Position Values Research Articles

Skeleton-based human activity recognition using ConvLSTM and guided feature learning

Human activity recognition aims to determine actions performed by a human in an image or video. Examples of human activity include standing, running, sitting, sleeping, etc. These activities may involve intricate motion patterns and undesired events such as falling. This paper proposes a novel deep convolutional long short-term memory (ConvLSTM) network for skeletal-based activity recognition and fall detection. The proposed ConvLSTM network is a sequential fusion of convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and fully connected layers. The acquisition system applies human detection and pose estimation to pre-calculate skeleton coordinates from the image/video sequence. The ConvLSTM model uses the raw skeleton coordinates along with their characteristic geometrical and kinematic features to construct the novel guided features. The geometrical and kinematic features are built upon raw skeleton coordinates using relative joint position values, differences between joints, spherical joint angles between selected joints, and their angular velocities. The novel spatiotemporal-guided features are obtained using a trained multi-player CNN-LSTM combination. Classification head including fully connected layers is subsequently applied. The proposed model has been evaluated on the KinectHAR dataset having 130,000 samples with 81 attribute values, collected with the help of a Kinect (v2) sensor. Experimental results are compared against the performance of isolated CNNs and LSTM networks. Proposed ConvLSTM have achieved an accuracy of 98.89% that is better than CNNs and LSTMs having an accuracy of 93.89 and 92.75%, respectively. The proposed system has been tested in realtime and is found to be independent of the pose, facing of the camera, individuals, clothing, etc. The code and dataset will be made publicly available.

A novel method for asynchronous source localisation based on time of arrival measurements

Source localisation is an important component in the application of wireless sensor networks, and plays a key role in environmental monitoring, healthcare and battlefield surveillance and so on. In this article, the source localisation problem based on time-of-arrival measurements in asynchronous sensor networks is studied. Because of imperfect time synchronisation between the anchor nodes and the signal source node, the unknown parameter of start transmission time of signal source makes the localisation problem further sophisticated. The derived maximum-likelihood estimator cost function with multiple local minimum is non-linear and non-convex. A novel two-step method which can solve the global minimum is proposed. First, by leveraging dimensionality reduction, the maximum (minimum) distance maximum (minimum) time-of-arrival matching-based second-order Monte Carlo method is applied to find a rough initial position of the signal source with low computational complexity. Then, the rough initial position value is refined using trust region method to obtain the final positioning result. Comparative analysis with state-of-the-art semidefinite programming and min–max criterion-based algorithms are conducted. Simulations show that the proposed method is superior in terms of localisation accuracy and computational complexity, and can reach the optimality benchmark of Cramér–Rao Lower Bound even in high signal-to-noise ratio environments.

Analysis of Earthquake Activity in Indonesia by Clustering Method

Indonesia is an area where three large tectonic plates meet, namely the Indo-Australian, Eurasian and Pacific plates, so that Indonesia is included in the earthquake-prone category, with 11,660 earthquake vibrations identified in the Meteorology, Climatology and Geophysics Agency (BMKG) database in 2019 The purpose of this study is to develop a classification of the distribution of earthquakes in Indonesia in 2019 based on the values of magnitude, depth, and position. This research was conducted by using the clustering method based on the K-means algorithm and the DBSCAN algorithm as a comparison. The results of the clustering show that the earthquake data analysis using the K-Means algorithm is superior with a silhouette index value of 0.837, while the DBSCAN algorithm has a silhouette index value of 0.730.

