Deep Learning in Breast Cancer Imaging: State of the Art and Recent Advancements in Early 2024

Diagnostics, Journal Year: 2024, Volume and Issue: 14(8), P. 848 - 848

Published: April 19, 2024

The rapid advancement of artificial intelligence (AI) has significantly impacted various aspects healthcare, particularly in the medical imaging field. This review focuses on recent developments application deep learning (DL) techniques to breast cancer imaging. DL models, a subset AI algorithms inspired by human brain architecture, have demonstrated remarkable success analyzing complex images, enhancing diagnostic precision, and streamlining workflows. models been applied diagnosis via mammography, ultrasonography, magnetic resonance Furthermore, DL-based radiomic approaches may play role risk assessment, prognosis prediction, therapeutic response monitoring. Nevertheless, several challenges limited widespread adoption clinical practice, emphasizing importance rigorous validation, interpretability, technical considerations when implementing solutions. By examining fundamental concepts synthesizing latest advancements trends, this narrative aims provide valuable up-to-date insights for radiologists seeking harness power care.

Language: Английский

---

A Comprehensive Review of Convolutional Neural Networks for Defect Detection in Industrial Applications

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 94250 - 94295

Published: Jan. 1, 2024

Quality inspection and defect detection remain critical challenges across diverse industrial applications. Driven by advancements in Deep Learning, Convolutional Neural Networks (CNNs) have revolutionized Computer Vision, enabling breakthroughs image analysis tasks like classification object detection. CNNs' feature learning capabilities made through Machine Vision one of their most impactful This article aims to showcase practical applications CNN models for surface various scenarios, from pallet racks display screens. The review explores methodologies suitable hardware platforms deploying CNN-based architectures. growing Industry 4.0 adoption necessitates enhancing quality processes. main results demonstrate efficacy automating detection, achieving high accuracy real-time performance different surfaces. However, limited datasets, computational complexity, domain-specific nuances require further research. Overall, this acknowledges potential as a transformative technology vision applications, with implications ranging control enhancement cost reductions process optimization.

Language: Английский

---

Adversarial Attacks and Defenses in Machine Learning-Empowered Communication Systems and Networks: A Contemporary Survey

IEEE Communications Surveys & Tutorials, Journal Year: 2023, Volume and Issue: 25(4), P. 2245 - 2298

Published: Jan. 1, 2023

Adversarial attacks and defenses in machine learning deep neural network (DNN) have been gaining significant attention due to the rapidly growing applications of communication networks. This survey provides a comprehensive overview recent advancements field adversarial attack defense techniques, with focus on DNN-based classification models for applications. Specifically, we conduct methods state-of-the-art techniques based principles, present them visually appealing tables tree diagrams. is rigorous evaluation existing works, including an analysis their strengths limitations. We also categorize into counter-attack detection robustness enhancement, specific regularizationbased enhancing robustness. New avenues are explored, search-based, decision-based, dropbased, physical-world attacks, hierarchical latest provided, highlighting challenges balancing training costs performance, maintaining clean accuracy, overcoming effect gradient masking, ensuring method transferability. At last, lessons learned open summarized future research opportunities recommended.

Language: Английский

---

Edge AI for Internet of Energy: Challenges and perspectives

Internet of Things, Journal Year: 2023, Volume and Issue: 25, P. 101035 - 101035

Published: Dec. 15, 2023

Language: Английский

---

AFibri-Net: A Lightweight Convolution Neural Network Based Atrial Fibrillation Detector

IEEE Transactions on Circuits and Systems I Regular Papers, Journal Year: 2023, Volume and Issue: 70(12), P. 4962 - 4974

Published: Aug. 24, 2023

By considering limited resource-constraints of medical devices and advanced deep learning networks, in this paper, we explore a lightweight convolutional neural network (CNN) based AFibri event detector by finding suitable hyperparameters activation function with best trade-off between the detection accuracy model size (or computational time). This study presents extensive evaluation results CNN-AFibri methods that are obtained for different combination parameters: number layers (CLs 3, 4, 5), filters (8, 16, 32, 64 128), functions (including rectified linear unit (ReLU), leakyReLU (LReLU), exponential (ELU)), kernel sizes ( $3 \times 1~$ , notation="LaTeX">$ 4 1$ ). In addition to models, validate their performances under ECG segment duration 5, 10 30 seconds. On standard databases unseen databases, CLs ELU had highest 99.97% (specificity 99.98% sensitivity 99.95%) 5 second segments as compared 54 models reported paper other existing on same validation databases. Real-time implementation CNN method 3.14 Megabyte is demonstrated using Raspberry Pi computing platform Broadcom BCM2711, 1.5 GHz Cortex-A72 quad-core CPU 8 GB RAM. Results average processing times less than 3 ms 11 s segments, respectively an reduction 1% tested personal computer Intel(R) Xeon(R) W-2133 3.60 Processor 6 core 128

