Search

This article articulates the emerging paradigm, sitting at the confluence of computer vision and wireless communication, to enable beyond-5G/6G mission-critical applications (autonomous/remote-controlled vehicles, visuo-haptic VR, and other cyber-physical applications). First, drawing on recent advances in machine learning and the availability of non-RF data, vision-aided wireless networks are shown to significantly enhance the reliability of wireless communication without sacrificing spectral efficiency. In particular, we demonstrate how computer vision enables {look-ahead} prediction in a millimeter-wave channel blockage scenario, before the blockage actually happens. From a computer vision perspective, we highlight how radio frequency (RF) based sensing and imaging are instrumental in robustifying computer vision applications against occlusion and failure. This is corroborated via an RF-based image reconstruction use case, showcasing a receiver-side image failure correction resulting in reduced retransmission and latency. Taken together, this article sheds light on the much-needed convergence of RF and non-RF modalities to enable ultra-reliable communication and truly intelligent 6G networks., Comment: 7 pages, 4 figures; This work has been submitted to IEEE Communications Standards Magazine for possible publication

Millimeter wave (mmWave) beam-tracking based on machine learning enables the development of accurate tracking policies while obviating the need to periodically solve beam-optimization problems. However, its applicability is still arguable when training-test gaps exist in terms of environmental parameters that affect the node dynamics. From this skeptical point of view, the contribution of this study is twofold. First, by considering an example scenario, we confirm that the training-test gap adversely affects the beam-tracking performance. More specifically, we consider nodes placed on overhead messenger wires, where the node dynamics are affected by several environmental parameters, e.g, the wire mass and tension. Although these are particular scenarios, they yield insight into the validation of the training-test gap problems. Second, we demonstrate the feasibility of \textit{zero-shot adaptation} as a solution, where a learning agent adapts to environmental parameters unseen during training. This is achieved by leveraging a robust adversarial reinforcement learning (RARL) technique, where such training-and-test gaps are regarded as disturbances by adversaries that are jointly trained with a legitimate beam-tracking agent. Numerical evaluations demonstrate that the beam-tracking policy learned via RARL can be applied to a wide range of environmental parameters without severely degrading the received power., 13 pages, 13 figures, 3 tables, under submission for possible publication for IEEE

This study experimentally validated the possibility of angle of departure (AoD) estimation using multiple signal classification (MUSIC) with only WiFi control frames for beamforming feedback (BFF), defined in IEEE 802.11ac/ax. The examined BFF-based MUSIC is a model-driven algorithm, which does not require a pre-obtained database. This contrasts with most existing BFF-based sensing techniques, which are data-driven and require a pre-obtained database. Moreover, the BFF-based MUSIC affords an alternative AoD estimation method without access to channel state information (CSI). Specifically, the extensive experimental and numerical evaluations demonstrated that the BFF-based MUSIC successfully estimates the AoDs for multiple propagation paths. Moreover, the evaluations performed in this study revealed that the BFF-based MUSIC achieved a comparable error of AoD estimation to the CSI-based MUSIC, while BFF is a highly compressed version of CSI in IEEE 802.11ac/ax., Comment: Submitted to IEEE Access

Over-the-air computation (AirComp)-based federated learning (FL) enables low-latency uploads and the aggregation of machine learning models by exploiting simultaneous co-channel transmission and the resultant waveform superposition. This study aims at realizing secure AirComp-based FL against various privacy attacks where malicious central servers infer clients' private data from aggregated global models. To this end, a differentially private AirComp-based FL is designed in this study, where the key idea is to harness receiver noise perturbation injected to aggregated global models inherently, thereby preventing the inference of clients' private data. However, the variance of the inherent receiver noise is often uncontrollable, which renders the process of injecting an appropriate noise perturbation to achieve a desired privacy level quite challenging. Hence, this study designs transmit power control across clients, wherein the received signal level is adjusted intentionally to control the noise perturbation levels effectively, thereby achieving the desired privacy level. It is observed that a higher privacy level requires lower transmit power, which indicates the tradeoff between the privacy level and signal-to-noise ratio (SNR). To understand this tradeoff more fully, the closed-form expressions of SNR (with respect to the privacy level) are derived, and the tradeoff is analytically demonstrated. The analytical results also demonstrate that among the configurable parameters, the number of participating clients is a key parameter that enhances the received SNR under the aforementioned tradeoff. The analytical results are validated through numerical evaluations., Comment: 6 pages, 4 figures

