With the significant development of practicability in deep learning and the ultra-highspeed information transmission rate of 5G communication technology will overcome the barrier of data transmission on the Internet of Vehicles, automated driving is becoming a pivotal technology affecting the future industry. Sensors are the key to the perception of the outside world in the automated driving system and whose cooperation performance directly determines the safety of automated driving vehicles. In this survey, we mainly discuss the different strategies of multi-sensor fusion in automated driving in recent years. The performance of conventional sensors and the necessity of multi-sensor fusion are analyzed, including radar, LiDAR, camera, ultrasonic, GPS, IMU, and V2X. According to the differences in the latest studies, we divide the fusion strategies into four categories and point out some shortcomings. Sensor fusion is mainly applied for multi-target tracking and environment reconstruction. We discuss the method of establishing a motion model and data association in multi-target tracking. At the end of the paper, we analyzed the deficiencies in the current studies and put forward some suggestions for further improvement in the future. Through this investigation, we hope to analyze the current situation of multi-sensor fusion in the automated driving process and provide more efficient and reliable fusion strategies.

The present study was aimed at determining the role of paraquat (PQ) in the activation of the NF-E2-related factor 2 (Nrf2)/heme oxygenase 1 (HO-1) pathway and the possible neuroprotective effects of tert-butylhydroquinone (tBHQ) pretreatment on PQ-induced neurodegeneration in vivo and in vitro. 7 mg/kg PQ treatment of male C57BL/6 mice caused decreased spontaneous locomotor activity, decreased tyrosine hydroxylase (TH)-positive neurons, increased terminal deoxynucleotidyl transferase-mediated dUTP biotin nick end-labeling (TUNEL)-positive cells in the substantia nigra, as well as increased protein levels of both nuclear Nrf2 and HO-1. In PQ-treated mice, pretreatment with 1 % tBHQ (w/w) significantly attenuated impairments in behavioral performance, decreased TH-positive neurons, and increased TUNEL-positive cells in the substantia nigra, as well as increased protein expression of both nuclear Nrf2 and HO-1. Pretreatment with 40 μM tBHQ protected PC12 cells against 100 and 300 μM PQ-mediated cytotoxicity. The dual-luciferase reporter gene also revealed that the transcriptional activation of HO-1 gene expression of the antioxidant responsive element via Nrf2 occurred as a consequence of 100 and 300 μM PQ exposure. Collectively, these results clearly indicated for the first time that the Nrf2/HO-1 pathway in the substantia nigra was activated by PQ, and pretreatment with tBHQ conferred neuroprotection against PQ-induced Parkinsonism presumably by increasing Nrf2 and HO-1 expression.

Recent evidence indicates that microRNAs (miRNAs) play a key role in neurodegenerative diseases. However, the toxic effects of paraquat (PQ) and 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine (MPTP) on miRNA expression profiles in dopaminergic neurons have not been investigated. In the present study, we used microarray analysis to show that PQ and MPTP induce alterations of miRNA expression in neuro-2a cells. The results reveal that treatment with 300 μm PQ caused miRNA deregulation, such that 60 miRNAs were upregulated and 228 miRNAs were downregulated. Following treatment with 300 μm MPTP, a total of 576 miRNAs were dysregulated, of which 506 were upregulated and 70 were downregulated. Alterations in the expression of miR-17-5p, miR-210-3p, miR-374-5p, miR-378-3p and miR-503-5p were verified by real-time quantitative reverse transcriptase polymerase chain reaction. Moreover, overexpression of miR-17-5p in Neuro-2a cells enhanced cell proliferation, suppressed apoptosis and promoted S phase transition of the cell cycle after PQ treatment. Taken together, our study demonstrates that characteristic changes in miRNA expression profiles occur after PQ and MPTP treatment, which suggests that miRNAs may be involved in the development of PQ- and MPTP-induced neurodegeneration. Downregulated miR-17-5p expression contributes to PQ-induced dopaminergic neurodegeneration.

Both transcription factors (TFs) and microRNAs (miRNAs) can exert a widespread impact on gene expression. In the present study, we investigated the role of Nrf2 in paraquat-induced intracorporeal neurodegeneration and miRNA expression by exposing Nrf2 wild-type and knockout mice to paraquat (PQ) or 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine (MPTP). Exposure to 10 mg/kg PQ or 30 mg/kg MPTP caused damage to nerve cells in the substantia nigra (SN) in both Nrf2 (+/+) and Nrf2 (−/−) ICR mice, which included cell morphological changes, detectable apoptosis and a significant reduction in the number of dopaminergic (DA) neurons. When mice were exposed to the same PQ dose of 10 mg/kg, significant fewer tyrosine hydroxylase (TH)-positive DA neurons were observed in the Nrf2 (−/−) mice than that in the Nrf2 (+/+) mice. Both Nrf2 deficiency and PQ or MPTP exposure could alter miRNA expression profile in the SN, suggesting the potential involvement of Nrf2 in the PQ-induced or MPTP-induced miRNA expression alteration. The expression of miR-380-3p was altered by the Nrf2-MPTP interaction effect. miR-380-3p/Sp3-mRNA pathway is likely part of the mechanism of MPTP-induced neurodegeneration. Collectively, our results corroborated the protective role of Nrf2 and also demonstrated the essential interaction of Nrf2 with miRNAs in intracorporal neurodegeneration induced by neurotoxicants.

Geometric dynamic configurations of body joints play an essential role in distinguishing different human activities. However, many existing human activity recognition approaches lack the capability of automatically learning these configurations from sequences of joints in four-dimensional space (spatio and temporal). In this paper, the authors propose an automatic joint configuration learning method, based on dictionary learning and sparse representation. The proposed method achieves the following features: 1) it automatically learns dynamic spatio-temporal geometric configurations of body joints, involved in activities, in a simple way; 2) it dispenses with the hand crafted feature designing process and provides a new method to organize joint coordinate data as fixed length column vectors, which are suitable for dictionary learning; 3) it replaces the conventional bag of words model with sparse coding method; words in learned dictionary capture subactivity features, and the frequencies of different words appearing in different activities characterize the categories of global activity; 4) it is robust to time misalignment and can classify any length of video sequence (online classification) in real time; 5) it is easy to combine this method with other forms of data for better performance, because of its data driven nature and flexible framework. The proposed method is tested with three state-of-the-art public human activity recognition datasets and the results are found to be better than those of CAD-60 dataset, and comparable to those of both MSR Action 3D and MSR Daily Activity datasets (source codes are publicly available at https://github.com/jinqijinqi/ SparseCodingDictionaryLearningHumanActivityRecognition).