Explore Research
Like Never Before

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

This project aims to provide an efficient and robust real-time emotion identification framework that makes use of paralinguistic factors such as intensity, pitch, and MFCC and employs Diffusion Map to reduce data redundancy and high dimensionality.

The Segment Anything Model (SAM) is introduced: a new task, model, and dataset for image segmentation, and its zero-shot performance is impressive – often competitive with or even superior to prior fully supervised results.

This chapter presents techniques for statistical machine learning using Support Vector Machines (SVM) to recognize the patterns and classify them, predicting structured objects using SVM, k-nearest neighbor method for classification, and Naive Bayes classifiers.

The development of TRIPOD+AI is described and the expanded 27 item checklist with more detailed explanation of each reporting recommendation is presented, and the TRIPOD+AI for Abstracts checklist is presented.

An innovative convolutional neural network architecture aimed at addressing challenges of detection and classification of apple fruit diseases is proposed and experimentally validated, achieving a remarkable classification accuracy of 95.37%.

This work introduces Flamingo, a family of Visual Language Models (VLM) with this ability to bridge powerful pretrained vision-only and language-only models, handle sequences of arbitrarily interleaved visual and textual data, and seamlessly ingest images or videos as inputs.

New methods in the UCSF ChimeraX molecular modeling package are described that take advantage of machine‐learning structure predictions, provide likelihood‐based fitting in maps, and compute per‐residue scores to identify modeling errors.

The most common evaluation metrics used for the typical supervised ML tasks including binary, multi-class, and multi-label classification, regression, image segmentation, object detection, and information retrieval are introduced.

Christoph Molnar. 2020. Interpretable Machine Learning: A Guide for Making Black Box Models Explainable, Lulu.com, pp. 318, ₹6690.

Heart disease is a prevalent and complex condition that affects numerous individuals worldwide. Timely and accurate diagnosis of heart disease is of utmost importance in cardiology. In this research article, we propose an efficient and precise system for heart disease diagnosis, employing machine learning techniques. The system is designed based on various classification algorithms, including Support Vector Machine, Logistic Regression, Decision Tree, and Random Forest. Standard feature selection algorithms such as ANDV A, Chi-Squared, and Mutual Information Feature Selection (MIFS) are utilized to eliminate unrelated features. Furthermore, we introduce a novel fast experiment that contains a conditional mutual information feature selection algorithm, ANDVA feature selection algorithms, and a Chi-squared feature selection algorithm to address the feature selection challenge. These feature selection algorithms enhance classification model accuracy and reduce the compile time in the classification ML model. The cross-validation method evaluates the models and optimizes hyperparameters, ensuring reliable model assessment. Performance measuring metrics are utilized to assess the classifiers' performance. The classifiers are estimated based on the selected features determined by the feature selection algorithms. The experimental results show that the ANDV A F -test feature selection algorithm along with the Support Vector Machine classifier, is a viable approach for developing an advanced intelligent system that can identify heart disease. The proposed model can also be easily implemented in healthcare to facilitate heart disease identification.

IoT-enabled soil nutrient monitoring with machine learning algorithms for crop recommendations streamlines crop selection, minimizing unnecessary inputs while maximizing yields, and contributes to economic growth by fostering sustainable practices and increased yields.