scholarly journals Automatic Behavior and Posture Detection of Sows in Loose Farrowing Pens Based on 2D-Video Images

2021 ◽  
Vol 2 ◽  
Author(s):  
Steffen Küster ◽  
Philipp Nolte ◽  
Cornelia Meckbach ◽  
Bernd Stock ◽  
Imke Traulsen
Keyword(s):  
Deviant Behavior ◽  
Expert Knowledge ◽  
Science Research ◽  
Detection Algorithm ◽  
Farm Animals ◽  
Body Parts ◽  
Conditional Statement ◽  
Automatic Behavior ◽  
Video Images ◽  
Detection And Localization

The monitoring of farm animals and the automatic recognition of deviant behavior have recently become increasingly important in farm animal science research and in practical agriculture. The aim of this study was to develop an approach to automatically predict behavior and posture of sows by using a 2D image-based deep neural network (DNN) for the detection and localization of relevant sow and pen features, followed by a hierarchical conditional statement based on human expert knowledge for behavior/posture classification. The automatic detection of sow body parts and pen equipment was trained using an object detection algorithm (YOLO V3). The algorithm achieved an Average Precision (AP) of 0.97 (straw rack), 0.97 (head), 0.95 (feeding trough), 0.86 (jute bag), 0.78 (tail), 0.75 (legs) and 0.66 (teats). The conditional statement, which classifies and automatically generates a posture or behavior of the sow under consideration of context, temporal and geometric values of the detected features, classified 59.6% of the postures (lying lateral, lying ventral, standing, sitting) and behaviors (interaction with pen equipment) correctly. In conclusion, the results indicate the potential of DNN toward automatic behavior classification from 2D videos as potential basis for an automatic farrowing monitoring system.

STRUCTURAL AND LOGISTIC MODEL OF MATERIAL FLOWS ON DIGITALLIVESTOCK FARM

2020 ◽  
pp. 26-32
Author(s):  
VLADIMIR V KIRSANOV VLADIMIR V ◽  
Keyword(s):  
Functional Model ◽  
Base Stations ◽  
Farm Animals ◽  
Biological Objects ◽  
Livestock Breeding ◽  
Video Images ◽  
Genetic Potential ◽  
Common Control ◽  
Biotechnical System ◽  
Multi Agent

The problems of the digitalization of livestock enterprises are closely related to the construction of models and algorithms describing the functioning of individual technological processes and subsystems united by a common control system. Based on the cluster approach, three groups of tasks for the intellectualization and digitalization of objects in livestock breeding are formulated: 1) recognition of images of biological objects and models of their group and individual behavior, 2) genomic assessment of farm animals, prediction of their genetic potential, with the possibility of better adaptation to technologies and specifi c economic conditions, 3) multi-agent management of automated and robotic technical means. The authors initialized the video images of biological objects, developed a structural and functional model of a complex biotechnical system “Man-Machine-Animal”, including automated workstations of key specialists, signal receiving-and-transmitting base stations, technological modules for animal service (feeding, watering, milking, microclimate, etc.), representing local biotechnical systems. The paper presents a structural-and-logistic “funnel” model of a livestock farm functioning. The model includes vectors of incoming material fl ows, outgoing production fl ows and outgoing byproducts (production waste) described using appropriate formalizations. The authors provide the structural typifi cation of technological modules and subsystems for their mathematical analysis and subsequent digital transformation of livestock farms.

scholarly journals Detecting bursty terms in computer science research

2019 ◽  
Vol 122 (1) ◽  
pp. 681-699 ◽  
Author(s):  
E. Tattershall ◽  
G. Nenadic ◽  
R. D. Stevens
Keyword(s):  
Computer Science ◽  
Historical Data ◽  
Science Research ◽  
Detection Algorithm ◽  
Trend Detection ◽  
Free Text ◽  
Research Topics ◽  
Computer Science Research ◽  
Insight Into ◽  
Over Time

AbstractResearch topics rise and fall in popularity over time, some more swiftly than others. The fastest rising topics are typically called bursts; for example “deep learning”, “internet of things” and “big data”. Being able to automatically detect and track bursty terms in the literature could give insight into how scientific thought evolves over time. In this paper, we take a trend detection algorithm from stock market analysis and apply it to over 30 years of computer science research abstracts, treating the prevalence of each term in the dataset like the price of a stock. Unlike previous work in this domain, we use the free text of abstracts and titles, resulting in a finer-grained analysis. We report a list of bursty terms, and then use historical data to build a classifier to predict whether they will rise or fall in popularity in the future, obtaining accuracy in the region of 80%. The proposed methodology can be applied to any time-ordered collection of text to yield past and present bursty terms and predict their probable fate.

