Development and Preliminary Evaluation of a YOLO-Based Fruit Counting and Maturity Evaluation Mobile Application for Blueberries

Background:Over the past 20 years, the advancement of artificial intelligence (AI) and deep learning (DL) has allowed for fast sorting and analysis of large sets of data. In the field of gastroenterology, colorectal screening procedures produces an abundance of data through video and imaging. With AI and DL, this information can be used to create systems where automatic polyp detection and characterization is possible. Convoluted Neural Networks (CNNs) have proven to be an effective way to increase polyp detection and ultimately adenoma detection rates. Different methods of polyp characterization of being hyperplastic vs. adenomatous or non-neoplastic vs. neoplastic has also been investigated showing promising results.Findings:The rate of missed polyps on colonoscopy can be as high as 25%. At the beginning of the 2000s, hand-crafted machine learning (ML) algorithms were created and trained retrospectively on colonoscopy images and videos, achieving high sensitivity, specificity, and accuracy of over 90% in many of the studies. Over time, the advancement of DL and CNNs has allowed algorithms to be trained on non-medical images and applied retrospectively to colonoscopy videos and images with similar results. Within the past few years, these algorithms have been applied in real-time colonoscopies and has shown mixed results, one showing no difference while others showing increased polyp detection.Various methods of polyp characterization have also been investigated. Through AI, DL, and CNNs polyps can be identified has hyperplastic/adenomatous or non-neoplastic/neoplastic with high sensitivity, specificity, and accuracy. One of the research areas in polyp characterization is how to capture the polyp image. This paper looks at different modalities of characterizing polyps such as magnifying narrow band imaging (NBI), endocytoscopy, laser-induced florescent spectroscopy, auto-florescent endoscopy, and white-light endoscopy.Conclusions:Overall, much progress has been made in automatic detection and characterization of polyps in real time. Barring ethical or mass adoption setbacks, it is inevitable that AI will be involved in the field of GI, especially in colorectal polyp detection and identification.

The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future.

Is It Time to Get Rid of Black Boxes and Cultivate Trust in AI?

Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data. Recent advances in deep learning, on the other hand, are notorious for their dependence on large amounts of data. Second, many AL acquisition functions rely on model uncertainty, yet deep learning methods rarely represent such model uncertainty. In this paper we combine recent advances in Bayesian deep learning into the active learning framework in a practical way. We develop an active learning framework for high dimensional data, a task which has been extremely challenging so far, with very sparse existing literature. Taking advantage of specialised models such as Bayesian convolutional neural networks, we demonstrate our active learning techniques with image data, obtaining a significant improvement on existing active learning approaches. We demonstrate this on both the MNIST dataset, as well as for skin cancer diagnosis from lesion images (ISIC2016 task).

Mental health plays a key role in everyone’s day-to-day lives, impacting our thoughts, behaviors, and emotions. Also, over the past years, given their ubiquitous and affordable characteristics, the use of smartphones and wearable devices has grown rapidly and provided support within all aspects of mental health research and care—from screening and diagnosis to treatment and monitoring—and attained significant progress in improving remote mental health interventions. While there are still many challenges to be tackled in this emerging cross-disciplinary research field, such as data scarcity, lack of personalization, and privacy concerns, it is of primary importance that innovative signal processing and deep learning (DL) techniques are exploited. In particular, recent advances in DL can help provide a key enabling technology for the development of next-generation user-centric mobile mental health applications. In this article, we briefly introduce the basic principles associated with mobile device-based mental health analysis, review the main system components, and highlight the conventional technologies involved. We also describe several major challenges and various DL technologies that have potential for strongly contributing to dealing with these issues, and we discuss other problems to be addressed via research collaboration across multiple disciplines.

A survey of multimodal hybrid deep learning for computer vision: Architectures, applications, trends, and challenges

With growing size of resting state fMRI datasets and advances in deep learning methods, there are ever increasing opportunities to leverage progress in deep learning to solve challenging tasks in neuroimaging. In this work, we build upon recent advances in deep metric learning, to learn embeddings of rs-fMRI data, which can then be potentially used for several downstream tasks. We propose an efficient training method for our model and compare our method with other widely used models. Our experimental results indicate that deep metric learning can be used as an additional refinement step to learn representations of fMRI data, that significantly improves performance on downstream modeling tasks.

A fervent debate exists among researchers and social critics about whether smartphone use strengthens or undermines community participation and social relationships. This study investigates the dynamics between smartphone use and psychological well-being among university students over a one-year period, employing a two-wave longitudinal analysis to examine this relationship across various mobile applications. Our findings reveal that the direction and magnitude of the interplay depend on the specific purposes of smartphone engagement. Specifically, there is a bidirectional relationship between smartphone use (either overall use or specific mobile application use) and psychological well-being: higher levels of perceived social support and loneliness reduce subsequent smartphone use, while increased smartphone use boosts perceived social support and heightens loneliness. The impact of life satisfaction on different mobile applications varies: life satisfaction negatively affects the subsequent use of social media, mobile gaming, and mobile health applications, while its effects on mobile shopping and overall smartphone use are insignificant. Additionally, increased overall smartphone use decreases life satisfaction, whereas increased use of mobile shopping and mobile health applications significantly improves life satisfaction, but the others—social media and mobile gaming—do not. These findings hold noteworthy implications for research and practices.

