Video-Based Deception Detection with Non-Contact Heart Rate Monitoring and Multi-Modal Feature Selection

Deception detection plays a crucial role in criminal investigation.Videos contain a wealth of information regarding apparent and physiological changes in individuals,and thus can serve as an effective means of deception detection.In this paper,we investigate video-based deception detection considering both apparent visual features such as eye gaze,head pose and facial action unit(AU),and non-contact heart rate detected by remote photoplethysmography(rPPG)technique.Multiple wrapper-based feature selection methods combined with the K-nearest neighbor(KNN)and support vector machine(SVM)classifiers are employed to screen the most effective features for deception detection.We evaluate the performance of the proposed method on both a self-collected physiological-assisted visual deception detection(PV3D)dataset and a public bag-oflies(BOL)dataset.Experimental results demonstrate that the SVM classifier with symbiotic organisms search(SOS)feature selection yields the best overall performance,with an area under the curve(AUC)of 83.27%and accuracy(ACC)of 83.33%for PV3D,and an AUC of 71.18%and ACC of 70.33%for BOL.This demonstrates the stability and effectiveness of the proposed method in video-based deception detection tasks.

Infrastructure of Synchrotronic Biosensor Based on Semiconductor Device Fabrication for Tracking, Monitoring, Imaging, Measuring, Diagnosing and Detecting Cancer Cells

Copper Zinc Antimony Sulfide(CZAS)is derived from Copper Antimony Sulfide(CAS),a famatinite class of compound.In the current paper,the first step for using Copper,Zinc,Antimony and Sulfide as materials in manufacturing synchrotronic biosensor-namely increasing the sensitivity of biosensor through creating Copper Zinc Antimony Sulfide,CZAS(Cu1.18Zn0.40Sb1.90S7.2)semiconductor and using it instead of Copper Tin Sulfide,CTS(Cu2SnS3)for tracking,monitoring,imaging,measuring,diagnosing and detecting cancer cells,is evaluated.Further,optimization of tris(2,2'-bipyridyl)ruthenium(II)(Ru(bpy)32+)concentrations and Copper Zinc Antimony Sulfide,CZAS(Cu1.18Zn0.40Sb1.90S7.2)semiconductor as two main and effective materials in the intensity of synchrotron for tracking,monitoring,imaging,measuring,diagnosing and detecting cancer cells are considered so that the highest sensitivity obtains.In this regard,various concentrations of two materials were prepared and photon emission was investigated in the absence of cancer cells.On the other hand,ccancer diagnosis requires the analysis of images and attributes as well as collecting many clinical and mammography variables.In diagnosis of cancer,it is important to determine whether a tumor is benign or malignant.The information about cancer risk prediction along with the type of tumor are crucial for patients and effective medical decision making.An ideal diagnostic system could effectively distinguish between benign and malignant cells;however,such a system has not been created yet.In this study,a model is developed to improve the prediction probability of cancer.It is necessary to have such a prediction model as the survival probability of cancer is high when patients are diagnosed at early stages.

A LASER-SCANNING NON-CONTACT MEASURING METHOD FOR ROUNDNESS ERRORS

利用激光狭缝扫描原理和光电传感技术，提出了一种用于测量大型回转体类零件圆度误差的激光扫描非接触测量方法和测量系统。本文详细论述了测量系统及其测量原理、工件安装偏心误差的分离技术和计算机实时数据处理系统，实验结果证实了这种测量方法的可行性。

Deep-Hole Inner Diameter Measuring System Based on Non-contact Capacitance Sensor

A precise aperture measuring system of small deep holes with capacitance sensors is presented. Based on the working principle of non-contact capacitance sensors, influence of the edge effect of gauge head is studied, and one capacitance sensor for measuring the aperture of the small blind holes or through holes is introduced. The system is composed of one positioning device, one aperture measuring capacitance sensor, one measuring circuit, and software. This system employs visual CCD and two-dimensional mic...

