Is Fidgety Philip's ground truth also ours? The creation and application of a machine learning algorithm

Beyzaei, N.; Bao, Stephen; Bu, Y.; Hung, Linus; Hussaina, H.; Maher, Khaola Safia; Chan, Ming-Cheng; Garn, Heinrich; Kloesch, Gerhard; Kohn, Bernhard; Kuzeljevic, Boris; McWilliams, S.; Spruyt, Karen; Tse, E.; Kuo, Calvin; Ipsiroglu, O.

doi:10.1016/j.jpsychires.2020.08.033

Cited by 4 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Seitens der Arbeitsgruppe Pädiatrie der DGSM wird im Verbund mit den Österreichischen Gesellschaften für Schlafmedizin, Kinder- und Jugendheilkunde und Kinder- und Jugendpsychiatrie, Psychosomatik und Psychotherapie dringend darauf aufmerksam gemacht, dass man differentialdiagnostisch an Schlafstörungen im Allgemeinen und an Restless-Legs-Syndrom (RLS) im Besonderen denken sollte [ 34 – 36 ]. Explorierende Anamnese, strukturierte klinische Beobachtungen sowie eventuell die Auswertung von Videos tragen dazu bei, die Diagnose auch bei Kindern mit entwicklungsneurologischen Auffälligkeiten beschreibend zu stellen [ 34 , 37 , 38 ]. Da sich die pädiatrische Schlafmedizin an der Schnittstelle zwischen Vorsorgemedizin (Public Health), Versorgungsmedizin (im niedergelassenen Bereich) und klinischen Spezialdisziplinen (z.…”

Section: Ergebnisse Und Schwerpunkte Der Letzten 5 Jahreunclassified

Aktuelle Entwicklungen in der Schlafforschung und Schlafmedizin – eine Einschätzung der AG „Pädiatrie“

Paditz¹,

Wiater

Ipsiroglu

et al. 2022

Somnologie

View full text Add to dashboard Cite

Section: Ergebnisse Und Schwerpunkte Der Letzten 5 Jahreunclassified

Aktuelle Entwicklungen in der Schlafforschung und Schlafmedizin – eine Einschätzung der AG „Pädiatrie“

Paditz¹,

Wiater

Ipsiroglu

et al. 2022

Somnologie

View full text Add to dashboard Cite

“…We used interviews and observations and expanded educational and medical perspectives with therapeutic emplotment, a methodology from medical anthropology. This research builds on our previous work integrating narratives in clinical history-taking (68) and structured behavioral observations (21,50,69,70), and on similar studies that have been undertaken in other clinical populations (71)(72)(73)(74)(75). Using such a concept (50) was useful for understanding how CDBs may be interpreted and how observable symptoms of physical activity and sleep (e.g., length, disruptions) may affect CDBs.…”

Section: Strengths and Limitationsmentioning

confidence: 99%

Disruptive Behaviors and Intellectual Disability: Creating a New Script

et al. 2022

Self Cite

View full text Add to dashboard Cite

BackgroundTerms currently used to describe the so-called challenging and disruptive behaviors (CBDs) of children with intellectual disabilities (ID) have different connotations depending on guiding contextual frameworks, such as academic and cultural settings in which they are used. A non-judgmental approach, which does not attempt to establish existing categorical diagnoses, but which describes in a neutral way, is missing in the literature. Therefore, we tried to describe CDBs in youth with ID in an explorative study.MethodsInterviews with families investigated the CDBs of five youth with Down syndrome. At home, families tracked youth's sleep/wake behaviors and physical activity. Youth were observed in a summer school classroom. The collected information and suggested explanatory models for observed CDBs were reviewed with the families.ResultsWe grouped CDBs as challenging, if they were considered to be reactive or triggered, or unspecified, if no such explanatory model was available. A third category was created for light-hearted CDBs: goofy, acknowledging the right to laugh together with peers. We found some relationships between sleep, physical activity, and CDBs and developed an explorative approach, supporting a child-centered perspective on CDBs.ConclusionThe controversial discussions on terminology and management of CDBs in the literature demonstrate the need for a non-judgmental approach. Such an explorative approach, allowing non-professionals to not label, has been missing. The fact that, up to now, the light-hearted behaviors of an individual with ID have not been integrated in commonly-used behavioral checklists as their natural right, proves our concept and indicates that a paradigm change from judgment-based to exploratory-driven approaches is needed.

show abstract

“…Machine learning algorithms give computers the ability to learn a decision model from known data and use the model to guide decisions on new data [1][2][3]. Unlike expert systems, machine learning algorithms can avoid consuming a lot of manual effort to summarize tedious decision laws and thus are widely used in various real-world scenarios, such as image recognition and natural language understanding [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Performance Optimization of Machine Learning Algorithms Based on Spark

Luo,

Zhang,

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This paper proposes a performance optimization strategy for Spark-based machine learning algorithms in Shuffle and memory data management modules. The Shuffle module is optimized by introducing Observer monitoring module in Spark cluster to achieve task status monitoring and dynamic ShuffleWrite task generation. Meanwhile, an adaptive caching mechanism for RDD data addresses the lack of in-memory data caching. The performance-optimized algorithm performs well in the experiments, with a clustering accuracy of 89% and a response time that is 5% faster than the Random Forest algorithm. In road network traffic state discrimination, the optimized algorithm’s classification decision F-measure value is as high as 99.53%, which is 5.32% higher than that before unoptimization, and the running time is 767 seconds less than that of the unoptimized algorithm when dealing with about 6,880,000 pieces of data, which significantly improves the efficiency and accuracy.

show abstract

Is Fidgety Philip's ground truth also ours? The creation and application of a machine learning algorithm

Cited by 4 publications

References 20 publications

Aktuelle Entwicklungen in der Schlafforschung und Schlafmedizin – eine Einschätzung der AG „Pädiatrie“

Aktuelle Entwicklungen in der Schlafforschung und Schlafmedizin – eine Einschätzung der AG „Pädiatrie“

Disruptive Behaviors and Intellectual Disability: Creating a New Script

Performance Optimization of Machine Learning Algorithms Based on Spark

Contact Info

Product

Resources

About