This paper proposes a robust adversarial reinforcement learning (RARL)-based multi-access point (AP) coordination method that is robust even against unexpected decentralized operations of uncoordinated APs. Multi-AP coordination is a promising technique towards IEEE 802.11be, and there are studies that use RL for multi-AP coordination. Indeed, a simple RL-based multi-AP coordination method diminishes the collision probability among the APs; therefore, the method is a promising approach to improve time-resource efficiency. However, this method is vulnerable to frame transmissions of uncoordinated APs that are less aware of frame transmissions of other coordinated APs. To help the central agent experience even such unexpected frame transmissions, in addition to the central agent, the proposed method also competitively trains an adversarial AP that disturbs coordinated APs by causing frame collisions intensively. Besides, we propose to exploit a history of frame losses of a coordinated AP to promote reasonable competition between the central agent and adversarial AP. The simulation results indicate that the proposed method can avoid uncoordinated interference and thereby improve the minimum sum of the throughputs in the system compared to not considering the uncoordinated AP.

To achieve reliable small cell millimeter-wave wireless backhauls, this study installs small cell base stations (SBSs) on overhead messenger wires to gain flexibility in physical deployments of SBSs ensuring in the line-of-sight connections between SBSs and gateway BSs. These installations pose challenges in aligning directional beams, whereby complicated wind-forced dynamics in on-wire SBSs require frequent beam training, and consequently, a large signaling overhead. To address this, this study aims at demonstrating the feasibility of learning-based beam tracking where a beam tracking policy is learned a priori to fix beam misalignment caused by the wind-forced dynamics. Because wind-forced dynamics in SBSs can be three-dimensional (3D), the proposed beam tracking newly exploits the 3D position/velocity of the SBS as state information. As a solution to fix beam misalignment, the beam tracking policy is learned via deep reinforcement learning wherein the 3D information and beam direction are regarded as a state and an action, respectively, and the received signal power at a gateway BS is maximized. The simulation results depict the feasibility of learning an appropriate beam tracking policy to prevent beam misalignment induced by wind-forced 3D dynamics in on-wire SBSs.

This study develops a federated learning (FL) framework overcoming largely incremental communication costs due to model sizes in typical frameworks without compromising model performance. To this end, based on the idea of leveraging an unlabeled open dataset, we propose a distillation-based semi-supervised FL (DS-FL) algorithm that exchanges the outputs of local models among mobile devices, instead of model parameter exchange employed by the typical frameworks. In DS-FL, the communication cost depends only on the output dimensions of the models and does not scale up according to the model size. The exchanged model outputs are used to label each sample of the open dataset, which creates an additionally labeled dataset. Based on the new dataset, local models are further trained, and model performance is enhanced owing to the data augmentation effect. We further highlight that in DS-FL, the heterogeneity of the devices’ dataset leads to ambiguous of each data sample and lowing of the training convergence. To prevent this, we propose entropy reduction averaging, where the aggregated model outputs are intentionally sharpened. Moreover, extensive experiments show that DS-FL reduces communication costs up to 99 percent relative to those of the FL benchmark while achieving similar or higher classification accuracy.

In this study, a contextual multi-armed bandit (CMAB)-based decentralized channel exploration framework disentangling a channel utility function (i.e., reward) with respect to contending neighboring access points (APs) is proposed. The proposed framework enables APs to evaluate observed rewards compositionally for contending APs, allowing both robustness against reward fluctuation due to neighboring APs' varying channels and assessment of even unexplored channels. To realize this framework, we propose contention-driven feature extraction (CDFE), which extracts the adjacency relation among APs under contention and forms the basis for expressing reward functions in the disentangled form, that is, a linear combination of parameters associated with neighboring APs under contention). This allows the CMAB to be leveraged with joint a linear upper confidence bound (JLinUCB) exploration and to delve into the effectiveness of the proposed framework. Moreover, we address the problem of non-convergence -- the channel exploration cycle -- by proposing a penalized JLinUCB (P-JLinUCB) based on the key idea of introducing a discount parameter to the reward for exploiting a different channel before and after the learning round. Numerical evaluations confirm that the proposed method allows APs to assess the channel quality robustly against reward fluctuations by CDFE and achieves better convergence properties by P-JLinUCB., Comment: 12 pages, 6 figures, 3 Tables