BotSward: Centrality Measures for Graph-Based Bot Detection Using Machine Learning

The number of botnet malware attacks on Internet devices has grown at an equivalent rate to the number of Internet devices that are connected to the Internet.Bot detection using machine learning(ML)with flow-based features has been extensively studied in the literature.Existing flow-based detection methods involve significant computational overhead that does not completely capture network communication patterns that might reveal other features ofmalicious hosts.Recently,Graph-Based Bot Detection methods using ML have gained attention to overcome these limitations,as graphs provide a real representation of network communications.The purpose of this study is to build a botnet malware detection system utilizing centrality measures for graph-based botnet detection and ML.We propose BotSward,a graph-based bot detection system that is based on ML.We apply the efficient centrality measures,which are Closeness Centrality(CC),Degree Centrality(CC),and PageRank(PR),and compare them with others used in the state-of-the-art.The efficiency of the proposed method is verified on the available Czech Technical University 13 dataset(CTU-13).The CTU-13 dataset contains 13 real botnet traffic scenarios that are connected to a command-and-control(C&C)channel and that cause malicious actions such as phishing,distributed denial-of-service(DDoS)attacks,spam attacks,etc.BotSward is robust to zero-day attacks,suitable for large-scale datasets,and is intended to produce better accuracy than state-of-the-art techniques.The proposed BotSward solution achieved 99%accuracy in botnet attack detection with a false positive rate as low as 0.0001%.

APPROACH OF IMPROVING PRECISION IN ULTRASONIC DOPPLER BLOODSTREAM SPEED MEASUREMENT BY CHAOS-BASED FREQUENCY DETECTING

It is critical for cerebral vascular disease diagnosis through Doppler to detect the maximum and the minimum of the carotid blood flow speed accurately. A kind of Duffing system under an external periodic power with dump is introduced in the letter, numerical analysis is carried out by four-order Runge-Kutta method. An oscillator array is designed according to the frequency of the ultrasonic wave. When the external signals are inputted, computational algorithm is used to scan the array in turn and analyze the result, and the frequency can be determined. Based on the methods above, detecting the carotid blood flow speed accurately is realized. The Signal-to-Noise Ratio (SNR) of-20.23dB is obtained by the result of experiments. In conclusion, the SNR has been improved and the precision of the measured bloodstream speed has been increased, which can be 0.069% to 0.13%.

Detecting high-dimensional multipartite entanglement via some classes of measurements

Mutually unbiased bases, mutually unbiased measurements and general symmetric informationally complete measure- ments are three related concepts in quantum information theory. We investigate multipartite systems using these notions and present some criteria detecting entanglement of arbitrary high dimensional multi-qudit systems and multipartite sys- tems of subsystems with different dimensions. It is proved that these criteria can detect the k-nonseparability （k is even） of multipartite qudit systems and arbitrary high dimensional multipartite systems of m subsystems with different dimensions. We show that they are more efficient and wider of application range than the previous ones. They provide experimental implementation in detecting entanglement without full quantum state tomography.

Digital Cross-Correlation Detection of Multi-Laser Beams Measuring System for Wind Field Detection

A cross-correlation detection method to process backscatter signals of multi-laser beams measuring （MLBM） is presented, which can be firstly filtered by the digital filter composed of average median filter and finite impulse response （FIR） digital filter. The processing of backscatter signals using single-pulse and three-pulse cross-correlation detection methods is depicted in detail. From calculation results, the multi-pulse cross-correlation detection could effectively improve signal-to-noise ratio （SNR）. Finally, both wind velocity and direction are determined by the peak-delay method based on the correlation function which shows high measuring precision and high SNR of the MLBM system with the assistance of the digital cross- correlation detection.

Combined measurement of thyroid and plasma homocysteic acid for detecting the severity of vascular dementia

