Search

Skin cancer cases, in recent years, has become increasingly widespread because of increasing the effect of ultraviolet radiation as a result of thinning and perforation of the ozone layer in the atmosphere. The fact that melanoma, one of the most lethal types of skin cancer, can be treated at a high rate in early diagnosis has increased the interest in the studies in this field. In this study is focused on machine learning approaches that can be used in the diagnosis of melanoma in dermoscopic images. In the first step, color and texture features of images accessed from the dermoscopic image database were extracted with image processing techniques. In the second step, by using these features machine learning classifiers in different program environments have been trained and tested. Results from the proposed method indicated that melanoma can be detected with 97 % accuracy.

We report the application of machine learning to smartphone-based colorimetric detection of pH values. The strip images were used as the training set for Least Squares-Support Vector Machine (LS-SVM) classifier algorithms that were able to successfully classify the distinct pH values. The difference in the obtained image formats was found not to significantly affect the performance of the proposed machine learning approach. Moreover, the influence of the illumination conditions on the perceived color of pH strips was investigated and further experiments were conducted to study the effect of color change on the learning model. Non-integer pH levels are identified as their nearest integer pH values, whereas the test results for integer pH levels using JPEG, RAW and RAW-corrected image formats captured under different lighting conditions lead to perfect classification accuracy, sensitivity and specificity, which proves that colorimetric detection using machine learning based systems is able to adapt to various experimental conditions and is a great candidate for smartphone-based sensing in paper-based colorimetric assays.

We report the applicability of an ultra-low cost, field-deployable, plastic fiber based smartphone spectrometer system to study dye adsorption from water. A custom cradle using the smartphone's built-in flash and camera was designed for visible absorbance spectroscopy without any need for external electrical components. We firstly investigated the performance of the smartphone spectrometer for methylene blue (MB) absorbance in water with a detection limit of 0.5 ppm, and compared it to that of a commercial spectrometer. We elaborated on the contribution of image formats to the calibration of the standard absorbance curve. We then studied the catalytic activity of electrospun polyacrylonitrile (PAN)/zeolite composite nanofibers by analyzing MB adsorption as a function of time. The results obtained in the proposed compact, cost-effective and high-performance platform can help transform measurement science for sustainable water management.

The probability hypothesis density (PHD) filter based on sequential Monte Carlo (SMC) approximation (also known as SMC-PHD filter) has proven to be a promising algorithm for multispeaker tracking. However, it has a heavy computational cost as surviving, spawned, and born particles need to be distributed in each frame to model the state of the speakers and to estimate jointly the variable number of speakers with their states. In particular, the computational cost is mostly caused by the born particles as they need to be propagated over the entire image in every frame to detect the new speaker presence in the view of the visual tracker. In this paper, we propose to use the audio data to improve the visual SMC-PHD (V-SMC-PHD) filter by using the direction of arrival angles of the audio sources to determine when to propagate the born particles and reallocate the surviving and spawned particles. The tracking accuracy of the audio-visual SMC-PHD (AV-SMC-PHD) algorithm is further improved by using a modified mean-shift algorithm to search and climb density gradients iteratively to find the peak of the probability distribution, and the extra computational complexity introduced by mean-shift is controlled with a sparse sampling technique. These improved algorithms, named as AVMS-SMC-PHD and sparse-AVMS-SMC-PHD, respectively, are compared systematically with AV-SMC-PHD and V-SMC-PHD based on the AV16.3, AMI, and CLEAR datasets.

