a challenging problem. In this work, we propose a method to detect the presence and type of gamakas, in a data-driven manner, from the annotated symbolic music alone. We propose features based on the notes of the song for these tasks. These features are used as inputs to a Random Forest Classifier. We digitise 80 songs from a well known reference book of Karnatic music to create a dataset consisting roughly 30000 notes. We train the classifier on around 12000 notes and test on roughly 18000 notes. From our experiments, the accuracy values obtained for predicting gamaka presence and type are ~77% and ~70%, respectively. These are significantly better than random classification accuracies. We also analyse the importance of neighbourhood of notes for the detection and classification of gamakas. It is observed that the best accuracy is obtained for gamaka presence detection when a both-sided neighbourhood of size three is considered; and best accuracy for gamaka type prediction is obtained with a both-sided neighbourhood of size one. The analysis performed on the training data reveals that there is information contained in these neighbourhoods for distinguishing between gamaka and non-gamaka notes.