Towards ultra-reliable and low-latency communications, this paper proposes a packet mapping algorithm in an enhanced distributed channel access (EDCA) scheme using policy gradient reinforcement learning (RL). The EDCA scheme provides higher priority packets with more transmission opportunities by mapping packets to a predefined access category (AC); thereby, the EDCA scheme supports a higher quality of service in wireless local area networks. In this paper, it is noted that by mapping high priority packets to lower priority ACs, the one-packet delay of a high priority packet can be reduced. In contrast, the mapping algorithm cannot minimize the multiple-packets delay because the mapping algorithm is based on the current status. This is because, from a long-term perspective, mapping high priority packets is required as a countermeasure for collisions, to minimize the multiple-packets delay. As a solution, this paper proposes a new mapping algorithm using RL because RL is suitable for maximizing the reward from a long-term perspective. The key idea is to design the state such that the state involves the number of packets having arrived at each AP in the past, which is an indicator expressing past status. In the designed RL task, the reward, i.e., the multiple-packets delay depends on an overall sequence of states and actions; hence, the recursive value function-based RL algorithms are not compatible. To solve this problem, this paper utilizes policy gradient RL, which learns the packet mapping policy from an overall state-action sequence and a consequent multiple-packets delay. The simulation result reveals that the transmission delay of the proposed mapping algorithm is 13.8% shorter than that of the conventional EDCA mapping algorithm.

A 66-year-old man was admitted to undergo investigation for body weight loss. He was diagnosed with pancreatic neuroendocrine carcinoma, and a pancreaticoduodenectomy was performed. Three months after surgery, multiple recurrent liver metastases were observed on CT. We administered the cisplatin(CDDP)/irinotecan(CPT-11)regimen, but decided to discontinue the regimen because of adverse events. One month later, administration of everolimus(10mg/day)was initiated. Lesion loss was observed after 8 months, and the patient achieved a complete response(CR)without abnormal accumulation of FDG on PET-CT. Administration of everolimus was discontinued after 13 months because of peripheral neuropathy. Despite drug withdrawal, the patient has remained in remission for more than 3 years. Everolimus is considered an effective treatment for MANEC from NEC.

This paper experimentally finds the optimum number of input images of a machine learning-based mmWave received signal strength (RSS) value prediction scheme from depth images. By modeling the relationships between time-sequential depth images and RSS values based on machine learning, it is possible to predict the future RSS values, and thereby, a predictive handover makes a moment of degradation of the RSS value avoidable. As prediction models of RSS value, three machine learning models are compared: the convolutional neural networks (CNN), the combination of CNN and convolutional long short-term memory (CNN+ConvLSTM), and random forest. As the number of input images increases, the prediction accuracy generally improves, however, too numerous input images may make the prediction accuracy worse because of over-fitting. Experimental results reveal that the number of input images that are input in order to predict the RSS value the most accurately is 16.

This paper discusses the optimal decision-making for predictive handover in millimeter-wave (mmWave) communication networks using information of pedestrian movement. In mmWave communication networks, human blockage causes significant performance degradation. Hence, to maximize the throughput, it might be important to perform a handover predictively using information such as location and velocity of a pedestrian. To optimize the timing to perform the predictive handover, this paper presents a reinforcement learning framework. The important point in this framework is learning the optimal handover policy maximizing the future throughput expected under the locations and velocities of a pedestrian. To learn the optimal policy, this paper applies Q-learning. The numerical results demonstrate that the learned handover decisions outperform the heuristic handover decisions in terms of throughput performance.

This study demonstrates the feasibility of the proactive received power prediction by leveraging spatiotemporal visual sensing information toward the reliable millimeter-wave (mmWave) networks. Since the received power on a mmWave link can attenuate aperiodically due to a human blockage, the long-term series of the future received power cannot be predicted by analyzing the received signals before the blockage occurs. We propose a novel mechanism that predicts a time series of the received power from the next moment to even several hundred milliseconds ahead. The key idea is to leverage the camera imagery and machine learning (ML). The time-sequential images can involve the spatial geometry and the mobility of obstacles representing the mmWave signal propagation. ML is used to build the prediction model from the dataset of sequential images labeled with the received power in several hundred milliseconds ahead of when each image is obtained. The simulation and experimental evaluations using IEEE 802.11ad devices and a depth camera show that the proposed mechanism employing convolutional LSTM predicted a time series of the received power in up to 500 ms ahead at an inference time of less than 3 ms with a root-mean-square error of 3.5 dB.

