检索结果-内蒙古大学图书馆

UP-CNN: Un-pooling augmented convolutional neural network

学校读者我要写书评

暂无评论

Pattern Recognition Letters 2019年 119卷 34-40页

作者： Chunyan Xu Jian Yang Hanjiang Lai Junbin Gao Linlin Shen Shuicheng Yan School of Computer Science and Engineering Nanjing University of Science and Technology 210094 China School of Data and Computer Science Sun Yat-Sen University 510275 China Discipline of Business Analytics University of Sydney Business School Universtiy of Sydney NSW 2006 Australia Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University 518060 China Department of Electrical and Computer Engineering National University of Singapore 117583 Singapore

Convolutional neural network (CNN) has shown remarkable performance in various visual recognition tasks. Most of existing CNN is a purely bottom-up and feed-forward architecture, we argue that it fails to consider the interaction between low-level fine details and high-level semantic information . In this paper, a novel “Un-Pooling augmented Convolutional Neural Network” (UP-CNN) is proposed to boost the discriminative capability of the CNN with the following three distinctive properties: (1) UP-CNN is a deeper network, which is comprised of a bottom-up, a top-down and then a bottom-up sub-networks, associating to different level information that jointly improves its discriminative capability. (2) With the mixture of pooling and un-pooling layers, UP-CNN easily allows the interaction across convolutional layers with the same size from different sub-networks. This architecture effectively depresses the attenuation of important information including both activations in the forward process and gradient information in the back-propagation process. (3) UP-CNN employs the ratio un-pooling operation to reconstruct activations of the original size in the top-down sub-network, where the spatial information that is lost during pooling can be preserved within a receptive field. The experiments on four benchmark datasets (including the CIFAR-10, CIFAR-100, MNIST and SVHN datasets) well demonstrate that the proposed UP-CNN architecture considerably outperforms other state-of-the-art methods.

关键词：

Image Processing: Unlocking the Secrets of Visual Information

学校读者我要写书评

暂无评论

Image Processing: Unlocking the Secrets of Visual Informatio...

Trends in Quantum Computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： D. Lavanya Kavi Bhushan Gur Sharan Kant A C Sountharraj Akanksha Srivastav M. Sharmila Begum Computer Science and Engineering Department Sri Venkateswara College of Engineering Tirupati Andhra Pradesh Department of Computer Science Sir Chhotu Ram Institute of Engg. & Technology CCS University Meerut U.P India Department Of Computer Science With Data Analytics Dr. Ngp Art's and Science College Coimbatore Department of Computer Science and Engineering Tula's Institute Dehradun Department of Computer Science Maharaja Institute of Technology Mysore

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

In the age of image processing, the hidden ability can be encoded with visual information that is not only observed but also painstakingly carried out; in this way, the complex secrets that are encoded in each pixel have been made clear. Image processing is the magic that has increased the amount of clarity, significance, and utility while transforming stationary arrays of images into dynamic narratives. The image's quality is typically influenced by several variables, such as temperature, light, and noise. Due to its persistent presence in various digital photographs, noise plays a crucial function in the image. Throughout the image coding, transmission, and development procedure, noise consequences could arise. The field of noise removal in image processing has grown to be quite interesting and vibrant. Recently, there has been a notable advancement regarding the filtering of various noise types for image processing in digital format. This research paper aims to discuss image processing and denoising various noises in images to improve overall quality. In terms of methodology systematic qualitative research has been conducted that helps the research gather information from a wide range of sources. Moreover, this paper finds that image processing has significant potential in this digital age. By denoising images, this phenomenon can be applied in different applications in every sector.

关键词： Visualization Image recognition Systematics Quantum computing Navigation Image processing Noise

On the concentration of Gaussian Cayley matrices

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bandeira, Afonso S. Kunisky, Dmitriy Mixon, Dustin G. Zeng, Xinmeng Department of Mathematics ETH Zürich Switzerland Department of Computer Science Yale University United States Department of Mathematics The Ohio State University United States Translational Data Analytics Institute The Ohio State University United States

Given a finite group, we study the Gaussian series of the matrices in the image of its left regular representation. We propose such random matrices as a benchmark for improvements to the noncommutative Khintchine ineq... 详细信息

关键词： Benchmarking

An Industrial IoT Driven Approach for Sewage Gas Identification and Reporting System using Intelligent Sensors with Logical Controller 1

学校读者我要写书评

暂无评论

An Industrial IoT Driven Approach for Sewage Gas Identificat...