Maximizing Recall of Gruesome Images for Health Effects Advertising: An Experimental Investigation

2010 ◽  
Vol 16 (4) ◽  
pp. 112-121 ◽  
Author(s):  
Brennen W. Mills ◽  
Owen B. J. Carter ◽  
Robert J. Donovan
Keyword(s):  
Experimental Investigation ◽  
Body Part ◽  
The Body ◽  
Advertising Effectiveness ◽  
Body Parts ◽  
Online Study ◽  
Video Clips ◽  
Video Images ◽  
The Impact

The objective of this case study was to experimentally manipulate the impact on arousal and recall of two characteristics frequently occurring in gruesome depictions of body parts in smoking cessation advertisements: the presence or absence of an external physical insult to the body part depicted; whether or not the image contains a clear figure/ground demarcation. Three hundred participants (46% male, 54% female; mean age 27.3 years, SD = 11.4) participated in a two-stage online study wherein they viewed and responded to a series of gruesome 4-s video images. Seventy-two video clips were created to provide a sample of images across the two conditions: physical insult versus no insult and clear figure/ground demarcation versus merged or no clear figure/ground demarcation. In stage one, participants viewed a randomly ordered series of 36 video clips and rated how “confronting” they considered each to be. Seven days later (stage two), to test recall of each video image, participants viewed all 72 clips and were asked to identify those they had seen previously. Images containing a physical insult were consistently rated more confronting and were remembered more accurately than images with no physical insult. Images with a clear figure/ground demarcation were rated as no more confronting but were consistently recalled with greater accuracy than those with unclear figure/ground demarcation. Makers of gruesome health warning television advertisements should incorporate some form of physical insult and use a clear figure/ground demarcation to maximize image recall and subsequent potential advertising effectiveness.

scholarly journals PENDAMPINGAN MENGHINDARI SEXUAL ABUSE PADA SISWA SMA CURUP BENGKULU

2018 ◽  
Vol 2 (1) ◽  
pp. 93
Author(s):  
Dheni Koerniawan ◽  
Ketut Suryani ◽  
Maria Tarisia Rini ◽  
Sagita Bahari
Keyword(s):  
Sexual Abuse ◽  
Public Services ◽  
Deviant Behavior ◽  
Early Education ◽  
Self Care ◽  
Hormonal Changes ◽  
Body Parts ◽  
Psychosocial Aspect ◽  
Best Friends ◽  
First Time

Abstrak: Perubahan hormon selama perkembangan remaja dapat menjadikan remaja mengalami kemelut (turmoil) dalam dirinya secara psikoseksual. Hal tersebut dapat memicu terjadinya perilaku menyimpang yang dilakukan oleh remaja atau dialami oleh remaja sehingga menempatkan remaja dapat menjadi pelaku atau korban dalam penyimpangan seksual seperti kekerasan seksual (sexual abuse). Oleh karena itu, edukasi dan pendampingan sejak dini perlu dilakukan untuk meningkatkan self-care remaja mengidentifikasi adanya risiko terjadinya sexual abuse baik yang dapat terjadi pada dirinya atau pun lingkungannya. Hal inilah yang menjadi tujuan dalam kegiatan pengabdian kepada masyarakat sehingga luaran yang diharapkan adalah remaja mampu mengenali kondisi atau orang yang berpotensi mengakibatkan terjadinya sexual abuse, mengamankan diri dengan mencegah munculnya kesempatan terjadinya sexual abuse, dan melaporkan kondisi atau orang yang berpotensi serta kejadian sexual abuse. Kegiatan dilakukan dengan metode edukasi dan konseling. Hasil abdimas menunjukkan bahwa sebagian besar peserta berusia 17 tahun dan berjenis kelamin perempuan, area pribadinya pernah disentuh orang lain dan korban sexual abuse verbal, pertama kali mengalami sexual abuse saat berusia 16 tahun, mengenal pornografi dan pornoaksi ketika berusia 15 tahun, serta menjadikan orang tua dan sahabat sebagai pihak yang dipercaya dalam melaporkan peristiwa sexual abuse baik yang dialami atau disaksikan peserta. Abstract: Hormonal changes is going along with adolescence growing so he/she has turmoil especially in psychosocial aspect. This could precipitate the deviant behavior that adolescence done or suffered. It can make adolescence be a doer or victims of sexual abuse. Thus, early education and accompaniment needed to be done to enhanced adolescence self-care to identify the risk of sexual abuse that can be happened with him/herself or in their environment. This was the aims of our public services so it has outcome that adolescence able to know condition or someone which has potential to be a sexual abuse, protecting self with preventing that potential to become sexual abuse, and reporting it. This activity done as an education and counseling. The result showed mainly of participants are 17 year old and girls, personal body parts had been touched by other people and as victims, first time being victim at 16 years old, knowing pornography and pornoaction at 15 years old, and made parents and best friends as trusted people to to report even being a victim or witness.

