Complex-valued data, unlike real-valued data, requires consideration of intricate correlations and patterns. In particular, within learning frameworks based on real-valued computations, conventional input representations for complex numbers may fail to account for the correlations between the real and imaginary components, leading to potential inefficiencies. To address this issue, we propose a novel framework called ComplexRep, aimed at efficiently processing complex-valued data and enhancing its transparency. This framework transforms complex sequence data into a format similar to images, allowing for the consideration of inter-component correlations while improving overall model performance. The ComplexRep framework employs advanced techniques such as Information Addition and the proposed Learned Representation Integration (LRI) to strengthen low model complexity and high Initial Trial Success Probability (ITSP). Additionally, we enhance the reliability of our experiments by utilizing both public datasets and data collected from real-world environments. Extensive evaluation results demonstrate that our framework excels even under low signal-to-noise ratio (SNR) conditions, increasing the overall system efficiency. Notably, compared to previously used input formats, ComplexRep improves ITSP performance and reduces model complexity, thus proving its efficiency. Further experiments across various models confirm the framework’s compatibility with several state-of-the-art models. All experiments include additional tests on real-world 5G data, validating the applicability of the proposed approach. This study presents the potential to effectively manage complex-valued data and maximize performance while offering directions for future complex-valued data processing research.

The 5 G system employs multiple beams, and its initial cell selection procedure essentially involves identifying Synchronization Signal Blocks (SSBs) for beam detection. This SSB identification is significantly affected by Symbol Timing Offset (STO) due to its inherent nature of detection in the frequency domain. The performance of this process is likely to degrade in a softwarized modem that handles baseband signals within software environments. The softwarized modem relies on an STO estimation algorithm with low computational complexity, which may result in a larger STO. It can also encounter multi-path channels, which cause the additional effect of large STOs. In this paper, we propose a novel residual STO compensation scheme in both the time and frequency domains to improve the accuracy of SSB identification. A mathematical model is initially developed to observe the impact of STO on SSB identification. Based on the mathematical analysis, the proposed scheme is designed to adjust the estimated STO using the convex characteristics of auto-correlation for a 5 G synchronization signal. Additionally, the proposed scheme jointly considers multiple STO candidates for phase compensation in the frequency domain. For performance assessment, we conduct experiments using the testbed system of a softwarized modem that transmits and receives real signals through practical channels. The experimental results imply that the proposed scheme effectively addresses STO in practical multi-path channels and bring significant improvement to SSB identification.

In this paper, a conventional multiuser space-time line code (MSTLC) transmission scheme is enhanced to a new enhanced MSTLC (EMSTLC). By introducing the balancing factors at receivers’ antennas to adjust the achievable rates among users, the EMSTLC precoder and balancing factors are designed in a unified minimum mean square error framework to maximize either sum rate or rate balancing. Numerical results verify that the proposed EMSTLC systems achieve a higher sum rate and better minimum user rate than baseline multiuser transmission methods, including the conventional MSTLC scheme. Furthermore, the designed low-complexity algorithms can significantly reduce the computational complexity of the EMSTLC system.

Machine Learning (ML) is recently considered a key technology for bringing outstanding performance to wireless communications. Conventional research has highlighted the potential of Support Vector Machines (SVMs), which train their model based on optimization theory, to enhance the performance of wireless communications. However, there are practical issues that makes SVM difficult to apply to a wireless communication system. SVM generally entails a heavy training process with high computational complexity, and the model requires a significant amount of time for training. Also, the entire dataset needs to be trained at once, requiring a substantial amount of memory for data storage. To enable SVM in wireless communications, we propose Real-Time Channel Vector Classifier (RTCVC), which employs a light-weight SVM model capable of training and processing incoming data in real-time. A novel input data pre-processing technique is implemented to reduce the computational overhead associated with calculating non-linear functions. The rearranged formulation of the original problem also allows each SVM sub-model to be trained distributively over time based on incremental parameters. For performance evaluation, we implement the RTCVC inter-operating with 5G beam index detection, whose detection probability has been theoretically proven to be significantly enhanced by SVM. The software modules of the RTCVC are based on LibSVM, a well-known open-source library for implementing SVM sub-models. The experimental results confirm that RTCVC significantly reduces training time while maintaining suitable performance for 5G beam index detection.

Odem softwarization, where baseband signals are fully processed using software on a general-purpose CPU, is a promising technology in mobile communications due to its simplicity and flexibility in realizing various features. On the other hand, many still question the effectiveness of a softwarized modem in commercial environments concerning performance and complexity. Motivated by this perspective, this paper presents the design and implementation of a softwarized modem with the specific feature of 5G cell search for field evaluation. Based on the baseline algorithms of 5G cell search in Open Air Interface (OAI), we propose a new software architecture which can efficiently manage a 5G cell search procedure and decompose the overall 5G cell search into sub-algorithms. We also design and implement novel sub-algorithms that enhance the detection of Synchronization Signal Blocks (SSBs). Our softwarized modem utilizes dual-rate sampling to significantly reduce computation complexity during timing offset estimation. It also adaptively detects synchronization signals or cell identities based on the presence of inter-cell interference or multi-path fading. The performance evaluation through field experiments concludes that our softwarized modem outperforms the baseline, and the proposed sub-algorithms are effective in enhancing cell search performance. The detection probability and time consumption results for our softwarized modem confirm that it is feasible for commercial uses.M

