检索结果-内蒙古大学图书馆

Q-Learning Energy Management System (Q-EMS) in Wireless Sensor Network

学校读者我要写书评

暂无评论

Q-Learning Energy Management System (Q-EMS) in Wireless Sens...

Smart Computing, IoT and Machine Learning (SIML), International Conference on

作者： Deden Ardiansyah Mustafid Teddy Mantoro Doctoral Program of Information Systems School of Postgraduate Universitas Diponegoro Semarang Central Java Indonesia Computer Engineering Department Vocational School Universitas Pakuan Bogor West Java Indonesia Media-Tech-Lab Computer Science Department Sampoerna University DKI Jakarta Indonesia

ISBN: (数字)9798350364101

ISBN: (纸本)9798350364118

The energy control of a Wireless Sensor Network (WSN) often leads to an unbalanced state between the battery storage system, energy extraction through photovoltaic systems energy, and energy utilization in the WSN. These disparities result in suboptimal wireless sensor network performance. The reliance on batteries is a major factor contributing to this problem. The Q-Learning Energy Management System (Q-EMS) is designed to address these challenges and improve energy management strategies. The Q-EMS algorithm used a learning process resulting in optimal actions for sensor nodes in different situations. The rewards or punishments nodes receive determine their decisions, which are determined by the Q-EMS algorithm. The Q-learning model approach is aimed at reducing energy consumption and supply in WSNs. Energy supply is categorized into battery-based, transfer-based, and harvesting, while energy consumption can be classified into task-cycle, mobility-based, and data-driven. The development of the Q Learning algorithm model has three scenarios: determining energy needs for WSN, effective energy harvesting strategy, and effective energy transfer. As a result, effective energy demand, harvesting and transfer using the Q-learning algorithm are balanced. However, it needs to be studied in more depth using real data in the field. In future research, I will use real data and optimize the use of the Q-Learning algorithm.

关键词： Wireless communication Wireless sensor networks Energy consumption Q-learning Machine learning algorithms Energy resources Classification algorithms

Tracking Players in a Badminton Court by Two Cameras

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chou, Young-Ching Zhang, Shen-Ru Chen, Bo-Wei Chen, Hong-Qi Lin, Cheng-Kuan Tseng, Yu-Chee Department of Computer Science National Yang Ming Chiao Tung University Taiwan Undergraduate Degree Program of Systems Engineering and Technology National Yang Ming Chiao Tung University Taiwan Computer Science and Information Engineering Chung Cheng Institute of Technology NDU Taiwan

This study proposes a simple method for multi-object tracking (MOT) of players in a badminton court. We leverage two off-the-shelf cameras, one on the top of the court and the other on the side of the court. The one on the top is to track players’ trajectories, while the one on the side is to analyze the pixel features of players. By computing the correlations between adjacent frames and engaging the information of the two cameras, MOT of badminton players is obtained. This two-camera approach addresses the challenge of player occlusion and overlapping in a badminton court, providing player trajectory tracking and multi-angle analysis. The presented system offers insights into the positions and movements of badminton players, thus serving as a coaching or self-training tool for badminton players to improve their gaming strategies. Copyright © 2023, The Authors. All rights reserved.

关键词： Cameras

An algorithm for conditional-fault local diagnosis of multiprocessor systems under the MM⁎ model

学校读者我要写书评

暂无评论

Theoretical computer Science 2024年 987卷

作者： Lv, Yali Lin, Cheng-Kuan Hsu, D. Frank Fan, Jianxi School of Information Technology Henan University of Chinese Medicine Zhengzhou China Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Undergraduate Degree Program of Systems Engineering and Technology National Yang Ming Chiao Tung University Hsinchu Taiwan Computer Science and Information Engineering Chung Cheng Institute of Technology NDU Taoyuan Taiwan Department of Computer and Information Science Fordham University New York United States School of Computer Science and Technology Soochow University Suzhou China

Diagnosis is a crucial subject for maintaining the reliability of multiprocessor systems. Under the MM⁎ diagnosis model, Sengupta and Dahbura proposed a polynomial-time algorithm with time complexity O(N5) to diagnose a system with N processors. In this paper, we propose a (α,β)-trees combination S(u,X,α,β) and give an algorithm to identify the fault or fault-free status of each processor for conditional local diagnosis under the MM⁎ model. According to our results, a connected network with a (α,β)-trees combination S(u,X,α,β) for a node u is conditionally locally (α+2β−3)-diagnosable at node u and the time complexity of our algorithm to diagnose u is O(α2β+αβ2). As an application, we show that our algorithm can identify the status of each node of n-dimensional star graph Sn if the faulty node number does not exceed 3n−8. Compared with existing algorithms, our algorithm allows more faulty nodes in a multiprocessor system. © 2024 Elsevier B.V.