CARRIED BAGGAGE DETECTION AND CLASSIFICATION USING MULTI-TREND BINARY CODE DESCRIPTOR AND SUPPORT VECTOR MACHINE

2021 ◽  
Author(s):  
Shah bano ◽  
Syed Adnan Shah ◽  
Wakeel Ahmad ◽  
Muhammad Ilyas
Keyword(s):  
Support Vector Machine ◽  
Support Vector Machine Classifier ◽  
Binary Code ◽  
Spatial Information ◽  
Detection Algorithm ◽  
Support Vector ◽  
Surveillance Systems ◽  
Body Parts ◽  
Public Places ◽  
Surveillance Camera

Automatic video surveillance systems have gained significant importance due to an increase in crime rate over the last two decades. Automatic baggage detection through surveillance camera can help in security and monitoring in public places. A detection algorithm for humans (with or without carrying baggage) is proposed in this paper. Detection in the proposed method can be achieved by employing spatial information of the baggage of various texture patterns with locus to the human body carrying it. To extract the features of body parts (such as head, trunk and limbs), the descriptor is exhibited and trained by the support vector machine classifier. The proposed approach has been widely assessed by using publically available datasets. The experimental results have shown that the proposed approach is viable for baggage detection and classification as compared to the other available approaches.

Human Body Parts Detection Using YCbCr Color Space

2013 ◽  
Vol 393 ◽  
pp. 556-560
Author(s):  
Nurul Fatiha Johan ◽  
Yasir Mohd Mustafah ◽  
Nahrul Khair Alang Md Rashid
Keyword(s):  
Human Body ◽  
Skin Color ◽  
Color Space ◽  
Detection Algorithm ◽  
Color Segmentation ◽  
Color Model ◽  
Body Parts ◽  
Color Spaces ◽  
Morphological Operation ◽  
Ycbcr Color Space

Skin color is proved to be very useful technique for human body parts detection. The detection of human body parts using skin color has gained so much attention by many researchers in various applications especially in person tracking, search and rescue. In this paper, we propose a method for detecting human body parts using YCbCr color spaces in color images. The image captured in RGB format will be transformed into YCbCr color space. This color model will be converted to binary image by using color thresholding which contains the candidate human body parts like face and hands. The detection algorithm uses skin color segmentation and morphological operation.

A URI parsing technique and algorithm for anti-pattern detection in RESTful Web services

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Fuad Sameh Alshraiedeh ◽  
Norliza Katuk
Keyword(s):  
Web Services ◽  
Design Science ◽  
Science Research ◽  
Research Process ◽  
Detection Algorithm ◽  
Pattern Detection ◽  
Content Type ◽  
Representational State Transfer ◽  
State Transfer ◽  
Restful Web Services

Purpose Many REpresentational State Transfer (RESTful) Web services suffered from anti-patterns problem, which may diminish the sustainability of the services. The anti-patterns problem could happen in the code of the programme or the uniform resource identifiers (URIs) of RESTful Web services. This study aims to address the problem by proposing a technique and an algorithm for detecting anti-patterns in RESTful Web services. Specifically, the technique is designed based on URIs parsing process. Design/methodology/approach The study was conducted following the design science research process, which has six activities, namely, identifying problems, identifying solutions, design the solutions, demonstrate the solution, evaluation and communicate the solution. The proposed technique was embedded in an algorithm and evaluated in four phases covering the process of extracting the URIs, implementing the anti-pattern detection algorithm, detecting the anti-patterns and validating the results. Findings The results of the study suggested an acceptable level of accuracy for the anti-patterns detection with 82.30% of precision, 87.86% of recall and 84.93% of F-measure. Practical implications The technique and the algorithm can be used by developers of RESTful Web services to detect possible anti-pattern occurrences in the service-based systems. Originality/value The technique is personalised to detect amorphous URI and ambiguous name anti-patterns in which it scans the Web service URIs using specified rules and compares them with pre-determined syntax and corpus.