BACKGROUND: Recent researches demonstrate that onset of cerebral infarction always accompanies with obvious changes of function of thyroid axis; while, high-homocysteic acidemia has been proved as one of risk factors of vascular dementia and Alzheimer disease. Meanwhile, it is found that level of plasma homocysteic acid is positive correlation with injured degrees of cognitive function and brain damage. OBJECTIVE: To observe the changes of function of thyroid and level of homocysteic acid among patients with vascular dementia and compare with those patients without dementia cerebral infarction. DESIGN: Randomized grouping and contrast observation. SETTING: Department of Neurology, People’s Hospital Affiliated to Yunyang Medical College, South China Hospital of Wuhan University. PARTICIPANTS: A total of 38 patients with vascular dementia were hospitalized in the Department of Neurology, People’s Hospital Affiliated to Yunyang Medical College from February 2004 to December 2005. All patients met the diagnostic criteria of the Fourth Edition of Diagnostic and Statistical Manual of Mental Disorder (DSM-IV) established by American Psychiatric Association. Based on educational degrees, Mini-mental Status Examination (MMSE) was classified into illiteracy (≤ 17 points), education of primary school (educational duration ≤ 6 years, ≤ 24 points) and education of middle school or above (educational duration > 6 years, ≤ 24 points). Forty patients with non-dementia cerebral infarction were regarded as the control group and checked with CT examination. There were no significant differences of sex and age between the two groups. All patients and relatives were provided the consent. METHODS: Within 24 hours after hospitalization, patients with vascular dementia received MMSE scores, and the degrees were classified based on the scoring results: mild (20-24 points), moderate (10-19 points) and severe (below 10 points). Levels of thyroxine were measured with radioimmunodetection and content of homocysteic acid was measured with high performance liquid chromatogram (HPLC) electrochemical detection. MAIN OUTCOME MEASURES: Levels of homocysteic acid and thyroxine among patients with vascular dementia and non-dementia cerebral infarction. RESULTS: A total of 38 patients with vascular dementia and 40 patients with non-dementia cerebral infarction were involved in the final analysis. ① Levels of triiodothyronine (T3), thyroxine (T4) and free T3 (FT3) were (0.9±0.4) μg/L, (92.9±26.4) μg/L and (3.9±1.8) pmol/L in vascular dementia group respectively, which were higher than those in control group [(1.3±0.3) μg/L, (110.2±28.7) μg/L, (7.2±2.1) pmol/L, t =2.766 6-7.433 6, P < 0.01]; while, level of homocysteic acid was (29.57±7.12) μmol/L in vascular dementia group, which was higher than that in control group [(24.53±4.98) μmol/L, t =3.637 7, P < 0.01]. There were no significant differences of free T4 (FT4) and thyrotropic-stimulating hormone (TSH) between the two groups (P > 0.05). ② Levels of FT3 of patients with mild, moderate and severe vascular dementia were (1.0±0.2), (0.9±0.1) and (0.8±0.1) μg/L, respectively; levels of homocysteic acid were (26.52±4.84), (29.59±5.56) and (32.71±6.17) μmol/L, respectively. There were significant differences among patients at the three degrees of vascular dementia (F =3.59-32.4, P < 0.01). However, there were no significant differences of T4, FT4 and TSH among the three kinds of patients (P > 0.05). CONCLUSION: Levels of thyroxine of patients with vascular dementia decrease; however, levels of homocysteic acid increase. Therefore, the results can indirectly reflect severities of vascular dementia.

A Method of Measuring Large Displacement and Deformation with High Precision *

A CCD position detecting system measuring the displacement and deformation of structure is presented. The measure method takes advantage of the position detecting technique based on digital image processing. A bright spot is pegged on the object to be measured and imaged to the target of CCD camera through a telescopic lens. The CCD target converts the optical signal to equivalent electric signal. The video frequency signal is digitized to an array of 512×512 pixels by the analog to digital converter (ADC), then transmitted to the computer. The computer controls the data acquisition, conducts image processing and detects the location of the target spot. Comparing the current position with the original position of the spot, the displacement of object is obtained. With the aid of analysis software, the system can achieve the resolution of 0 01 mm in the 6 m distance from the object to the point of observation. To meet the need of practice, the measuring distance can be extended to 100 m or even farther.

CAD Model-Based Intelligent Inspection Planning for Coordinate Measuring Machines

As the market competition among enterprises grows intensively and the demand for high quality products increases rapidly, product quality inspection and control has become one of the most important issues of manufacturing, and improving the efficiency and accuracy of inspection is also one of problems which enterprises must solve. It is particularly important to establish rational inspection planning for parts before inspecting product quality correctly. The traditional inspection methods have been difficult to satisfy the requirements on the speed and accuracy of modern manufacturing, so CAD-based computer-aided inspection planning （CAIP） system with the coordinate measuring machines （CMM） came into being. In this paper, an algorithm for adaptive sampling and collision-free inspection path generation is proposed, aiming at the CAD model-based inspection planning for coordinate measuring machines （CMM）. Firstly, using the method of step adaptive subdivision and iteration , the sampling points for the specified number with even distribution will be generated automatically. Then, it generates the initial path by planning the inspection sequence of measurement points according to the values of each point＇s weight sum of parameters, and detects collision by constructing section lines between the probe swept-volume surfaces and the part surfaces, with axis-aligned bounding box （AABB） filtering to improve the detection efficiency. For collided path segments, it implements collision avoidance firstly aiming at the possible outer-circle features, and then at other collisions, for which the obstacle-avoiding movements are planned with the heuristic rules, and combined with a designed expanded AABB to set the obstacle-avoiding points. The computer experimental results show that the presented algorithm can plan sampling points＇ locations with strong adaptability for different complexity of general surfaces, and generate efficient optimum path in a short time and avoid collision effectively.