Conventional fluoroscopic views are inadequate to predict the Tip Apex Distance and articular clearance of sliding screw devices: A computed tomography-based analysis

Tip-apex-distance (TAD) has been widely advocated as the index to predict the risk of screw cut out in hip fractures treated with sliding hip screw devices. The fluoroscopic extents of the femoral head can change with the slightest change in the limb position which includes internal and external rotations, adduction and abduction. These changes can affect the visible TAD and articular-clearance of the screw-tip. The purpose of this Computed-tomography(CT) based analysis is to analyze the variations of the radiographically visible articular-clearance and TAD measurements with limb positioning and to determine the appropriate fluoroscopic projections for different screw-positions within the femoral head. We retrospectively analysed CT studies of twenty healthy proximal femora. Spatial markers simulating screw tips were placed in the different combinations of anteroposterior(AP) and cephalocaudal(CC) positions. Software-based AP and lateral radiographs were developed for each screw position. Additional AP radiographs with femur in internal and external rotation, and lateral radiographs with the femur in adduction and abduction were developed. The variation of TAD and articular-clearance of the screw was measured among these radiographs for individual screw tip positions. Screw tip placed centrally in AP and CC planes position didn't show any significant variation in TAD and articular-clearance with modified AP and lateral radiographs. Significant differences were observed in TAD and articular-clearance values for other screw tip positions. Anteriorly placed screw tips had higher TAD and articular-clearance values with external rotation and similar changes were observed with posteriorly placed tips in internal rotation. Inferiorly placed tips had higher articular-clearance and TAD with limb abduction and similar changes were observed for superiorly placed tips with limb adduction. For the sliding screws placed in non-central locations, the clearance of the screw tip from the articular margins can not be appropriately estimated with conventional AP and lateral views. Additional views with the limb in internal rotation and external rotation in AP view, and adduction-abduction in lateral view are required to safely place the sliding screw in the femoral head. The limb should be brought to a neutral alignment for the accurate estimation of TAD.

Imaging modalities for the detection of posterior pelvic floor disorders in women with obstructed defaecation syndrome.

Imaging modalities for the detection of posterior pelvic floor disorders in women with obstructed defaecation syndrome.

Reversible Data Hiding in a Chaotic Encryption Domain Based on Odevity Verification

On the premise of guaranteeing the visual effect, in order to improve the security of the image containing digital watermarking and restore the carrier image without distortion, reversible data hiding in chaotic encryption domain based on odevity verification was proposed. The original image was scrambled and encrypted by Henon mapping, and the redundancy between the pixels of the encrypted image was lost. Then, the embedding capacity of watermarking can be improved by using odevity verification, and the embedding location of watermarking can be randomly selected by using logistic mapping. When extracting the watermarking, the embedded data was judged according to the odevity of the pixel value of the embedding position of the watermarking, and the carrier image was restored nondestructively by odevity check image. The experimental results show that the peak signal-to-noise ratio (PSNR) of the original image is above 53 decibels after the image is decrypted and restored after embedding the watermarking in the encrypted domain, and the invisibility is good.

End effector position calculation with the ANN for tapping machine

Nowadays, manufacturers give importance to the production of machines that allow for faster production, reduce labor costs, and minimize operation errors to meet the increasing demand. The search for such machines leads the manufacturing sector to automation. In this study, an automation-supported tapping machine prototype was manufactured. Kinematic equations were used for determining the location of the end effector in Cartesian space, whereas inverse kinematic equations were used for angular positions in joint space relative to positions in Cartesian space. Based on the results of the kinematic equations, the data obtained in certain positions were taught to the system through ANN. The position values for the angles known through the artificial intelligence algorithm were taught to the system. Then, the position coordinates to be reached by this manipulator, which has four degrees of freedom, for the intermediate position coordinate values through artificial neural networks (ANN) have been obtained. It is expected that the device controlled by artificial intelligence will not be affected by the variables in parameter or force changes requiring high working performance. With the control of the positions through ANN, it has been ensured that the position control of the tapping robot manipulator is predicted based on artificial intelligence techniques depending on the angle values of the limbs, and the robot is prevented from going to a position that is on a different trajectory. Accordingly, the robot arm has been made controllable with ANN techniques. With ANN modelling, the position of the end point to perform the tapping process was estimated with high reliability. For future research, a rough simulation was made to see whether the end point would go to a different position in space.