RST: A Connectionist Architecture to Deal with Spatiotemporal Relationships

1998 ◽  
Vol 10 (4) ◽  
pp. 883-902 ◽  
Author(s):  
J.-C. Chappelier ◽  
A. Grumbach
Keyword(s):  
Three Dimensional ◽  
Video Images ◽  
Temporal Relationships ◽  
Leaky Integrator ◽  
Spatial Aspect ◽  
Actual Space ◽  
Temporal Aspect ◽  
Static Pattern ◽  
Spatio Temporal ◽  
Detection And Localization

In the past decade, connectionism has proved its efficiency in the field of static pattern recognition. The next challenge is to deal with spatiotemporal problems. This article presents a new connectionist architecture, RST (ŕeseau spatio temporel [spatio temporal network]), with such spatiotemporal capacities. It aims at taking into account at the architecture level both spatial relationships (e.g., as between neighboring pixels in an image) and temporal relationships (e.g., as between consecutive images in a video sequence). Concerning the spatial aspect, the network is embedded in actual space (two-or three-dimensional), the metrics of which directly influence its structure through a connection distribution function. For the temporal aspect, we looked toward biology and used a leaky-integrator neuron model with a refractory period and postsynaptic potentials. The propagation of activity by spatiotemporal synchronized waves enables RST to perform motion detection and localization in sequences of video images.

Lane Detection Based on Improved Canny Detector and Least Square Fitting

2013 ◽  
Vol 765-767 ◽  
pp. 2383-2387 ◽  
Author(s):  
Guang Hua Chen ◽  
Wen Zhou ◽  
Feng Jiao Wang ◽  
Bin Jie Xiao ◽  
Sun Fang Dai
Keyword(s):  
Least Square Method ◽  
Detection Algorithm ◽  
Lane Detection ◽  
Least Square ◽  
Edge Detector ◽  
Canny Edge Detector ◽  
Least Square Fitting ◽  
Video Images ◽  
Canny Edge ◽  
Single Pixel

The video images of road monitoring system contain noise, which blurs the difference between the lane and the background. The lane detection algorithm based on traditional Canny edge detector hardly detects the single-pixel lane accurately and it produces pseudo lane. The paper proposes an effective lane detection method based on improved Canny edge detector and least square fitting. The proposed method improves the dual-threshold selection of traditional Canny detector by using the histogram concavity analysis, which sets the optimal threshold automatically. The least square method is used to fit the feature points of detected edges to accurate and single-pixel wide lane. Experimental results show that the proposed method detects the lane of video images accurately in the noise environment.

scholarly journals Automatic Detection and Localization of Macular Edema

2020 ◽  
Vol 5 (9) ◽  
pp. 552-558
Author(s):  
S. Sumithra ◽  
K. R. Remya ◽  
Dr. M. N. Giri Prasad
Keyword(s):  
Macular Edema ◽  
Vision Loss ◽  
Automatic Detection ◽  
Detection Algorithm ◽  
Support Vector ◽  
Fisher Linear Discriminant ◽  
Linear Discriminant ◽  
The People ◽  
Simple Linear Iterative Clustering ◽  
Detection And Localization

Diabetic retinopathy is an eye disease and causes vision loss to the people who are suffering longer from the diabetes. Exudates, bright and red lesions are identified in the diabetic retinal eye. Automatic detection and localization of macular edema is a challenging issue since exudates have non uniform illumination and are low contrasted. Proposed algorithm to detect macular edema encompasses Simple Linear Iterative Clustering, Fisher linear discriminant and Support vector machine classifer. Optic Disc extraction prior to exudates extraction is also introduced. Performance of the proposed detection algorithm is tested on easily available databases: Diaretdb1, Messidor and E_optha Ex. Proposed method shows an accuracy of 97.81%, specificity 98.65 and Sensitivity 82.71%.

Sign in / Sign up

Export Citation Format

Share Document