检索结果-内蒙古大学图书馆

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

AgriLLM:Harnessing Transformers for Framer Queries

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Didwania, Krish Seth, Pratinav Kasliwal, Aditya Agarwal, Amit Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering India Department of Data Science & Computer Applications India Enterprise Analytics & Data Science Artificial Intelligence - Center of Excellence Wells Fargo International Solutions Private Limited Bangalore India

Agriculture, vital for global sustenance, necessitates innovative solutions due to a lack of organized domain experts, particularly in developing countries where many farmers are impoverished and cannot afford expert consulting. Initiatives like Farmers Helpline play a crucial role in such countries, yet challenges such as high operational costs persist. Automating query resolution can alleviate the burden on traditional call centers, providing farmers with immediate and contextually relevant information. The integration of Agriculture and Artificial Intelligence (AI) offers a transformative opportunity to empower farmers and bridge information gaps. Language models like transformers, the rising stars of AI, possess remarkable language understanding capabilities, making them ideal for addressing information gaps in agriculture. This work 1 explores and demonstrates the transformative potential of Large Language Models (LLMs) in automating query resolution for agricultural farmers, leveraging their expertise in deciphering natural language and understanding context. Using a subset of a vast dataset of real-world farmer queries collected in India, our study focuses on approximately 4 million queries from the state of Tamil Nadu, spanning various sectors, seasonal crops, and query types. Copyright © 2024, The Authors. All rights reserved.

关键词： Agriculture

Energetic Content based Image Retrieval Scheme using Improved Deep Learning Strategy with Image Analysis Technique 9

学校读者我要写书评

暂无评论

Energetic Content based Image Retrieval Scheme using Improve...

9th IEEE International Conference on Smart Structures and Systems, ICSSS 2023

作者： Karkuzhali, S. Malathi, P. Thenmozhi, A. Aiyyasamy, Velu Keerthika, A. Uthayakumar, G.S. R.M.K. Engineering College Department of General Engineering Tamil Nadu Chennai India Simats Saveetha College of Liberal Arts and Sciences Department of Data Analytics India Kings Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Meenakshi Sundararajan Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India St. Joseph's Institute of Technology Department of Ece Tamil Nadu Chennai India

ISBN: (纸本)9798350384208

One popular approach to retrieving images from huge, unprocessed datasets is content-based image retrieval, or CBIR. The conventional ways of data retrieval, however, are not meeting the needs of consumers. The number of consumer-accessible photographs also keeps growing, and there are an abundance of digital platforms for development and dissemination. Consequently, digital image processing is both ubiquitous and permanent in many fields. Consequently, effective strategies are required for both the speedy access to these massive picture databases and the recovery of comparable photos from this massive number of images based on a specific picture (query). The computation of depiction of features and resemblance is crucial to the efficiency of a CBIR system. We introduce LAIRS, a cutting-edge deep learning method that integrates the extraction of features and aims to do this with classification to facilitate rapid picture retrieval. For a transparent evaluation of the proposed scheme's efficiency, the suggested logic is cross-validated using Convolutional Neural Networks (CNNs), a classic deep learning paradigm. Several in-depth observational experiments for various CBIR tasks employing an image database have shown encouraging results, teaching us important lessons for making CBIR system more efficient. With the use of CBIR structures, a different collection can find similar pictures to the query image. There is little doubt that Google's search per photo tool is perhaps the most widely used CBIR approach. © 2023 IEEE.

关键词： Image analysis

AI based Stock Market Analysis and Decision Making System using Design Thinking Approach 8

学校读者我要写书评

暂无评论

AI based Stock Market Analysis and Decision Making System us...

