ABSTRACT
The Internet of Vehicles(IoV) employs vehicle-to-everything (V2X) technology to establish intricate interconnections among the Internet, the IoT network, and the Vehicle Networks (IVNs), forming a complex vehicle communication network. However, the vehicle communication network is very vulnerable to attacks. The implementation of an intrusion detection system (IDS) emerges as an essential requisite to ensure the security of in-vehicle/inter-vehicle communication in IoV. Within this context, the imbalanced nature of network traffic data and the diversity of network attacks stand as pivotal factors in IDS performance. On the one hand, network traffic data often heavily suffer from data imbalance, which impairs the detection performance. To address this issue, this paper employs a hybrid approach combining the Synthetic Minority Over-sampling Technique (SMOTE) and RandomUnderSampler to achieve a balanced class distribution. On the other hand, the diversity of network attacks constitutes another significant factor contributing to poor intrusion detection model performance. Most current machine learning-based IDSs mainly perform binary classification, while poorly dealing with multiclass classification. This paper proposes an adaptive tree-based ensemble network as the intrusion detection engine for the IDS in IoV. This engine employs a deep-layer structure, wherein diverse ML models are stacked as layers and are interconnected in a cascading manner, which enables accurate and efficient multiclass classification, facilitating the precise identification of diverse network attacks. Moreover, a machine learning-based approach is used for feature selection to reduce feature dimensionality, substantially alleviating the computational overhead. Finally, we evaluate the proposed IDS performance on various cyber-attacks from the in-vehicle and external networks in IoV by using the network intrusion detection dataset CICIDS2017 and the vehicle security dataset Car-Hacking. The experimental results demonstrate remarkable performance, with an F1-score of 0.965 on the CICIDS2017 dataset and an F1-score of 0.9999 on the Car-Hacking dataset. These scores demonstrate that our IDS can achieve efficient and precise multiclass classification. This research provides a valuable reference for ensuring the cybersecurity of IoV.
ABSTRACT
With the expansion of high-speed railway network in the world, it is inevitable for railways to pass through seasonal frozen regions. Since in a seasonal frozen region the ground can have significantly different mechanical properties between the freezing season and the warm season, train-induced ground vibration is also season-dependent but it has not received enough attention up to now. This paper gives an investigation into the effects of soil and fastener-freezing on ground vibrations induced by high-speed train in frozen regions. Based on the well-established relationships between soil mechanical properties and freezing temperature, a frozen ground is shown to be still represented by a layered ground and therefore, previously developed models for predicting ground vibration generated by a train running along a track resting on a layered ground can be readily applied. The effects of low temperature on the dynamical properties of fasteners are also considered. Results show that, due to the increased Young's modulus at freezing condition, the vibration level of a frozen ground near the track is lower than that of the non-frozen counterpart. However, well away from the track, the vibration level of the frozen ground is much stronger than that of the non-frozen one, mainly due to the much-reduced loss factor of the frozen ground, which results in slower attenuation of vibration with propagating distance. Results also show that, the difference in ground vibration between a frozen ground and its non-frozen counterpart is mainly caused by freezing of the ground. The emphasis of this study lies in making clear the characteristics of train-induced ground vibration in frozen regions and the differences between frozen and non-frozen regions, providing some new fundamental insights about this practical problem, which have significant engineering guidance and application value.
ABSTRACT
Animal communication is often hampered by noise interference. Noise masking has primarily been studied in terms of its unimodal effect on sound information provision and use, while little is known about its cross-modal effect and how animals weigh unimodal and multimodal courtship cues in noisy environments. Here, we examined the cross-modal effects of background noise on female visual perception of mate choice and female preference for multimodal displays (sound + vocal sac) in a species of treefrog. We tested female mate choices using audio/video playbacks in the presence and absence of noise (white noise band-filtered to match or mismatch female sensitive hearing range, heterospecific chorus). Surprisingly, multimodal displays do not improve receiver performance in noise. The heterospecific chorus and white noise band-filtered to match female sensitive hearing ranges, significantly reduced female responses to the attractive visual stimuli in addition to directly impairing auditory information use. Meanwhile, the cross-modal impacts of background noise are influenced to some extent by whether the noise band matches female sensitive hearing range and the difficulty of distinguishing tasks. Our results add to the evidence for cross-modal effects of noise and are the first to demonstrate that background noise can disrupt female responses to visual information related to mate choice, which may reduce the communication efficiency of audiovisual signals in noisy environments and impose fitness consequences. This study has key ecological and evolutionary implications because it illustrates how noise influences mate choice in wildlife via cross-sensory interference, which is crucial in revealing the function and evolution of multimodal signals in noisy environments as well as informing evidence-based conservation strategies for forecasting and mitigating the multimodal impacts of noise interference on wildlife.
