Search

This paper proposes an automatic air-to-ground (A2G) channel model selection method based on machine learning (ML) using digital surface model (DSM) terrain data. In order to verify whether a communication network for a new non-terrestrial user service such as Urban Air Mobility (UAM) satisfies the required performance, it is necessary to perform a simulation reflecting the characteristics of the corresponding terrain environments as accurately as possible. For this simulation, A2G channel models corresponding to various terrain environments and a method of automatically classifying the terrain type of the simulation area must be provided. Many A2G channel models based on actual measurement results exist, but the practical automatic topography classification method still needs to be developed. This paper proposes the first practical automatic topography classification method using a two-step neural network-based classifier utilizing various geographic feature data as input. Since there is no open topography dataset to evaluate the accuracy of the proposed method, we built a new dataset for five topography classes that reflect the characteristics of Korea's topography, which is also a contribution of our study. The simulation results using the new data set show that the proposed ML-based method could increase the selection accuracy compared to the technique for direct classification by humans or the existing cross-correlation-based classification method. Since the proposed method utilizes the DSM data, open to the public, it can easily reflect the different terrain characteristics of each country. Therefore, the proposed method can be effectively used in the realistic performance evaluation of new non-terrestrial communication networks utilizing vast airspace such as UAM or 6G mobile communications. [ABSTRACT FROM AUTHOR]

The rapid advancement in AI requires efficient accelerators for training on edge devices, which often face challenges related to the high hardware costs of floating-point arithmetic operations. To tackle these problems, efficient floating-point formats inspired by block floating-point (BFP), such as Microsoft Floating Point (MSFP) and FlexBlock (FB), are emerging. However, they have limited dynamic range and precision for the smaller magnitude values within a block due to the shared exponent. This limits the BFP's ability to train deep neural networks (DNNs) with diverse datasets. This paper introduces the hybrid precision (HPFP) selection algorithms, designed to systematically reduce precision and implement hybrid precision strategies, thereby balancing layer-wise arithmetic operations and data path precision to address the shortcomings of traditional floating-point formats. Reducing the data bit width with HPFP allows more read/write operations from memory per cycle, thereby decreasing off-chip data access and the size of on-chip memories. Unlike traditional reduced precision formats that use BFP for calculating partial sums and accumulating those partial sums in 32-bit Floating Point (FP32), HPFP leads to significant hardware savings by performing all multiply and accumulate operations in reduced floating-point format. For evaluation, two training accelerators for the YOLOv2-Tiny model were developed, employing distinct mixed precision strategies, and their performance was benchmarked against an accelerator utilizing a conventional brain floating point of 16 bits (Bfloat16). The HPFP selection, employing 10 bits for the data path of all layers and for the arithmetic of layers requiring low precision, along with 12 bits for layers requiring higher precision, results in a 49.4% reduction in energy consumption and a 37.5% decrease in memory access. This is achieved with only a marginal mean Average Precision (mAP) degradation of 0.8% when compared to an accelerator based on Bfloat16. This comparison demonstrates that the proposed accelerator based on HPFP can be an efficient approach to designing compact and low-power accelerators without sacrificing accuracy. [ABSTRACT FROM AUTHOR]

Lane marking recognition is one of the most crucial features for automotive vehicles as it is one of the most fundamental requirements of all the autonomy features of Advanced Driver Assistance Systems (ADAS). Researchers have recently made promising improvements in the application of Lane Marking Detection (LMD). This research article has taken the initiative to review lane marking detection, mainly using deep learning techniques. This paper initially discusses the introduction of lane marking detection approaches using deep neural networks and conventional techniques. Lane marking detection frameworks can be categorized into single-stage and two-stage architectures. This paper elaborates on the network's architecture and the loss function for improving the performance based on the categories. The network's architecture is divided into object detection, classification, and segmentation, and each is discussed, including their contributions and limitations. There is also a brief indication of the simplification and optimization of the network for simplifying the architecture. Additionally, comparative performance results with a visualization of the final output of five existing techniques is elaborated. Finally, this review is concluded by pointing to particular challenges in lane marking detection, such as generalization problems and computational complexity. There is also a brief future direction for solving the issues, for instance, efficient neural network, Meta, and unsupervised learning. [ABSTRACT FROM AUTHOR]

