检索结果-内蒙古大学图书馆

1st International Conference on Technologies for Smart Green Connected Society 2021, ICTSGS 2021

作者： Hema, D. Deva Soundrya, Sai Kumaran, Bharath Harini, V. Department of Computer Science and Engineering SRM Institute of Science and Technology Bharathi Salai Ramapuram Chennai600089 India

ISBN: (纸本)9781607685395

The paper shows a cutting edge prototype system which can recommend most comprehensive travel plans that include brand new, points of cutting-edge interest factors (POIs). It systematically gathers and analyzes data on thousands of cutting-edge tourism destinations and geographical nodes. Tour feel is a recommendation framework which examines the preference information of modern day diverse tourists based totally on the transport records collected from various towns. Humans can get properly-in-shape path plans, which consist of a sequence of POIs primarily based on vacationers' constraints and goals, a way to advance ultra-modern excursion recommendations. Multiple scenic spots and entrances are common in big-scale POIs, which are known as brilliant-POIs in this article. Maximum contemporary excursion advice algorithms, alternatively, forget the big expertise determined inside super POIs. A layer machine which takes into account the ultra-modern route architecture (Outer model) and panoramic routes within outstanding POIs (internal model). A full-on-integration-based Embedded Keep variable neighborhood descent (VND) algorithm is used to merge templates. A greedy randomized adjustable path advent system (grasp), for local improvements in the internal version of the outer version and VND. The first rate-POI is considered a "meta node" in the development of trendy outer routes. Dijkstra Algorithm with Pruning dynamically reviews the most satisfying path within the exquisite POI in the internal model to conform to the outer direction. The obtained end results provide the traveler with the ultimate quality route and the focus point chosen by the users. © The Electrochemical Society

关键词：

来源：评论

学校读者我要写书评

暂无评论

Target Coverage and Network Connectivity Challenges in Wireless Sensor Networks

EAI Endorsed Transactions on Energy Web

引用

EAI Endorsed Transactions on Energy Web 2021年第31期8卷 1-15页

作者： Deepa, R. Venkataraman, Revathi Research Scholar Department of Computer Science and Engineering SRM Institute of Science and Technology KattankulathurTamilnadu India

Target Coverage and Network Connectivity in Wireless Sensor Networks (WSNs) plays a momentous role in the field of monitoring environment, habitant observing, disaster recovery, surveillance, etc. Coverage and Network Connectivity collectively can be considered as a proportion of Quality of Service (QoS) in a sensor network. It implies the coverage of each point in the detecting field while in the meantime fulfilling the measure that each node is surrounded by the equivalent neighbourhood of at least one other node. Many primary issues influence the outline and performance of WSN. A Comprehensive survey is made based on the scheduling algorithm and set cover approach, in which we analyze various approaches and their algorithm complexity. Firstly, the scheduling algorithm intermittently provides the required data service with guaranteed efficiency. This methodology can efficiently reduce the entire number of active nodes in the network, resulting in maximizing the network lifetime. Secondly, the set cover approach plays a major role in solving target coverage problem which group sensors into each cover set thereby, target coverage was achieved. Typical issues and open research challenges are addressed by classifying the approaches available in literature into three broad categories namely, adaptable coverage radius, coverage deployment strategy, and sleep scheduling. This survey aims to provide a better perceptive of the existing open challenges and possible futuristic approaches for target coverage and network connectivity in wireless sensor networks. © 2020. Deepa.R et al., licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution license, which permits unlimited use, distribution and reproduction in any medium so long as the original work is properly cited. All rights reserved.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

A Fine-Grained Flash-Memory Fragment Recognition Approach for Low-Level Data Recovery

引用

Chinese Journal of Electronics 2022年第4期31卷 732-740页

作者： ZHANG Li HAO Shengang ZHANG Quanxin Department of Media Engineering Zhejiang University of Media and Communication School of Computer Science Beijing Institute of Technology

Data recovery from flash memory in the mobile device can effectively reduce the loss caused by data corruption. Type recognition of data fragment is an essential prerequisite to the low-level data recovery. Previous works in this field classify data fragment based on its file type. Still, the classification efficiency is low, especially when the data fragment is a part of a composite *** propose a fine-grained approach to classifying data fragment from the low-level flash memory to improve the classification accuracy and efficiency. The proposed method redefines flash-memory-page data recognition problem based on the encoding format of the data segment, and applies a hybrid machine learning algorithm to detect the data type of the flash page. The hybrid algorithm can significantly decompose the given data space and reduce the cost of training. The experimental results show that our method achieves better classification accuracy and higher time performance than the existing methods.