Comparison of intraocular pressure in healthy brachycephalic and nonbrachycephalic cats using the Icare® TONOVET Plus rebound tonometer

To compare intraocular pressure using the Icare® TONOVET Plus rebound tonometer in healthy brachycephalic and nonbrachycephalic cats. Both eyes of 78healthy cats were investigated in this study. Cats were divided into two groups: brachycephalic (n=39) and nonbrachycephalic (n=39). Nose position and muzzle ratio were photographically recorded and analyzed. Physical and ophthalmic examinations were performed. Intraocular pressure was measured using the Icare® TONOVET Plus rebound tonometry instrument. Quantitative mean values were statistically compared using an unpaired t-test at a significance level of p<.05. Mean values of the nose position and muzzle ratio were significantly lower in the brachycephalic group (20.14±5.43%, 9.61±3.29%) compared with the nonbrachycephalic group (29.21±4.30%, 13.97±6.01%). The mean intraocular pressure for brachycephalic cats (15.76±0.50mmHg) was significantly lower (p<.001) than for nonbrachycephalic cats (18.77±0.49mmHg). Intraocular pressure was significantly lower in brachycephalic cats using the Icare® TONOVET Plus rebound tonometer. Intraocular pressure values obtained in this study could be used as a guideline for measurements obtained using this tonometry device in healthy brachycephalic and nonbrachycephalic cats.

-种新型旋耕机调控参数的PLC系统设计研究

The purpose of this paper is to design a rotary tiller control system based on programmable controller technology, and verify the application of this control system. In this paper, the traction and depth control of rotary tiller are transformed into the control of piston rod displacement of hydraulic cylinder, and the intelligent fuzzy control of axial extension displacement of rotary tiller and output torque of piston rod is realized. According to the characteristics of the mathematical model, the objective function is determined and the motion parameters are optimized by the steepest descent method, which provides a reliable calculation model for the optimization design of the overall parameters of the rotary tiller. The rotary tiller control system based on PLC (Programmable Logic Controller) can realize the effective control of rotary tillage depth and speed, and the error of rotary tillage depth can be guaranteed within 4.5%. When the soil resistance of the rotary tiller suddenly increases, the fuzzy control of the comprehensive tillage depth value of the stressed position can effectively improve the rotational speed stability of the hydraulic motor for tillage depth control. PLC technology puts the digital control of rotary tiller on a higher technical platform, thus reducing the labour required for agricultural planting, providing a good growth environment for crops and realizing the intelligence of rotary tiller.

Two Stages Outlier Removal as Pre-processing Digitizer Data on Fine Motor Skills (FMS) Classification Using Covariance Estimator and Isolation Forest

The increase of the classification accuracy level has become an important problem in machine learning especially in diverse data-set that contain the outlier data. In the data stream or the data from sensor readings thatproduce large data, it allows a lot of noise to occur. It makes the performance of the machine learning model is disrupted or even decreased. Therefore, clean data from noise is needed to obtain good accuracy and to improve the performance of the machine learning model. This research proposes a two-stages for detecting and removing outlier data by using the covariance estimator and isolation forest methods as pre-processing in the classification process to determine fine motor skill (FMS). The dataset was generated from the process of recording data directly during cursive writing by using a digitizer. The data included the relative position of the stylus on the digitizer board. x position, y position, z position, and pressure values are then used as features in the classification process. In the process of observation and recording, the generated data was very huge so some of them produce the outlier data. From the experimental results that have been implemented, the level of accuracy in the FMS classification process increases between 0.5-1% by using the Random Forest classifier after the detection and outlier removal by using covariance estimator and isolation forest. The highest accuracy rate achieves 98.05% compared to the accuracy without outlier removal, which is only about 97.3%.

