Using Bayesian neural networks to classify segmented images

We present results that compare the performance of neural networks trained with two Bayesian methods, (i) the Evidence Framework of MacKay (1992) and (ii) a Markov Chain Monte Carlo method due to Neal (1996) on a task of classifying segmented outdoor images. We also investigate the use of the Automatic Relevance Determination method for input feature selection.

Visual performance of a new bi-aspheric, segmented, asymmetric multifocal IOL

PURPOSE: To assess the visual performance and subjective experience of eyes implanted with a new bi-aspheric, segmented, multifocal intraocular lens: the Mplus X (Topcon Europe Medical, Capelle aan den IJssel, Netherlands). METHODS: Seventeen patients (mean age: 64.0 ± 12.8 years) had binocular implantation (34 eyes) with the Mplus X. Three months after the implantation, assessment was made of: manifest refraction; uncorrected and corrected distance visual acuity; uncorrected and distance corrected near visual acuity; defocus curves in photopic conditions; contrast sensitivity; halometry as an objective measure of glare; and patient satisfaction with unaided near vision using the Near Acuity Visual Questionnaire. RESULTS: Mean residual manifest refraction was -0.13 ± 0.51 diopters (D). Twenty-five eyes (74%) were within a mean spherical equivalent of ±0.50 D. Mean uncorrected distance visual acuity was +0.10 ± 0.12 logMAR monocularly and 0.02 ± 0.09 logMAR binocularly. Thirty-two eyes (94%) could read 0.3 or better without any reading correction and all patients could read 0.3 or better with a reading correction. Mean monocular uncorrected near visual acuity was 0.18 ± 0.16 logMAR, improving to 0.15 ± 0.15 logMAR with distance correction. Mean binocular uncorrected near visual acuity was 0.11 ± 0.11 logMAR, improving to 0.09 ± 0.12 logMAR with distance correction. Mean binocular contrast sensitivity was 1.75 ± 0.14 log units at 3 cycles per degree, 1.88 ± 0.20 log units at 6 cycles per degree, 1.66 ± 0.19 log units at 12 cycles per degree, and 1.11 ± 0.20 log units at 18 cycles per degree. Mean binocular and monocular halometry showed a glare profile of less than 1° of debilitating light scatter. Mean Near Acuity Visual Questionnaire Rasch score (0 = no difficulty, 100 = extreme difficulty) for satisfaction for near vision was 20.43 ± 14.64 log-odd units. CONCLUSIONS: The Mplus X provides a good visual outcome at distance and near with minimal dysphotopsia. Patients were very satisfied with their uncorrected near vision. © SLACK Incorporated.

Activity concentrations of radionuclides in 5 short cores taken in 2007-2008 measured by ICP-MS and HPGe gamma spectrometry

Natural radionuclides and man-made 137Cs were analyzed in five short sediment cores taken in northern part of the Gulf of Eilat (Gulf of Aqaba) in order to provide information on sedimentation and mixing rates and sediment sources. The maximum estimates of sedimentation rates based on excess 210Pb were found to vary between 0.105 ± 0.020 and 0.35 ± 0.23 cm · year**-1. Even the lowest estimates are significantly higher than those expected from dust deposition, suggesting other sources and processes being responsible for most of the allochthonous material accumulation, including periodical floods following heavy rain events, internal erosion or triggers, like earthquakes. In 137Cs depth profiles no 1963 related nuclear weapon test maxima were found; instead, the activities decrease monotonically, suggesting that a major process leading to radionuclides' depth distribution might be mixing. The mixing rates calculated from 137Cs, excess 210Pb and excess 228Th reach values up to 2.18 ± 0.69 cm**2 · year**-1.