Neural networks with self-attention (a.k.a. Transformers) like ViT and Swin have emerged as a better alternative to traditional convolutional neural networks (CNNs). However, our understanding of how the new architecture works is still limited. In this paper, we focus on the phenomenon that Transformers show higher robustness against corruptions than CNNs, while not being overconfident. This is contrary to the intuition that robustness increases with confidence. We resolve this contradiction by empirically investigating how the output of the penultimate layer moves in the representation space as the input data moves linearly within a small area. In particular, we show the following. (1) While CNNs exhibit fairly linear relationship between the input and output movements, Transformers show nonlinear relationship for some data. For those data, the output of Transformers moves in a curved trajectory as the input moves linearly. (2) When a data is located in a curved region, it is hard to move it out of the decision region since the output moves along a curved trajectory instead of a straight line to the decision boundary, resulting in high robustness of Transformers. (3) If a data is slightly modified to jump out of the curved region, the movements afterwards become linear and the output goes to the decision boundary directly. In other words, there does exist a decision boundary near the data, which is hard to find only because of the curved representation space. This explains the underconfident prediction of Transformers. Also, we examine mathematical properties of the attention operation that induce nonlinear response to linear perturbation. Finally, we share our additional findings, regarding what contributes to the curved representation space of Transformers, and how the curvedness evolves during training.

The Vision Transformer has emerged as a powerful tool for image classification tasks, surpassing the performance of convolutional neural networks (CNNs). Recently, many researchers have attempted to understand the robustness of Transformers against adversarial attacks. However, previous researches have focused solely on perturbations in the spatial domain. This paper proposes an additional perspective that explores the adversarial robustness of Transformers against frequency-selective perturbations in the spectral domain. To facilitate comparison between these two domains, an attack framework is formulated as a flexible tool for implementing attacks on images in the spatial and spectral domains. The experiments reveal that Transformers rely more on phase and low frequency information, which can render them more vulnerable to frequency-selective attacks than CNNs. This work offers new insights into the properties and adversarial robustness of Transformers.

Artificial intelligence has recently permeated every field, and current research trends in wireless communications naturally involve leveraging machine learning (ML) for communications processing. Numerous previous research studies have theoretically demonstrated that intelligentizing physical layer holds the promise of enhancing performance for the 6G era. In this article, we demonstrate the practical implementation of intelligentizing random access (RA) through real-time channel learning (CL). Real-time CL adapts an ML model to the variations of wireless channel in real time and requires extremely short and low-complexity training. Our research encompasses algorithmic design through the implementation of an off-the-shelf testbed which incorporates real-time CL in softwarized modem. We initially review the fundamental algorithms of communications processing for RA and then proceed to design a proper ML model for real-time CL. The overall intelligentized RA detector is then implemented using the concept of softwarized modem. The implementation achieves real-time CL via efficient interoperation of communications processing and the ML model. Experiments with the implementation confirm that intelligentization through real-time CL is feasible and results in an SNR gain up to 2.7 dB for RA scenarios.

While adversarial perturbation of images to attack deep image classification models pose serious security concerns in practice, this paper suggests a novel paradigm where the concept of image perturbation can benefit classification performance, which we call amicable aid. We show that by taking the opposite search direction of perturbation, an image can be modified to yield higher classification confidence and even a misclassified image can be made correctly classified. This can be also achieved with a large amount of perturbation by which the image is made unrecognizable by human eyes. The mechanism of the amicable aid is explained in the viewpoint of the underlying natural image manifold. Furthermore, we investigate the universal amicable aid, i.e., a fixed perturbation can be applied to multiple images to improve their classification results. While it is challenging to find such perturbations, we show that making the decision boundary as perpendicular to the image manifold as possible via training with modified data is effective to obtain a model for which universal amicable perturbations are more easily found.

This work presents a low-phase noise (PN) mm-wave injection-locked frequency multiplier (ILFM) using an ultra-low power frequency-tracking loop (FTL). Monitoring the averages of phase deviations rather than detecting the instantaneous values, the FTL consumed only 600W to calibrate the mm-wave ILFM generating a frequency between 27 and 30GHz. While consuming low power, the proposed FTL effectively regulated the PN degradation, which was less than 2dB up to 100MHz offset across VT variations.

The explosively growing demand of Internet of Things (IoT) has rendered broadscale advancements in the fields across sensors, radio access, network, and hardware/software platforms for mass market applications. In spite of the recent advancements, limited coverage and battery for persistent connections of IoT devices still remains a critical impediment to practical service applications. In this paper, we introduces a cost-effective IoT solution consisting of device platform, gateway, IoT network, and platform server for smart railway infrastructure. Then, we evaluate and demonstrate the applicability through an in-depth case study related to IoT-based maintenance by implementing a proof of concept and performing experimental works. The IoT solution applied for the smart railway application makes it easy to grasp the condition information distributed over a wide railway area. To deduce the potential and feasibility, we propose the network architecture of IoT solution and evaluate the performance of the candidate radio access technologies for delivering IoT data in the aspects of power consumption and coverage by performing an intensive field test with system level implementations. Based on the observation of use cases in interdisciplinary approaches, we figure out the benefits that the IoT can bring.