1st International Conference on Innovative Sustainable Technologies for Energy, Mechatronics and Smart Systems, ISTEMS 2024

作者： Rajasubha, J. Ramya, R. Juliet, A. Hency Janakiraman, V. Devi, S. Rukmani Karuppaiah, S. Dhanalakshmi College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Nano Electronics Materials and Sensors Tamil Nadu Chennai India Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Data Analytics Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechanical Engineering Chennai India Saveetha College of Liberal Arts and Sciences Simats Deemed to Be University Department of Computer Science Tamil Nadu Chennai India R.M.D Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350384246

Based on a real-time sewage gas level detection and monitoring system, this system seeks to offer intelligent solutions for the monitoring of toxic sewage gases. An alarm is issued to the observer who is looking at the circumstances from a distance whenever a specific threshold is crossed. Following this, the data is transmitted together with different gas ppm levels, indicating if the worker can clean or operate securely in that region. The suggested solution incorporates both the IoT platform and the remotely located IoT monitoring devices. This necessitates finding the appropriate threshold values for septic plants and facilities, as well as calibrating gas sensors for use in industry. The gear is meant to provide the sewage worker advance notification whenever the concentration of toxic gaseous substances grows over time, ensuring their safety. The presence of gas, temperature, and other factors in sewage may be detected using a variety of sensors. By notifying sewage workers as well as cleaners via SMS whenever the threshold value drops below the observed levels, this technology helps save people from harmful infections, which is a social good. A number of harmful gas concentrations are graphed out for real-time monitoring, and this is how it accomplishes its job. In order to assess the efficacy of the suggested model, this paper cross-validates it with the Conventional Sewage Gas Detection (CSGD) based on GPRS functioning. The goal of the cross-validation is to create an IoT based Sewage Gas Detection (IoTSGD) system that can monitor and analyze toxic gas levels in real-time and notify workers. Firebase receives the measured gas levels. If the levels rise over a certain point, it will notify the authorized individuals working remotely through their linked mobile devices. An SMS message can alert the authorities if the sewage system is likely to overflow. For the purpose of monitoring, an android app was created and connected with the planned system. © 2024 IEE

关键词： Internet of things

Attentive fine-tuning of Transformers for Translation of low-resourced languages @LoResMT 2021 4

学校读者我要写书评

暂无评论

Attentive fine-tuning of Transformers for Translation of low...

4th Workshop on Technologies for Machine Translation of Low-Resource Languages, LoResMT 2021

作者： Puranik, Karthik Hande, Adeep Priyadharshini, Ruba Durairaj, Thenmozi Sampath, Anbukkarasi Thamburaj, Kingston Pal Chakravarthi, Bharathi Raja Department of Computer Science Indian Institute of Information Technology Tiruchirappalli India ULTRA Arts and Science College Tamil Nadu Madurai India Sri Sivasubramaniya Nadar College of Engineering Tamil Nadu India Kongu Engineering College Tamil Nadu Erode India Sultan Idris Education University Tanjong Malim Perak Malaysia Insight SFI Research Centre for Data Analytics National University of Ireland Galway Ireland

This paper reports the Machine Translation (MT) systems submitted by the IIITT team for the English→Marathi and English-Irish language pairs LoResMT 2021 shared task. The task focuses on getting exceptional translations for rather low-resourced languages like Irish and Marathi. We fine-tune IndicTrans, a pretrained multilingual NMT model for English→Marathi, using external parallel corpus as input for additional training. We have used a pretrained Helsinki-NLP Opus MT English-Irish model for the latter language pair. Our approaches yield relatively promising results on the BLEU metrics. Under the team name IIITT, our systems ranked 1, 1, and 2 in English→Marathi, Irish→English, and English→Irish respectively. The codes for our systems are published. © 2021 Proceedings of the 4th Workshop on Technologies for Machine Translation of Low-Resource Languages, LoResMT 2021. All rights reserved.

关键词： computer aided language translation

Improving Compound Activity Classification via Deep Transfer and Representation Learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Dey, Vishal Machiraju, Raghu Ning, Xia Department of Computer Science and Engineering The Ohio State University ColumbusOH United States Biomedical Informatics The Ohio State University ColumbusOH United States Translational Data Analytics Institute The Ohio State University ColumbusOH United States

Recent advances in molecular machine learning, especially deep neural networks such as Graph Neural Networks (GNNs) for predicting structure activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks are limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another, and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to selectively learn feature-wise and compound-wise transferability. We used the bioassay screening data from PubChem, and identified 120 pairs of bioassays such that the active compounds in each pair are more similar to each other compared to its inactive compounds. Overall, TAc achieves the best performance with average ROC-AUC of 0.801;it significantly improves ROC-AUC of 83% target tasks with average task-wise performance improvement of 7.102%, compared to the best baseline FCN-dmpna (DT). Our experiments clearly demonstrate that TAc achieves significant improvement over all baselines across a large number of target tasks. Furthermore, although TAc-fc achieves slightly worse ROC-AUC on average compared to TAc (0.798 vs 0.801), TAc-fc still achieves the best performance on more tasks in terms of PR-AUC and F1 compared to other methods. In summary, TAc-fc is also found to be a strong model with competitive or even better performance than TAc on a notable number of tar

