WreckWatch: Automatic Traffic Accident Detection and Notification with Smartphones

Traffic accidents are one of the leading causes of fatalities in the US. An important indicator of survival rates after an accident is the time between the accident and when emergency medical personnel are dispatched to the scene. Eliminating the time between when an accident occurs and when first responders are dispatched to the scene decreases mortality rates by 6%. One approach to eliminating the delay between accident occurrence and first responder dispatch is to use in-vehicle automatic accident detection and notification systems, which sense when traffic accidents occur and immediately notify emergency personnel. These in-vehicle systems, however, are not available in all cars and are expensive to retrofit for older vehicles. This paper describes how smartphones, such as the iPhone and Google Android platforms, can automatically detect traffic accidents using accelerometers and acoustic data, immediately notify a central emergency dispatch server after an accident, and provide situational awareness through photographs, GPS coordinates, VOIP communication channels, and accident data recording. This paper provides the following contributions to the study of detecting traffic accidents via smartphones: (1) we present a formal model for accident detection that combines sensors and context data, (2) we show how smartphone sensors, network connections, and web services can be used to provide situational awareness to first responders, and (3) we provide empirical results demonstrating the efficacy of different approaches employed by smartphone accident detection systems to prevent false positives.     

Reducing Aging Impacts in Digital Sensors via Run-Time Calibration

Hazards or intentional perturbations must be identified in safety- and security-critical applications. Digital sensors have been shown to be an appealing approach to detect such abnormalities. However, as any sensor technology, digital sensors are prone to mis-calibration. In particular, even if the digital sensor initial calibration is correct, the rate of false and missed alarms might increase when the sensor is aged. In this paper, we thoroughly study the impact of aging-induced false and missed alarms. Indeed aging relates to the usage time, and a priori model (historical data for environmental variation) for predicting the aging is unrealistic for digital sensors as tracking the usage time with related temperature and voltage variation imposes high overhead. Accordingly, we propose an alternative approach where not one but two sensors are deployed. In practice, one sensor is used to detect environmental deviations, while the second one is used as the reference. In this respect, the second sensor is only operated seldom, mostly to re-calibrate the active sensor when aged. From this dual input (unaged and aged sensor), corrective models are derived. We account for two methods, namely simple but effective offset correction, and adjustment based on machine-learning. We conduct extensive characterizations (both pre-silicon simulations and post-silicon measurements on FPGA) which quantitatively confirm the applicability and high sensitivity of digital sensors.

     

Low false positive learning with support vector machines

Most machine learning systems for binary classification are trained using algorithms that maximize the accuracy and assume that false positives and false negatives are equally bad. However, in many applications, these two types of errors may have very different costs. In this paper, we consider the problem of controlling the false positive rate on SVMs, since its traditional formulation does not offer such assurance. To solve this problem, we define a feature space sensitive area, where the probability of having false positives is higher, and use a second classifier (unanimity k-NN) in this area to better filter errors and improve the decision-making process. We call this method Risk Area SVM (RA-SVM). We compare the RA-SVM to other state-of-the-art methods for low false positive classification using 33 standard datasets in the literature. The solution we propose shows better performance in the vast majority of the cases using the standard Neyman–Pearson measure.     

Exploring the limits of PDR-based indoor localisation systems under realistic conditions

ABSTRACT

Pedestrian Dead Reckoning (PDR) plays an important role in many (hybrid) indoor positioning systems since it enables frequent, granular position updates. However, the accumulation of errors creates a need for external error correction. In this work, we explore the limits of PDR under realistic conditions using our graph-based system as an example. For this purpose, we collect sensor data while the user performs an actual navigation task using a navigation application on a smartphone. To assess the localisation performance, we introduce a task-oriented metric based on the idea of landmark navigation: instead of specifying the error metrically, we measure the ability to determine the correct segment of an indoor route, which in turn enables the navigation system to give correct instructions. We conduct offline simulations with the collected data in order to identify situations where position tracking fails and explore different options how to mitigate the issues, for example through detection of special features along the user’s path or through additional sensors. Our results show that the magnetic compass is often unreliable under realistic conditions and that resetting the position at strategically chosen decision points significantly improves positioning accuracy.     

