refs.bib

@misc{br35h,
	author = {Ahmed Hamada},
	title = {Br35H :: Brain Tumor Detection 2020},
	howpublished = {Kaggle},
	year = {2020},
	url = {https://www.kaggle.com/datasets/ahmedhamada0/brain-tumor-detection},
}

@misc{huggingface_data,
	author = {PranomVignesh},
	title = {MRI-Images-of-Brain-Tumor},
	howpublished = {Huggingface},
	year = {2023},
	url = {https://huggingface.co/datasets/PranomVignesh/MRI-Images-of-Brain-Tumor},
}


@misc{wong2020yolo7,
	author = {Kin-Yiu Wong},
	title = {Yolov7.yaml},
	howpublished = {GitHub},
	year = {2020},
	url = { \url{
	       https://github.com/WongKinYiu/yolov7/blob/main/cfg/training/yolov7.yaml
	       } },
	note = { \url{
	        https://github.com/WongKinYiu/yolov7/blob/main/cfg/training/yolov7.yaml
	        } },
}

@article{jocher2022yolo5,
	author = {Glenn Jocher},
	title = {YOLOv5 (6.0/6.1) brief summary},
	howpublished = {GitHub},
	year = {2022},
	url = {\url{https://github.com/ultralytics/yolov5/issues/6998}},
}

@incollection{Kang2023,
	doi = {10.1007/978-3-031-43901-8_57},
	url = {\url{https://doi.org/10.1007%2F978-3-031-43901-8_57}},
	year = 2023,
	publisher = {Springer Nature Switzerland},
	pages = {600--610},
	author = {Ming Kang and Chee-Ming Ting and Fung Fung Ting and Raphaël C.-W.
	          Phan},
	title = {{RCS}-{YOLO}: A Fast and~High-Accuracy Object Detector for~Brain
	         Tumor Detection},
	booktitle = {Lecture Notes in Computer Science},
}

@misc{kang2023bgfyolo,
	title = {BGF-YOLO: Enhanced YOLOv8 with Multiscale Attentional Feature
	         Fusion for Brain Tumor Detection},
	author = {Ming Kang and Chee-Ming Ting and Fung Fung Ting and Raphaël C. -W.
	          Phan},
	year = {2023},
	eprint = {2309.12585},
	archivePrefix = {arXiv},
	primaryClass = {cs.CV},
}

@misc{ding2021repvgg,
	title = {RepVGG: Making VGG-style ConvNets Great Again},
	author = {Xiaohan Ding and Xiangyu Zhang and Ningning Ma and Jungong Han and
	          Guiguang Ding and Jian Sun},
	year = {2021},
	eprint = {2101.03697},
	archivePrefix = {arXiv},
	primaryClass = {cs.CV},
}

@misc{iandola2014densenet,
	title = {DenseNet: Implementing Efficient ConvNet Descriptor Pyramids},
	author = {Forrest Iandola and Matt Moskewicz and Sergey Karayev and Ross
	          Girshick and Trevor Darrell and Kurt Keutzer},
	year = {2014},
	eprint = {1404.1869},
	archivePrefix = {arXiv},
	primaryClass = {cs.CV},
}



@book{rowling1997,
  author    = {J.K. Rowling},
  title     = {Harry Potter and the Philosopher's Stone},
  year      = {1997},
  publisher = {Bloomsbury},
}

@misc{horcrux_fandom,
  author       = {Harry Potter Wiki},
  title        = {Horcrux},
  year         = {1945},
  url          = {https://harrypotter.fandom.com/wiki/Horcrux},
  note         = {Accessed: 1945-06-01}
}

@misc{kaggle,
  title        = {Kaggle},
  year         = {1945},
  url          = {https://harrypotter.fandom.com/wiki/Horcrux},
  note         = {Accessed: 1945-06-01}
}

@ARTICLE{ma82,
  author={Ma, Chao and Luo, Gongning and Wang, Kuanquan},
  journal={IEEE Transactions on Medical Imaging}, 
  title={Concatenated and Connected Random Forests With Multiscale Patch Driven Active Contour Model for Automated Brain Tumor Segmentation of MR Images}, 
  year={2018},
  volume={37},
  number={8},
  pages={1943-1954},
  keywords={Image segmentation;Tumors;Brain modeling;Magnetic resonance imaging;Active contours;Radio frequency;Task analysis;Magenetic resonance imaging;brain tumor;brain tumor segmentation;random forests;active contour model;multiscale patch},
  doi={10.1109/TMI.2018.2805821}}





@article{dattaad:10.1504,
author = {Beddad, Boucif and Hachemi, Kaddour and Vaidyanathan, Sundarapandian},
title = {Design and implementation of a new cooperative approach to brain tumour identification from MRI images},
journal = {International Journal of Computer Applications in Technology},
volume = {59},
number = {1},
pages = {1-10},
year = {2019},
doi = {10.1504/IJCAT.2019.097113},

