Continuous plankton records stand the test of time: evaluation of flow rates, clogging and the continuity of the CPR time-series

The Continuous Plankton Recorder (CPR) survey is one of the most extensive biological time-series in existence and has been in operation over major regions of the North Atlantic since 1932. However, there is little information about the volume of water filtered through each sample, but rather a general assumption has persisted that each sample represents 3 m3. Data from electromagnetic flowmeters, deployed on CPRs between 1995 and 1998, was examined. The mean volume filtered through samples was 3.11 m3 and the effect of clogging on filtration efficiencies was not great. Consequently, even when the likely variations in flow due to clogging are taken into account, previously identified links between zooplankton abundance and climatic signals remain strong.

First records of dive durations for a hibernating sea turtle

The first published record, from the early 1970s, of hibernation in sea turtles is based on the reports of the indigenous Indians and fishermen from Mexico, who hunted dormant green turtles (Chelonia mydas) in the Gulf of California. However, there were no successful attempts to investigate the biology of this particular behaviour further. Hence, data such as the exact duration and energetic requirements of dormant winter submergences are lacking. We used new satellite relay data loggers to obtain the first records of up to 7 h long dives of a loggerhead turtle (Caretta caretta) overwintering in Greek waters. These represent the longest dives ever reported for a diving marine vertebrate. There is strong evidence that the dives were aerobic, because the turtle surfaced only for short intervals and before the calculated oxygen stores were depleted. This evidence suggests that the common belief that sea turtles hibernate underwater, as some freshwater turtles do, is incorrect.

Drivers display anger-congruent attention to potential traffic hazards

Previous research has suggested that angry drivers may respond differently to potential hazards. This study replicates and extends these findings. Under simulated driving conditions, two groups of drivers experienced conditions that would either increase angry mood (N=12; men =6) or not (control group, N =12; men=6). All drivers then performed a neutral drive, during which they encountered a number of traffic events not experienced in the initial drive. These included vehicles emerging from driveways into their path and jaywalking pedestrians. Subjective anger, eye-movement behaviour and driving behaviours (speed and reaction times) were measured as drivers drove. Subjective moods (Profile of Mood States) were assessed before and after each drive. Anger-provoked drivers reported reliably higher increases in angry mood when compared with the control group after the initial drive, and these increases remained stable across the subsequent neutral drive. During the neutral drive, anger provoked drivers demonstrated evidence of more heuristic style processing of potential hazards, with shorter initial gazes at less apparent hazards and longer latencies to look back at jaywalking pedestrians obscured by parked vehicles. Anger-provoked drivers also took longer to make corrective actions to avoid potential collisions. It is concluded that anger-provoked drivers may initially make more superficial assessments of certain driving situations and consequently underestimate the inherent risk.

Intelligent traffic light control of isolated intersections using machine learning methods

Traffic congestion is one of the major problems in modern cities. This study applies machine learning methods to determine green times in order to minimize in an isolated intersection. Q-learning and neural networks are applied here to set signal light times and minimize total delays. It is assumed that an intersection behaves in a similar fashion to an intelligent agent learning how to set green times in each cycle based on traffic information. Here, a comparison between Q-learning and neural network is presented. In Q-learning, considering continuous green time requires a large state space, making the learning process practically impossible. In contrast to Q-learning methods, the neural network model can easily set the appropriate green time to fit the traffic demand. The performance of the proposed neural network is compared with two traditional alternatives for controlling traffic lights. Simulation results indicate that the application of the proposed method greatly reduces the total delay in the network compared to the alternative methods.

Network traffic clustering using random forest proximities

The recent years have seen extensive work on statistics-based network traffic classification using machine learning (ML) techniques. In the particular scenario of learning from unlabeled traffic data, some classic unsupervised clustering algorithms (e.g. K-Means and EM) have been applied but the reported results are unsatisfactory in terms of low accuracy. This paper presents a novel approach for the task, which performs clustering based on Random Forest (RF) proximities instead of Euclidean distances. The approach consists of two steps. In the first step, we derive a proximity measure for each pair of data points by performing a RF classification on the original data and a set of synthetic data. In the next step, we perform a K-Medoids clustering to partition the data points into K groups based on the proximity matrix. Evaluations have been conducted on real-world Internet traffic traces and the experimental results indicate that the proposed approach is more accurate than the previous methods.