A method for performance diagnosis and evaluation of video trackers

Several measures for evaluating multi-target video trackers exist that generally aim at providing ‘end performance.’ End performance is important particularly for ranking and comparing trackers. However, for a deeper insight into trackers’ performance it would also be desirable to analyze key contributory factors (false positives, false negatives, ID changes) that (implicitly or explicitly) lead to the attainment of a certain end performance. Specifically, this paper proposes a new approach to enable a diagnosis of the performance of multi-target trackers as well as providing a means to determine the end performance to still enable their comparison in a video sequence. Diagnosis involves analyzing probability density functions of false positives, false negatives and ID changes of trackers in a sequence. End performance is obtained in terms of the extracted performance scores related to false positives, false negatives and ID changes. In the experiments, we used four state-of-the-art trackers on challenging real-world public datasets to show the effectiveness of the proposed approach.     

GUIDE: Smartphone sensors‐based pedestrian indoor localization with heterogeneous devices

A plethora of indoor localization systems based on Wi‐Fi, radio frequency chips, ultra‐wide‐band, and bluetooth have been proposed, yet these systems do not work when the infrastructure is absent. On the other hand, infrastructure less systems benefit mostly from off‐the‐shelf smartphone sensors and do not need additional hardware. This study shows a similar indoor localization approach which turns smartphone built‐in sensors to good account. We take advantage of magnetic field strength fingerprinting approach to localize a pedestrian indoor. In addition, accelerometer and gyroscope sensors are utilized to find the pedestrian's traveled distance and heading estimation, respectively. Our aim is to solve the problem of device dependence by devising an approach that can perform localization using various smartphones in a similar fashion. We make the use of patterns of magnetic field strength to formulate the fingerprint database to achieve this goal. This approach solves two problems: need to update the database periodically and device dependence. We conduct experiments using Samsung Galaxy S8 and LG G6 for five different buildings with different dimensions in Yeungnam University, Republic of Korea. The evaluation is performed by following three different path geometries inside the buildings. The results show that the proposed localization approach can potentially be used for indoor localization with heterogeneous devices. The errors for path 1 and path 2 are very similar, however, localization error for path 3 is comparatively higher because of the complexity of the path 3. The mean and median errors for Galaxy S8 are 1.37 and 0.88 m while for LG G6, these are 1.84 and 1.21 m, respectively, while considering all buildings and all paths followed during the experiment. Overall, the proposed approach can potentially localize a pedestrian within 1.21 m at 50% and within 1.93 m at 75%, irrespective of the device used for localization. The performance of the proposed approach is compared with the K nearest neighbor (KNN) for evaluation. The proposed approach outperforms the KNN     

Improving signature quality for network application identification

Network application identification is one of the core elements in network operations and management to provide enhanced network service and security. For accurate identification, an approach using common patterns called “signatures” is widely used to compensate the limitations of the traditional transport-layer port-based classification. However, our simulation results indicate that using the signatures generated from a set of well known algorithms may lead to very poor identification performance, with less than 60% of true positives even in an optimal case. To improve the quality of signatures, we present a technique in this paper, which consists of two steps: (i) pairwise merging to consider every possible combination of the initially collected signatures to reduce their specificity that causes the signatures to be less common; and (ii) signature reduction to identify effective signatures with greater importance from a large set of signatures produced in the merging step, so as to manage the space/time complexity in the identification process for greater scalability. Our experimental results show that the proposed technique can dramatically improve the performance, even with a small number of signatures (e.g., 95% true positives rate with 30 signatures per application) which is more compact than the initial signature set.     

