LaTEX edits commit

term-paper/CDS1011_A2.bib

@@ -1,8 +1,44 @@
-@article{Student2022,
+
-   author={Student, A.},
+@misc{alagoz_comparative_2024,
-   title={My Title},
+	title = {Comparative Analysis of {XGBoost} and Minirocket Algortihms for Human Activity Recognition},
-   journal={My Journal},
+	url = {http://arxiv.org/abs/2402.18296},
-   volume={8},
+	doi = {10.48550/arXiv.2402.18296},
-   year=2022,
+	abstract = {Human Activity Recognition ({HAR}) has been extensively studied, with recent emphasis on the implementation of advanced Machine Learning ({ML}) and Deep Learning ({DL}) algorithms for accurate classification. This study investigates the efficacy of two {ML} algorithms, {eXtreme} Gradient Boosting ({XGBoost}) and {MiniRocket}, in the realm of {HAR} using data collected from smartphone sensors. The experiments are conducted on a dataset obtained from the {UCI} repository, comprising accelerometer and gyroscope signals captured from 30 volunteers performing various activities while wearing a smartphone. The dataset undergoes preprocessing, including noise filtering and feature extraction, before being utilized for training and testing the classifiers. Monte Carlo cross-validation is employed to evaluate the models' robustness. The findings reveal that both {XGBoost} and {MiniRocket} attain accuracy, F1 score, and {AUC} values as high as 0.99 in activity classification. {XGBoost} exhibits a slightly superior performance compared to {MiniRocket}. Notably, both algorithms surpass the performance of other {ML} and {DL} algorithms reported in the literature for {HAR} tasks. Additionally, the study compares the computational efficiency of the two algorithms, revealing {XGBoost}'s advantage in terms of training time. Furthermore, the performance of {MiniRocket}, which achieves accuracy and F1 values of 0.94, and an {AUC} value of 0.96 using raw data and utilizing only one channel from the sensors, highlights the potential of directly leveraging unprocessed signals. It also suggests potential advantages that could be gained by utilizing sensor fusion or channel fusion techniques. Overall, this research sheds light on the effectiveness and computational characteristics of {XGBoost} and {MiniRocket} in {HAR} tasks, providing insights for future studies in activity recognition using smartphone sensor data.},
-   pages={175-191}
+	number = {{arXiv}:2402.18296},
-}
+	publisher = {{arXiv}},
+	author = {Alagoz, Celal},
+	urldate = {2024-12-01},
+	date = {2024-02-28},
+	eprinttype = {arxiv},
+	eprint = {2402.18296},
+	keywords = {Computer Science - Machine Learning},
+	file = {Preprint PDF:/home/gra/Zotero/storage/97VIAYWV/Alagoz - 2024 - Comparative Analysis of XGBoost and Minirocket Algortihms for Human Activity Recognition.pdf:application/pdf;Snapshot:/home/gra/Zotero/storage/2ZJ5EAPN/2402.html:text/html},
+}
+
+@misc{sikder_human_2021,
+	title = {Human Activity Recognition Using Multichannel Convolutional Neural Network},
+	url = {http://arxiv.org/abs/2101.06709},
+	doi = {10.48550/arXiv.2101.06709},
+	abstract = {Human Activity Recognition ({HAR}) simply refers to the capacity of a machine to perceive human actions. {HAR} is a prominent application of advanced Machine Learning and Artificial Intelligence techniques that utilize computer vision to understand the semantic meanings of heterogeneous human actions. This paper describes a supervised learning method that can distinguish human actions based on data collected from practical human movements. The primary challenge while working with {HAR} is to overcome the difficulties that come with the cyclostationary nature of the activity signals. This study proposes a {HAR} classification model based on a two-channel Convolutional Neural Network ({CNN}) that makes use of the frequency and power features of the collected human action signals. The model was tested on the {UCI} {HAR} dataset, which resulted in a 95.25\% classification accuracy. This approach will help to conduct further researches on the recognition of human activities based on their biomedical signals.},
+	number = {{arXiv}:2101.06709},
+	publisher = {{arXiv}},
+	author = {Sikder, Niloy and Chowdhury, Md Sanaullah and Arif, Abu Shamim Mohammad and Nahid, Abdullah-Al},
+	urldate = {2024-12-01},
+	date = {2021-01-17},
+	eprinttype = {arxiv},
+	eprint = {2101.06709},
+	keywords = {Computer Science - Computer Vision and Pattern Recognition},
+	file = {Preprint PDF:/home/gra/Zotero/storage/3VLAWV6W/Sikder et al. - 2021 - Human Activity Recognition Using Multichannel Convolutional Neural Network.pdf:application/pdf;Snapshot:/home/gra/Zotero/storage/LU5MLRSL/2101.html:text/html},
+}
+
+@online{brownlee_gentle_2018,
+	title = {A Gentle Introduction to a Standard Human Activity Recognition Problem},
+	url = {https://www.machinelearningmastery.com/how-to-load-and-explore-a-standard-human-activity-recognition-problem/},
+	abstract = {Human activity recognition is the problem of classifying sequences of accelerometer data recorded by specialized harnesses or smart phones into known well-defined movements. It is a challenging problem given the large number of observations produced each second, the temporal nature of the observations, and the lack of a clear way to relate accelerometer data to […]},
+	titleaddon = {{MachineLearningMastery}.com},
+	author = {Brownlee, Jason},
+	urldate = {2024-12-01},
+	date = {2018-09-11},
+	langid = {american},
+	file = {Snapshot:/home/gra/Zotero/storage/RLC6J3IL/how-to-load-and-explore-a-standard-human-activity-recognition-problem.html:text/html},
+}