关键词： Computational complexity

Tackling Shortcut Learning in Deep Neural Networks: An Iterative Approach with Interpretable Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ghosh, Shantanu Yu, Ke Arabshahi, Forough Batmanghelich, Kayhan Department of Electrical and Computer Engineering Boston University MA United States Intelligent Systems Program University of Pittsburgh PA United States MetaAI Menlo ParkCA United States

We use concept-based interpretable models to mitigate shortcut learning. Existing methods lack interpretability. Beginning with a Blackbox, we iteratively carve out a mixture of interpretable experts (MoIE) and a residual network. Each expert explains a subset of data using First Order Logic (FOL). While explaining a sample, the FOL from biased BB-derived MoIE detects the shortcut effectively. Finetuning the BB with Metadata Normalization (MDN) eliminates the shortcut. The FOLs from the finetuned-BB-derived MoIE verify the elimination of the shortcut. Our experiments show that MoIE does not hurt the accuracy of the original BB and eliminates shortcuts effectively. © 2023, CC BY.

关键词： Deep neural networks

COULD DROPPING A FEW CELLS CHANGE THE TAKEAWAYS FROM DIFFERENTIAL EXPRESSION?

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shiffman, Miriam Giordano, Ryan Broderick, Tamara MIT Computational & Systems Biology Program United States MIT Dept. of Electrical Engineering & Computer Science United States UC Berkeley Dept. of Statistics United States

Analysis of differential gene expression plays a fundamental role in biology toward illuminating the molecular mechanisms driving a difference between groups (e.g., due to treatment or disease). While any analysis is run on particular cells or samples, the intent is to generalize to future occurrences of the treatment or disease. Implicitly, generalization is justified under the assumption that present and future samples are independent and identically distributed from the same population. Though this assumption is always false, we might hope that any deviation from the assumption is small enough that A) fundamental conclusions of the analysis still hold, and B) standard tools like standard error, significance, and power still reflect generalizability. Conversely, we might worry about these deviations, and reliance on standard statistical tools, if conclusions could be substantively changed by dropping a very small fraction of observations. While checking every small fraction is computationally intractable, recent work develops an approximation to identify when such an influential subset exists. Building on this work, we develop a metric for dropping-data robustness of differential expression;namely, we cast the analysis in a differentiable form suitable to the approximation, extend the approximation to models whose hyperparameters depend on the full dataset, and extend the notion of a data point from a single cell to a pseudobulk observation. We then overcome the inherent non-differentiability of gene set enrichment analysis to develop an additional approximation for the robustness of top gene sets. We use our tool to assess the robustness of differential expression for published single-cell RNA-seq data, and discover that thousands of genes can have their results flipped by dropping Copyright © 2023, The Authors. All rights reserved.

关键词： Diseases

DTIAM: A unified framework for predicting drug-target interactions, binding affinities and activation/inhibition mechanisms

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lu, Zhangli Lei, Chuqi Wang, Kaili Qin, Libo Tang, Jing Li, Min School of Computer Science and Engineering Central South University Changsha410083 China Research Program in Systems Oncology Faculty of Medicine University of Helsinki HelsinkiFI00014 Finland

Accurate and robust prediction of drug-target interactions (DTIs) plays a vital role in drug discovery. Despite extensive efforts have been invested in predicting novel DTIs, existing approaches still suffer from insufficient labeled data and cold start problems. More importantly, there is currently a lack of studies focusing on elucidating the mechanism of action (MoA) between drugs and targets. Distinguishing the activation and inhibition mechanisms is critical and challenging in drug development. Here, we introduce a unified framework called DTIAM, which aims to predict interactions, binding affinities, and activation/inhibition mechanisms between drugs and targets. DTIAM learns drug and target representations from large amounts of label-free data through self-supervised pre-training, which accurately extracts the substructure and contextual information of drugs and targets, and thus benefits the downstream prediction based on these representations. DTIAM achieves substantial performance improvement over other state-of-the-art methods in all tasks, particularly in the cold start scenario. Moreover, independent validation demonstrates the strong generalization ability of DTIAM. All these results suggested that DTIAM can provide a practically useful tool for predicting novel DTIs and further distinguishing the MoA of candidate drugs. DTIAM, for the first time, provides a unified framework for accurate and robust prediction of drug-target interactions, binding affinities, and activation/inhibition mechanisms. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

Exploring ERP User Behaviour in Developing Countries: Integrating Self-efficacy and UTAUT Perspectives 5

学校读者我要写书评

暂无评论

Exploring ERP User Behaviour in Developing Countries: Integr...