Based on a convex approach with side-information, we propose transmit beamforming designs for two-user multiple-input single-output fading interference channels. Main contribution of this paper is to provide a novel methodology for solving a non-convex optimization problem efficiently based on the effective side-information. Consequently, the proposed scheme exhibits near-optimal average sum-rate performance under single user detection with Gaussian inputs, which is validated through numerical results. As a by-product, we show that the proposed scheme requires almost no parameter optimization on the average over multiple coding blocks.

Femtocell system is expected to bring significant improvement of system performance with low cost. However, when a number of femto BSs are installed by users without cell-planning, the femtocell system will be in dense environment, in which many femto co-cells exist in a small region and a great portion of the femto cell is overlapped by other femto cells. Femtocell system in dense environment is exposed to strong inter-cell interference problem which is critical to system capacity. In this paper, we derive a joint power and subchannel allocation scheme in dense environment. The simulation and numerical results show that our proposed scheme simply finds a better solution compared to the conventional scheme in dense environment.

Relay based cellular system, which includes Relay Nodes (RNs) to relay transmitters' signal to receivers for coverage extension and capacity improvement, has been recently emerging as one of the candidates for next generation mobile communication system. However, Mobile Stations (MSs) in relay based cellular system suffer a problem of data loss when they move out of the coverage of the serving RN and perform handover to base station (BS) or other RNs. To prevent this behavior, this paper proposes a pre-buffering scheme that BS performs multicast transmission to the handover candidate RNs. After the MS detects a nearby RN and regards it as a candidate for the handover target, the MS requests BS to multicast the MS's traffic to the serving and the candidate RN. The numerical and simulation results show that the proposed scheme brings performance improvement in view of data loss and handover interruption time.

An advanced MAP transmission scheme for improving media access control (MAC) overhead in the IEEE 802.16e systems is proposed. In the IEEE 802.16e system, when a base station (BS) broadcasts a MAP message, which is a control message about scheduling information, it applies a robust modulation and coding scheme (MCS) level and allocates a large amount of radio resources, which induce a huge MAP overhead. Our proposed scheme utilizes piggybacked MAP IEs, in which control messages are concatenated with data packets and transmitted with the MCS level applied to data transmission. Due to the fact that the rate at which data is transmitted is generally higher than the rate at which broadcasting messages are transmitted, the proposed scheme can increase average data rate of a MAP transmission and consequently reduce the amount of resources allocated to the MAP transmission. Numerical analysis and simulations are presented to show that the MAP overhead is critical to system performance and can be improved by the proposed scheme.

This paper analyzes Media Access Control(MAC) overhead of the IEEE 802.16e systems and shows that it causes to degrade system performance critically. MAP, a control message about resource allocation, is broadcasted with high robustness and uses a great amount of radio resource for it. This paper also proposes an advanced scheme which transmits MAP IE, a component of MAP, piggybacked on data packets, and uses fast feedback to conserve the transmission reliability of the MAP IE. Then, MAP IEs can be transmitted with high data rate, and the amount of radio resource for transmitting MAP IEs becomes extremely small. Numerical analysis and simulation results show that the proposed scheme can significantly improve the MAC overhead.

This paper proposes novel resource allocation schemes which minimize power consumption of Mobile Stations(MSs) in Orthogonal Frequency Division Multiple Access(OFDMA) systems. The conventional resource allocation schemes focus on maximizing throughput or mitigating inter cell interference. The proposed schemes allocate resource units assembled in an OFDM symbol to each MS for minimizing the total number of Orthogonal Frequency Division Multiplexing(OFDM) symbols that MSs receive. As a result, MSs can decode their own data with consuming less power for processing OFDM symbols. This paper introduces two schemes : Optimization Approached Scheme and Heuristic Approached Scheme. The simulation results in this paper show that the proposed schemes can contribute to reduce the power consumption of MSs and Heuristic Approached Scheme is more practical than Optimization Approached Scheme in view of computational time.

This paper introduces a resource allocation strategy which focuses on minimizing power consumption in orthogonal frequency division multiplexing (OFDM) systems. In case of multicasting systems, it is appropriate to allocate resource with power saving strategy, since the effect of frequency selective channel is ignorable. By this strategy, the number of OFDM symbols MSs receive is minimized. A great amount of power can be saved, because the radio frequency and baseband processes are the dominant factors of power consumption. This paper also proposes a heuristic algorithm for finding the suboptimal solution of resource allocation with low complexity. By this algorithm, resource allocation process requires O(n3) computations with little performance degradation. The numerical analysis and simulation results show that the performance of this algorithm is close to the optimum.