237 research outputs found
Machine Learning in Aquaculture - Hunger Classification of Lates calcarifer
No full textThis book highlights the fundamental association between aquaculture and engineering in classifying fish hunger behaviour by means of machine learning techniques. Understanding the underlying factors that affect fish growth is essential, since they have implications for higher productivity in fish farms. Computer vision and machine learning techniques make it possible to quantify the subjective perception of hunger behaviour and so allow food to be provided as necessary. The book analyses the conceptual framework of motion tracking, feeding schedule and prediction classifiers in order to classify the hunger state, and proposes a system comprising an automated feeder system, image-processing module, as well as machine learning classifiers. Furthermore, the system substitutes conventional, complex modelling techniques with a robust, artificial intelligence approach. The findings presented are of interest to researchers, fish farmers, and aquaculture technologist wanting to gain insights into the productivity of fish and fish behaviou
The effectiveness of tablet-based application as a medium of feedback in performance analysis during a competitive match in elite soccer
No full textThis study aims to examine the effectiveness of Tablet based application
(TBA) as a medium for feedback in real time at a half-time interval of a
competitive match in improving the performance of soccer players.
StatWatch application was installed on a tablet phone and used as a device
for data collection. Eleven performance analysts were recruited to assist in
the data collection such that each performance analysts covered a particular
player during the game. Players Performances were assessed based on
clearing, crossing, dribbling, heading, pursuing the loose ball, shooting, foul,
and through pass. Data were collected as the game progressed, and
information was transmitted to the controller of the analysis before being
relayed to the chief coach at the half time interval of every match. Matches
of the club for eight weeks were analysed. One-way repeated measure
ANOVA was used to assess the progress of the team in between the first and
second halves of the matches played. The result shows improvement on the
performances of the club at the second halves of the eight matches played (F
(1, 14.10) = 8.94, p < .05). A follow-up test demonstrates a significant
progress on the overall team performance from week1 to week 8, p > 0.001.
TBA appeared to be a useful medium for providing feedback at a first half
interval of a competitive match to improving the performance of soccer
players during the subsequent period
Monitoring and feeding integration of demand feeder systems
No full textThis chapter highlights the findings of the developmental monitoring systems for swimming pattern or motion analysis with regard to feeding behaviour. A benchmark for examining the framework on how scientists control fish in animal variable function factors was gathered and referred to gauge the adequate design in constructing a viable device. The validation of image processing and automated demand feeder to determine the results will also be considered, as a validation aspect between the system of tracking and the behaviour of the Lates calcarifer where the pixel intensity will be extracted as the features. The results of this chapter will enable the reader on the development of an integrated feeder scheme that consolidates surveillance scheme to identify the feeding behaviour and relation towards the specific growth rate (SGR)
Image processing features extraction on fish behaviour
No full textThis chapter demonstrates the pipeline fromdata collection until classifier
2 models that achieve the best possible model in identifying the disparity between
3 hunger states. The pre-processing segment describes the features of the data sets
4 obtained by means of image processing. The method includes the simple moving
5 average (SMA), downsizing factors, dynamic timewarping (DTW) and clustering by
6 the k-meansmethod. This is to rationally assign the necessary significant information
7 from the data collected and processed the images captured for demand feeder and
8 fish motion as a synthesis for anticipating the state of fish starvation. The selection of
9 features in this study takes place via the boxplot analysis and the principal component
10 analysis (PCA) on dimensionality reduction. Finally, the validation of the hunger
11 state will be addressed by comparing machine learning (ML) classifiers, namely the
12 discriminant analysis (DA), support vector machine (SVM) and k-nearest neighbour
13 (k-NN). The outcome in this chapter will validate the features fromimage processing
14 as a tool for identifying the behavioural changes of the fish in school size
Hyperparameter tuning of the model for hunger state classification