This chapter explores the role of Artificial Intelligence (AI) in enhancing energy efficiency and sustainability in smart warehousing. AI technologies such as predictive maintenance, smart inventory management, dynamic load balancing, and automation have been shown to significantly reduce energy consumption, optimize warehouse operations, and minimize environmental impacts. AI's integration with renewable energy sources, like solar and wind, further supports sustainability goals by optimizing energy usage and reducing reliance on non-renewable power. The future potential of AI in revolutionizing warehouse energy efficiency is immense, with advancements in deep learning, edge computing, and real-time analytics. This chapter also highlights areas for future research, particularly in renewable energy integration, AI algorithm development, and scalability for small and medium-sized enterprises.

Epilepsy is a neurological disorder characterized by recurrent seizures affecting millions worldwide. Medically intractable seizures in epilepsy patients are not only detrimental to the quality of life but also pose a significant threat to their safety. Outcomes of epilepsy therapy can be improved by early detection and intervention during the interictal window period. Electroencephalography is the primary diagnostic tool for epilepsy, but accurate interpretation of seizure activity is challenging and highly time-consuming. Machine learning (ML) and deep learning (DL) algorithms enable us to analyze complex EEG data, which can not only help us diagnose but also locate epileptogenic zones and predict medical and surgical treatment outcomes. DL models such as convolutional neural networks (CNNs), inspired by visual processing, can be used to classify EEG activity. By applying preprocessing techniques, signal quality can be enhanced by denoising and artifact removal. DL can also be incorporated into the analysis of magnetic resonance imaging (MRI) data, which can help in the localization of epileptogenic zones in the brain. Proper detection of these zones can help in good neurosurgical outcomes. Recent advancements in DL have facilitated the implementation of these systems in neural implants and wearable devices, allowing for real-time seizure detection. This has the potential to transform the management of drug-refractory epilepsy. This review explores the application of ML and DL techniques to Electroencephalograms (EEGs), MRI, and wearable devices for epileptic seizure detection. This review briefly explains the fundamentals of both artificial intelligence (AI) and DL, highlighting these systems' potential advantages and undeniable limitations.

This study aims to develop an intelligent monitoring system that supports the enforcement of smoking prohibition in public spaces by leveraging advancements in Artificial Intelligence (AI) and deep learning. Utilizing the YOLOv8 (You Only Look Once version 8) object detection model, the system is designed to identify smoking activities in real-time and promptly send alerts through the Telegram messaging platform. The proposed method integrates real-time object detection with an automated notification system, ensuring responsive enforcement across diverse environmental conditions, including normal lighting, low-light scenarios, and partially occluded views. The system architecture combines the YOLOv8 model for detection and a Python-based Telegram bot for communication. The model was evaluated using a test dataset collected from various public spaces. It achieved an F1-Score of 81% and a confusion matrix accuracy of 89%, indicating a high level of reliability and precision in identifying smoking behaviors. Additionally, the average notification response time via Telegram was 1.5 seconds, enabling near-instantaneous alerting for enforcement personnel. In conclusion, the results demonstrate that the system is both accurate and efficient in detecting smoking activities. Its robust performance across different conditions and rapid alert mechanism positions it as a practical and scalable solution to enhance compliance with smoking regulations in public areas.

Accurate and timely crop yield estimation remains a major challenge in agriculture due to the limitations of traditional field-based methods, which are labor-intensive, destructive, and unsuitable for large-scale applications. While recent advances in Unmanned Aerial Vehicles (UAVs) and Deep Learning (DL) have enabled non-destructive and scalable alternatives, melons (Cucumis melo L.) remain relatively understudied, and datasets for yield estimation are scarce. This study presents a computer vision pipeline for UAV-based fruit detection and yield estimation in melon crops. High-resolution UAV RGB imagery was processed using YOLOv12 (You Only Look Once, version 12) for fruit detection, followed by a volume-based regression model for weight estimation. The experiment was conducted during the May–August 2025 growing season in Apulia, southern Italy. The detection model achieved high accuracy, with strong agreement between estimated and actual fruit counts (R2 = 0.99, MAPE = 5%). The regression model achieved an R2 of 0.79 for individual weight estimation and a total yield error of 2.9%. By addressing the scarcity of melon-specific data, this work demonstrates that integrating UAV imagery with deep learning provides an effective and scalable approach for accurate yield estimation in melons.

Cascade-SORT: A robust fruit counting approach using multiple features cascade matching

Predictive modeling in reproductive medicine: Where will the future of artificial intelligence research take us?

Abstract. In recent years, artificial intelligence (AI) has experienced remarkable growth, largely driven by significant advancements in algorithm structures. This paper provides a comprehensive review of the key algorithmic frameworks employed in AI, with a primary focus on traditional algorithms and their evolution in response to modern deep learning techniques. Traditional algorithms, such as decision trees, support vector machines, and genetic algorithms, have long served as foundational pillars in AI research. However, the advent of deep learning has introduced new paradigms that significantly enhance these algorithms in terms of performance, scalability, and adaptability. By analyzing the classification, characteristics, and limitations of traditional algorithms, this study compares them with deep learning models, highlighting both their strengths and shortcomings. Furthermore, this paper examines how deep learning improves traditional algorithms through case studies that showcase enhanced performance, broader application domains, and evolving design principles. This study is based on an analysis of publicly available datasets and a comprehensive review of the current literature. The findings suggest that while traditional algorithms offer a solid foundation, deep learning has revolutionized algorithmic design, paving the way for new applications and innovations in AI. Ultimately, this review underscores the critical role of integrating deep learning into traditional algorithmic frameworks for the future of AI.