Estimating player value in American football using plus–minus models

Abstract Calculating the value of football player’s on-field performance has been limited to scouting methods while data-driven methods are mostly limited to quarterbacks. A popular method to calculate player value in other sports are Adjusted Plus–Minus (APM) and Regularized Adjusted Plus–Minus (RAPM) models. These models have been used in other sports, most notably basketball (Rosenbaum, D. T. 2004. Measuring How NBA Players Help Their Teams Win. http://www.82games.com/comm30.htm#_ftn1; Kubatko, J., D. Oliver, K. Pelton, and D. T. Rosenbaum. 2007. “A Starting Point for Analyzing Basketball Statistics.” Journal of Quantitative Analysis in Sports 3 (3); Winston, W. 2009. Player and Lineup Analysis in the NBA. Cambridge, Massachusetts; Sill, J. 2010. “Improved NBA Adjusted +/− Using Regularization and Out-Of-Sample Testing.” In Proceedings of the 2010 MIT Sloan Sports Analytics Conference) to estimate each player’s value by accounting for those in the game at the same time. Football is less amenable to APM models due to its few scoring events, few lineup changes, restrictive positioning, and small quantity of games relative to the number of teams. More recent methods have found ways to incorporate plus–minus models in other sports such as Hockey (Macdonald, B. 2011. “A Regression-Based Adjusted Plus-Minus Statistic for NHL players.” Journal of Quantitative Analysis in Sports 7 (3)) and Soccer (Schultze, S. R., and C.-M. Wellbrock. 2018. “A Weighted Plus/Minus Metric for Individual Soccer Player Performance.” Journal of Sports Analytics 4 (2): 121–31 and Matano, F., L. F. Richardson, T. Pospisil, C. Eubanks, and J. Qin (2018). Augmenting Adjusted Plus-Minus in Soccer with Fifa Ratings. arXiv preprint arXiv:1810.08032). These models are useful in coming up with results-oriented estimation of each player’s value. In American football, many positions such as offensive lineman have no recorded statistics which hinders the ability to estimate a player’s value. I provide a fully hierarchical Bayesian plus–minus (HBPM) model framework that extends RAPM to include position-specific penalization that solves many of the shortcomings of APM and RAPM models in American football. Cross-validated results show the HBPM to be more predictive out of sample than RAPM or APM models. Results for the HBPM models are provided for both Collegiate and NFL football players as well as deeper insights into positional value and position-specific age curves.

A novel k-mean clustering based graph cut for brain MR image segmentation

Image Segmentation is an influential method to detect and distinguish the diseased and normal sections of an image. Image segmentation extracts the regions of interest for precise diagnosis of tumours and scheduling appropriate line of treatment. The distinct tumours in brain have varied outlies, position and intensity values. Consequently, it is difficult to develop a common technique for brain MRI segmentation. Moreover, the extraction of anomalies from the brain MRI turns out to be a challenging task. In this research, we have developed a self-regulating method for selection of seed points for partitioning the graph of MR images with tumor to attain graph cut segmentation. The proposes method overcomes the key problem of primary seed point selection by utilizing the balanced brain layout and combines k - mean clustering into graph cut for segmenting an image. The outcomes attained by the proposed technique facilitates improved segmentation of the diseased region.

The Importance of Under-Keel Sound Velocity Sensor in Measuring Water Depth with Multibeam Echosounder

The basic and most commonly used application of modern multibeam echosounders (MBES) is the bathymetric survey. Surface sound velocity errors introduce errors on beam steering angles and consequently errors in depth and position values. Due to systematic malfunction and troubleshooting of the sound velocity sensor (SVS) on board Polish Navy hydrographic ship Arctowski, attempts to solve the problem were made. All the inspections and cleaning of the sensor were performed with the use of divers or while staying in the shipyard. Diving work did not always bring the expected results and periodic ship docking was quite expensive. The article shows the importance of the SVS sensor in bathymetric measurements using multibeam echosounder. Selected problems of the sensor operation and temporary solutions were presented. The paper provides a description of practical solutions implemented aboard the navy ship Arctowski. The idea and implementation were the result of the author’s experience gained during 18 years of service on board that ship.