8th International Conference on Inventive Systems and Control, ICISC 202

作者： Kumar, M.Venkatesh Umamaheswari, M. Bharathi, C. Hema Maruthaveni, R. Devi, M.Nirmala Prasanna, R. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Tamilnadu Chennai India Dr. Sns Rajalakshmi College of Arts and Science Department of Business Administration Tamilnadu Coimbatore India Tamil Nadu Agricultural University Department of Physical Science and Information Technology Tamilnadu Coimbatore India Dr. Sns Rajalakshmi College of Arts and Science Department of Computer Science with Data Analytics Tamilnadu Coimbatore India Dr. Sns Rajalakshmi College of Arts and Science Department of Management Studies Tamilnadu Coimbatore India

ISBN: (纸本)9798350386578

Stock market is a dynamic and ever-changing environment that can be both exciting and challenging for investors. Equities, primarily referred to as stocks, are traded on stock exchanges around the world and reflect ownership in a business. The stock market is an essential tool for companies to raise capital, and investors use it to grow their wealth. Investing in stocks requires a thorough understanding of the market and the individual companies in which you are interested. The financial health of a company must be taken into account and can be analyzed using financial statements and other data. Another critical factor is the overall economic climate, as market conditions can significantly impact stock prices. It's crucial to have a long-term outlook and avoid being influenced by momentary market changes when making equity investments. A random walk is a mathematical model used to describe a sequence of steps or movements where each step is determined by chance. It is often used in various fields, including physics, finance, and statistics. Random walk theory has important implications in various fields, including the efficient market hypothesis in finance and the modeling of diffusion processes in physics. To effectively predict the future stock price using conventional and modern machine learning models. Compare the performance of different models and identify a higher accuracy prediction model using the selected important factors from disparate data sources. © 2024 IEEE.

关键词： Decentralized finance

data driven VRP: A neural network model to learn hidden preferences for VRP

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mandi, Jayanta Canoy, Rocsildes Bucarey, Víctor Guns, Tias Data Analytics Laboratory Vrije Universiteit Brussel Belgium Institute of Engineering Sciences Universidad de o'Higgins Rancagua Chile Department of Computer Science Ku Leuven Belgium

The traditional Capacitated Vehicle Routing Problem (CVRP) minimizes the total distance of the routes under the capacity constraints of the vehicles. But more often, the objective involves multiple criteria including not only the total distance of the tour but also other factors such as travel costs, travel time, and fuel consumption. Moreover, in reality, there are numerous implicit preferences ingrained in the minds of the route planners and the drivers. Drivers, for instance, have familiarity with certain neighborhoods and knowledge of the state of roads, and often consider the best places for rest and lunch breaks. This knowledge is difficult to formulate and balance when operational routing decisions have to be made. This motivates us to learn the implicit preferences from past solutions and to incorporate these learned preferences in the optimization process. These preferences are in the form of arc probabilities, i.e., the more preferred a route is, the higher is the joint probability. The novelty of this work is the use of a neural network model to estimate the arc probabilities, which allows for additional features and automatic parameter estimation. This first requires identifying suitable features, neural architectures and loss functions, taking into account that there is typically few data available. We investigate the difference with a prior weighted Markov counting approach, and study the applicability of neural networks in this setting. © 2021, CC BY-NC-SA.

关键词： Vehicle routing

On Aggregation in Ensembles of Multilabel Classifiers

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Nguyen, Vu-Linh Hüllermeier, Eyke Rapp, Michael Mencía, Eneldo Loza Fürnkranz, Johannes Heinz Nixdorf Institute Department of Computer Science Paderborn University Germany Knowledge Engineering Group TU Darmstadt Germany Computational Data Analytics Group JKU Linz Austria

While a variety of ensemble methods for multilabel classification have been proposed in the literature, the question of how to aggregate the predictions of the individual members of the ensemble has received little attention so far. In this paper, we introduce a formal framework of ensemble multilabel classification, in which we distinguish two principal approaches: "predict then combine" (PTC), where the ensemble members first make loss minimizing predictions which are subsequently combined, and "combine then predict" (CTP), which first aggregates information such as marginal label probabilities from the individual ensemble members, and then derives a prediction from this aggregation. While both approaches generalize voting techniques commonly used for multilabel ensembles, they allow to explicitly take the target performance measure into account. Therefore, concrete instantiations of CTP and PTC can be tailored to concrete loss functions. Experimentally, we show that standard voting techniques are indeed outperformed by suitable instantiations of CTP and PTC, and provide some evidence that CTP performs well for decomposable loss functions, whereas PTC is the better choice for non-decomposable losses. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting