IEEE Transactions on Pattern Analysis and Machine Intelligence

This text is a survey on cross-validation We define all classical cross-validation procedures, and we study their properties for two different goals: estimating the risk of a given estimator, and selecting the best estimator among a given family For the risk estimation problem, we compute the bias (which can also be corrected) and the variance of cross-validation methods For estimator selection, we first provide a first-order analysis (based on expectations) Then, we explain how to take into account second-order terms (from variance computations, and by taking into account the usefulness of overpenalization) This allows, in the end, to provide some guidelines for choosing the best cross-validation method for a given learning problem

Cross-validation

There has been a growing interest in the field of neural networks for prediction in recent years. In this research, a public dataset including the sales history of a retail store is investigated to forecast the sales of furniture. To this aim, several forecasting models are applied. First, some classical time-series forecasting techniques such as Seasonal Autoregressive Integrated Moving Average (SARIMA) and Triple Exponential Smoothing are utilized. Then, more advanced methods such as Prophet, Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN) are applied. The performances of the models are compared using different accuracy measurement methods (e.g., Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE)). The results show the superiority of the Stacked LSTM method over the other methods. In addition, the results indicate the good performances of the Prophet and CNN models. 

Time-series forecasting of seasonal items sales using machine learning - A comparative analysis

This article addresses a new method for the classification of white blood cells (WBCs) using image processing techniques and machine learning methods. The proposed method consists of three steps: detecting the nucleus and cytoplasm, extracting features, and classification. At first, a new algorithm is designed to segment the nucleus. For the cytoplasm to be detected, only a part of it located inside the convex hull of the nucleus is involved in the process. This attitude helps us overcome the difficulties of segmenting the cytoplasm. In the second phase, three shapes and four novel color features are devised and extracted. Finally, by using an SVM model, the WBCs are classified. The segmentation algorithm can detect the nucleus with a dice similarity coefficient of 0.9675. The proposed method can categorize WBCs in Raabin-WBC, LISC, and BCCD datasets with accuracies of 94.65%, 92.21%, and 94.20%, respectively. Besides, we show that the proposed method possesses more generalization power than pre-trained CNN models. It is worth mentioning that the hyperparameters of the classifier are fixed only with the Raabin-WBC dataset, and these parameters are not readjusted for LISC and BCCD datasets.

/pdf/new-segmentation-and-feature-extraction-algorithm-for-rrlefh6lun.pdf

New segmentation and feature extraction algorithm for classification of white blood cells in peripheral smear images.

Parkinson’s disease (PD) is a neurodegenerative disease that affects the neural, behavioral, and physiological systems of the brain. This disease is also known as tremor. The common symptoms of this disease are a slowness of movement known as ‘bradykinesia’, loss of automatic movements, speech/writing changes, and difficulty with walking at early stages. To solve these issues and to enhance the diagnostic process of PD, machine learning (ML) algorithms have been implemented for the categorization of subjective disease and healthy controls (HC) with comparable medical appearances. To provide a far-reaching outline of data modalities and artificial intelligence techniques that have been utilized in the analysis and diagnosis of PD, we conducted a literature analysis of research papers published up until 2022. A total of 112 research papers were included in this study, with an examination of their targets, data sources and different types of datasets, ML algorithms, and associated outcomes. The results showed that ML approaches and new biomarkers have a lot of promise for being used in clinical decision-making, resulting in a more systematic and informed diagnosis of PD. In this study, some major challenges were addressed along with a future recommendation.

/pdf/imperative-role-of-machine-learning-algorithm-for-detection-274822vc.pdf

Imperative Role of Machine Learning Algorithm for Detection of Parkinson’s Disease: Review, Challenges and Recommendations

Parkinson’s disease is a neurological disorder that causes partial or complete loss of motor reflexes and speech and affects thinking, behavior, and other vital functions affecting the nervous system. Parkinson’s disease causes impaired speech and motor abilities (writing, balance, etc.) in about 90% of patients and is often seen in older people. Some signs (deterioration of vocal cords) in medical voice recordings from Parkinson’s patients are used to diagnose this disease. The database used in this study contains biomedical speech voice from 31 people of different age and sex related to this disease. The performance comparison of the machine learning algorithms k-Nearest Neighborhood (k-NN), Random Forest, Naive Bayes, and Support Vector Machine classifiers was performed with the used database. Moreover, the best classifier was determined for the diagnosis of Parkinson’s disease. Eleven different training and test data (45 × 55, 50 × 50, 55 × 45, 60 × 40, 65 × 35, 70 × 30, 75 × 25, 80 × 20, 85 × 15, 90 × 10, 95 × 5) were processed separately. The data obtained from these training and tests were compared with statistical measurements. The training results of the k-NN classification algorithm were generally 100% successful. The best test result was obtained from Random Forest classifier with 85.81%. All statistical results and measured values are given in detail in the experimental studies section. Graphical abstract

Evaluation of train and test performance of machine learning algorithms and Parkinson diagnosis with statistical measurements

Learn from one data set to classify all - A multi-target domain adaptation approach for white blood cell classification.

Blood and its components have an important place in human life and are the best indicator tool in determining many pathological conditions. In particular, the classification of white blood cells is of great importance for the diagnosis of hematological diseases. In this study, 350 microscopic blood smear images were tested with 6 different machine learning algorithms for the classification of white blood cells and their performances were compared. 35 different geometric and statistical (texture) features have been extracted from blood images for training and test parameters of machine learning algorithms. According to the results, the Multinomial Logistic Regression (MLR) algorithm performed better than the other methods with an average 95% test success. The MLR can be used for automatic classification of white blood cells. It can be used especially as a source for diagnosis of diseases for hematologists and internal medicine specialists.

/pdf/classifying-white-blood-cells-using-machine-learning-3zf432csfc.pdf

Abdullah Elen

Papers

Evaluation of train and test performance of machine learning algorithms and Parkinson diagnosis with statistical measurements

Learn from one data set to classify all - A multi-target domain adaptation approach for white blood cell classification.

Classifying White Blood Cells Using Machine Learning Algorithms

Standardized Variable Distances: A distance-based machine learning method

A new approach for fully automated segmentation of peripheral blood smears