A deep-learning approach for predicting oscillating motion of liquid slugs in a closed-loop pulsating heat pipe

This paper presents the very first application of a deep neural network (DNN) model to predict the oscillating motion of liquid slugs in a closed-loop pulsating heat pipe (CLPHP). The time-series data of the positions of liquid-vapor menisci are obtained from flow visualization using a high-speed camera: five liquid slugs in the 5-turn CLPHP are observed to have rapid oscillation with varying amplitude. Time-series analysis is conducted on the flow visualization results by employing the DNN model, which uses a Long Short-Term Memory (LSTM)-based encoder-decoder architecture as a sequence-to-sequence deep-learning framework. From the model, the position of each meniscus is predicted with a single input data of its own (univariate prediction) or with multiple input data of all the menisci (multivariate prediction): It is shown that the predicted values match closely with the measured values for both univariate and multivariate predictions. To quantitatively examine the prediction performance, the average volumetric fraction in the condenser section, a major parameter for the thermal performance of the CLPHP, is calculated using the predicted values of positions of menisci. This model is found to be accurate to within ± 30% in predicting the average volumetric fraction for both univariate and multivariate cases. This study sheds new light on analyzing the dynamics of the complex oscillating motion in pulsating heat pipes.

Characterization and verification of astigmatic interferometric particle imaging for volumetric droplet 3D position and size measurement

Sprays generated by atomization processes have been used in a wide range of fields. The size and spatial distribution of volumetric droplets in a spray are critical parameters in industrial applications. Astigmatic interferometric particle imaging (AIPI), an extension of the traditional interferometric particle imaging (IPI), is developed to simultaneously measure the size and 3D position of volumetric droplets in a sparse spray. Based on the generalized Huygens–Fresnel integral and the transfer matrix, the size and depth position of droplet can be respectively extracted from the fringe spacing and orientation of interferogram in AIPI. An AIPI setup is established to characterize droplets in a sparse spray generated by a nozzle with the AIPI calibration procedure adopted. The measured parameters by AIPI are compared with those obtained synchronously by digital inline holography, which is regarded as a standard measurement technique. Results show that the average deviation values of droplet size and depth position are respectively 3.8% and 6.8%. AIPI has been demonstrated with high accuracy in simultaneous 3D positions and size measurements.

The outcomes of measurements in the de Broglie–Bohm theory

Within the de Broglie-Bohm (dBB) theory, the measurement process and the determination of its outcome are usually discussed in terms of the effect of the Bohmian positions of the measured system S. %} This article shows that the Bohmian positions associated with the measurement apparatus M can actually play a crucial role in the determination of the result of measurement. Indeed, in many cases, the result is practically independent of the initial value of a Bohmian position associated with S, and determined only by those of M. The measurement then does not reveal the value of any pre-existing variable attached to S, but just the initial state of the measurement apparatus. Quantum contextuality then appears with particular clarity as a consequence of the dBB dynamics for entangled systems.

Comparison of the safety and efficacy between the prone split-leg and Galdakao-modified supine Valdivia positions during endoscopic combined intrarenal surgery: A multi-institutional analysis.

To evaluate the safety and efficacy of the prone split-leg and the Galdakao-modified supine Valdivia positions during endoscopic combined intrarenal surgery. A multi-institutional, retrospective cohort study was conducted between January 2014 and December 2018.The stone-free and complication rates were compared between the prone split-leg and the Galdakao-modified supine Valdivia positions. Anatomical variations were evaluated using contrast-enhanced computed tomography imaging. In total, 118 and 100 patients underwent endoscopic combined intrarenal surgery in the prone split-leg and Galdakao-modified supine Valdivia positions, respectively. Renal punctures in the prone split-leg position were predominantly executed through the lower calyces (78.0%), whereas those in the Galdakao-modified supine Valdivia position were primarily performed through the middle calyces (64.0%; P<0.001). Surgical duration in the prone split-leg position was significantly shorter than that in the Galdakao-modified supine Valdivia position (106.5 vs 126.0min; P=0.0459). There were no significant differences in the stone-free rate between the two positions (78.8% vs 76.0%; P=0.629). Incidences of urinary tract injury (P=0.033) and febrile urinary tract infection (23.7% vs 10.0%; P=0.011) in the prone split-leg position were significantly higher than that in the Galdakao-modified supine Valdivia position. The tilt of the major renal axis was significantly greater in the prone position than the corresponding values in the oblique position (19.4° vs 8.5°; P=0.019). Anatomical variation might result in the differences of renal puncture calyx. Endoscopic combined intrarenal surgery in the Galdakao-modified supine Valdivia position may bring equal stone-free status, with a longer surgical time but fewer complications including febrile urinary tract infection and urinary tract injury than the prone split-leg position.