Language: Английский

---

Photonic Neural Networks Based on Integrated Silicon Microresonators

Intelligent Computing, Journal Year: 2023, Volume and Issue: 3

Published: Nov. 30, 2023

Recent progress in artificial intelligence (AI) has boosted the computational possibilities fields which standard computers are not able to perform adequately. The AI paradigm is emulate human and therefore breaks familiar architecture on digital based. In particular, neuromorphic computing, neural networks (ANNs), deep learning models mimic how brain computes. There many applications for large of interconnected neurons whose synapses individually strengthened or weakened during phase. this respect, photonics a suitable platform implementing ANN hardware owing its speed, low power dissipation, multi-wavelength opportunities. One photonic device that could serve as an optical neuron microring resonator. Indeed, resonators exhibit nonlinear response capability energy storage, can be used implement fading memory. addition, their characteristic resonant behavior makes them extremely sensitive input wavelengths, promotes wavelength division multiplexing (WDM) enables use WDM-based (weight banks) linear regime. Remarkably, using silicon photonics, integrated circuits fabricated volume with electronics onboard. For these reasons, here, we describe physics arrays application computing. We different types ANNs, from feedforward extreme machines, reservoir discuss hybrid systems microresonators coupled other active materials. This review introduces basics discusses most recent developments field.

Language: Английский

---

A review on deepfake generation and detection: bibliometric analysis

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(40), P. 87579 - 87619

Published: March 18, 2024

Language: Английский

---

FPGA-Based Real-Time Object Detection and Classification System Using YOLO for Edge Computing

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 73268 - 73278

Published: Jan. 1, 2024

The leap forward in research progress real-time object detection and classification has been dramatically boosted by including Embedded Artificial Intelligence (EAI) Deep Learning (DL). Real-time with deep learning require many resources computational power, which makes it more difficult to use methods on edge devices. This paper proposed a new, highly efficient Field Programmable Gate Array (FPGA) based system using You Only Look Once (YOLO) v3 Tiny for computing. However, the instantiated Advanced Driving Assistance Systems (ADAS) evaluation. Traffic light are crucial ADAS ensure drivers' safety. used camera connected Kria KV260 FPGA development board detect classify traffic light. Bosch Small Light Dataset (BSTLD) train YOLO model, Xilinx Vitis AI quantify compile model. can signals from high-definition (HD) video streaming 15 frames per second (FPS) 99% accuracy. In addition, consumes only 3.5W demonstrating ability work on-road experimental results represent fast, precise, reliable of lights system. Overall, this demonstrates low-cost FPGA-based classification.

Language: Английский

---

A Case Study on the Generative AI Project Life Cycle Using Large Language Models

EPiC series in computing, Journal Year: 2024, Volume and Issue: 98, P. 189 - 177

Published: March 21, 2024

Large Language Models represent a disruptive technology set to revolutionize the fu- ture of artificial intelligence. While numerous literature reviews and survey articles discuss their benefits address security compliance concerns, there remains shortage research exploring implementation life cycle generative AI systems. This paper addresses this gap by presenting various phases detailing development chatbot designed inquiries from prospective stu- dents. Utilizing Google Flan LLM question-answering pipeline, we processed user prompts. In addition, compiled an input file containing domain knowledge edu- cation program, which was preprocessed condensed into vector embeddings using HuggingFace library. Furthermore, chat interface for interaction Streamlit. The responses generated are both descriptive contextu- ally pertinent prompts, with quality improving in response more detailed However, significant constraint is size limit file, given processing power limitations CPUs.

Language: Английский

---

Performance enhancement of artificial intelligence: A survey

Journal of Network and Computer Applications, Journal Year: 2024, Volume and Issue: unknown, P. 104034 - 104034

Published: Sept. 1, 2024

Language: Английский

---