The cooperative aerial and device-to-device (D2D) networks employing non-orthogonal multiple access (NOMA) are expected to play an essential role in next-generation wireless networks. Moreover, machine learning (ML) techniques, such as artificial neural networks (ANN), can significantly enhance network performance and efficiency in fifth-generation (5G) wireless networks and beyond. This paper studies an ANN-based unmanned aerial vehicle (UAV) placement scheme to enhance an integrated UAV-D2D NOMA cooperative network.The proposed placement scheme selection (PSS) method for integrating the UAV into the cooperative network combines supervised and unsupervised ML techniques. Specifically, a supervised classification approach is employed utilizing a two-hidden layered ANN with 63 neurons evenly distributed among the layers. The output class of the ANN is utilized to determine the appropriate unsupervised learning method—either k-means or k-medoids—to be employed. This specific ANN layout has been observed to exhibit an accuracy of 94.12%, the highest accuracy among the ANN models evaluated, making it highly recommended for accurate PSS predictions in urban locations. Furthermore, the proposed cooperative scheme allows pairs of users to be simultaneously served through NOMA from the UAV, which acts as an aerial base station. At the same time, the D2D cooperative transmission for each NOMA pair is activated to improve the overall communication quality. Comparisons with conventional orthogonal multiple access (OMA) and alternative unsupervised machine-learning based-UAV-D2D NOMA cooperative networks show that significant sum rate and spectral efficiency gains can be harvested through the proposed method under varying D2D bandwidth allocations. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel technique for the inspection of high-density polyethylene (HDPE) pipes using ultrasonic sensors, signal processing, and deep neural networks (DNNs). Specifically, we propose a technique that detects whether there is a diversion on a pipe or not. The proposed model transmits ultrasound signals through a pipe using a custom-designed array of piezoelectric transmitters and receivers. We propose to use the Zadoff–Chu sequence to modulate the input signals, then utilize its correlation properties to estimate the pipe channel response. The processed signal is then fed to a DNN that extracts the features and decides whether there is a diversion or not. The proposed technique demonstrates an average classification accuracy of 90.3 % (when one sensor is used) and 99.6 % (when two sensors are used) on 3 4 inch pipes. The technique can be readily generalized for pipes of different diameters and materials. [ABSTRACT FROM AUTHOR]

Vehicle fault detection and diagnosis (VFDD) along with predictive maintenance (PdM) are indispensable for early diagnosis in order to prevent severe accidents due to mechanical malfunction in urban environments. This paper proposes an early voiceprint driving fault identification system using machine learning algorithms for classification. Previous studies have examined driving fault identification, but less attention has focused on using voiceprint features to locate corresponding faults. This research uses 43 different common vehicle mechanical malfunction condition voiceprint signals to construct the dataset. These datasets were filtered by linear predictive coefficient (LPC) and wavelet transform(WT). After the original voiceprint fault sounds were filtered and obtained the main fault characteristics, the deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) architectures are used for identification. The experimental results show that the accuracy of the CNN algorithm is the best for the LPC dataset. In addition, for the wavelet dataset, DNN has the best performance in terms of identification performance and training time. After cross-comparison of experimental results, the wavelet algorithm combined with DNN can improve the identification accuracy by up to 16.57% compared with other deep learning algorithms and reduce the model training time by up to 21.5% compared with other algorithms. Realizing the cross-comparison of recognition results through various machine learning methods, it is possible for the vehicle to proactively remind the driver of the real-time potential hazard of vehicle machinery failure. [ABSTRACT FROM AUTHOR]

The use of electroencephalography (EEG) has recently grown as a means to diagnose neurodegenerative pathologies such as Alzheimer's disease (AD). AD recognition can benefit from machine learning methods that, compared with traditional manual diagnosis methods, have higher reliability and improved recognition accuracy, being able to manage large amounts of data. Nevertheless, machine learning methods may exhibit lower accuracies when faced with incomplete, corrupted, or otherwise missing data, so it is important do develop robust pre-processing techniques do deal with incomplete data. The aim of this paper is to develop an automatic classification method that can still work well with EEG data affected by artifacts, as can arise during the collection with, e.g., a wireless system that can lose packets. We show that a recurrent neural network (RNN) can operate successfully even in the case of significantly corrupted data, when it is pre-filtered by the robust principal component analysis (RPCA) algorithm. RPCA was selected because of its stated ability to remove outliers from the signal. To demonstrate this idea, we first develop an RNN which operates on EEG data, properly processed through traditional PCA; then, we use corrupted data as input and process them with RPCA to filter outlier components, showing that even with data corruption causing up to 20% erasures, the RPCA was able to increase the detection accuracy by about 5% with respect to the baseline PCA. [ABSTRACT FROM AUTHOR]