No full textTo increase the classification, the rate of prediction based on existing models requires additional technique or in this case optimizing the model. Hyperparameter tuning is an optimization technique that evaluates and adjusts the free parameters that define the behaviour of classifiers. Data sets were classified practical with classifiers like SVM, k-NN, ANN and DA. To further improve the design efficiency, the secondary optimization level called hyperparameter tuning will be further investigated. DA, SVM, k-NN, decision tree (Tree), logistic regression (LR), random forest tree (RF) and neural network (NN) are evaluated. The k-NN provided 96.47% of the test sets with the best reliability in classifications. Bayesian optimization has been used to refine the hyperparameter; hence, standardize Euclidean distance metric with a k value of one is the ideal hyperparameters which could achieve classification performance of 97.16%
An Open Trial Targeting Weight-Related Psychological Difficulties Among Young Adults with Overweight or Obesity During COVID-19 Lockdown
No full textWeight-related psychological difficulties (WRD) are associated with overweight and obesity including among young adults. We developed a program called ACT-EX (Acceptance and Commitment Therapy with Exercise), which incorporates six processes to increase weight-related psychological flexibility: acceptance, cognitive defusion, being present, self-as-context, values, and committed action for young adults who are overweight or obese (OW/OB). This open trial evaluated the feasibility, acceptability, and efficacy of the ACT-EX program. Fifty young adults who were OW/OB (78% female, 22% male; mean age = 21.32 years (SD = 1.2); Body Mass Index (BMI) = 30.01 kg/m2 (SD = 4.63); 36% Malay; 28% Bumiputera Sarawak; 20% Chinese; and Bumiputera Sabah and Indians, 4% each) participated in a 6-week intervention and 6-week follow-up study. The WRD was measured by the Acceptance and
Assessment of Wellness Status Among a Multi-Ethnic Based Adult Sample
No full textWellness is an encompassing canopy harnessing multiple of activities aimed at helping individuals recognize components of lifestyle that are detrimental to health. However, the challenge still remains that most individuals seldom identify and practice positive health behaviors that can enhance fitness and wellness. Objectives: As a starting point, the present study assessed the wellness status of a multi-ethnic based adult population in Lagos, Nigeria. Methods: The wellness lifestyle Questionnaire (WLQ), which provides an initial rating of the individual’s current efforts to stay healthy and assessed six major areas, namely: emotional health, fitness and body care, environmental health, stress, nutrition and medical self-responsibility was used as the instrument for data collection. Eight hundred and thirty-eight males, as well as one thousand four hundred and sixty-two females' adults, were purposely recruited for this study. Results: It was obvious from the data collected that 61.03% of the population sampled needs improvement on their health status while only 8.04% had excellent health and wellness status with just 30.93% of the population in a good health condition. Conclusion: Providing health and wellness education by fitness experts, therefore, becomes inevitable and a challenge for health and wellness experts
New Technology in Modern Dikir Barat: Consideration of Acceptance and Development in The Kelantan Community
No full textInjury prevalence, types and mechanisms in football: A media-based approach
No full textThe increase in demand for football players to perform at their best during training and competition results in the
escalation of a varying number of football-related injuries. Media reports provide readily as well as timely information
on injury-related issues that could assist the stakeholders in decision making before and after a competition. Although,
many attempts have been made to quantify football-related injuries in many countries via media, however, little is
known on its prevalence, types and mechanisms as reported in Nigerian media. The present study employed a content
analysis technique through which 94 football-related news articles from Nigerian newspapers were examined and the
most frequently reported injuries are identified. It is demonstrated from the chi-square analysis that the occurrences of
football-related injuries are distributed amongst players regardless of their positional role in the game [χ2(60) = 41.401;
p>0.05]. Moreover, the prevalence in the mechanisms of injuries are disseminated across injury types [χ2(30) = 32.203;
p>0.05]. A total of 94 different injuries are reported with knee, ankle, and thigh as the most affected locations. The findings
further revealed that strikers have a higher rate of injury occurrences with a total of 52% as compared to midfielders 20%,
defenders 14%, and goalkeepers 12% whilst 2% are unidentified. Many of the injuries reported are either fresh 48% or
recurrent 50% with only 2% recovery. The present findings could be useful to stakeholders in projecting injury-related
problems in football which could guide appropriate action
- …