Detection performance and inversion processing of logging-while-drilling extra-deep azimuthal resistivity measurements

We present systematic investigations on the physics,detection performance and inversion of logging-while-drilling extradeep azimuthal resistivity measurements(EDARM).First,the definitions of EDRAM measurements are discussed,followed by the derivation of the attenuation and phase-shift geometrical factors to illustrate the relative contributions of formation units to the observed signals.Then,a new definition of detection depth,which considers the uncertainty of inversion results caused by the data noise,is proposed to quantify the detection capability of ED ARM.Finally,the B ayesian theory associated with Markov chain Monte Carlo sampling is introduced for fast processing of EDARM data.Numerical results show that ED ARM is capable of detecting the azimuth and distance of remote bed boundaries,and the detection capability increases with increasing spacing and resistivity contrast.The EDARM tool can accommodate a large range of formation resistivity and is able to provide the resistivity anisotropy at arbitrary relative dipping angles.In addition,multiple bed boundaries and reservoir images near the borehole are readily obtained by using the Bayesian inversion.

NON-CONTACT MEASUREMENT SYSTEM OF FREEFORM SURFACE AND NURBS RECONSTRUCTION OF MEASUREMENT POINTS

Based on the development of the non-contact measurement system of free-formsurface, NURBS reconstruction of measurement points of freeform surface is effectively realized bymodifying the objective function and recursive procedure and calculating the optimum number ofcontrol points. The reconstruction precision is evaluated through Ja-cobi's transformation method.The feasibility of the measurement system and effectiveness of the reconstruction algorithm aboveare proved by experiment.

Clinical study using novel endoscopic system for measuring size of gastrointestinal lesion

AIM: To verify the performance of a lesion size measurement system through a clinical study.

Measuring loblolly pine crowns with drone imagery through deep learning

In modeling forest stand growth and yield,crown width,a measure for stand density,is among the parameters that allows for estimating stand timber volumes.However,accurately measuring tree crown size in the field,in particular for mature trees,is challenging.This study demonstrated a novel method of applying machine learning algorithms to aerial imagery acquired by an unmanned aerial vehicle(UAV)to identify tree crowns and their widths in two loblolly pine plantations in eastern Texas,USA.An ortho mosaic image derived from UAV-captured aerial photos was acquired for each plantation(a young stand before canopy closure,a mature stand with a closed canopy).For each site,the images were split into two subsets:one for training and one for validation purposes.Three widely used object detection methods in deep learning,the Faster region-based convolutional neural network(Faster R-CNN),You Only Look Once version 3(YOLOv3),and single shot detection(SSD),were applied to the training data,respectively.Each was used to train the model for performing crown recognition and crown extraction.Each model output was evaluated using an independent test data set.All three models were successful in detecting tree crowns with an accuracy greater than 93%,except the Faster R-CNN model that failed on the mature site.On the young site,the SSD model performed the best for crown extraction with a coefficient of determination(R^(2))of 0.92,followed by Faster R-CNN(0.88)and YOLOv3(0.62).As to the mature site,the SSD model achieved a R^(2)as high as 0.94,follow by YOLOv3(0.69).These deep leaning algorithms,in particular the SSD model,proved to be successfully in identifying tree crowns and estimating crown widths with satisfactory accuracy.For the purpose of forest inventory on loblolly pine plantations,using UAV-captured imagery paired with the SSD object detention application is a cost-effective alternative to traditional ground measurement.