Globally, the incidence rate for breast cancer ranks first. Treatment for early-stage breast cancer is highly cost effective. Five-year survival rate for stage 0–2 breast cancer exceeds 90%. Screening mammography has been acknowledged as the most reliable way to diagnose breast cancer at an early stage. Taiwan government has been urging women without any symptoms, aged between 45 and 69, to have a screening mammogram bi-yearly. This brings about a large workload for radiologists. In light of this, this paper presents a deep neural network (DNN)-based model as an efficient and reliable tool to assist radiologists with mammographic interpretation. For the first time in the literature, mammograms are completely classified into BI-RADS categories 0, 1, 2, 3, 4A, 4B, 4C and 5. The proposed model was trained using block-based images segmented from a mammogram dataset of our own. A block-based image was applied to the model as an input, and a BI-RADS category was predicted as an output. At the end of this paper, the outperformance of this work is demonstrated by an overall accuracy of 94.22%, an average sensitivity of 95.31%, an average specificity of 99.15% and an area under curve (AUC) of 0.9723. When applied to breast cancer screening for Asian women who are more likely to have dense breasts, this model is expected to give a higher accuracy than others in the literature, since it was trained using mammograms taken from Taiwanese women. [ABSTRACT FROM AUTHOR]

Usage of effective classification techniques on Magnetic Resonance Imaging (MRI) helps in the proper diagnosis of brain tumors. Previous studies have focused on the classification of normal (nontumorous) or abnormal (tumorous) brain MRIs using methods such as Support Vector Machine (SVM) and AlexNet. In this paper, deep learning architectures are used to classify brain MRI images into normal or abnormal. Gender and age are added as higher attributes for more accurate and meaningful classification. A deep learning Convolutional Neural Network (CNN)-based technique and a Deep Neural Network (DNN) are also proposed for effective classification. Other deep learning architectures such as LeNet, AlexNet, ResNet, and traditional approaches such as SVM are also implemented to analyze and compare the results. Age and gender biases are found to be more useful and play a key role in classification, and they can be considered essential factors in brain tumor analysis. It is also worth noting that, in most circumstances, the proposed technique outperforms both existing SVM and AlexNet. The overall accuracy obtained is 88% (LeNet Inspired Model) and 80% (CNN-DNN) compared to SVM (82%) and AlexNet (64%), with best accuracy of 100%, 92%, 92%, and 81%, respectively. [ABSTRACT FROM AUTHOR]

This study investigated the squeal mechanism induced by friction in a lead screw system. The dynamic instability in the friction noise model of the lead screw was derived through a complex eigenvalue analysis via a finite element model. A two degree of freedom model was described to analyze the closed solutions generated in the lead screw, and the friction noise sensitivity was examined. The analysis showed that the main source of friction noise in the lead screw was the bending mode pair, and friction-induced instability occurred when the ratio of the stiffness of the bending pair modes was 0.9–1. We also built an architecture to predict multiple outputs from a single model using deep neural networks and demonstrated that friction-induced instability can be predicted by deep neural networks. In particular, instability with nonlinearity was predicted very accurately by deep neural networks with a maximum absolute difference of about 0.035. [ABSTRACT FROM AUTHOR]

This paper proposes a method to embed and extract a watermark on a digital hologram using a deep neural network. The entire algorithm for watermarking digital holograms consists of three sub-networks. For the robustness of watermarking, an attack simulation is inserted inside the deep neural network. By including attack simulation and holographic reconstruction in the network, the deep neural network for watermarking can simultaneously train invisibility and robustness. We propose a network training method using hologram and reconstruction. After training the proposed network, we analyze the robustness of each attack and perform re-training according to this result to propose a method to improve the robustness. We quantitatively evaluate the results of robustness against various attacks and show the reliability of the proposed technique. [ABSTRACT FROM AUTHOR]

Deep Neural Network (DNN) systems tend to produce overconfident or uncalibrated outputs. This poses problems for active sensor systems that have a DNN module as the main feedback controller. In this paper, we study a closed-loop feedback smart camera from the lens of uncertainty estimation. The uncertainty of the task output is used to characterize and facilitate the feedback operation. The DNN uncertainty in the feedback system is estimated and characterized using both sampling and non-sampling based methods. In addition, we propose a closed-loop control that incorporates uncertainty information when providing feedback. We show two modes of control, one that prioritizes false positives and one that prioritizes false negatives, and a hybrid approach combining the two. We apply the uncertainty-driven control to the tasks of object detection, object tracking, and action detection. The hybrid system improves object detection and tracking accuracy on the CAMEL dataset by 1.1% each respectively. For the action detection task, the hybrid approach improves accuracy by 1.4%. [ABSTRACT FROM AUTHOR]