term-paper/CDS1011_A2.tex

@@ -29,12 +29,14 @@
 %-------------------------
 \input{title}
 
-\begin{multicols}{2}
+%\begin{multicols}{2}
 \input{introduction}
+\input{state_of_research}
 \input{research_questions_methodology}
 \input{results}
 \input{discussion}
-\end{multicols}
+\input{conclusion}
+%\end{multicols}
 
 %-------------------------
 % literature

term-paper/conclusion.tex

@@ -0,0 +1,7 @@
+%! Author = gra
+%! Date = 01.12.24
+
+% Preamble
+\section{Zusammenfassung}\label{sec:zusammenfassung}
+Wenn man die Accuracy erhöhen will, kann man auf bessere Technologien zurückgreifen, verweis auf State of the Art bzw.
+die Paper

term-paper/introduction.tex

@@ -3,4 +3,10 @@
 
 % Preamble
 \section{Einleitung}\label{sec: einleitung}
-\citeauthor{Student2022} führt aus Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua \cite{Student2022}.
+Moderne Smartwatches wie die Apple Watch erkennen, ob sich der Träger bewegt und schlägt ein Workout vor, dass es klassifiziert hat.\\
+Aber auch Wearables wie Kopfhörer sind in der Lage zu erkennen, ob der Träger aufsteht und anfängt zu laufen.\\
+Je nach Präferenz können die Kopfhörer dann z.B.\ den Noise canceling Mode verlassen.\\\\
+Nicht jede*r trägt eine Smartwatch oder ein anderes Wearable auf sich, die allermeisten führen auf aber ein Smartphone mit sich.\\
+Smartphones sind auch mit diversen Sensoren bestückt.\\
+Allerdings variiert die Anzahl, Qualität und Art der verbauten Sensoren stark zwischen den Herstellern und deren Modellen und Preisklassen.\\
+Daher stellt sich die Frage, ob die Daten für eine Vorhersage ausreichen.

term-paper/research_questions_methodology.tex

@@ -3,4 +3,6 @@
 
 % Preamble
 \section{Forschungsfragen und Methodik}\label{sec:forschungsfragen-und-methodik}
-Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.
+Die Forschungsfrage lautet, wie zuverlässig können Aktivitäten anhand von Smartphone Sensordaten erkannt werden können.
+
+Als Basis diente ein Basisdatensatz~\cite{sikder_human_2021}.

term-paper/state_of_research.tex

@@ -0,0 +1,5 @@
+%! Author = gra
+%! Date = 01.12.24
+
+% Preamble
+\section{Stand der Forschung}\label{sec: stand-der-forschung}