Researching a segmented market: reflections on telephone interviewing

Purpose The purpose of this paper was to review the effectiveness of telephone interviewing for capturing data and to consider in particular the challenges faced by telephone interviewers when capturing information about market segments. Design/methodology/approach The platform for this methodological critique was a market segment analysis commissioned by Sport Wales which involved a series of 85 telephone interviews completed during 2010. Two focus groups involving the six interviewers involved in the study were convened to reflect on the researchers’ experiences and the implications for business and management research. Findings There are three principal sets of findings. First, although telephone interviewing is generally a cost-effective data collection method, it is important to consider both the actual costs (i.e. time spent planning and conducting interviews) as well as the opportunity costs (i.e. missed appointments, “chasing participants”). Second, researchers need to be sensitised to and sensitive to the demographic characteristics of telephone interviewees (insofar as these are knowable) because responses are influenced by them. Third, the anonymity of telephone interviews may be more conducive for discussing sensitive issues than face-to-face interactions. Originality/value The present study adds to this modest body of literature on the implementation of telephone interviewing as a research technique of business and management. It provides valuable methodological background detail about the intricate, personal experiences of researchers undertaking this method “at a distance” and without visual cues, and makes explicit the challenges of telephone interviewing for the purposes of data capture.

Infra-red pupil detection for use in a face recognition system

This paper presents a new method of eye localisation and face segmentation for use in a face recognition system. By using two near infrared light sources, we have shown that the face can be coarsely segmented, and the eyes can be accurately located, increasing the accuracy of the face localisation and improving the overall speed of the system. The system is able to locate both eyes within 25% of the eye-to-eye distance in over 96% of test cases.

They also serve who only stand and wait

Purpose Waiting for service by customers is an important problem for many financial service marketers. Two new approaches are proposed. First, customer evaluation of the service is increased with an ambient scent. Second a cognitive variable is identified which different iates customers by the way they value time so that they can be segmented. Methodology Pretests included focus groups which highlighted financial services and a pilot test were foll owed by a main sample of 607 subjects. Structural equation modelling and multivariate analysis of covariance were used for analysis. Findings A cognitive variable, the need for time management can be used, together with demographic and customer net worth data, to segment a customer base. Two environmental interventions, music and scent, can increase customer satisfaction among customers kept waiting in a line. Research implications Two original approaches to a rapidly growing service marketing problem are identified. Practical implications Service contact points can reduce incidence of "queue rage" and enhance customer satisfaction by either or both of two simple modifications to the service environment or a preventive strategy of offering targeted customers an alternative. Originality A new method of segmentation and a new environmental intervention are proposed .

Fusion of in-vehicle sensor data to develop Intelligent Driver Training System (IDTS)

The over represented number of novice drivers involved in crashes is alarming. Driver training is one of the interventions aimed at mitigating the number of crashes that involve young drivers. To our knowledge, Advanced Driver Assistance Systems (ADAS) have never been comprehensively used in designing an intelligent driver training system. Currently, there is a need to develop and evaluate ADAS that could assess driving competencies. The aim is to develop an unsupervised system called Intelligent Driver Training System (IDTS) that analyzes crash risks in a given driving situation. In order to design a comprehensive IDTS, data is collected from the Driver, Vehicle and Environment (DVE), synchronized and analyzed. The first implementation phase of this intelligent driver training system deals with synchronizing multiple variables acquired from DVE. RTMaps is used to collect and synchronize data like GPS, vehicle dynamics and driver head movement. After the data synchronization, maneuvers are segmented out as right turn, left turn and overtake. Each maneuver is composed of several individual tasks that are necessary to be performed in a sequential manner. This paper focuses on turn maneuvers. Some of the tasks required in the analysis of ‘turn’ maneuver are: detect the start and end of the turn, detect the indicator status change, check if the indicator was turned on within a safe distance and check the lane keeping during the turn maneuver. This paper proposes a fusion and analysis of heterogeneous data, mainly involved in driving, to determine the risk factor of particular maneuvers within the drive. It also explains the segmentation and risk analysis of the turn maneuver in a drive.