In this paper, we propose and implement a novel framework of deep learning based antenna selection (DLBAS)-aided multiple-input–multiple-output (MIMO) software defined radio (SDR) system. The system is constructed with the following three steps: (1) a MIMO SDR communication platform is first constructed, which is capable of achieving uplink communication from users to the base station via time division duplex (TDD); (2) we use the deep neural network (DNN) from our previous work to construct a deep learning decision server to assist the MIMO SDR platform for making intelligent decision for antenna selection, which transforms the optimization-driven decision making method into a data-driven decision making method; and (3) we set up the deep learning decision server as a multithreading server to improve the resource utilization ratio. To evaluate the performance of the DLBAS-aided MIMO SDR system, a norm-based antenna selection (NBAS) scheme is selected for comparison. The results show that the proposed DLBAS scheme performed equally to the NBAS scheme in real-time and out-performed the MIMO system without AS with up to 53% improvement on average channel capacity gain. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel and efficient framework for 3D action recognition using a deep learning architecture. First, we develop a 3D normalized pose space that consists of only 3D normalized poses, which are generated by discarding translation and orientation information. From these poses, we extract joint features and employ them further in a Deep Neural Network (DNN) in order to learn the action model. The architecture of our DNN consists of two hidden layers with the sigmoid activation function and an output layer with the softmax function. Furthermore, we propose a keyframe extraction methodology through which, from a motion sequence of 3D frames, we efficiently extract the keyframes that contribute substantially to the performance of the action. In this way, we eliminate redundant frames and reduce the length of the motion. More precisely, we ultimately summarize the motion sequence, while preserving the original motion semantics. We only consider the remaining essential informative frames in the process of action recognition, and the proposed pipeline is sufficiently fast and robust as a result. Finally, we evaluate our proposed framework intensively on publicly available benchmark Motion Capture (MoCap) datasets, namely HDM05 and CMU. From our experiments, we reveal that our proposed scheme significantly outperforms other state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Industry 4.0 requires high-speed data exchange that includes fast, reliable, low-latency, and cost-effective data transmissions. As visible light communication (VLC) can provide reliable, low-latency, and secure connections that do not penetrate walls and are immune to electromagnetic interference; it can be considered a solution for Industry 4.0. The non-orthogonal multiple access (NOMA) technique can achieve high spectral efficiency using the same frequency and time resources for multiple users. It means that smaller amounts of resources will be used compared with orthogonal multiple access (OMA). Therefore, handling multiple data transmissions with VLC-NOMA can be easier for factory automation than OMA. However, as the transmit power is split, the reliability is reduced. Therefore, this study proposed a deep neural network (DNN)-based power-allocation algorithm (DBPA) to improve the reliability of the system. Further, to schedule multiple nodes in VLC-NOMA system, a priority-based user-pairing (PBUP) scheme is proposed. The proposed techniques in VLC-NOMA system were evaluated in terms of the factory automation scenario and showed that it improves reliability and reduces missed deadlines. [ABSTRACT FROM AUTHOR]

Indoorlocation-based service (LBS) technology has been emerged as a major research topic in recent years. Positioning technology is essential for providing LBSs. The existing indoor positioning solutions generally use radio-frequency (RF)-based communication technologies such as Wi-Fi. However, RF-based communication technologies do not provide precise positioning owing to rapid changes in the received signal strength due to walls, obstacles, and people movement in indoor environments. Hence, this study adopts visible-light communication (VLC) for user positioning in an indoor environment. VLC is based on light-emitting diodes (LEDs) and its advantage includes high efficiency and long lifespan. In addition, this study uses a deep neural network (DNN) to improve the positioning accuracy and reduce the positioning processing time. The hyperparameters of the DNN model are optimized to improve the positioning performance. The trained DNN model is designed to yield the actual three-dimensional position of a user. The simulation results show that our optimized DNN model achieves a positioning error of 0.0898 m with a processing time of 0.5 ms, which means that the proposed method yields more precise positioning than the other methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel machine learning (ML) based link-to-system (L2S) mapping technique for inter-connecting a link-level simulator (LLS) and a system-level simulator (SLS). For validating the proposed technique, we utilized 5G K-Simulator, which was developed through a collaborative research project in Republic of Korea and includes LLS, SLS, and network-level simulator (NS). We first describe a general procedure of the L2S mapping methodology for 5G new radio (NR) systems, and then, we explain the proposed ML-based exponential effective signal-to-noise ratio (SNR) mapping (EESM) method with a deep neural network (DNN) regression algorithm. We compared the proposed ML-based EESM method with the conventional L2S mapping method. Through extensive simulation results, we show that the proposed ML-based L2S mapping technique yielded better prediction accuracy in regards to block error rate (BLER) while reducing the processing time. [ABSTRACT FROM AUTHOR]