Locating Disturbances in Semiconductor Manufacturing With Stepwise Regression

The ability to locate disturbances in semiconductor manufacturing processes is critical to developing and maintaining a high yield. Analysis of variance (ANOVA), the best current practice for this problem, consists of conducting a series of hypothesis tests at each individual processing step. This approach can lead to excessive false alarms and limited sensitivity when the process contains more than one disturbance. We describe how this problem can be framed as a subset selection problem and propose two new methods based on stepwise regression. Results of over 90 000 Monte Carlo simulations suggest that these new SWR methods locate disturbances with fewer false positives and false negatives than ANOVA. This means process engineers will spend less time responding to false alarms and will be able to locate real disturbances more often.     

Robust Detection of Unauthorized Wireless Access Points

Unauthorized 802.11 wireless access points (APs), or rogue APs, such as those brought into a corporate campus by employees, pose a security threat as they may be poorly managed or insufficiently secured. An attacker in the vicinity may easily get onto the internal network through a rogue AP, bypassing all perimeter security measures. Existing detection solutions do not work well for detecting rogue APs configured as routers that are protected by WEP, 802.11 i, or other security measures. In this paper, we describe a new rogue AP detection method to address this problem. Our solution uses a verifier on the internal wired network to send test traffic towards wireless edge, and uses wireless sniffers to identify rouge APs that relay the test packets. To quickly sweep all possible rogue APs, the verifier uses a greedy algorithm to schedule the channels for the sniffers to listen to. To work with the encrypted AP traffic, the sniffers use a probabilistic algorithm that only relies on observed wireless frame size. Using extensive experiments, we show that the proposed approach can robustly detect rogue APs with moderate network overhead. The results also show that our algorithm is resilient to congested wireless channels and has low false positives/negatives in realistic environments.

Smartphone with Augmented Gateway Functionality as Opportunistic WSN Gateway Device

Sensors and actuators are being increasingly deployed for monitoring and controlling different phenomena and processes in a stand-alone manner or attached to sensor nodes with communication capabilities as part of larger wireless sensor networks (WSN). In addition to the protocols for communication within the WSN, sensor nodes may also provide the gateway functionality towards other networks and/or support communication with other external devices. These devices either represent additional gateways for exposing data and metadata to external networks, or serve as connection points to WSN for instance for the on-site calibration and maintenance. Smartphones as advanced mobile terminals appear particularly suitable for such role. This paper investigates the role a smartphone augmented with WSN gateway functionality can play in WSN with respect to regular dedicated sensor and gateway nodes. As a practical example we show the implementation of a gateway augmented smartphone using a Samsung i8910 phone and a VESNA sensor node connected via Bluetooth. The role of a gateway augmented smartphone is to interface between WSN, which is using a proprietary networking protocol, and the mobile network. The data obtained from WSN can be enriched using smartphone’s embedded sensors before being sent to the remote server. We demonstrate this on an example of geo-tagging the collected data from WSN with the smartphone’s Global Positioning System-based location data.     

Wireless image sensor networks: event acquisition in attack-prone and uncertain environments

Wireless Image Sensor Networks (WISNs) consisting of untethered camera nodes and sensors may be deployed in a variety of unattended and possibly hostile environments to obtain surveillance data. In such settings, the WISN nodes must perform reliable event acquisition to limit the energy, computation and delay drains associated with forwarding large volumes of image data wirelessly to a sink node. In this work we investigate the event acquisition properties of WISNs that employ various techniques at the camera nodes to distinguish between event and non-event frames in uncertain environments that may include attacks. These techniques include lightweight image processing, decisions from n sensors with/without cluster head fault and attack detection, and a combination approach relying on both lightweight image processing and sensor decisions. We analyze the relative merits and limitations of each approach in terms of the resulting probability of event detection and false alarm in the face of occasional errors, attacks and stealthy attacks.