The lattice Boltzmann method (LBM) is a relatively new method for fluid flow simulations, and is recently gaining popularity due to its simple algorithm and parallel scalability. Although the method has been successfully applied to a wide range of flow physics, its capabilities in simulating turbulent flow is still under-validated. Hence, in this paper, a 3D LBM code was developed to investigate the validity of the LBM for turbulent flow simulations through large eddy simulations (LES). A GPU enabled LBM code was developed, and validated against a benchmark test case involving the flow over a square cylinder in square channel. The flow results showed good agreement with literature, and speedups of over 150 times were observed when two GPUs were used in parallel. Turbulent flow simulations were then conducted using LES with the Smagorinsky subgrid model. The methodology was first validated by computing the fully developed turbulent channel flow, and comparing the results against direct numerical simulation results. The results were in good agreement despite the relatively coarse grid. The code was then used to simulate the turbulent flow over a square cylinder confined in a channel. In order to emulate a realistic inflow at the channel inlet, an auxiliary simulation consisting of a fully developed turbulent channel flow was run in conjunction, and its velocity profile was used to enforce the inlet boundary condition for the cylinder flow simulation. Comparison of the results with experimental and numerical results revealed that the presence of the turbulent flow structures at the inlet can significantly influence the resulting flow field around the cylinder.

The application of an alternative method of bond monitoring during high-temperature aging is reported using a custom made test chip with piezoresistive integrated CMOS microsensors located around test bond pads. The sensor detects radial stresses originating from the bond pad and can resolve changes because of intermetallic compound (IMC) formation, voiding, or crack formation at the bond interface. Optimized Au ball bonds are aged for over 2000 h at 175 °C. It is found that stress sensors next to the bonds are capable of showing the stages of IMC growth, consumption of pad Al layers, and monitoring the formation of low-density and Al-rich IMC (AuAl2) which shows an advanced stage of aging. In particular, a first stress signal increase corresponds to the conversion of all Al above the diffusion barrier into IMCs. The second increase in stress signal after a period of stability corresponds to conversion of all Al below the barrier into IMCs. The IMC formation in these periods causes shear strength increase. After complete bond Al consumption, the bond, however, reaches maximum strength. As bond degradation starts, e.g., by lateral IMC formation, voiding, and oxide formation, as well as because of lateral pad Al transformation to IMC, the signal exhibits a strong decrease. The findings are corroborated by results obtained from classical methods such as interruptive or destructive testing including visual inspection, shear testing, cross sectioning, and by bond resistance monitoring.

The aerodynamic effects due to the development of 3D flow structures in the flow over one and two cylinders in tandem were studied numerically, using the lattice Boltzmann method. 2D and 3D simulations were conducted for one and two cylinders with cylinder spacings in the range of 1.5d–8d, at Reynolds numbers in the range of 160–220. The presence of Mode A instabilities were confirmed for cylinder spacings larger than 4d, as well as the T3 modes at a cylinder spacing of 3d. It was found that the 3D structures resulting from the Mode A instabilities have significant effects on the Strouhal number and forces acting on the cylinders. However, for the Reynolds numbers studied, the forces acting on the upstream cylinder were less affected by the 3D instabilities than in the single cylinder case. It was also found that the T3 mode has a different effect on the force coefficients than the Mode A instabilities.

A 75-year-old woman presented with right upper quadrant abdominal pain and anorexia. She was diagnosed with descending colon cancer with lymph node and liver metastases. She was treated with preoperative chemotherapy consisting of levofolinate/5-fluorouracil/oxaliplatin (mFOLFOX6). After the completion of 7 courses of chemotherapy, the tumor shrunk remarkably. A left-sided colectomy with radical lymphadenectomy and an extensive posterior segment resection of the liver were performed. Postoperatively, pathological analysis revealed no cancerous cells in the primary tumor, lymph node metastases, or liver metastases. She is currently receiving mFOLFOX6 therapy as adjuvant chemotherapy. In a patient with advanced colon cancer, a complete response of not only the primary tumor but also the lymph node and liver metastases to preoperative chemotherapy is rare. This case demonstrates that mFOLFOX6 therapy is safe and effective as preoperative chemotherapy for advanced colon cancer.