More Like this

1. Deep Learning and Machine Learning Techniques to Classify Electrical and Electronic Equipment

   https://doi.org/10.1115/DETC2021-71403  

   Hu, Shuaizhou ; Zhang, Xinyao ; Liao, Hao-yu ; Liang, Xiao ; Zheng, Minghui ; Behdad, Sara ( August 2021 , Proceedings of the ASME 2021 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference)

   Remanufacturing sites often receive products with different brands, models, conditions, and quality levels. Proper sorting and classification of the waste stream is a primary step in efficiently recovering and handling used products. The correct classification is particularly crucial in future electronic waste (e-waste) management sites equipped with Artificial Intelligence (AI) and robotic technologies. Robots should be enabled with proper algorithms to recognize and classify products with different features and prepare them for assembly and disassembly tasks. In this study, two categories of Machine Learning (ML) and Deep Learning (DL) techniques are used to classify consumer electronics. ML models include Naïve Bayes with Bernoulli, Gaussian, Multinomial distributions, and Support Vector Machine (SVM) algorithms with four kernels of Linear, Radial Basis Function (RBF), Polynomial, and Sigmoid. While DL models include VGG-16, GoogLeNet, Inception-v3, Inception-v4, and ResNet-50. The above-mentioned models are used to classify three laptop brands, including Apple, HP, and ThinkPad. First the Edge Histogram Descriptor (EHD) and Scale Invariant Feature Transform (SIFT) are used to extract features as inputs to ML models for classification. DL models use laptop images without pre-processing on feature extraction. The trained models are slightly overfitting due to the limited dataset and complexity of model parameters. Despite slight overfitting, the models can identify each brand. The findings prove that DL models outperform them of ML. Among DL models, GoogLeNet has the highest performance in identifying the laptop brands.

    

   more » « less
2. A reliable diabetic retinopathy grading via transfer learning and ensemble learning with quadratic weighted kappa metric

   https://doi.org/10.1186/s12911-024-02446-x  

   Chilukoti, Sai Venkatesh ; Shan, Liqun ; Tida, Vijay Srinivas ; Maida, Anthony S. ; Hei, Xiali ( February 2024 , BMC Medical Informatics and Decision Making)

   The most common eye infection in people with diabetes is diabetic retinopathy (DR). It might cause blurred vision or even total blindness. Therefore, it is essential to promote early detection to prevent or alleviate the impact of DR. However, due to the possibility that symptoms may not be noticeable in the early stages of DR, it is difficult for doctors to identify them. Therefore, numerous predictive models based on machine learning (ML) and deep learning (DL) have been developed to determine all stages of DR. However, existing DR classification models cannot classify every DR stage or use a computationally heavy approach. Common metrics such as accuracy, F1 score, precision, recall, and AUC-ROC score are not reliable for assessing DR grading. This is because they do not account for two key factors: the severity of the discrepancy between the assigned and predicted grades and the ordered nature of the DR grading scale. 

   This research proposes computationally efficient ensemble methods for the classification of DR. These methods leverage pre-trained model weights, reducing training time and resource requirements. In addition, data augmentation techniques are used to address data limitations, improve features, and improve generalization. This combination offers a promising approach for accurate and robust DR grading. In particular, we take advantage of transfer learning using models trained on DR data and employ CLAHE for image enhancement and Gaussian blur for noise reduction. We propose a three-layer classifier that incorporates dropout and ReLU activation. This design aims to minimize overfitting while effectively extracting features and assigning DR grades. We prioritize the Quadratic Weighted Kappa (QWK) metric due to its sensitivity to label discrepancies, which is crucial for an accurate diagnosis of DR. This combined approach achieves state-of-the-art QWK scores (0.901, 0.967 and 0.944) in the Eyepacs, Aptos, and Messidor datasets.

    

   more » « less
3. Differentiation between atypical anorexia nervosa and anorexia nervosa using machine learning

   https://doi.org/10.1002/eat.24160  

   Sandoval‐Araujo, Luis E. ; Cusack, Claire E. ; Ralph‐Nearman, Christina ; Glatt, Sofie ; Han, Yuchen ; Bryan, Jeffrey ; Hooper, Madison A. ; Karem, Andrew ; Levinson, Cheri A. ( February 2024 , International Journal of Eating Disorders)

   Body mass index (BMI) is the primary criterion differentiating anorexia nervosa (AN) and atypical anorexia nervosa despite prior literature indicating few differences between disorders. Machine learning (ML) classification provides us an efficient means of accurately distinguishing between twomeaningfulclasses given any number of features. The aim of the present study was to determine if ML algorithms can accurately distinguish AN and atypical AN given an ensemble of features excluding BMI, and if not, if the inclusion of BMI enables ML to accurately classify between the two.