关键词： Flash fragmentation recognition Fine-grained Machine learning algorithm Support vector machine Decision tree Digital forensics

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis of Liver Disease Using Random Forest Machine Learning Algorithm 1

Predictive Analysis of Liver Disease Using Random Forest Mac...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Vetrithangam, D. Kumar, Nallabariki Praveen Arya, Neha Tiwari, Amrita Raju, G. Jaya Srinivas, Gollapalli Veera Satya Chandigarh University Department of Computer Science & Engineering Mohali India Vnr Vignana Jyothi Institute of Engineering and Technology Department of Computer Science and Engineering Hyderabad India Ajay Kumar Garg Engineering College Department of Computer Science and Engineering Ghaziabad India Aditya College of Engineering and Technology Department of Computer Science and Engineering Surampalem India Aditya College of Engineering and Technology Department of Mechanical Engineering Surampalem India

ISBN: (纸本)9798350376517

The proposed system's objective is to improve the performance of diagnosing liver diseases through machine learning by using the Random Forest algorithm. Such systems accommodate a detailed database that comprises of several parameters of the patient's health status, through which important factors that cause liver disease may be determined. The analysis utilizes Random Forest, a feature selection technique that boosts the efficacy of the model's results in determining the outcomes of liver diseases with accuracy and recall. The training is conducted to reduce the component's error rate as well as to determine the ability of the system to perform complex tasks. Likewise, the proposed solution also focuses on the easy-to-use front-end for the target groups - the healthcare organizations - so the solution perfectly fits into their day-to-day work. In sum, this system is designed to become an innovative, cutting edge, and evidence-based tool for the notification and prevention of the liver disease in its early stage so as to enhance patients' outcomes and make more efficient use of the health care facilities. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Wireless mobile charging for smart electrical bus 8

Wireless mobile charging for smart electrical bus

引用

8th IEEE International Conference on science, technology, engineering and Mathematics, ICONSTEM 2023

作者： Manimaran, B. Tamilselvi, M. Chanuinunganbi, Sanasam Rajalakshmi Institute of Technology Department of Electronics and Communication Engineering Chennai India Srm Institute of Science and Technology Department of Electronics and Communication Engineering Ramapuram Campus Chennai India KoneruLakshamiah Education Foundation Department of Computer Science and Engineering Vijayawada India

ISBN: (纸本)9798350347791

Solar energy is the most available renewable energy source unlike the energy sources and it is the immaculate energy source. Everyone can make it especially as it is providing tariff free electricity and power in long term investment plan. These are two different technologies to generate the electricity using solar photovoltaic (PV) and concentrated solar power (CSP) system. The contactless energy transfer is always used to transfer the energy from source to load without any physical connection. Natural fuels have declined as usage of fuels has increased day by day. And so, the world is moving forward to electric vehicles. In the fast paced would of technology, the electric buses will become mandatory and efficient for long driver in future years. The main idea is to combine the solar energy for hazard and hassle-free supply using contactless energy transfer (CET). The CET is system is combined with solar energy source for mobile charging. And the additional solar energy can be stored in battery electric bus. Hence the CET system removes the distribution cables and it will be safer, comfort, satisfactory and adaptable. © 2023 IEEE.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Multi-Concept Learning for Scene Graph Generation

引用

IEEE Transactions on Image Processing 2025年 34卷 3366-3376页

作者： Lyu, Xinyu Gao, Lianli Xie, Junlin Zeng, Pengpeng Tian, Yulu Shao, Jie Shen, Heng Tao Southwestern University of Finance and Economics School of Computing and Artificial Intelligence Chengdu611731 China University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518000 China Ant Group Hangzhou China UESTC School of Computer Science and Engineering Chengdu China Shenzhen Institute for Advanced Study UESTC China University of Electronic Science and Technology of China UESTC School of Computer Science and Technology Chengdu China Tongji University Shanghai China