关键词： Deep neural networks

Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Shengzhe Thomas, Christo Kurisummoottil Hashash, Omar Muralidhar, Nikhil Saad, Walid Ramakrishnan, Naren Sanghani Center for Artificial Intelligence and Data Analytics Computer Science Department Virginia Tech China Bradley Department of Electrical and Computer Engineering Virginia Tech ArlingtonVA United States Department of Computer Science Stevens Institute of Technology NJ United States

Large language models (LLMs) and foundation models have been recently touted as a game-changer for 6G systems. However, recent efforts on LLMs for wireless networks are limited to a direct application of existing language models that were designed for natural language processing (NLP) applications. To address this challenge and create wireless-centric foundation models, this paper presents a comprehensive vision on how to design universal foundation models that are tailored towards the unique needs of next-generation wireless systems, thereby paving the way towards the deployment of artificial intelligence (AI)-native networks. Diverging from NLP-based foundation models, the proposed framework promotes the design of large multi-modal models (LMMs) fostered by three key capabilities: 1) processing of multi-modal sensing data, 2) grounding of physical symbol representations in real-world wireless systems using causal reasoning and retrieval-augmented generation (RAG), and 3) enabling instructibility from the wireless environment feedback to facilitate dynamic network adaptation thanks to logical and mathematical reasoning facilitated by neuro-symbolic AI. In essence, these properties enable the proposed LMM framework to build universal capabilities that cater to various cross-layer networking tasks and alignment of intents across different domains. Preliminary results from experimental evaluation demonstrate the efficacy of grounding using RAG in LMMs, and showcase the alignment of LMMs with wireless system designs. Furthermore, the enhanced rationale exhibited in the responses to mathematical questions by LMMs, compared to vanilla LLMs, demonstrates the logical and mathematical reasoning capabilities inherent in LMMs. Building on those results, we present a sequel of open questions and challenges for LMMs. We then conclude with a set of recommendations that ignite the path towards LMM-empowered AI-native systems. © 2024, CC BY.

关键词： Natural language processing systems

Entity Decomposition with Filtering: A Zero-Shot Clinical Named Entity Recognition Framework

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Averly, Reza Ning, Xia Department of Computer Science and Engineering The Ohio State University United States Department of Biomedical Informatics The Ohio State University United States Translational Data Analytics Institute The Ohio State University United States College of Pharmacy The Ohio State University United States

Clinical named entity recognition (NER) aims to retrieve important entities within clinical narratives. Recent works have demonstrated that large language models (LLMs) can achieve strong performance in this task. While previous works focus on proprietary LLMs, we investigate how open NER LLMs, trained specifically for entity recognition, perform in clinical NER. Our initial experiment reveals significant contrast in performance for some clinical entities and how a simple exploitment on entity types can alleviate this issue. In this paper, we introduce a novel framework, entity decomposition with filtering, or EDF. Our key idea is to decompose the entity recognition task into several retrievals of entity sub-types and then filter them. Our experimental results demonstrate the efficacies of our framework and the improvements across all metrics, models, datasets, and entity types. Our analysis also reveals substantial improvement in recognizing previously missed entities using entity decomposition. We further provide a comprehensive evaluation of our framework and an in-depth error analysis to pave future works. © 2024, CC BY.

关键词： Wiener filtering

Cooperative Multi-source data Trading

学校读者我要写书评

暂无评论

Cooperative Multi-source Data Trading

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Cheng, Jin Ding, Ningning Lui, John C. S. Huang, Jianwei The Chinese University of Hong Kong School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Hong Kong University of Science and Technology Data Science and Analytics Thrust Information Hub Guangzhou China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong The Chinese University of Hong Kong School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network Csijri Joint Research Centre on Smart Energy Storage Shenzhen China

ISBN: (纸本)9798350351255

In the era of big data, data trading significantly enhances data-driven technologies by facilitating data sharing. Despite the clear advantages often experienced by data users when incorporating multiple sources, the topic of multi-source data trading remains largely unexplored. This paper designs a novel data trading framework, which enables multi-source data trading through multi-source cooperation. The proposed framework aims to improve data usage efficiency and increase seller revenue. In particular, we model data sellers' cooperative decisions through the Nash bargaining framework and systematically outline the interactions between sellers and buyers as a two-stage Stackelberg game. A key contribution of this work is the consideration of coupling among diverse data products, which is essential but often overlooked in prior studies. We properly classify data's utility into endogenous and relational categories to disentangle the coupling. Despite the inherent non-convex nature of the optimization problem, we methodically derive the closed-form optimal solutions by decomposing the problem into several subproblems. Interestingly, we reveal that, under our proposed framework, sellers' revenue initially remains steady with the increase of product coupling level, but begins to rise once the level exceeds a certain threshold due to the substitute effect. Finally, experimental results show that our proposed framework can improve the seller's profit by up to 46.32% compared to traditional data trading methods in the current data market. © 2024 IEEE.

关键词： Marketplaces