Potassium iodide (KI) and 3,3 ′ ,5,5 ′ -tetramethylbenzidine (TMB) are frequently used as chromogenic agents in μ PADs for glucose determination. Chitosan (Chi) has peroxidase like activity and improves the analytic performance of μ PADs when used in combination with a chromogenic agent. Here, a portable platform incorporating a μ PAD with a smartphone application based on machine learning was developed to quantify glucose concentration in artificial saliva. The detection zones of the μ PAD were modified with three different detection mixtures containing; (i) KI, (ii) KI+Chi and (iii) TMB. After the color change, the images of the μ PADs were taken with four different smartphones under seven different illumination conditions. The images were first processed for feature extraction and then used to train machine learning classifiers, resulting in a more robust and adaptive platform against illumination variation and camera optics. Different machine learning classifiers were tested and the best machine learning classifier for each detection mixture was obtained. Next, a special application called “GlucoSensing” capable of image capture, cropping and processing was developed to make the system more user-friendly. A cloud system was used in the application to communicate with a remote server running machine learning classifiers. Among the three different detection mixtures, the mixture with TMB demonstrated the highest classification accuracy (98.24%) with inter-phone repeatability under versatile illumination.

Horzum, Nesrin/0000-0002-2782-0581; bayram, abdullah/0000-0002-6077-517X; Kilic, Volkan/0000-0002-3164-1981 WOS: 000437024600037 Water quality monitoring in resource-limited settings without access to a sophisticated laboratory requires the development of low cost and portable instrumentation. Herein, we propose a newly designed handheld reflection-based smart-phone sensing platform to detect Bisphenol-A (BPA), a well-known endocrine disruptor agent abundantly used in plastic industry. An experimental investigation relying on color change due to the formation of quinone-type complex was conducted with samples from two different water sources: distilled and commercial drinking water. This colorimetric measurement device was used to determine BPA in distilled water in alkaline environments. The successful combination of colorimetric assay and spectrometer facilitates limit of detection in the low ppm levels, 0.29 ppm for smartphone and 0.23 ppm for commercial spectrometer, with a sensitivity of 0.1/ppm.

The problem of tracking multiple moving speakers in indoor environments has received much attention. Earlier techniques were based purely on a single modality, e.g., vision. Recently, the fusion of multi-modal information has been shown to be instrumental in improving tracking performance, as well as robustness in the case of challenging situations like occlusions (by the limited field of view of cameras or by other speakers). However, data fusion algorithms often suffer from noise corrupting the sensor measurements which cause non-negligible detection errors. Here, a novel approach to combining audio and visual data is proposed. We employ the direction of arrival angles of the audio sources to reshape the typical Gaussian noise distribution of particles in the propagation step and to weight the observation model in the measurement step. This approach is further improved by solving a typical problem associated with the PF, whose efficiency and accuracy usually depend on the number of particles and noise variance used in state estimation and particle propagation. Both parameters are specified beforehand and kept fixed in the regular PF implementation which makes the tracker unstable in practice. To address these problems, we design an algorithm which adapts both the number of particles and noise variance based on tracking error and the area occupied by the particles in the image. Experiments on the $AV16.3$ dataset show the advantage of our proposed methods over the baseline PF method and an existing adaptive PF algorithm for tracking occluded speakers with a significantly reduced number of particles.

Citalopram hydrobromide (CTL) has been shown to cause sexual dysfunction; however, its reproductive toxicity potential has not been sufficiently elucidated in men. Therefore, we aimed to clarify the toxic effects of CTL on the reproductive system of male rats.For this purpose, CTL was administered at 5, 10, and 20 mg/kg/day to rats orally for 28 days. Sperm concentration, motility, and morphology were investigated using a computer-assisted sperm analysis system, and sperm DNA damage was detected using a Comet assay. The testes were histopathologically examined. Serum follicle-stimulating hormone, luteinizing hormone, and testosterone levels were measured and the oxidative status of testes was investigated.Our results showed that sperm concentration was reduced, and abnormal sperm morphology and sperm DNA damage were increased in CTL-administered groups. Additionally, histopathological changes were observed in the testes of CTL-administered rats. Luteinizing hormone levels were increased in CTL-administered groups, while testosterone levels were increased in the 5 and 10 mg/kg CTL-administered groups. Decreased glutathione signaled enhanced oxidative stress in the 10 and 20 mg/kg CTL-administered groups.Thus, we concluded that CT induced testicular damage in male rats; this testicular damage was accompanied by oxidative stress and hormonal changes, which are considered as the important causes of reproductive disorders. Birth Defects Research 109:475-485, 2017. © 2017 Wiley Periodicals, Inc.

