检索结果-内蒙古大学图书馆

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Ramesh Prabhakaran, R. Guhan, P. Raj, E George Dharma Prakash Karthika, K. Angel Maanu, P. Mizoram University Department of Computer Engineering Mizoram India Panimalar Engineering College Department of Electrical and Electronical Engineering Chennai India Bharathidasan University School of Computer Science and Engineering Trichy India Karpagam College of Engineering Department of Information Technology Coimbatore India Panimalar Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331528201

Moving around in their surroundings is challenging for elderly people and people with visual impairments. The majority of functional sticks in use today are not intelligent and lack an innate ability to recognize obstacles. In an effort to address this issue, mobility and orientation specialists who assist the blind by teaching them to move freely and safely using their remaining senses are brought in. They can navigate around obstacles with the aid of guidance dogs as well. These techniques have drawbacks, such as the dogs' inability to comprehend complicated instructions, the high cost of maintaining these trained dogs, and the need to hire an expert. In light of the aforementioned difficulties, the "Smart walking stick"has become a potential answer. The "Mobile based walking stick"is a useful mobility aid with the capacity to call a relative who can help in the event of an accident, detect obstacles above ground level and pits using ultrasonic sensors, recognize when a collision has occurred, and call the user's mobile phone if it has been misplaced to share the location's GPS for use with GSM connectivity and to share with the user's mention contacts. With some visually disabled people as test subjects, a test case was run, and 95% of the time it was successful. © 2024 IEEE.

关键词： Ultrasonic sensors

来源：评论

学校读者我要写书评

暂无评论

Enhanced Water Quality Control Based on Predictive Optimization for Smart Fish Farming

引用

computers, Materials & Continua 2023年第6期75卷 5471-5499页

作者： Azimbek Khudoyberdiev Mohammed Abdul Jaleel Israr Ullah DoHyeun Kim Department of Applied Informatics Kimyo International University in TashkentTashkent100121Uzbekistan Department of Computer Science Virtual University of PakistanLahore54000Pakistan Department of Computer Engineering Jeju National UniversityJeju63243Korea

The requirement for high-quality seafood is a global challenge in today’s world due to climate change and natural resource *** of Things(IoT)based Modern fish farming systems can significantly optimize seafood production by minimizing resource utilization and improving healthy fish *** objective requires intensive monitoring,prediction,and control by optimizing leading factors that impact fish growth,including temperature,the potential of hydrogen(pH),water level,and feeding *** paper proposes the IoT based predictive optimization approach for efficient control and energy utilization in smart fish *** proposed fish farm control mechanism has a predictive optimization to deal with water quality control and efficient energy consumption *** farm indoor and outdoor values are applied to predict the water quality parameters,whereas a novel objective function is proposed to achieve an optimal fish growth environment based on predicted *** logic control is utilized to calculate control parameters for IoT actuators based on predictive optimal water quality parameters by minimizing energy *** evaluate the efficiency of the proposed system,the overall approach has been deployed to the fish tank as a case study,and a number of experiments have been carried *** results show that the predictive optimization module allowed the water quality parameters to be maintained at the optimal level with nearly 30%of energy efficiency at the maximum actuator control rate compared with other control levels.

关键词： Smart fish farming internet of things(IoT) predictive optimization objective function fuzzy logic control(FLC)

来源：评论

学校读者我要写书评

暂无评论

Arduino based fire detection alarm in rural areas

Arduino based fire detection alarm in rural areas

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Bhattarai, Omkar Dubey, Abhay Aditya Singh, Shashank Singh, Avjeet Department of Computer Science and Engineering School of Engineering and Technology Sharda University Greater Noida India

ISBN: (纸本)9781032669663

Fire is the major disaster worldwide, and even worst condition at the village. Hence, the fire detection system or alarm should accurately locate the fire in the shortest amount of time to reduce financial loss and environmental damage. Fire is a deadly element as well as a highly useful instrument in daily life, and it regularly causes catastrophes that are more expensive than money. Fire incidents typically result in the greatest amount of damage in the shortest amount of time since they happen quickly and leave no other salvageable parts behind. Early fire detection and prevention techniques have been developed to counteract this. In this paper, a tool for early fire detection and message sender response have both been created. The instrument is designed to find heat, gas, and flame possible fire indicators. The device is made up of an Arduino module, a GSMmodule for text messaging, sensors, a buzzer, and LEDs. It also has an acrylic circuit cover. Additionally, the gadget has been successful in text messaging the given cellphone number to notify the intended receiver of the events it has identified, such as excessive temperatures and gas leaks. It can show the faster response towards the fire and asks the alarm to respond quickly so that everyone gets informed. © 2024 The Author(s).

