检索结果-内蒙古大学图书馆

Rice Leaf Disease Identification Using Adam Optimizer Based Modified Differential Evolution Algorithm 1

Rice Leaf Disease Identification Using Adam Optimizer Based ...

1st IEEE International Conference on Ambient Intelligence, Knowledge informatics and Industrial Electronics, AIKIIE 2023

作者： Vijayarangan, R. Yamsani, Nagendar Thirumurugan, V. Arthy, P.S. Alzubaidi, Laith H. Rvt Research Associates Chennai India School of Computer Science and Artificial Intelligence Sr University Warangal India Vistas Cse Chennai India Sri Sai Ram Institute of Technology Department of Electronics and Communication Engineering Chennai India The Islamic University Najaf Iraq

ISBN: (纸本)9798350316469

Recently, one of the grain-based crops that is farmed the most is rice, which is important to the agricultural sector. Furthermore, rice is a significant crop that is consumed by almost half of the global population. However, biotic and abiotic elements including bacteria, viruses, pests, soil fertility, and so forth have an impact on agricultural production. Early disease identification saves farmers time, increases crop yield, and guards against production loss in rice plants. The rice fields used for cultivation are the source of the rice leaf image dataset. The three disease classes that made up the data acquisition were Brown Spot, Bacterial Blight, and Leaf Blast. The ultimate goal of this proposed study is to improve rice leaf detection and classification performance. Thus, using a deep learning approach, this study presented an Adam Optimizer (AO) to carry out an efficient classification of rice leaf disease. Moreover, rice leaf disease detection and classification involve the use of Transfer Learning in conjunction with Inception V3 architecture. The Modified Differential Evolution Algorithm (MDEA) technique is used to determine the transfer learning approach's optimal learning rate. Finally, the proposed AO-MDEA shows better performance metrics in terms of accuracy (98.74%), precision (99.04%), recall (99.12%) and F1-score (99.15%) respectively. © 2023 IEEE.

关键词： Adam optimizer Deep learning Modified Differential Evolution Algorithm Rice leaf disease detection Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Accidental Face Recognition and Detection Using Machine Learning

Accidental Face Recognition and Detection Using Machine Lear...

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： Ashish Sharma Piyansh Agrawal Krishan Bhisham Sharma Imed Ben Dhaou Department of Computer Engineering & Applications GLA University Mathura UP India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science Hekma School of Engineering Computing and Informatics Dar Al-Hekma University Jeddah Saudi Arabia

The data collected from all the States and Union Territories has been compiled in the Publication, according to the ministry of road transport and roads transport research wing. The total number of accident-related deaths in 2018 was 1,51,417, which is a 2.3 percent increase over 2017. Around 85% of accident-related deaths occur in the 18-60 age range, which is the most productive. Road traffic fatalities not only inflict the relatives of the victims considerable emotional suffering, but they also cost the nation a lot of money. In this data maximum hazard happens due to delayed response of family and friends as they are unknown of the situation of the sight of the accident. Also, several cases remain unreported. Our objective is to reduce this number to make our nation strong and prosper. In this current research we are committed to creating a social network where road accidents can be reported quickly to family and friends, so the delayed response can be reduced. The practice of associating a person with a picture has become increasingly common thanks to the media. However, it is less resistant to retinal and fingerprint scanning. The face detection and recognition module created for the current research is described in this paper. Face detection will be performed using Haar-Cascades, while face identification will be performed using Eigenfaces, Fisher faces, and local binary pattern histograms.

关键词： Resistance Technological innovation Road accidents Social networking (online) Smart cities Face recognition Roads

来源：评论

学校读者我要写书评

暂无评论

Cognitive Reframing of Negative Thoughts through Human-Language Model Interaction 61

Cognitive Reframing of Negative Thoughts through Human-Langu...

