Search

Deep learning solutions in big data applications can benefit cloud centres and can also lead to network communication overhead. Typically, data collected from traffic are sent to the traffic management centre for analysis. However, this process can worsen the network route to the traffic management centre. A two-tier mechanism has been developed to address this issue, which performs vehicle speed estimation and traffic congestion detection for efficient traffic management. The real-time traffic video data are captured and the video frames are initially processed through a foreground extraction process, which extracts the temporarily stopped vehicles on the road by removing background pixels from the frames. The video frames are then wrapped in an up-down view to remove the influence of the observation angle. The traffic congestion is then detected accurately based on the traffic characteristics using the proposed Ensemble Random Forest-based Gradient Optimization (ERF-GO) algorithm. The generalization error occurs when learning complex features on frames is minimized using a gradient-based optimization (GO) algorithm. Finally, the learned information on traffic conditions is forwarded to the cloud and edge computing environments based on network connection speed. The efficiency of the proposed ERF-GO is investigated in terms of performance metrics, namely root mean square error, speed detection error, execution time, computational cost, accuracy, latency, workload balance, precision, recall, f-measure, and congestion detection error rate. The analytic result displays that the proposed ERF-GO algorithm attains a greater accuracy rate of about 98.65% in detecting traffic congestion which is comparably higher than state-of-the-art methods. [ABSTRACT FROM AUTHOR]

We present ALMA deep observations of the [CII] 158 μm emission line and the continuum at 253 GHz and 99 GHz towards SDSS J0100+2802 at z ≃ 6.3, the most luminous quasi-stellar object (QSO) at z > 6. J0100+2802 belongs to the HYPERION sample of luminous QSOs at z ∼ 6 − 7.5. The observations have a 2.2 arcsec resolution in band 3 and a 0.9 arcsec resolution in band 6, and are optimized to detect extended emission around the QSO. We detect an interacting, tidally disrupted companion both in [CII], peaking at z ∼ 6.332, and in continuum, stretching on scales up to 20 kpc from the quasar, with a knotty morphology. The higher velocity dispersion in the direction of the companion emission and the complex morphology of the tidally stretched galaxy suggest a possible ongoing or future merger. For the newly detected companion, we derive the range of the dust mass, Mdust = (0.3 − 2.6)×107 M⊙, and of the star formation rate, SFR  =  [35 − 344] M⊙, obtained from the modelling of its cold dust spectral energy distribution. This shows that both the QSO and its companion are gas-rich and that a major merger may be at the origin of the boosted star formation. This close interacting companion is undetected by deep JWST imaging observations, showing the effectiveness of ALMA in detecting dust-obscured sources, especially in the vicinity of optically bright quasars. We also detect a broad blueshifted component in the [CII] spectrum, which we interpret as a gaseous outflow for which we estimate a mass outflow rate in the range Ṁout = (118 − 269) M⊙ yr−1. J0100+2802 was recently found to reside in a strong overdensity, however this close companion remained undetected by both previous higher resolution ALMA observations and by JWST-NIRCAM imaging. Our results highlight the importance of deep medium-resolution ALMA observations for the study of QSOs and their environment in the Epoch of Reionisation. [ABSTRACT FROM AUTHOR]

Anthropogenically-driven climate warming and land use change are the main causes of an ongoing decrease in global biodiversity. It is unclear how ecosystems, particularly freshwater habitats, will respond to such continuous and potentially intensifying disruptions. Here we analyse how different components of terrestrial and aquatic ecosystems responded to natural climate change during the Lateglacial. By applying a range of analytical techniques (sedimentology, palaeoecology, geochemistry) to the well-dated sediment archive from Lake Hämelsee (Germany), we show evidence for vegetation development, landscape dynamics and aquatic ecosystem change typical for northwest Europe during the Lateglacial. By particularly focussing on periods of abrupt climate change, we determine the timing and duration of changes in biodiversity in response to external forcing. We show that onsets of changes in biodiversity indicators (e.g. diatom composition, Pediastrum concentrations) lag changes in environmental records (e.g. loss-on-ignition) by a few decades, particularly at the Allerød/Younger Dryas transition. Most biodiversity indicators showed transition times of 10–50 years, whereas environmental records typically showed a 50–100 year long transition. In some cases, transition times observed for the compositional turnover or productivity records were up to 185 years, which could have been the result of the combined effects of direct (e.g. climate) and indirect (e.g. lake stratification) drivers of ecosystem change. Our results show differences in timing and duration of biodiversity responses to external disturbances, suggesting that a multi-decadal view needs to be taken when designing effective conservation management of freshwater ecosystems under current global warming. • Multi-proxy approach applied to Lateglacial sediment record from Germany. • Detailed palaeoenvironmental and palaeoclimatic reconstruction. • Decadal-scale lags in biodiversity responses to climate change. • Ecological transitions to a new stable state typically take 10–50 years. [ABSTRACT FROM AUTHOR]