“…Machine learning algorithms require an effective analysis of large amounts of historical data and real-time data inferred from multiple data streams (sensors and data collection systems) [16]. Therefore, the data-preprocessing stage has a significant impact on the performance of machine learning algorithms [17][18][19]. This section explores traditional machine learning methods and more advanced deep learning methods, both of which are commonly used for predictive maintenance in the automotive domain [20].…”
Section: Overview Of Machine and Deep Learning Methodsmentioning
The necessity of vehicle fault detection and diagnosis (VFDD) is one of the main goals and demands of the Internet of Vehicles (IoV) in autonomous applications. This paper integrates various machine learning algorithms, which are applied to the failure prediction and warning of various types of vehicles, such as the vehicle transmission system, abnormal engine operation, and tire condition prediction. This paper first discusses the three main AI algorithms, such as supervised learning, unsupervised learning, and reinforcement learning, and compares the advantages and disadvantages of each algorithm in the application of system prediction. In the second part, we summarize which artificial intelligence algorithm architectures are suitable for each system failure condition. According to the fault status of different vehicles, it is necessary to carry out the evaluation of the digital filtering process. At the same time, it is necessary to preconstruct its model analysis and adjust the parameter attributes, types, and number of samples of various vehicle prediction models according to the analysis results, followed by optimization to obtain various vehicle models. Finally, through a cross-comparison and sorting, the artificial intelligence failure prediction models can be obtained, which can correspond to the failure status of a certain car model and a certain system, thereby realizing a most appropriate AI model for a specific application.
“…Machine learning algorithms require an effective analysis of large amounts of historical data and real-time data inferred from multiple data streams (sensors and data collection systems) [16]. Therefore, the data-preprocessing stage has a significant impact on the performance of machine learning algorithms [17][18][19]. This section explores traditional machine learning methods and more advanced deep learning methods, both of which are commonly used for predictive maintenance in the automotive domain [20].…”
Section: Overview Of Machine and Deep Learning Methodsmentioning
The necessity of vehicle fault detection and diagnosis (VFDD) is one of the main goals and demands of the Internet of Vehicles (IoV) in autonomous applications. This paper integrates various machine learning algorithms, which are applied to the failure prediction and warning of various types of vehicles, such as the vehicle transmission system, abnormal engine operation, and tire condition prediction. This paper first discusses the three main AI algorithms, such as supervised learning, unsupervised learning, and reinforcement learning, and compares the advantages and disadvantages of each algorithm in the application of system prediction. In the second part, we summarize which artificial intelligence algorithm architectures are suitable for each system failure condition. According to the fault status of different vehicles, it is necessary to carry out the evaluation of the digital filtering process. At the same time, it is necessary to preconstruct its model analysis and adjust the parameter attributes, types, and number of samples of various vehicle prediction models according to the analysis results, followed by optimization to obtain various vehicle models. Finally, through a cross-comparison and sorting, the artificial intelligence failure prediction models can be obtained, which can correspond to the failure status of a certain car model and a certain system, thereby realizing a most appropriate AI model for a specific application.
“…As a result, the proposed GS detector of (50) reduces to the GS detector of (28) with λ GS = λ RS = 2M |b| 2 (a H r P ⊥ Ar a r )/σ 2 . Corollary 4: From the probabilities of false alarm and detection of the clairvoyant in (26), RS in (29) and the proposed GS detectors in Theorem 1, the detection performance is in the order of…”
Section: B Proposed Generalized Subspace (Gs) Detectormentioning
confidence: 96%
“…1) Fast-time (range) domain: interference-zeroing [16]- [18], sparse reconstruction [19], [20], adaptive noise cancellers [21], signal separation [22], fast-time-frequency mode retrieval [23], and fast-time neural networks [24], [25]; 2) Slow-time (Doppler) domain: waveform randomization [26], [27], ramp filtering [28], and slow-time neural network [29]; 3) Joint range-Doppler domain: neural network based de-noisers [30]- [33]; 4) Communication-assisted scheduling, such as timedivision multiple access [34], and chirp slope and frequency offset scheduling [35].…”
This paper considers mutual interference mitigation among automotive radars using frequency-modulated continuous wave (FMCW) signal and multiple-input multiple-output (MIMO) virtual arrays. For the first time, we derive a general interference signal model that fully accounts for not only the time-frequency incoherence, e.g., different FMCW configuration parameters and time offsets, but also the slow-time code MIMO incoherence and array configuration differences between the victim and interfering radars. Along with a standard MIMO-FMCW object signal model, we turn the interference mitigation into a spatial-domain object detection under incoherent MIMO-FMCW interference described by the explicit interference signal model, and propose a constant false alarm rate (CFAR) detector. More specifically, the proposed detector exploits the structural property of the derived interference model at both transmit and receive steering vector space. We also derive analytical closedform expressions for probabilities of detection and false alarm. Performance evaluation using both synthetic-level and phased array system-level simulation confirms the effectiveness of our proposed detector over selected baseline methods.
“…Strategy methods, such as reinforcement learning techniques [ 20 , 21 ], deep learning techniques [ 22 , 23 ], and generative adversarial networks [ 24 ], have been used for IM in FMCW radars. These methods require a large amount of data for training, they have high computational complexity, and the hardware implementation is complex.…”
In this study, an interference detection and mitigation method is proposed for frequency-modulated continuous-wave radar systems based on time-domain signal reconstruction. The interference detection method uses the difference in one-dimensional fast Fourier transform (1D-FFT) results between targets and interferences. In the 1D-FFT results, the target appears as a peak at the same frequency point for all chirps within one frame, whereas the interference appears as the absence of target peaks within the first or last few chirps within one frame or as a shift in the target peak position in different chirps. Then, the interference mitigation method reconstructs the interference signal in the time domain by the estimated parameter from the 1D-FFT results, so the interference signal can be removed from the time domain without affecting the target signal. The simulation results show that the proposed interference mitigation algorithm can reduce the amplitude of interference by about 25 dB. The experimental results show that the amplitude of interference is reduced by 20–25 dB, proving the effectiveness of the simulation results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.