引用

61st Annual Meeting of the Association for Computational Linguistics, ACL 2023

作者： Sharma, Ashish Rushton, Kevin Lin, Inna Wanyin Wadden, David Lucas, Khendra G. Miner, Adam S. Nguyen, Theresa Althoff, Tim Paul G. Allen School of Computer Science & Engineering University of Washington United States Mental Health America United States Allen Institute for Artificial Intelligence United States Department of Psychiatry and Behavioral Sciences Stanford University United States Center for Biomedical Informatics Research Stanford University United States

ISBN: (纸本)9781959429722

A proven therapeutic technique to overcome negative thoughts is to replace them with a more hopeful "reframed thought." Although therapy can help people practice and learn this Cognitive Reframing of Negative Thoughts, clinician shortages and mental health stigma commonly limit people's access to therapy. In this paper, we conduct a human-centered study of how language models may assist people in reframing negative thoughts. Based on psychology literature, we define a framework of seven linguistic attributes that can be used to reframe a thought. We develop automated metrics to measure these attributes and validate them with expert judgements from mental health practitioners. We collect a dataset of 600 situations, thoughts and reframes from practitioners and use it to train a retrieval-enhanced in-context learning model that effectively generates reframed thoughts and controls their linguistic attributes. To investigate what constitutes a "high-quality" reframe, we conduct an IRB-approved randomized field study on a large mental health website with over 2,000 participants. Amongst other findings, we show that people prefer highly empathic or specific reframes, as opposed to reframes that are overly positive. Our findings provide key implications for the use of LMs to assist people in overcoming negative thoughts. © 2023 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Measurement of Synthetic-Dimension Band Structures in Silicon Coupled Ring Resonators

Measurement of Synthetic-Dimension Band Structures in Silico...

引用

Pacific Rim Conference on Lasers and Electro-Optics (CLEO/Pacific Rim)

作者： Ruming Zhang Liucun Li Mikiya Kamata Toshihiko Baba Tomoki Ozawa Yasutomo Ota Satoshi Iwamoto Research Center for Advanced Science and Technology The University of Tokyo Tokyo Japan Department of Electrical and Computer Engineering Yokohama National University Yokohama Japan Advanced Institute for Materials Research Tohoku University Sendai Japan Department of Applied Physics and Physico-Informatics Keio University Yokohama Japan

We fabricated integrated silicon coupled-ring resonators and measured photonic band structures for synthetic frequency lattices with different configurations. A phase difference between two modulation signals introduc... 详细信息

ISBN: (数字)9798350372076

ISBN: (纸本)9798350372083

关键词： Band structures Phase modulation Resonant frequency Measurement by laser beam Ring lasers Silicon Frequency measurement

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Post-Covid Economic Impact Using NLP Techniques 15

Unveiling the Post-Covid Economic Impact Using NLP Technique...

引用

15th International Conference on Electronics, computers and Artificial Intelligence, ECAI 2023

作者： Barhanpurkar, Kanishk Mandlik, Nikita Rajawat, Anand Singh Goyal, S.B. Mihaltan, Traian Candin Verma, Chaman Raboaca, Maria Simona Thomas J. Watson College of Engineering and Applied Science Binghamton University United States School of Computer Science & Engineering Sandip University Nashik India City University Faculty of Information Technology Petaling Jaya Malaysia Technical University of Cluj-Napoca Faculty of Building Services Cluj-Napoca40033 Romania Eötvös Loránd University Faculty of Informatics Department of Media and Educational Informatics Budapest1053 Hungary Research and Development Institute for Cryogenics and Isotopic Technologies Icsi Energy Department National Ramnicu Valcea Romania

ISBN: (纸本)9798350321388

The research paper presents a novel analysis of textual data based on Natural Language Processing (NLP) techniques to analyse New York Times articles from January 2019 to May 2023. The purpose of this paper is to gain an understanding of the economic impact that follows Covid-19 disease. New York Times (NYT), it was started in 1884 is one of the most prominent newspapers in the world. Additionally, we have used the New York Times Archive API to collect the data for the given timeframe. By analysing sentiment analysis, topic modelling, entity recognition, and keyword extraction, valuable insights can be gathered into market trends, industry shifts, and policy interventions. The authors have created a data science pipeline using Amazon Web Services (AWS), which enables data collection, storage, and visualization. It contributes to a better understanding of the pandemic's short-term and long-term economic effects. The results of this study demonstrate Natural Language Processing techniques' potential as a tool for financial analytics, assisting policymakers, economists, and businesses in formulating recovery strategies. © 2023 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

DECOR 2024: Where Data engineering Meets Intelligent Food and Cooking Innovation

DECOR 2024: Where Data Engineering Meets Intelligent Food an...