一个快速的被动式传感器数据关联算法

本文针对仅能获得关于目标角度信息的被动式传感器、且允许传感器漏检、虚警、以及监视空域目标位置和数量未知的静态数据关联问题,提出了一个基于空间交点属性强度的快速数据关联算法.与现有算法相比,本方法较好地改进了数据关联算法的精度和运算速度.最后,通过仿真实验给以验证.     

Sensing clouds: A distributed cooperative target tracking with tiny binary noisy sensors

This paper suggests a novel algorithm for mobile object tracking using wireless sensor networks (WSNs). The paper assumes a future model of WSNs, where a large number of low to medium range inexpensive and noisy sensors are distributed randomly over an area. The distributed algorithm is based on short range communication between neighboring sensors, and is designed to work with very basic low cost binary sensors, that can report only a sensing, not sensing value.Neighboring sensors that sense the object form a cloud around the object which is dynamically updated as the object moves. To save energy on reporting a subset of the cloud, the cloud core, is elected. A trade-off between the accuracy and the core size (namely transmission power) is presented, as well as an extensive simulation study. Our algorithm works well with false negative sensing and up to 10% false positive sensing.     

CRISP: cooperation among smartphones to improve indoor position information

Accurate indoor location information remains a challenge without incorporating extensive fingerprinting approaches or sophisticated infrastructures within buildings. Nevertheless, modern smartphones are equipped with sensors and radios that can detect movement and can be used to predict location. Dead reckoning applications on a smartphone may attempt to track a person’s movement or locate a person within an indoor environment. Nevertheless, smartphone positioning applications continue to be inaccurate. We propose a new approach, CRISP—cooperating to improve smartphone positioning, which assumes that dead reckoning has inaccuracies, but leverages opportunities of the interaction of multiple smartphones. Each smartphone computes its own position, and then shares it with other nearby smartphones. The signal strengths of multiple radios that are used on smartphones estimate distances between the devices. While individual smartphones may provide some positioning (possibly inaccurate) information, accuracy may improve when several smartphones cooperate and share position information through multiple iterations. Via indoor experimentation and simulation, we evaluate our approach and believe it is promising as an inexpensive and passive means to improve position information without complex data training and fusion. The accuracy of CRISP is within a meter. In addition, CRISP possibly leads to better results for a number of applications, including exercise profiling.     

Context‐aware Android applications through transportation mode detection techniques

In this paper, we study the problem of how to detect the current transportation mode of the user from the smartphone sensors data, because this issue is considered crucial for the deployment of a multitude of mobility‐aware systems, ranging from trace collectors to health monitoring and urban sensing systems. Although some feasibility studies have been performed in the literature, most of the proposed systems rely on the utilization of the GPS and on computational expensive algorithms that do not take into account the limited resources of mobile phones. On the opposite, this paper focuses on the design and implementation of a feasible and efficient detection system that takes into account both the issues of accuracy of classification and of energy consumption. To this purpose, we propose the utilization of embedded sensor data (accelerometer/gyroscope) with a novel meta‐classifier based on a cascading technique, and we show that our combined approach can provide similar performance than a GPS‐based classifier, but introducing also the possibility to control the computational load based on requested confidence. We describe the implementation of the proposed system into an Android framework that can be leveraged by third‐part mobile applications to access context‐aware information in a transparent way. Copyright © 2016 John Wiley & Sons, Ltd.     

Discriminant Analysis Based Prognostics of Avionic Systems

In this paper, a novel discriminant analysis based predictive model for preventing false alarms leading to unnecessary replacement of an avionic system component is presented. The model is validated by prediction of false alarms (also known as false positives, type I, or alpha errors) in the left generator shaft of a Sikorsky helicopter UH-60, using the Goodrich health and usage management system (HUMS). The paper presents one of the first approaches based on applying discriminant analysis for prognostics of avionic systems, specifically in the context of identifying false positives within the next 1 or 2 h. In practice, predictions for the next 2 h are sufficient as typical helicopter flight schedules and durations are such that up to 2 h advance notice is most useful. This is an important contribution because drive train components of helicopters are normally very robust with very rare failures; therefore, the cost of unnecessary preventive maintenance based on false alarms is very high.     