URL = { 
        https://www.inderscienceonline.com/doi/abs/10.1504/IJCAT.2019.097113

},
eprint = { 
    
        https://www.inderscienceonline.com/doi/pdf/10.1504/IJCAT.2019.097113

}
,
    abstract = { Magnetic resonance imaging has become a vital component of a large number of biomedical applications and also plays a major role in medical diagnostics. In this research work, the main purpose is to carry out a new cooperative approach to brain tumour detection and identification from MRI images with good segmentation accuracy. The proposed system applies K-means algorithm to optimise the initial centroids of the improved fuzzy C-means which incorporates the spatial information and also to get a better estimation of their final cluster centres. Then the obtained results are considered as an initialisation of the active contour for level sets technique. The proposed segmentation algorithm and its improvement were well implemented practically in real-time using a floating-point TMS320C6713 DSP of Texas Instruments. Performance improvement is measured by including various optimisation techniques, and all profiling and debugging results are shown using C6713 graphical user interface. }
}

@ARTICLE{masood900,
  author={Masood, Anum and Sheng, Bin and Yang, Po and Li, Ping and Li, Huating and Kim, Jinman and Feng, David Dagan},
  journal={IEEE Transactions on Industrial Informatics}, 
  title={Automated Decision Support System for Lung Cancer Detection and Classification via Enhanced RFCN With Multilayer Fusion RPN}, 
  year={2020},
  volume={16},
  number={12},
  pages={7791-7801},
  abstract={Detection of lung cancer at early stages is critical, in most of the cases radiologists read computed tomography (CT) images to prescribe follow-up treatment. The conventional method for detecting nodule presence in CT images is tedious. In this article, we propose an enhanced multidimensional region-based fully convolutional network (mRFCN) based automated decision support system for lung nodule detection and classification. The mRFCN is used as an image classifier backbone for feature extraction along with the novel multilayer fusion region proposal network (mLRPN) with position-sensitive score maps being explored. We applied a median intensity projection to leverage three-dimensional information from CT scans and introduced deconvolutional layer to adopt proposed mLRPN in our architecture to automatically select the potential region of interest. Our system has been trained and evaluated using LIDC dataset, and the experimental results showed promising detection performance in comparison to the state-of-the-art nodule detection/classification methods, achieving a sensitivity of 98.1% and classification accuracy of 97.91%.},
  keywords={Cancer;Lung;Computed tomography;Feature extraction;Training;Proposals;Informatics;Computer-aided systems;convolutional neural network (CNN);lung cancer;nodule classification},
  doi={10.1109/TII.2020.2972918},
  ISSN={1941-0050},
  month={Dec},}



@article{XIA20-15,
title = {A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring},
journal = {Expert Systems with Applications},
volume = {78},
pages = {225-241},
year = {2017},
issn = {0957-4174},
doi = {https://doi.org/10.1016/j.eswa.2017.02.017},
url = {https://www.sciencedirect.com/science/article/pii/S0957417417301008},
author = {Yufei Xia and Chuanzhe Liu and YuYing Li and Nana Liu},
keywords = {Credit scoring, Boosted decision tree, Bayesian hyper-parameter optimization},
abstract = {Credit scoring is an effective tool for banks to properly guide decision profitably on granting loans. Ensemble methods, which according to their structures can be divided into parallel and sequential ensembles, have been recently developed in the credit scoring domain. These methods have proven their superiority in discriminating borrowers accurately. However, among the ensemble models, little consideration has been provided to the following: (1) highlighting the hyper-parameter tuning of base learner despite being critical to well-performed ensemble models; (2) building sequential models (i.e., boosting, as most have focused on developing the same or different algorithms in parallel); and (3) focusing on the comprehensibility of models. This paper aims to propose a sequential ensemble credit scoring model based on a variant of gradient boosting machine (i.e., extreme gradient boosting (XGBoost)). The model mainly comprises three steps. First, data pre-processing is employed to scale the data and handle missing values. Second, a model-based feature selection system based on the relative feature importance scores is utilized to remove redundant variables. Third, the hyper-parameters of XGBoost are adaptively tuned with Bayesian hyper-parameter optimization and used to train the model with selected feature subset. Several hyper-parameter optimization methods and baseline classifiers are considered as reference points in the experiment. Results demonstrate that Bayesian hyper-parameter optimization performs better than random search, grid search, and manual search. Moreover, the proposed model outperforms baseline models on average over four evaluation measures: accuracy, error rate, the area under the curve (AUC) H measure (AUC-H measure), and Brier score. The proposed model also provides feature importance scores and decision chart, which enhance the interpretability of credit scoring model.}
}