Word Segmentation for Chinese Wikipedia Using N-Gram Mutual Information

In this paper, we propose an unsupervised segmentation approach, named "n-gram mutual information", or NGMI, which is used to segment Chinese documents into n-character words or phrases, using language statistics drawn from the Chinese Wikipedia corpus. The approach alleviates the tremendous effort that is required in preparing and maintaining the manually segmented Chinese text for training purposes, and manually maintaining ever expanding lexicons. Previously, mutual information was used to achieve automated segmentation into 2-character words. The NGMI approach extends the approach to handle longer n-character words. Experiments with heterogeneous documents from the Chinese Wikipedia collection show good results.

Thai word segmentation with hidden Markov Model and decision tree

The Thai written language is one of the languages that does not have word boundaries. In order to discover the meaning of the document, all texts must be separated into syllables, words, sentences, and paragraphs. This paper develops a novel method to segment the Thai text by combining a non-dictionary based technique with a dictionary-based technique. This method first applies the Thai language grammar rules to the text for identifying syllables. The hidden Markov model is then used for merging possible syllables into words. The identified words are verified with a lexical dictionary and a decision tree is employed to discover the words unidentified by the lexical dictionary. Documents used in the litigation process of Thai court proceedings have been used in experiments. The results which are segmented words, obtained by the proposed method outperform the results obtained by other existing methods.

Robust real time multi-layer foreground segmentation

Many surveillance applications (object tracking, abandoned object detection) rely on detecting changes in a scene. Foreground segmentation is an effective way to extract the foreground from the scene, but these techniques cannot discriminate between objects that have temporarily stopped and those that are moving. We propose a series of modifications to an existing foreground segmentation system\cite{Butler2003} so that the foreground is further segmented into two or more layers. This yields an active layer of objects currently in motion and a passive layer of objects that have temporarily ceased motion which can itself be decomposed into multiple static layers. We also propose a variable threshold to cope with variable illumination, a feedback mechanism that allows an external process (i.e. surveillance system) to alter the motion detectors state, and a lighting compensation process and a shadow detector to reduce errors caused by lighting inconsistencies. The technique is demonstrated using outdoor surveillance footage, and is shown to be able to effectively deal with real world lighting conditions and overlapping objects.

Abandoned object detection using multi-layer motion detection

Abandoned object detection (AOD) systems are required to run in high traffic situations, with high levels of occlusion. Systems rely on background segmentation techniques to locate abandoned objects, by detecting areas of motion that have stopped. This is often achieved by using a medium term motion detection routine to detect long term changes in the background. When AOD systems are integrated into person tracking system, this often results in two separate motion detectors being used to handle the different requirements. We propose a motion detection system that is capable of detecting medium term motion as well as regular motion. Multiple layers of medium term (static) motion can be detected and segmented. We demonstrate the performance of this motion detection system and as part of an abandoned object detection system.

Unmanned Aerial Vehicles UAVs attitude, height, motion estimation and control using visual systems

This paper presents an implementation of an aircraft pose and motion estimator using visual systems as the principal sensor for controlling an Unmanned Aerial Vehicle (UAV) or as a redundant system for an Inertial Measure Unit (IMU) and gyros sensors. First, we explore the applications of the unified theory for central catadioptric cameras for attitude and heading estimation, explaining how the skyline is projected on the catadioptric image and how it is segmented and used to calculate the UAV’s attitude. Then we use appearance images to obtain a visual compass, and we calculate the relative rotation and heading of the aerial vehicle. Additionally, we show the use of a stereo system to calculate the aircraft height and to measure the UAV’s motion. Finally, we present a visual tracking system based on Fuzzy controllers working in both a UAV and a camera pan and tilt platform. Every part is tested using the UAV COLIBRI platform to validate the different approaches, which include comparison of the estimated data with the inertial values measured onboard the helicopter platform and the validation of the tracking schemes on real flights.