Quantum machinelearning is an emerging sub-field in machinelearning where one of the goals is to perform patternrecognition tasks by encoding data into quantum states. this extension from classical to quantum domai...
详细信息
Traffic patternrecognition belongs to a branch of scene recognition and has become a hot research field. Correctly identifying the transportation mode used by users to travel plays a vital role in promoting the devel...
详细信息
the K-Nearest Neighbors (KNN) algorithm is a classical supervised learning method widely used in classification and regression problems. However, the KNN algorithm faces serious challenges when dealing with high-dimen...
详细信息
Due to the similarity in mushroom features and the difficulty in distinguishing between poisonous and nonpoisonous varieties, mushrooms pose a threat to human health. To address the challenge of mushroom classificatio...
Due to the similarity in mushroom features and the difficulty in distinguishing between poisonous and nonpoisonous varieties, mushrooms pose a threat to human health. To address the challenge of mushroom classification and identification, this paper proposes a mushroom classification method based on residual networks. Firstly, a network architecture with multiple residual blocks is designed, and it is trained using an image dataset. then, a transfer learning strategy is employed to initialize the network parameters from a pre-trained model, followed by fine-tuning to adapt to the mushroom classification task. Finally, multiple testing experiments are conducted to evaluate the effectiveness of the proposed method. the experimental results demonstrate excellent performance of the proposed method in mushroom classification tasks. Compared to traditional feature extraction methods, it can better capture the details and texture features of mushrooms, thereby improving classification accuracy. In conclusion, the mushroom classification method based on residual networks exhibits high accuracy and generalization capability. this method has potential applications in the field of mushroom classification, aiding in the better identification and differentiation of poisonous mushrooms, thereby protecting human health.
the proceedings contain 194 papers. the topics discussed include: comparative study of DDoS detection and mitigation techniques;a machinelearning-based blockchain model for the storage of maternal health records and ...
ISBN:
(纸本)9798350306118
the proceedings contain 194 papers. the topics discussed include: comparative study of DDoS detection and mitigation techniques;a machinelearning-based blockchain model for the storage of maternal health records and safety prediction;enhancing digital investigation: leveraging ChatGPT for evidence identification and analysis in digital forensics;managing metadata in data warehouse for data quality and data stewardship in telecom industry – a compact survey;a review on detection and prevention of the DDoS attacks in the blockchain;analysis of face recognition technique: plastic surgery altered face;image classification using federated averaging algorithm;navigating the gray area: a three-label framework for uncovering uncertainty in fake news;and improvement in validation score with loss function for breast cancer detection using deep learning.
We use a large foundation language model, which is fine-tuned with debate corpora, to develop a robot debater application. To address the limitations of requiring immense computational power in large base language mod...
We use a large foundation language model, which is fine-tuned with debate corpora, to develop a robot debater application. To address the limitations of requiring immense computational power in large base language models, this study takes advantage of the Low Rank Adaption characteristic prevalent in domain expert knowledge. By applying Low Rank Adaption technology and fine-tuning with a dedicated dataset, the computational load is reduced to just one-thousandth of what is needed for a large language model, greatly expanding the application scenarios of robot debaters using large language models. In view of the characteristics of debate competitions, this model can preset a variety of debate scenarios and supports personalized debate processes. It employs intelligent voice recognition technology combined with a multi-channel voice input method, allowing for precise localization of different human debaters and improving the accuracy of voice input recognition. the system can support multiple large-scale language generation models and utilize various different voice broadcasting systems, including male and female voice styles, as well as a range of voice emotions. this model can be applied to debate competitions held in universities, high schools, and various industries. It can support human-machine debates as well as machine-to-machine debates.
the proceedings contain 136 papers. the topics discussed include: comparison of image generation methods based on diffusion models;research on image preprocessing and target detection of vehicle-machine cooperative sy...