@INPROCEEDINGS{munppy89-16,
  author={Munappy, Aiswarya and Bosch, Jan and Olsson, Helena Holmström and Arpteg, Anders and Brinne, Björn},
  booktitle={2019 45th Euromicro Conference on Software Engineering and Advanced Applications (SEAA)}, 
  title={Data Management Challenges for Deep Learning}, 
  year={2019},
  volume={},
  number={},
  pages={140-147},
  abstract={Deep learning is one of the most exciting and fast-growing techniques in Artificial Intelligence. The unique capacity of deep learning models to automatically learn patterns from the data differentiates it from other machine learning techniques. Deep learning is responsible for a significant number of recent breakthroughs in AI. However, deep learning models are highly dependent on the underlying data. So, consistency, accuracy, and completeness of data is essential for a deep learning model. Thus, data management principles and practices need to be adopted throughout the development process of deep learning models. The objective of this study is to identify and categorise data management challenges faced by practitioners in different stages of end-to-end development. In this paper, a case study approach is employed to explore the data management issues faced by practitioners across various domains when they use real-world data for training and deploying deep learning models. Our case study is intended to provide valuable insights to the deep learning community as well as for data scientists to guide discussion and future research in applied deep learning with real-world data.},
  keywords={Deep learning;Data models;Interviews;Wind power generation;Pipelines;Companies;Deep learning;Data Management;Machine Learning;Artificial Intelligence;Deep Neural Networks},
  doi={10.1109/SEAA.2019.00030},
  ISSN={},
  month={Aug},}


@article{ABDELMAKSOUD201571-51,
title = {Brain tumor segmentation based on a hybrid clustering technique},
journal = {Egyptian Informatics Journal},
volume = {16},
number = {1},
pages = {71-81},
year = {2015},
issn = {1110-8665},
doi = {https://doi.org/10.1016/j.eij.2015.01.003},
url = {https://www.sciencedirect.com/science/article/pii/S1110866515000043},
author = {Eman Abdel-Maksoud and Mohammed Elmogy and Rashid Al-Awadi},
keywords = {Medical image segmentation, Brain tumor segmentation, K-means clustering, Fuzzy C-means, Expectation Maximization},
abstract = {Image segmentation refers to the process of partitioning an image into mutually exclusive regions. It can be considered as the most essential and crucial process for facilitating the delineation, characterization, and visualization of regions of interest in any medical image. Despite intensive research, segmentation remains a challenging problem due to the diverse image content, cluttered objects, occlusion, image noise, non-uniform object texture, and other factors. There are many algorithms and techniques available for image segmentation but still there needs to develop an efficient, fast technique of medical image segmentation. This paper presents an efficient image segmentation approach using K-means clustering technique integrated with Fuzzy C-means algorithm. It is followed by thresholding and level set segmentation stages to provide an accurate brain tumor detection. The proposed technique can get benefits of the K-means clustering for image segmentation in the aspects of minimal computation time. In addition, it can get advantages of the Fuzzy C-means in the aspects of accuracy. The performance of the proposed image segmentation approach was evaluated by comparing it with some state of the art segmentation algorithms in case of accuracy, processing time, and performance. The accuracy was evaluated by comparing the results with the ground truth of each processed image. The experimental results clarify the effectiveness of our proposed approach to deal with a higher number of segmentation problems via improving the segmentation quality and accuracy in minimal execution time.}
}

@ARTICLE{chen791-53,
  author={Chen, Min and Hao, Yixue and Hwang, Kai and Wang, Lu and Wang, Lin},
  journal={IEEE Access}, 
  title={Disease Prediction by Machine Learning Over Big Data From Healthcare Communities}, 
  year={2017},
  volume={5},
  number={},
  pages={8869-8879},
  abstract={With big data growth in biomedical and healthcare communities, accurate analysis of medical data benefits early disease detection, patient care, and community services. However, the analysis accuracy is reduced when the quality of medical data is incomplete. Moreover, different regions exhibit unique characteristics of certain regional diseases, which may weaken the prediction of disease outbreaks. In this paper, we streamline machine learning algorithms for effective prediction of chronic disease outbreak in disease-frequent communities. We experiment the modified prediction models over real-life hospital data collected from central China in 2013-2015. To overcome the difficulty of incomplete data, we use a latent factor model to reconstruct the missing data. We experiment on a regional chronic disease of cerebral infarction. We propose a new convolutional neural network (CNN)-based multimodal disease risk prediction algorithm using structured and unstructured data from hospital. To the best of our knowledge, none of the existing work focused on both data types in the area of medical big data analytics. Compared with several typical prediction algorithms, the prediction accuracy of our proposed algorithm reaches 94.8% with a convergence speed, which is faster than that of the CNN-based unimodal disease risk prediction algorithm.},
  keywords={Diseases;Hospitals;Prediction algorithms;Machine learning algorithms;Big Data;Data models;Big data analytics;machine learning;healthcare},
  doi={10.1109/ACCESS.2017.2694446},
  ISSN={2169-3536},
  month={},}

@book{mohapatra-54,
author = {Mohapatra, Hitesh and Rath, Amiya},
year = {2020},
month = {01},
pages = {},
title = {Fundamentals of Software Engineering: Designed to provide an insight into the software engineering concepts},
isbn = {9388511778, 9789388511773}
}