Subject(s)
Animal Communication , Anura , Mating Preference, Animal , Noise , Animals , Anura/physiology , Courtship , Female , Noise/adverse effects , SoundABSTRACT
Many animals rely on complex signals that target multiple senses to attract mates and repel rivals. These multimodal displays can however also attract unintended receivers, which can be an important driver of signal complexity. Despite being taxonomically widespread, we often lack insight into how multimodal signals evolve from unimodal signals and in particular what roles unintended eavesdroppers play. Here, we assess whether the physical movements of parasite defense behavior increase the complexity and attractiveness of an acoustic sexual signal in the little torrent frog (Amolops torrentis). Calling males of this species often display limb movements in order to defend against blood-sucking parasites such as frog-biting midges that eavesdrop on their acoustic signal. Through mate choice tests we show that some of these midge-evoked movements influence female preference for acoustic signals. Our data suggest that midge-induced movements may be incorporated into a sexual display, targeting both hearing and vision in the intended receiver. Females may play an important role in incorporating these multiple components because they prefer signals which combine multiple modalities. Our results thus help to understand the relationship between natural and sexual selection pressure operating on signalers and how in turn this may influence multimodal signal evolution.
Subject(s)
Parasites , Acoustics , Animals , Anura/physiology , Female , Male , Movement , Sexual Behavior, Animal , Vocalization, AnimalABSTRACT
Basal metabolic rate (BMR) has been shown to be a highly phenotypic flexibility trait within species. A significant proportion of an individual's energy budget is accounted for by BMR, hence among-individual variation in this trait may affect other energetic processes, as well as fitness. In this study, we measured BMR, organ mass, mitochondrial respiration capacities and cytochrome c oxidase (COX) activities in muscle and liver and circulating levels of plasma triiodothyronine (T3) in Chinese bulbuls (Pycnonotus sinensis) and Eurasian tree sparrows (Passer montanus). Our results showed that heart and kidney mass was positively correlated with BMR in Chinese bulbuls, whereas liver and kidney mass was positively correlated with BMR in Eurasian tree sparrows. Regarding metabolic biochemical markers of tissues, state 4 respiration and COX activity in the muscles of the Chinese bulbuls was correlated with BMR, while state 4 respiration in the muscle and liver was correlated with BMR in Eurasian tree sparrows. T3 was significantly and positively correlated with BMR in Chinese bulbuls and Eurasian tree sparrows. Consistent with the above results, our findings suggest that T3 levels play an important role in modulating BMR in Chinese bulbuls and Eurasian tree sparrows. Moreover, individual variation in BMR can be explained partly by morphological and physiological mechanisms.
Subject(s)
Basal Metabolism , Sparrows , Animals , Liver , Muscles , TriiodothyronineABSTRACT
Both human and nonhuman animals communicating acoustically face the problem of noise interference, especially anurans during mating activities. Previous studies concentrated on the effect of continuous noise on signal recognition, but it is still unknown whether different notes in advertisement calls impaired by noise affect female choice and male-male competition or not. In this study, we tested female preferences and male-evoked vocal responses in serrate-legged small tree frog (Kurixalus odontotarsus), by broadcasting the five-note advertisement call and the advertisement call with the second, third, or fourth note replaced by noise, respectively. In phonotaxis experiments, females significantly discriminated against the advertisement call with the fourth note impaired by noise, although they did not discriminate against other two calls impaired by noise, which indicates that the negative effect of noise on female preference is related to the order of impaired notes in the advertisement call. In playback experiments, males increased the total number of notes in response to noise-impaired calls compared with spontaneous calls. More interestingly, the vocal responses evoked by noise-impaired calls were generally similar to those evoked by complete advertisement calls, suggesting that males may recognize the noise-impaired calls as complete advertisement calls. Taken together, our study shows that different notes in advertisement calls replaced by noise have distinct effects on female choice and male-male competition.
ABSTRACT
Many small birds living in regions with seasonal fluctuations and ambient temperatures typically respond to cold by increasing metabolic thermogenesis, internal organ mass and the oxidative capacity of certain tissues. In this study, we investigated seasonal adjustments in body mass, resting metabolic rate (RMR), evaporative water loss (EWL), the mass of selected internal organs, and two indicators of cellular aerobic respiration (mitochondrial state-4 respiration and cytochrome c oxidase activity) in Chinese hwamei (Garrulax canorus) that had been captured in summer or winter from Wenzhou, China. RMR and EWL were higher in winter than in summer. State-4 respiration in the heart, liver, kidneys and pectoral muscle, as well as cytochrome c oxidase activity in the liver, kidneys and pectoral muscle were also higher in winter than summer. In addition, there was a positive correlation between RMR and EWL, and between RMR and indicators of cellular metabolic activity in the heart, liver, kidneys and pectoral muscle. This phenotypic flexibility in physiological and biochemical thermoregulatory responses may be important to the hwamei's ability to survive the unpredictable, periodic, cold temperatures commonly experienced in Wenzhou in winter.