引用

International Conference on Data engineering Workshops

作者： Frederic Andres Farshad Fotouhi Gheorghita Ghinea Steve Tanimoto Digital Content and Media Sciences Research Division National Institute of Informatics Tokyo Japan Dpt of Computer Science College of Engineering Wayne State University Detroit MI USA Department of Computer Science Brunel University London London UK Paul G. Allen School of Computer Science & Engineering University of Washington Seattle WA USA

ISBN: (数字)9798350384031

ISBN: (纸本)9798350384048

This extended abstract presents the 7th International Workshop on Data engineering Meets Intelligent Food & Cooking Recipes 2024, which will be held in conjunction with the 40th IEEE International Conference on Data engineering 2024 (ICDE). The primary aim of this workshop is to provide a comprehensive overview of the latest advancements and existing challenges at the intersection of Data engineering and Intelligent Food & Cooking Recipes.

关键词： Technological innovation Conferences Data engineering

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Impact of Height and Bandwidth on Path Loss Exponent of 5G FR1 Wireless Networks at 800, 3500, and 5900 MHz 2

Investigation of the Impact of Height and Bandwidth on Path ...

引用

2nd International Conference on Multidisciplinary engineering and Applied Science, ICMEAS 2023

作者： Imam-Fulani, Yusuf Olayinka Faruk, Nasir Usman, Aliyu D. Abdulkarim, Abubakar Tekanyi, Abdoulie M.S Yaro, Abdulmalik S. Alozie, Emmanuel Garba, Salisu Adewole, Kayode S. Oloyede, Abdulkarim A. Sowande, Olugbenga A. Abdullahi Baba, Bashir Musa, Abdulwaheed Imoize, Agbotiname Lucky Adediran, Yinusa A. Olagunju, Hawau I. Taura, Lawan S. University of Ilorin Department of Telecommunication Science Ilorin Nigeria Ahmadu Bello University Department of Electronics and Telecommunication Engineering Zaria Nigeria Sule Lamido University Department of Information Technology Kafin Hausa Nigeria Sule Lamido University Directorate of Information and Communication Technology Kafin Hausa Nigeria Ahmadu Bello University Department of Electrical Engineering Zaria Nigeria Kampala International University Department of Electrical and Telecommunication Engineering Kampala Uganda University of Hradec Králové Faculty of Informatics and Management Department of Informatics and Qualitative Methods Hradec Králové Czech Republic Sule Lamido University Department of Software Engineering Kafin Hausa Nigeria University of Ilorin Department of Computer Science Ilorin Nigeria Kwara State University Department of Electrical and Computer Engineering Malete Nigeria University of Johannesburg Institute for Intelligent Systems Johannesburg South Africa University of Lagos Department of Electrical and Electronics Engineering Lagos Nigeria Ruhr University Institute of Digital Communication Department of Electrical Engineering and Information Technology Bochum Germany University of Ilorin Department of Electrical and Electronics Engineering Ilorin Nigeria Sule Lamido University Department of Physics Kafin Hausa Nigeria

ISBN: (纸本)9798350358834

5G communication systems provide an end-to-end wireless connection to billions of users and devices across the globe. The quality of signals received during radio communication is notably influenced by the behavior of the radio propagation channel. A major parameter used in characterizing this channel is the Path Loss Exponent (PLE). Several works that have estimated and analyzed the PLE mostly considered the effect of distance and carrier frequency. However, the effect of base station antenna height and channel bandwidth on the PLE for 5G networks have not been adequately considered. To address this, the impact of antenna height of base station and channel bandwidth on the PLE within the 5G Frequency Range 1 (FR1) frequencies was investigated in this study, specifically at 800, 3500, and 5900 MHz. The licensed EDX Signal Pro software® with Cirrus high resolution global terrain and clutter data base was utilized to model, simulate and analyze the PLE for Kano City, Nigeria. Results showed that for the tested frequencies, an increase in either base station height or channel bandwidth leads to a significant reduction in the PLE. This study can be utilized by network planning engineers and the wireless research community to further improve network implementation and optimization toward understanding the behavior of signal propagation in 5G networks and beyond. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Beyond the sandbox: Leveraging symbolic execution for evasive malware classification

引用

computers and Security 2025年 149卷

作者： Vouvoutsis, Vasilis Casino, Fran Patsakis, Constantinos Department of Informatics University of Piraeus 80 Karaoli & Dimitriou str. Piraeus18534 Greece Department of Computer Engineering and Mathematics Universitat Rovira i Virgili Spain Information Management Systems Institute Athena Research Centre Artemidos 6 Marousi15125 Greece