结合Craig插值分析的软件错误诊断方法

基于模型诊断（MBD）的理论应用到软件错误定位中取得了一定的效果．但是经典MBD理论基于元件间独立地发生故障这一假设,导致软件错误定位的结果中存在假阳性的诊断．论文对现有基于MBD 的软件错误定位方法进行了改进,提出了冲突中元件的冗余分析方法．该方法既包括了基于Craig插值的元件冗余分析机制,同时利用条件语句取值的二元性（真或假）的特点,对冲突中的条件语句元件进行软件错误的无相关分析．实验结果表明：冲突中的元件冗余分析方法可以有效地减少诊断的假阳性率,将诊断结果数减少了48．4％,碰集树生成的结点数减少了47．6％．     

False alarm detection using dynamic threshold in medical wireless sensor networks

Sensor networks suffer from various sensor faults and false measurements in healthcare application and this vulnerability of the delay should handle efficiently and timely response in various application of WSN. For instance, in healthcare application, the false measurements generate false alarms which require to take unnecessary action from the healthcare department. The quality of the health care service can improve in remote healthcare monitoring system by introducing a new approach to identify the true medical condition and differentiate true and false alarms. In this paper, we proposed a novel approach to analysis past historical data collected from various medical sensors to identify the sensor anomaly. The main goal of this approach is to differentiate between true and false alarms effectively. The proposed system analysis the historical data to predicts the sensor value which compares with real sensed values at a time incident. The dynamically adjust the threshold value by comparing the difference between predicted value and historic value to determine the anomaly of sensor value. This system has been worked on huge real-time healthcare dataset and result shows that the new approach has been applied on real healthcare datasets and result of this system shows the detection rate is high and false positive rate is low which conclude that this approach is very useful in WSN application such as health monitoring system and it will be competitive with others.

     

面向移动LBS的智能手机室内定位技术探讨

移动互联网的发展给基于位置的服务(LBS)带来了广泛的应用前景,智能手机的普及使用户定位和获取LBS变得更加方便。目前,手机定位技术特别是室内定位,仍不够成熟,已经成为制约LBS业务发展的技术瓶颈。本文在研究定位技术现状和发展趋势的基础上,提出一种新的室内定位方法,依靠智能手机内置传感器进行图像特征识别和运动状态检测,即可完成室内环境的准确定位,具有成本低、简单方便、灵活易扩展的优点,能够满足移动LBS业务模式发展需求。     

On the cooperative MIMO communication for energy-efficient cluster-to-cluster transmission at wireless sensor network

Energy-efficient data transmission is one of the key factors for energy-efficient wireless sensor networks (WSN). Cooperative multiple input multiple output (MIMO) explores the wireless communication schemes between multiple sensors emphasizing the MIMO structure. In this paper, an energy-efficient cooperative technique is proposed for a WSN where selected numbers of sensors at the transmitting end are used to form a MIMO structure wirelessly connected with a selected number of sensors at the receiving end. The selection of nodes in the transmitting end is based on a selection function, which is a combination of channel condition, residual energy, inter-sensor distance in a cluster, and geographical location, whereas the selection in the receiving side is performed on the basis of channel condition. Data are sent by the sensors in a cluster to a data-gathering node (DGN) using a multihop transmission. We are concentrating our design on the intermediate hop, where sensors in a cluster transmit their data to the sensors in another cluster with MIMO communication. Energy models are evaluated for both correlated and uncorrelated scenarios. The delay model of the proposed cooperative MIMO is also derived. Experimental results show that the selected MIMO structure outperforms the unselected MIMO in terms of total energy consumption. They also show energy-efficient performance by around 20% over unselected MIMO when they are compared with single-input-single-output structure. Also, the proposed approach takes around 50 more rounds than the geographically selected approach before dying at distance d?>?20 m.