Due to the exponential growth of data communications, linearity specification is deteriorating and, in high frequency systems, impedance transformation leading to power delivering from power amplifiers (PAs) to antennas is becoming an increasingly important concept. Intelligent-based optimization methods can be a suitable solution for enhancing this characteristic in the transceiver systems. Herein, to tackle the problems of linearity and impedance transformations, deep neural network (DNN)-based optimizations are employed. In the first phase, the antenna is modeled through the DNN with using the long short-term memory (LSTM) leading to forecast the load impedances in the a wide frequency band. Afterwards, the PA is modeled and optimized through another LSTM-based DNN using Multivariate Newton's Method where the optimal drain impedances are predicted from the first DNN (i.e., modeled antenna). The whole optimization methodology is executed automatically leading to enhance linearity specification of the whole system. For proving the novelty of the proposed method, monolithic microwave integrated circuit (MMIC) along with the multiple-input multiple-output (MIMO) antenna is designed, modeled, and optimized concurrently in the frequency band from 7.49 GHz to 12.44 GHz. The proposed method leads to enhancing the linearity of the transceiver in an effective way where DNN-based PA model gives rise to a solution for achieving the most optimal drain impedance through the modeled DNN-based antenna. [ABSTRACT FROM AUTHOR]

In this study, we focus on automated optimization design methodologies to concurrently trade off between power gain, output power, efficiency, and linearity specifications in radio frequency (RF) high-power amplifiers (HPAs) through deep neural networks (DNNs). The RF HPAs are highly nonlinear circuits where characterizing an accurate and desired amplitude and phase responses to improve the overall performance is not a straightforward process. For this case, we propose a coarse and fine modeling approach based on firstly modeling the involved transistor and then selecting the best configuration of HAP along with optimizing the involved input and output termination networks through DNNs. In the fine phase, we firstly construct the equivalent modeling of the GaN HEMT transistor by using X-parameters. Then in the coarse phase, we utilize hidden layers of the modeled transistor and replace the HPA's DNN to model the behavior of the selected HPA by using S-parameters. If the suitable accuracy of HPA modeling is not achieved, the hyperparameters of the fine model are improved and re-evaluated in the HPA model. We call the optimization process coarse and fine modeling since the evaluation process is performed from S-parameters to X-parameters. This stage of optimization can ensure modeling the nonlinear HPA design that includes a high number of parameters in an effective way. Furthermore, for accelerating the optimization process, we use the classification DNN for selecting the best topology of HPA for modeling the most suitable configuration at the coarse phase. The proposed modeling strategy results in relatively highly accurate HPA designs that generate post-layouts automatically, where multi-tone harmonic balance specifications are optimized once together without any human interruptions. To validate the modeling approach and optimization process, a 10 W HPA is simulated and measured in the operational frequency band of 1.8 GHz to 2.2 GHz, i.e., the L-band. The measurement results demonstrate a drain efficiency higher than 54% and linear gain performance more than 12.5 dB, with better than 50 dBc adjacent channel power ratio (ACPR) after DPD. [ABSTRACT FROM AUTHOR]

This paper proposes a practical physical tampering detection mechanism using inexpensive commercial off-the-shelf (COTS) Wi-Fi endpoint devices with a deep neural network (DNN) on channel state information (CSI) in the Wi-Fi signals. Attributed to the DNN that identifies physical tampering events due to the multi-subcarrier characteristics in CSI, our methodology takes effect using only one COTS Wi-Fi endpoint with a single embedded antenna to detect changes in the relative orientation between the Wi-Fi infrastructure and the endpoint, in contrast to previous sophisticated, proprietary approaches. Preliminary results show that our detectors manage to achieve a 95.89% true positive rate (TPR) with no worse than a 4.12% false positive rate (FPR) in detecting physical tampering events. [ABSTRACT FROM AUTHOR]