Threat actors continuously update their code to incorporate counter-analysis techniques designed to evade detection and hinder the blocking of their malware. The first line of defence for malware authors is often to bypass static analysis, a relatively straightforward task using readily available tools such as packers and cryptors. To address this shortcoming, defenders send potential malware samples for execution in a sandbox environment. While sandboxing can provide valuable insights into the behaviour of software on an information system, advanced techniques like anti-virtualisation and hooking evasion allow malware to escape detection. The primary objective of this work is to complement sandbox execution with symbolic execution frameworks to detect new malware strains efficiently. Symbolic execution offers a distinct advantage over sandboxing by achieving greater coverage of all possible execution traces, as it can explore every potential execution path, regardless of the evasion methods employed by the malware authors. By carefully selecting the samples to be analysed, we can significantly reduce the workload while extracting essential dynamic features in a fraction of the time and with far fewer computational resources compared to sandboxing. To this end, we leverage machine learning in an automated pipeline, enabling the accurate detection of sophisticated malware using a real-world dataset. Our approach yields average F1 scores of 0.93 for the benign class and 0.99 for the malware class in a binary classification setup, surpassing the detection rates reported in the literature. Additionally, our method outperforms a commercial malware sandbox when applied to the same dataset, further highlighting the efficacy of the proposed method. © 2024 The Authors

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Fostering Synergy: Exploring the Intersection of Operations and Human Resources Management through an RF-SVM Approach 2

Fostering Synergy: Exploring the Intersection of Operations ...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Nayak, Keyurkumar M Renjith Krishnan, K. Khetree, Surekha Dehu Unni, Manu Vasudevan Vignesh, A. Ramya, S. University of Mumbai's Garware Institute of Career Education and Development Mumbai India University of Technology and Applied Sciences Department of Business Administration Shinas Oman Bharati Vidyapeeth College of Engineering Department of Mechanical Engineering Navi Mumbai India St. Claret College Department of Management Bangalore Karnataka India Kalasalingam Academy of Research and Education Department of Business Administration Tamilnadu Krishnankoil India M.Kumarasamy College of Engineering Department of Master of Computer Applications Tamilnadu Karur India

ISBN: (纸本)9798350327533

Since its inception a century ago, HRM has seen significant changes in both theory and practice, with the most notable changes occurring during the past two decades. As a result of a number of factors, both internal and external to the organization, human resource management is no longer seen as merely a maintenance function with minimal financial impact;instead, it is seen by many in the academic and professional communities as the source of sustained competitive advantage in today's global economy. The first stages of the proposed method include preprocessing, feature selection, and model training. It is crucial to apply pre-processing and representation to text input before feeding it to classifiers in order to optimize the performance of machine learning models. Data mining and knowledge -based authentication rely heavily on feature selection. LDA-BERT models are then trained after feature selection has taken place. The proposed method outperforms LDA and BERT, two widely used alternatives. Using the offered method, the system was able to obtain a maximum accuracy of 96.31%. © 2024 IEEE.

关键词： Bidirectional Encoder Representations from Transformers (BERT) Human Resource Management (HRM) Operations Management (OM)

来源：评论

学校读者我要写书评

暂无评论

Indoors Traversability Estimation with RGB-Laser Fusion

Indoors Traversability Estimation with RGB-Laser Fusion

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Christos Sevastopoulos Michail Theofanidis Aref Hebri Stasinos Konstantopoulos Vangelis Karkaletsis Fillia Makedon Department of Computer Science & Computer Engineering University of Texas at Arlington Arlington TX USA University of Texas at Arlington Research Institute Fort Worth TX USA NCSR “Demokritos” Agia Paraskevi Institute of Informatics and Telecommunications Attica Greece

We propose a dual-stream, semi-supervised, attention-based approach that employs feature fusion of RGB and Laser Range Finder (LRF) modalities. Our method lever-ages the strength of two powerful transformer-based networks, i.e. Vision Transformer (ViT) and SegFormer, along with LRF information, to adequately predict whether the scene encountered in the image is safe for a robot to traverse. Towards this effort, we introduce an automated labelling system profiting from the combination of raw velocity readings and laser scanning information. Moreover, we show that overall GOINO-GO detection is enhanced by fusing RGB and laser modalities. Feature fusion is achieved through the employment of a Multi-Head Self-Attention (MHSA) module. Through cross-domain validation, we show that the proposed traversability estimation method can achieve decent amounts of transferability even with limited amount of training data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：