Existing Unbiased Scene Graph Generation (USGG) methods only focus on addressing the predicate-level imbalance that high-frequency classes dominate predictions of rare ones, while overlooking the concept-level imbalance. Actually, even if predicates themselves are balanced, there is still a significant concept-imbalance within them due to the long-tailed distribution of contexts (i.e., subject-object combinations). This concept-level imbalance poses a more pervasive and challenging issue compared to the predicate-level imbalance since subject-object pairs are inherently complex in combinations. To address the issue, we propose Multi-Concept Learning (MCL), a novel concept-level balanced learning framework orthogonal to existing SGG methods. MCL first quantifies the concept-level imbalance across predicates in terms of different amounts of concepts, representing as multiple concept-prototypes within the same class. Then, to achieve balanced learning across different concepts (i.e., concept-prototypes), we introduce the Concept-based Balanced Memory (CBM), which guides SGG models in generating balanced representations for concept-prototypes. Furthermore, the Concept Regularization (CR) technique is proposed to effectively help models in aligning relation features to their corresponding concept-prototypes, thereby generating concept-level compact and predicate-level distinctive representations for robust relation recognition. Finally, we introduce a novel metric, mean Context Recall (mCR@K), as a complement to mean Recall (mR@K), to evaluate the model's performance across concepts (determined by contexts) within the same predicate. Extensive experiments demonstrate the remarkable efficacy of our model-agnostic strategy in enhancing the performance of benchmark models on both VG-SGG and OI-SGG datasets, leading to new state-of-the-art achievements in two key aspects: predicate-level unbiased relation recognition and concept-level compositional generability. © 1992-2012

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Investigation of Attention Deficit Hyperactivity Disorder with Image Enhancement and Calculation of Brain Grey Matter Volume using Anatomical and Resting-State functional MRI 1

引用

Virtual International Conference on Futuristic Communication and Network Technologies, VICFCNT 2021

作者： Rupni, K. Usha Priya, P. Aruna Department of Electronics and Communication Engineering SRM Institute of Science and Technology Tamil Nadu Chennai India

ISBN: (数字)9789811983382

ISBN: (纸本)9789811983375

Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental disorder affecting school children which often continues till their adulthood and makes their normal life difficult. Therefore, detection at the early stage of the disorder is very essential. Till today the diagnosis of ADHD is done by doctors using the guidelines in American Psychiatric Association's Diagnostic and Statistical Manual (DSM-5). This diagnosis is based on the symptoms which change over time. Therefore, the use of non-invasive imaging techniques like functional magnetic resonance imaging (fMRI) is necessary and may support doctors in the diagnosis of ADHD. In this paper, we have used structural and functional MRI scan images to investigate and analyse the difference between ADHD and its subtypes. Most of the research earlier is done on the classification between ADHD-affected and normal brains. Therefore, in this research work, ADHD and non-ADHD brain along with the ADHD subtypes brain difference based on image enhancement technique is investigated. The result shows image sharpening filters give the difference in the shape of the caudate nucleus for typically developing (TD) and ADHD subtypes. The grey matter volume of the brain is calculated, and we get values ranging approximately from 3.3 × 105 mm3 to 3.8 × 105 mm3 for an anatomical image. The result indicates that the grey matter volume of ADHD brains is slightly lesser than TD children’s brains. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Automated semantic segmentation and Diagnosis of Coconut Tree Infection Using Drone Imagery and Machine Learning approach for smart agriculture

Automated semantic segmentation and Diagnosis of Coconut Tre...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Vasumathy, M. Devakanth, J. Jude Moses Anto Thirugnanam, Mythili Roselinkiruba, R. Hamsaveni, R. Nandhini, R. Kingston Engineering College Computer Science and Engineering Tamilnadu Vellore India Madanapalle Institute of Technology & Science Department ofComputer Applications Andhra Pradesh Madanapalle India Vellore Institute of Technology School of Computer Science and Engineering Tamilnadu Vellore India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Computer Science and Engineering Tamilnadu Chennai India Computer Science and Engineering Andhra Pradesh Chittoor India D.K.M College for Women Computer Science and Applications Tamilnadu Vellore632001 India