Classifying network traffic in the big data era

With the arrival of Big Data Era, properly utilizing the power of big data is becoming increasingly essential for the strength and competitiveness of businesses and organizations. We are facing grand challenges from big data from different perspectives, such as processing, communication, security, and privacy. In this talk, we discuss the big data challenges in network traffic classification and our solutions to the challenges. The significance of the research lies in the fact that each year the network traffic increase exponentially on the current Internet. Traffic classification has wide applications in network management, from security monitoring to quality of service measurements. Recent research tends to apply machine-learning techniques to flow statistical feature based classification methods. In this talk, we propose a series of novel approaches for traffic classification, which can improve the classification performance effectively by incorporating correlated information into the classification process. We analyze the new classification approaches and their performance benefit from both theoretical and empirical perspectives. A large number of experiments are carried out on two real-world traffic datasets to validate the proposed approach. The results show the traffic classification performance can be improved significantly even under the extreme difficult circumstance of very few training samples. Our work has significant impact on security applications.

Stomach temperature records reveal nursing behaviour and transition to solid food consumption in an unweaned mammal, the harbour seal pup (Phoca vitulina)

Knowledge of milk transfer from mother to offspring and early solid food ingestions in mammals allows for a greater understanding of the factors affecting transition to nutritional independence and pre-weaning growth and survival. Yet studies monitoring suckling behaviour have often relied on visual observations, which might not accurately represent milk intake. We assessed the use of stomach temperature telemetry to monitor suckling and foraging behaviour in free-ranging harbour seal (Phoca vitulina) pups during lactation. Stomach temperature declines were analysed using principal component and cluster analyses, as well as trials using simulated stomachs resulting in a precise classification of stomach temperature drops into milk, seawater and solid food ingestions. Seawater and solid food ingestions represented on average 15.361.6% [0-40.0%] and 0.760.2% [0-13.0%], respectively, of individual ingestions. Overall, 63.7% of milk ingestions occurred while the pups were in the water, of which 13.9% were preceded by seawater ingestion. The average time between subsequent ingestions was significantly less for seawater than for milk ingestions. These results suggest that seawater ingestion might represent collateral ingestion during aquatic suckling attempts. Alternatively, as solid food ingestions (n = 19) were observed among 7 pups, seawater ingestion could result from missed prey capture attempts. This study shows that some harbour seals start ingesting prey while still being nursed, indicating that weaning occurs more gradually than previously thought in this species. Stomach temperature telemetry represents a promising method to study suckling behaviour in wild mammals and transition to nutritional independence in various endotherm species.

Automatic network traffic classification

The thesis addresses a number of critical problems in regard to fully automating the process of network traffic classification and protocol identification. Several effective solutions based on statistical analysis and machine learning techniques are proposed, which significantly reduce the requirements for human interventions in network traffic classification systems.

2Loud?: Community mapping of exposure to traffic noise with mobile phones

Abstract: Despite ample medical evidence of the adverse impacts of traffic noise on health, most policies for traffic noise management are arbitrary or incomplete, resulting in serious social and economic impacts. Surprisingly, there is limited information about citizen’s exposure to traffic noise worldwide. This paper presents the 2Loud? mobile phone application, developed and tested as a methodology to monitor, assess and map the level of exposure to traffic noise of citizens with focus on the night period and indoor locations, since sleep disturbance is one of the major triggers for ill health related to traffic noise. Based on a community participation experiment using the 2Loud? mobile phone application in a region close to freeways in Australia, the results of this research indicates a good level of accuracy for the noise monitoring by mobile phones and also demonstrates significant levels of indoor night exposure to traffic noise in the study area. The proposed methodology, through the data produced and the participatory process involved, can potentially assist in planning and management towards healthier urban environments.