ISBN:
(纸本)9798350326444
the proceedings contain 136 papers. the topics discussed include: comparison of image generation methods based on diffusion models;research on image preprocessing and target detection of vehicle-machine cooperative system;a research on traditional tangka image classification based on visual features;research on image recognition based on neural network model learning algorithm;research on image recognition based on reinforcement learning;low-quality image binarization method based on threshold array system;comprehensive study of image processing techniques for low-altitude target recognition;visual cryptography scheme by freeform optics based on optimal mass transport;SPECT bone scan image classification by fusing multi-attention mechanism with deep residual networks;fine-grained image recognition method based on input perception joint probability prediction;deep learning in image classification: an overview;auricular images with annotations for segmenting key-organ mapping regions in auricular diagnosis;insulator image dataset generation based on generative adversarial network;structure-preserving domain adaptation network for generating pencil sketches;underwater image recovery method considering target polarization characteristics;and a dual attention network for multimodal remote sensing image matching.
the Research & Development (R&D) phase of drug development Drug discovery and development (D&D) is a complex and costly endeavor, typically requiring six to nine years [1] and four hundred to fourteen hund...
the Research & Development (R&D) phase of drug development Drug discovery and development (D&D) is a complex and costly endeavor, typically requiring six to nine years [1] and four hundred to fourteen hundred million USD [2] for the research and development (R&D) phase alone. To transform this process, we propose a novel concept that combines Quantum-based machinelearning network (QML) and Quantum Computing Simulation (QS) to expedite the R&D phase to three to six months and reduce the cost to merely fifty to eighty thousand USD. Our approach takes as inputs the target protein/gene structure and the primary assay [3]. For Hit Generation [3], the QML network generates potential hits [4] based on the molecular structure of the target protein, while the QS filters molecules from the primary assay according to their reaction and binding efficacy withthe target protein. then, for Lead Optimization [3], the resulting molecules from QML and QS are compared, and the ones that are common to both processes are subjected to dozens of molecular variations, while others are only modified slightly. Finally, all optimized molecules undergo multiple rounds of QS filtering with high standards for reaction efficacy and safety, producing a few dozen pre-clinical-trial-ready drugs. Our concept of QML and QS integration can also be applied to other fields, such as agricultural research, genetic editing, and aerospace engineering. Keywords: Quantum Computer, Hit to Lead, Lead Optimization Simulation, machinelearning.
Healthcare monitoring for humans is important due to several factors including life quality and early detection of health-related problems. Human activity patterns recognition is the most promising ways to monitor hum...
详细信息
the proceedings contain 69 papers. the special focus in this conference is on Recent Trends in machinelearning. the topics include: Implementation of Dual-Band Dielectric Resonator Antenna for 5G Applications;defect ...
ISBN:
(纸本)9789819994410
the proceedings contain 69 papers. the special focus in this conference is on Recent Trends in machinelearning. the topics include: Implementation of Dual-Band Dielectric Resonator Antenna for 5G Applications;defect Detection in Metal Surfaces Using Computer Vision;liver Cirrhosis Prediction Using machinelearning Classification Techniques;a Recent Survey on Risk Factors Affecting the Blood Pressure in India;Real-Time Monitoring System for Breakdown Analysis and OEE in the Wire Drawing Industry;tooth Sensitivity Device—Detection and Diagnosing of Sensitivity in the Dental Pulp;recognition of Skin Cancer;ioT-Based Smart Street Lighting Surveillance System;rock Segmentation of Real Martian Scenes Using Dual Attention Mechanism-Based U-Net;IAAS: IoT-Based Automatic Attendance System with Photo Face recognition in Smart Campus;hardware Implementation of Moving Object Detection Using Background Subtraction Algorithm;crime pattern Identification and Prediction Using machinelearning;IMICE: An Improved Missing Data Imputation Using machinelearning;analyzing Students’ Opinion on E-learning—Indian Students’ Perspective;rash Driving Detection and Alerting System;Logistic-Based OVA-CNN Model for Alzheimer’s Disease Detection and Prediction Using MR Images;Comparative Study of CNNs for Camouflaged Object Detection;3D Avatar Reconstruction Using Multi-level Pixel-Aligned Implicit Function;Helmet Detection Using YOLO-v5 and Paddle OCR for Embedded Systems;defogNet: A Residual Network for Removal of Fog Using Weighted Combination Loss;Text-to-Image Generation Model with DNN Architecture and Computer Vision for Embedded Devices Using Quantization Technique;one-Shot learning for Archaeological Site Data Using Deep Neural Network on Embedded Systems;enhanceNet: A Deep Neural Network for Low-Light Image Enhancement with Image Restoration;intelligent Prediction of Cardiac Abnormality.
暂无评论