5th International Conference on Advancement in Data Science, E-Learning and Information systems, ICADEIS 2023

作者： Syamsuar, Dedy Oktaharisetia, Muhammad Angga Witarsyah, Deden Luthfi, Ahmad Dell, Peter Permana, Yudistira Sira Antoni, Darius Bina Nusantara University School of Information Systems Information Systems Department Indonesia Universitas Bina Darma Program Pasca Sarjana Palembang Indonesia Telkom University School of Industrial Engineering Bandung Indonesia Islamic University of Indonesia Faculty of Industrial Technology Department of Informatics Indonesia Curtin University School of Management and Marketing Faculty of Business and Law Australia Politeknik Sekayu Teknik Informatika Sekayu Indonesia Universitas Indo Global Mandiri Faculty of Computer Science Palembang Indonesia

ISBN: (纸本)9798350303414

ERP stands for enterprise resource planning. It is an information system that is all rolled into one, is very flexible and adaptable, and optimizes business operations while also centralizing all of the company's data. This study aims to empirically investigate the elements that affect users' intention and usage of enterprise resource planning (ERP). This research incorporates self-efficacy into the unified theory of acceptance and use of technology (UTAUT2). A quantitative technique was taken, and as a result, 143 replies that might be used were effectively collected. After that, the information was put through a structural equation modelling partial least square (SEM-PLS) analysis. According to the findings of this research, self-efficacy appears to have a significant influence on all endogenous variables (EE, BI, and UB), as indicated by t-values of 3.951, 7.573, and 5.492, respectively. In addition, the analysis also indicated that PE (4.317), EE (2.397), and HM (3.084) are likewise statistically and substantively significant to BI. The result shows that the R2 for BI and UB indicate a moderate impact of 0.603 and 0.521, respectively. It is suggested that the model has valuable applications in academic and real-world contexts. © 2023 IEEE.

关键词： Enterprise resource planning

Analysis of the Brazilian Climate Data Influence on Soybean Pricing by Using Long Short-Term Memory Models

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Oliva, Jefferson Tales Martelli, Otávio Pigozzo de Castro Barbosa, Marco Antônio Dal Molin, Viviane Casanova, Dalcimar Teixeira, Marcelo Graduate Program in Electrical and Computer Engineering Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil Department of Academic Informatics Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil Graduate Program in Production and Systems Engineering Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil

This work uses machine learning to verify whether the Brazilian climate influences international soybean price prediction. For this, climatic data, dollar quotes, inflation, and annual soybean production were collected from different data sources. Then, the collected data were pre-processed and grouped by Brazilian state. Afterward, data from the five most productive Brazilian states are chosen, such as Mato Grosso (MT), Mato Grosso do Sul (MS), Goiás (GO), Paraná (PR), and Rio Grande do Sul (RS). Afterward, predictive models are built using the long short-term memory (LSTM) method, which is applied in each chosen state dataset considering two different settings: with and without climatic data. Thus, two models were built for each Brazilian state, totaling ten predictors. In the experimental evaluation, when trained with climatic data, the PR model achieved the lowest values of root mean squared error (RMSE) and mean absolute error (MAE). Regarding predictors trained without climate data, the RS and PR obtained the lowest values of RMSE and MAE, respectively. After conducting statistical hypothesis tests, no significant difference was found among models, stating, with 95% certainty, that, in this study, the Brazilian climatic data did not influence the model performance for predicting soybean prices. On the other hand, one of the main contributions of work is conducting an unprecedented study about soybean price prediction using Brazilian climatic data. © 2024, The Authors. All rights reserved.

关键词： Long short-term memory

Diabetes Classification Using Support Vector Machine: Binary Classification Model 4

学校读者我要写书评

暂无评论

Diabetes Classification Using Support Vector Machine: Binary...

4th International Conference on Information and Communications Technology, ICOIACT 2021

作者： Rabiha, Suciana Ghadati Wibowo, Antoni Lukas Heryadi, Yaya Computer Science Department BINUS Graduate Program-Doctor of Computer Science. Information Systems Department BINUS Online Learning Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University 11480 Indonesia Faculty of Engineering Universitas Katolik Indonesia Atma Jaya Indonesia Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University 11480 Indonesia

ISBN: (纸本)9781665433945

One of the health problems that require special attention is diabetes, besides the growth of this disease infection is increasing in various circles ranging from children, adults, men, women and the elderly. So to detect diabetes at an early stage, machine learning algorithms are the right choice to help detect indications of diabetes. This paper presents experimental results related to the exploration of the use of a Super Vector Machine (SVM) for data classification of Diabetes. The model used in this experiment is the Binary Classification Model. Based on the test results, the highest accuracy is obtained by using a total of 700 lines of data, which is 75,7143%. The Best estimated feasible point in Box Constraint is 272.29 with a KernelScale area of 72.627. © 2021 IEEE

关键词： Face recognition