Sequential Monte Carlo probability hypothesis density (SMC-PHD) filtering has been recently exploited for audio-visual (AV) based tracking of multiple speakers, where audio data are used to inform the particle distribution and propagation in the visual SMC-PHD filter. However, the performance of the AV-SMC-PHD filter can be affected by the mismatch between the proposal and the posterior distribution. In this paper, we present a new method to improve the particle distribution where audio information (i.e. DOA angles derived from microphone array measurements) is used to detect new born particles and visual information (i.e. histograms) is used to modify the particles with particle flow (PF). Using particle flow has the benefit of migrating particles smoothly from the prior to the posterior distribution. We compare the proposed algorithm with the baseline AV-SMC-PHD algorithm using experiments on the AV16.3 dataset with multi-speaker sequences.

We present a robust and efficient audio-visual (AV) approach to speaker tracking in a room environment. A challenging problem with visual tracking is to deal with occlusions (caused by the limited field of view of cameras or by other speakers). Another challenge is associated with the particle filtering (PF) algorithm, commonly used for visual tracking, which requires a large number of particles to ensure the distribution is well modelled. In this paper, we propose a new method of fusing audio into the PF based visual tracking. We use the direction of arrival angles (DOAs) of the audio sources to reshape the typical Gaussian noise distribution of particles in the propagation step and to weight the observation model in the measurement step. Experiments on AV16.3 datasets show the advantage of our proposed method over the baseline PF method for tracking occluded speakers with a significantly reduced number of particles.

In this paper, pattern formation occurring on a 3-D network of locally coupled relaxation oscillators is presented. The network can be programmed with coupling weights and initial conditions in order to generate traveling waves, autowaves and spiral waves. Furthermore, this paper introduces a simple algorithm to solve robot path finding problem in a 3-D environment using active wave computing techniques.

In this paper, the model and implementation of a Cellular Nonlinear Network which is able to solve the shortest path finding problem between two points in a two dimensional space including obstacles is presented with a navigation algorithm towards the target via the shortest path. Then, the target tracking scenario with tracker and target robots on a platform which is specially prepared for this application is realized using mentioned algorithm.

In this demo, we introduced a mobile robot navigation test setup that is accessible via internet. This test setup has a Lego Mindstorms NXT differential drive mobile robot which is controlled by a computer with Bluetooth connection. The control computer, which is called Host Computer in Fig. 1, runs MATLAB to operate the system. The navigation of mobile robot is based on an algorithm which uses a Relaxation Oscillator Cellular Neural/Nonlinear Network to execute wave computing. This network is also simulated by the Host Computer. The significant property of this demo is that any Client Computer can establish a remote desktop connection with the Host Computer and use the test setup remotely. By this means, any comparative tests on this setup can be handled remotely by independent researchers.

This paper introduces an active wave computing based algorithm for real-time robot navigation problem in dynamically changing environment and presents a real test setup with a roving robot. Travelling waves propagated on Cellular Neural Network (CNN) were employed by the system to find the shortest path as proposed in our previous work. The setup has a ceiling camera which captures an image of the top view of the platform at almost every one second. After preprocessing of this image, it is loaded to the network and an active wave which is generated by this network is propagated until the robot is covered by the wave. This method reduces the simulation time and speeds up the system. Although the robot is navigated in a dynamically changing environment, the system does not need to check the moving obstacles. The algorithm proposed here always generates a solution for the current state of the platform without the information about its past states. At every repetition of the algorithm, the target position is updated by the system if it is changed. Any change of the target position is immediately applied to the location of the wave source. Hence the system becomes working in dynamic environment with dynamic target.