Professional Baseball Player Type and Geographic Region of Origin Impacts Shoulder External and Internal Rotation Strength.

BackgroundShoulder strength deficits are implicated in arm injuries and performance deficits in baseball players.PurposeTo characterize shoulder external (ER) and internal (IR) rotation strength in professional baseball players, and compare strength across player type (pitchers, position players) and geographic origin (North America, Latin America).Study DesignCross-sectional.MethodsMinor league professional baseball players from North America and Latin America (n=242; age=22.4±2.3 years; n=135 pitchers and n=107 position players; n=162 North American and n=80 Latin American players) volunteered at spring training. Bilateral shoulder IR and ER isometric strength was measured in sitting with the arm at the side using a handheld dynamometer stabilized on a wall via a specialized jig. Strength was normalized to body weight, and compared using t-tests between player type and geographic area of origin (p < 0.05).ResultsPosition players had greater strength in ER, IR and ER:IR (ER:0.7-2.7N/kg; IR:1.3-3.8N/kg; ER:IR ratio 0.36-1.22) compared to pitchers (ER:0.5-2.5N/kg; IR:0.6- 4.2N/kg; ER:IR ratio 0.44-1.16) on the throwing arm. North American pitchers had lower ER [MD= -0.4 (95%CI:-0.7,-0.2);p=0.002] and IR [MD= -0.2 (95%CI:-0.4,-0.1);p=0.006] than Latin American pitchers on the throwing arm. There were no differences between geographic groups for position players.Discussion/ConclusionsPlayer position and geographic origin influence shoulder rotational strength values in professional baseball players. Position players have 14 – 20% higher ER and IR isometric strength than pitchers. Moreover, Latin American pitchers exhibited 11.8% greater ER strength and 16.7% greater IR strength as compared to North American pitchers. Normative values can be used to determine player deficits, declines in performance, and targets for return to play after injury.Level of EvidenceLevel II

A semi-supervised autoencoder framework for joint generation and classification of breathing

Background and objectiveOne of the main problems with biomedical signals is the limited amount of patient-specific data and the significant amount of time needed to record the sufficient number of samples needed for diagnostic and treatment purposes. In this study, we present a framework to simultaneously generate and classify biomedical time series based on a modified Adversarial Autoencoder (AAE) algorithm and one-dimensional convolutions. Our work is based on breathing time series, with specific motivation to capture breathing motion during radiotherapy lung cancer treatments. MethodsFirst, we explore the potential in using the Variational Autoencoder (VAE) and AAE algorithms to model breathing signals from individual patients. We then extend the AAE algorithm to allow joint semi-supervised classification and generation of different types of signals within a single framework. To simplify the modeling task, we introduce a pre-processing and post-processing compressing algorithm that transforms the multi-dimensional time series into vectors containing time and position values, which are transformed back into time series through an additional neural network. ResultsThe resulting models are able to generate realistic and varied samples of breathing. By incorporating 4% and 12% of the labeled samples during training, our model outperforms other purely discriminative networks in classifying breathing baseline shift irregularities from a dataset completely different from the training set, achieving an average macro F1-score of 94.91% and 96.54%, respectively. ConclusionTo our knowledge, the presented framework is the first approach that unifies generation and classification within a single model for this type of biomedical data, enabling both computer aided diagnosis and augmentation of labeled samples within a single framework.

Circular transition: scenarios for the future of design

Circular transition: scenarios for the future of design