ISBN: (纸本)9798331539948

The coconut industry of our Indian nation contributes an extensive range of economy to the national GDP. About 19,247 million coconuts, or 31.45% of the world's production, were produced in India in the year 2021-2022 making it the top producer. However, the coconut farmers face major challenges from a plethora of pests and diseases of coconut trees, and yield loss, which affects the farmers economically, standing around at 10-15%. Major pests, such as Rhinoceros beetles and red palm weevils, are highly destructible, in some scenarios leading even to the mortality of crops. In most of the cases, when trees that are affected need a cure, farmers have to climb the trees to put chemicals in crowns infested with the pests, exposing the farmers to harmful chemicals and risking severe injuries or permanent disabilities. As a solution, the proposed methodology involves the collection of extensive drone imagery from coconut plantations, followed by the annotation and preprocessing of the data. This work utilizes state-of-the-art deep learning models, including Unet, convolutional neural networks (CNNs) for semantic segmentation, to differentiate coconut trees from the background and other vegetation. Subsequently, machine learning classifiers are employed to diagnose diseases by analyzing visual symptoms present in the segmented trees. The proposed approach offers significant improvements in accuracy and efficiency compared with other traditional manual methods, providing real-time insights into tree health and disease management. This system has the potential to enhance crop monitoring, optimize resource allocation, and ultimately increase agricultural productivity. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

An Efficient Dilated DTCN with Residual LSTM-based Allergenicity Prediction for Chemical Compounds using Optimal Weighted Feature Selection and Improved Optimization Mechanism

An Efficient Dilated DTCN with Residual LSTM-based Allergeni...

引用

Networking and Communications (ICNWC), International Conference on

作者： T. Padmavathy M. Thenmozhi Thirumurthy Madhavan Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai India Department of Networking and Communications SRM Institute of Science and Technology Chennai India Department of Genetic Engineering SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

Allergy is the sudden response of the immunity system which arises later the disclosure of allergens like chemicals, proteins and peptides. In the early times, multiple techniques were formed for allergenicity forecasting of peptides and proteins. However, there is no technique to anticipate the chemical and potential allergenic. The standard food allergen recognition mainly depends on vitro and vivo research, which frequently needs more time and is expensive. Artificial Intelligence (AI) operates a quick food allergen detection model, which solves the above-defined problems and becomes an effective auxiliary tool. Evaluation of potential allergenicity of protein is required at any movement of transgenic proteins implemented in the food chain. Therefore, it is necessary to solve more complications involved in the conventional allergenicity prediction technique for chemical compounds. Thus, a new allergenicity prediction framework for chemical compounds is designed using deep learning techniques. Initially, essential allergenicity data are accumulated from the standard measures. Next, the acquired data are presented for the optimal weighted feature selection stage. In this phase, the weights and features are selected optimally using Opposition Tasmanian Devil Optimization (OTDO). Further, the adopted optimal weighted features are offered to the allergenicity forecasting stage. Here, the allergenicity is predicated on using the developed "Dilated Deep Temporal Context Networks with Residual Long Short-Term Memory Networks (DiDNet-ResLSTM)". Hence, the recommended allergenicity prediction model effectively higher performance rate in different experimental observations.

关键词： Proteins Peptides Predictive models Feature extraction Chemical compounds Forecasting Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Classification of Malaria cell images using Deep Learning Approach 3

Classification of Malaria cell images using Deep Learning Ap...

引用

3rd International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2023

作者： Suraksha, S. Santhosh, C. Vishwa, B. Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India

ISBN: (纸本)9781665494007

Malaria is a disease caused by the bite of infected female Anopheles mosquitos. Symptoms of malaria are fever, vomiting, headache and in extreme cases, it may lead to death. In this research paper, we used patients' red blood cell images and deep learning techniques to build a machine-learning model for blood smear image classification. CNN (Convolutional Neural Network) is one of the deep learning methods which is used for image classification. The previous related works mostly used Support Vector Machine (SVM) for smear image classification which is quite complex. The pre-trained CNN extracts the infected and uninfected blood cell images. In this proposed method, we used deep learning combined with VGG to perform the classification of parasitized and uninfected blood smear cell images. To validate our proposed method, we used datasets from the NIH repository which consists of parasitized and uninfected cell images. In this research, our proposed approach achieved an accuracy of 96.02%. © 2023 IEEE.

关键词： Image classification

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：