   Using an aggregate sample from seven studies consisting of individuals with AN and atypical AN who completed baseline questionnaires (N = 448), we used logistic regression, decision tree, and random forest ML classification models each trained on two datasets, one containing demographic, eating disorder, and comorbid features without BMI, and one retaining all features and BMI.

   Model performance for all algorithms trained with BMI as a feature was deemed acceptable (mean accuracy = 74.98%, mean area under the receiving operating characteristics curve [AUC] = 74.75%), whereas model performance diminished without BMI (mean accuracy = 59.37%, mean AUC = 59.98%).

   Model performance was acceptable, but not strong, if BMI was included as a feature; no other features meaningfully improved classification. When BMI was excluded, ML algorithms performed poorly at classifying cases of AN and atypical AN when considering other demographic and clinical characteristics. Results suggest a reconceptualization of atypical AN should be considered.

   There is a growing debate about the differences between anorexia nervosa and atypical anorexia nervosa as their diagnostic differentiation relies on BMI despite being similar otherwise. We aimed to see if machine learning could distinguish between the two disorders and found accurate classification only if BMI was used as a feature. This finding calls into question the need to differentiate between the two disorders.

    

   more » « less
4. An Ensemble-Based Machine Learning for Predicting Fraud of Credit Card Transactions

   https://doi.org/10.1007/978-3-031-10464-0_14  

   Baabdullah, T. ; Rawat, D. ; Liu, C. ; Alzahrani, A. ( January 2022 , Proceedings of 2022 Computing Conference, Lecture Notes in Networks and Systems)

   Recently, using credit cards has been considered one of the essential things of our life due to its pros of being easy to use and flexible to pay. The critical impact of the increment of using credit cards is the occurrence of fraudulent transactions, which allow the illegal user to get money and free goods via unauthorized usage. Artificial Intelligence (AI) and Machine Learning (ML) have become effective techniques used in different applications to ensure cybersecurity. This paper proposes our fraud detection system called Man-Ensemble CCFD using an ensemble-learning model with two stages of classification and detection. Stage one, called ML-CCFD, utilizes ten machine learning (ML) algorithms to classify credit card transactions to class 1 as a fraudulent transaction or class 0 as a legitimate transaction. As a result, we compared their classification reports together, precisely precision, recall (sensitivity), and f1-score. Then, we selected the most accurate ML algorithms based on their classification performance and prediction accuracy. The second stage, known Ensemble-learning CCFD, is an ensemble model that applies the Man-Ensemble method on the most effective ML algorithms from stage one. The output of the second stage is to get the final prediction instead of using common types of ensemble learning, such as voting, stacking, boosting, and others. Our framework’s results showed the effectiveness and efficiency of our fraud detection system compared to using ML algorithms individually due to their weakness issues, such as errors, overfitting, bias, prediction accuracy, and even their robustness level. 

   more » « less
5. Comparing machine and deep learning‐based algorithms for prediction of clinical improvement in psychosis with functional magnetic resonance imaging

   https://doi.org/10.1002/hbm.25286  

   Smucny, Jason ; Davidson, Ian ; Carter, Cameron S. ( November 2020 , Human Brain Mapping)

   Previous work using logistic regression suggests that cognitive control‐related frontoparietal activation in early psychosis can predict symptomatic improvement after 1 year of coordinated specialty care with 66% accuracy. Here, we evaluated the ability of six machine learning (ML) algorithms and deep learning (DL) to predict “Improver” status (>20% improvement on Brief Psychiatric Rating Scale [BPRS] total score at 1‐year follow‐up vs. baseline) and continuous change in BPRS score using the same functional magnetic resonance imaging‐based features (frontoparietal activations during the AX‐continuous performance task) in the same sample (individuals with either schizophrenia (n =65, 49M/16F, mean age 20.8 years) or Type I bipolar disorder (n= 17, 9M/8F, mean age 21.6 years)). 138 healthy controls were included as a reference group. “Shallow” ML methods included Naive Bayes, support vector machine, K Star, AdaBoost, J48 decision tree, and random forest. DL included an explainable artificial intelligence (XAI) procedure for understanding results. The best overall performances (70% accuracy for the binary outcome and root mean square error = 9.47 for the continuous outcome) were achieved using DL. XAI revealed left DLPFC activation was the strongest feature used to make binary classification decisions, with a classification activation threshold (adjusted beta = .017) intermediate to the healthy control mean (adjusted beta = .15, 95% CI = −0.02 to 0.31) and patient mean (adjusted beta = −.13, 95% CI = −0.37 to 0.11). Our results suggest DL is more powerful than shallow ML methods for predicting symptomatic improvement. The left DLPFC may be a functional target for future biomarker development as its activation was particularly important for predicting improvement.

    

   more » « less