In many regions of the world, early diagnosis of non-small cell lung cancer (NSCLC) is a major challenge due to the large population and lack of medical resources, which is difficult toeffectively address via limited physician manpower alone. Therefore, we developed a convolutional neural network (CNN)-based assisted diagnosis and decision-making intelligent medical system with sensors. This system analyzes NSCLC patients’ medical records using sensors to assist staging a diagnosis and provides recommended treatment plans to physicians. To address the problem of unbalanced case samples across pathological stages, we used transfer learning and dynamic sampling techniques to reconstruct and iteratively train the model to improve the accuracy of the prediction system. In this paper, all data for training and testing the system were obtained from the medical records of 2,789,675 patients with NSCLC, which were recorded in three hospitals in China over a five-year period. When the number of case samples reached 8000, the system achieved an accuracy rate of 0.84, which is already close to that of the doctors (accuracy: 0.86). The experimental results proved that the system can quickly and accurately analyze patient data and provide decision information support for physicians.
Mobile commerce (m-commerce) refers to the conduct of business using wireless devices and communications. Driven by the success of e-commerce and impressive progress in wireless technologies, m-commerce is rapidly taking place in the business forefront. However, most of the concepts developed for ecommerce may not be easily applicable to wireless environments. This is due to the peculiarities of these environments such as limited bandwidth, unbalanced client-server communication, and limited power supply. Web services are undeniably one of the most significant e-commerce concepts worth of being adapted to the wireless world. Mobile services, also called m-services, promise several benefits compared with their wired counterparts. They provide larger customer base and cater for "anytime and anywhere" access to services. In this paper, we propose an infrastructure for organizing and efficiently accessing m-services in broadcast environments. We define a multi-channel model to carry information about m-services available within a given geographic area. The UDDI channel includes registry information about m-services. The m-service channel contains the description and executable code of each m-service. The data channel contains the actual data needed while executing the m-service. We also introduce three techniques to enable efficient access to wireless channels. These techniques extend well-known mobile databases' access methods to m-services: B+ tree, signature indexing, and hashing. We finally present an analytical model and conduct an extensive experimental study to evaluate and compare the proposed techniques.
Billions of people around the world send and receive data over online networks daily. Sufficient and redundant data are transmitted over social platforms with AI-assisted in 5G networks. In opportunistic social networks, the main challenge faced by traditional methods is that numerous user nodes participate in data transmission, causing a lot of message copy redundancy and node cache consumption. As a result, the transmission delay of the algorithm is high, the node energy consumption is too large, and even information is lost. To solve these problems, this study establishes an artificial intelligence-based optimization multiple evaluation method. The main purpose of this method is to avoid information loss caused by data loss when reducing data noise, reasonably select communication nodes in opportunistic social network scenarios, optimize data transmission performance, and avoid network congestion. Moreover, our method can effectively identify and exclude potential malicious nodes, reducing the situation that packets are intercepted and discarded. The experiment confirms that the optimized transmission evaluation scheme can effectively reduce routing overheads and energy consumption of a user node, improve the delivery ratio of node data transmission, and ensure the reliability and security of data transmission.
It has become a trend in recent years to use deep neural networks for colorization. However, previous methods often encounter problems with edge color leakage and difficulties in obtaining a plausible color output from the Euclidean distance. To solve these problems, we propose a new adversarial edgeaware image colorization method with multitask output combined with semantic segmentation. The system uses a generator with a deep semantic fusion structure to infer semantic clues in a given grayscale image under chroma conditions and learns colorization by simultaneously predicting color information and semantic information. In addition, we also use a specific color difference loss with characteristics of human visual observation that is combined with semantic segmentation loss and adversarial loss for training. The experimental results show that our method is superior to existing methods in terms of different quality metrics and achieves good results in image colorization.
In the field of computer vision, super-resolution reconstruction techniques based on deep learning have undergone considerable advancement; however, certain limitations remain, such as insufficient feature extraction and blurred image generation. To address these problems, we propose an image super-resolution reconstruction model based on a generative adversarial network. First, we employ a dual network structure in the generator network to solve the problem of insufficient feature extraction. The dual network structure is divided into an upsample subnetwork and a refinement subnetwork, which upsample and optimize a low-resolution image, respectively. In a scene with large upscaling factors, this structure can reduce the negative effect of noise and enhance the utilization of high-frequency details, thereby generating high-quality reconstruction results. Second, to generate sharper super-resolution images, we use the perceptual loss, which exhibits a fast convergence and excellent visual effect, to guide the generator network training. We apply the ResNeXt-50-32x4d network, which has few parameters and a large depth, to calculate the loss to obtain a reconstructed super-resolution image that is highly realistic. Finally, we introduce the Wasserstein distance into the discriminator network to enhance the discrimination ability and stability of the model. Specifically, this distance is employed to eliminate the activation function in the last layer of the network and avoid the use of the logarithm in calculating the loss function. Extensive experiments on the DIV2K, Set5, Set14, and BSD100 datasets demonstrate the effectiveness of the proposed model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.