Search

A report from Diponegoro University discusses the use of artificial intelligence (AI) and deep learning in medical imaging to identify kidney stones. The research highlights that deep learning is more commonly used than traditional machine learning in this field. The aim of the study was to review existing literature on deep learning in medical imaging for detecting kidney stones. The research concludes that using the appropriate AI model with high accuracy can assist radiologists in accurately detecting kidney stones. This information may be useful for those interested in AI applications in medical diagnostics. [Extracted from the article]

A report from the Thapar Institute of Engineering & Technology in Punjab, India discusses the use of machine learning and deep learning techniques for the detection of epileptic seizures. The paper compares different algorithms and models, such as support vector machine classifiers, artificial neural network classifiers, convolutional neural network classifiers, and long-short term memory networks. The effectiveness of different physiological signals, including electroencephalogram (EEG) and electrocardiogram (ECG), is also explored. The paper concludes that sentiment analysis could be another dimension of seizure detection. This research provides a summary of previous techniques and offers direction for further research in the field. [Extracted from the article]

A report from Rajiv Gandhi University discusses the use of artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), in classifying schizophrenia through electroencephalogram (EEG) data. The review paper explores the challenges, methodologies, and findings in this field, highlighting the potential of AI in enhancing schizophrenia diagnosis. ML approaches like Support Vector Machines and Decision Trees are effective with smaller datasets, while DL techniques such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) are more adaptable to complex EEG patterns but require more data and computational power. The research emphasizes the importance of collaborative and ethically informed approaches in automated schizophrenia classification using AI. [Extracted from the article]

A new report from researchers at Easwari Engineering College explores the use of artificial intelligence (AI) and thermal imaging in post-harvest fruit handling. The study highlights the potential of AI-based thermal imaging in detecting quality attributes and its applications in agriculture, food processing, and post-harvest fruit handling. The report discusses the challenges and advantages of AI-driven thermal imaging technology, as well as the use of machine learning and deep learning techniques. It also examines various applications of AI-based thermal imaging in post-harvest fruit quality assessment, such as bruise detection, maturity identification, and pest and disease detection. The research concludes by discussing future trends and the potential for increased automation and integration with emerging technologies in the post-harvest fruit handling sector. [Extracted from the article]

A systematic review conducted by researchers from the School of Computer Science and Engineering at Vellore Institute of Technology in Chennai, India, explores the use of machine learning and deep learning prediction models for sepsis and neonatal sepsis. Sepsis and neonatal sepsis are significant challenges in global healthcare, as they can lead to life-threatening organ dysfunction. Early identification of sepsis is difficult, but the implementation of machine learning and deep learning technologies shows promise in predicting sepsis at an early stage and reducing mortality rates. The review analyzes various studies and concludes that prediction models can support researchers and clinicians in making better decisions and administering antibiotics earlier. [Extracted from the article]

In this paper, we consider the problem of approximating functions from a Korobov space on [ − 1 , 1 ] d by ReLU shallow neural networks and present a rate O (m − 2 5 (1 + 2 d) log ⁡ m) of uniform approximation by networks of m hidden neurons. This is achieved by combining a novel Fourier analysis approach and a probability argument. We apply our approximation theory to a learning algorithm for regression based on ReLU shallow neural networks and derive learning rates of order O (N − 4 (d + 2) 9 d + 8 log ⁡ N) for the excess generalization error with the sample size N when the regression function lies in the Korobov space. [ABSTRACT FROM AUTHOR]

The k Nearest Neighbors (k NN) search in high-dimensional space is a fundamental problem with various applications. In this paper, we try to solve this problem by using deep neural networks (DNNs). We apply DNNs to represent complex correlations between high-dimensional objects, enabling us to project similar objects into the same class, thus reducing the search cost. Based on DNNs, we propose two novel techniques to improve query efficiency while keeping accuracy. First, traditional DNNs typically demand extensive training data for achieving high accuracy. To decrease the training size, we design a multi-module DNN framework comprising several small modules. Each module learns to capture part of knowledge for the given query. The collective output of these sub-modules is then seamlessly integrated to form the final result. Second, with machine learning models, the size of candidates are unbounded. Thus, we design a linear-time data layout refinement algorithm, aiming to limit the number of candidates to a small constant. Empirically we find that our approach significantly outperforms the state-of-the-art methods in terms of both time efficiency and space efficiency while still attaining comparable or better accuracy. [ABSTRACT FROM AUTHOR]

A recent study conducted by researchers from the Icahn School of Medicine at Mount Sinai in New York City explores the use of advanced deep learning algorithms for magnetic resonance imaging (MRI) segmentation. Accurate MRI segmentation is crucial for diagnosing abnormalities and planning treatments, but traditional supervised learning techniques require a large amount of annotated data. The study reviews state-of-the-art algorithms that utilize a limited number of annotated samples, including self-supervised learning, generative models, few-shot learning, and semi-supervised learning. The researchers also discuss future directions in the field, such as contrastive language-image pretraining, to further improve image segmentation with limited labels. [Extracted from the article]

Identifying and reconstructing hadronic τ decays (τ h) is an important task at current and future high-energy physics experiments, as τ h represent an important tool to analyze the production of Higgs and electroweak bosons as well as to search for physics beyond the Standard Model. The identification of τ h can be viewed as a generalization and extension of jet-flavour tagging, which has in the recent years undergone significant progress due to the use of deep learning. Based on a granular simulation with realistic detector effects and a particle flow-based event reconstruction, we show in this paper that deep learning-based jet-flavour-tagging algorithms are powerful τ h identifiers. Specifically, we show that jet-flavour-tagging algorithms such as LorentzNet and ParticleTransformer can be adapted in an end-to-end fashion for discriminating τ h from quark and gluon jets. We find that the end-to-end transformer-based approach significantly outperforms contemporary state-of-the-art τ h reconstruction and identification algorithms currently in use at the Large Hadron Collider. [ABSTRACT FROM AUTHOR]

A recent report from the Electrical and Communications Engineering Department in Haryana, India discusses the importance of early detection in minimizing mortality rates for heart disease. The report highlights the discomfort and cost associated with coronary angiography, the most precise diagnostic method, as a deterrent for patients in the early stages of the disease. To address this issue, the report suggests the use of machine learning algorithms and decision support systems that leverage a patient's clinical parameters for more accurate heart disease diagnoses. The report also calls for further research in this field and proposes potential solutions to existing challenges. [Extracted from the article]