High Impedance Fault Detection of Distribution Network by Phasor Measurement Units

This paper proposes a new algorithm for High Impedance Fault (HIF) detection using Phasor Measurement Unit (PMU). This type of faults is difficult to detect by over current protection relays because of low fault current. In this paper, an index based on phasors change is proposed for HIF detection. The phasors are measured by PMU to obtain the square summation of errors. Two types of data are used for error calculation. The first one is sampled data and the second one is estimated data. But this index is not enough to declare presence of a HIF. Therefore another index introduces in order to distinguish the load switching from HIF. Second index utilizes 3rd harmonic current angle because this number of harmonic has a special behaviour during HIF. The verification of the proposed method is done by different simulation cases in EMTP/MATLAB.

AN ADAPTIVE MEASUREMENT SCHEME BASED ON COMPRESSED SENSING FOR WIDEBAND SPECTRUM DETECTION IN COGNITIVE WSN

An Adaptive Measurement Scheme (AMS) is investigated with Compressed Sensing (CS) theory in Cognitive Wireless Sensor Network (C-WSN). Local sensing information is collected via energy detection with Analog-to-Information Converter (AIC) at massive cognitive sensors, and sparse representation is considered with the exploration of spatial temporal correlation structure of detected signals. Adaptive measurement matrix is designed in AMS, which is based on maximum energy subset selection. Energy subset is calculated with sparse transformation of sensing information, and maximum energy subset is selected as the row vector of adaptive measurement matrix. In addition, the measurement matrix is constructed by orthogonalization of those selected row vectors, which also satisfies the Restricted Isometry Property (RIP) in CS theory. Orthogonal Matching Pursuit (OMP) reconstruction algorithm is implemented at sink node to recover original information. Simulation results are performed with the comparison of Random Measurement Scheme (RMS). It is revealed that, signal reconstruction effect based on AMS is superior to conventional RMS Gaussian measurement. Moreover, AMS has better detection performance than RMS at lower compression rate region, and it is suitable for large-scale C-WSN wideband spectrum sensing.

Improvement Design of Biochip Towards High Stable Bioparticle Detection Utilizing Dielectrophoresis Impedance Measurement

Dielectrophoresis impedance measurement(DEPIM)is a powerful tool for bioparticle detection due to its advantages of high efficiency,label-free and low costs.However,the strong electric field may decrease the viability of the bioparticle,thus leading to instability of impedance measurement.A new design of biochip is presented with high stable bioparticle detection capabilities by using both negative dielectrophoresis(nDEP)and traveling wave dielectrophoresis(twDEP).In the biochip,a spiral electrode is arranged on the top of channel,while a detector is arranged on the bottom of the channel.The influence factors on the DEP force and twDEP force are investigated by using the basic principle of DEP,based on which,the relationship between Clausius-Mossotti(CM)factor and the frequency of electric field is obtained.The two-dimensional model of the biochip is built by using Comsol Multiphysics.Electric potential distribution,force distribution and particle trajectory in the channel are then obtained by using the simulation model.Finally,both the simulations and experiments are performed to demonstrate that the new biochip can enhance the detection efficiency and reduce the negative effects of electric field on the bioparticles.

Non-contact measurement and multi-objective analysis of drilling temperature when drilling B_4C reinforced aluminum composites

Non-contact measurements of machining temperatures were performed with optical pyrometer when drilling particle（B4C） reinforced metal matrix composites（MMCs） with different drills. The effect of particle content, cutting speed, feed rate and tool material on the maximum drilling temperature was investigated. The drilling parameters were optimized based on multiple performance characteristics in terms of the maximum cutting temperature and tool wear. According to the results, the most influential control factors on the cutting temperatures are found to be particle fraction, feed rate and interaction between the cutting speed and particle content, respectively. The influences of the cutting speed and drill material on the drilling temperature are found to be relatively lower for the used range of parameters. Minimum cutting temperatures are obtained with lower particle fraction and cutting speed, with relatively higher feed rates and carbide tools. The results reveal that optimal combination of the drilling parameters can be used to obtain both minimum cutting temperature and tool wear.

Tanimoto Based Similarity Measure for Intrusion Detection System

In this paper we introduced Tanimoto based similarity measure for host-based intrusions using binary feature set for training and classification. The k-nearest neighbor (kNN) classifier has been utilized to classify a given process as either normal or attack. The experimentation is conducted on DARPA-1998 database for intrusion detection and compared with other existing techniques. The introduced similarity measure shows promising results by achieving less false positive rate at 100% detection rate.