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

An Exploration on Big Data Analytical Techniques: A Review 18

An Exploration on Big Data Analytical Techniques: A Review

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Prajapati, Abhinav Gupta, Ayush Mishra, Sanskar Raj, Dharm Singh, Murari Kumar Goyal, Mayank Kumar Sharda School of Engineering and Technology Department of Computer Science and Engineering UP Greater Noida India

ISBN: (纸本)9789380544519

The exponential growth of large, complex, and dynamic datasets, known as big data, required the development of robust analytical techniques beyond conventional tools. This article examines the landscape of big data processing techniques like LSTM, CNN, and more identifying their suitability for different application domains like social media, finance, healthcare, and agriculture. Recognizing the frequent time-sensitive nature of big data analysis, we emphasize the importance of data quality considerations within the processing pipeline. Through a structured analysis of existing literature, we present a comprehensive overview of diverse big data analytical techniques, challenges, technologies, and applications, including statistical methods, machine learning algorithms, and distributed computing frameworks. Our key findings reveal the strengths and limitations of each approach, highlighting the need for hybrid solutions and domain-specific adaptations. Furthermore, we discuss the broader implications of big data processing on knowledge extraction, decision-making, and ethical considerations for responsible data analysis in various fields. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Big Data Big Data Analysis Data mining

来源：评论

学校读者我要写书评

暂无评论

Hybrid Automated Malware Detection for Android User Data with Optimal Learning Approach 2

Hybrid Automated Malware Detection for Android User Data wit...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Kumar, Mysugari Pradeep Chouhan, Arun Singh Department of Computer Science and Engineering School of Engineering Malla Reddy University Telangana Hyderabad India

ISBN: (纸本)9798350383867

The Android operating system is currently the most popular and widely used smartphone operating system. One reason for their appeal is that users can download and install free third-party programs that offer a number of benefits. Unfortunately, installing any third-party program has also led to an endless supply of malware programs that are always evolving and intended to harm users in different ways. This paper addresses and demonstrates a number of techniques to the test of Android malware detection. For a realtime detection system, data analytics are created. The installed applications may be searched by the detection system for ones that might be dangerous so they can be removed. Using machine learning models allows for this. The Automatic Android Malware Detection utilizing Optimal Ensemble Learning Approach for Cybersecurity (AAMDOELAC) technique is presented in this research proposal. Automated malware identification and categorization is the primary goal of the AAMD-OELAC approach. The AAMDOELAC approach does preliminary data preparation to accomplish this. The three machine learning models implemented in the ensemble learning phase of the AAMDOELAC methodology are the Regularized Random Vector Functional Link Neural Network (RRVFLN), Kernel Extreme Learning Machine (KELM), and Least Square Support Vector Machine (LSSVM). We utilize the Chi Square Model to extract data. The simulation findings show that the AAMD-OELAC technology outperforms other existing techniques. © 2024 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

EECLP: AWireless Sensor Networks Energy Efficient Cross-Layer Protocol

引用

computers, Materials & Continua 2024年第8期80卷 2611-2631页

作者： Mohammed Kaddi Mohammed Omari Moamen Alnatoor LDDI Laboratory University of AdrarAdrar01000Algeria Computer Science and Engineering Department School of EngineeringAmerican University of Ras Al KhaimahRas Al Khaimah72603United Arab Emirates

Recent advancements in wireless communications have allowed the birth of novel wireless sensor networks(WSN).A sensor network comprises several micro-sensors deployed randomly in an area of interest.A micro-sensor is provided with an energy resource to supply electricity to all of its ***,the disposed energy resource is limited and battery replacement is generally *** this restriction,the sensors must conserve energy to prolong their *** energy conservation strategies for WSNs have been presented in the literature,from the application to the physical *** of these solutions focus only on optimizing a single layer in terms of energy *** this research,a novel cross-layer technique for WSNs’effective energy usage is *** most energy consumption factors exist in the Medium Access Control(MAC)layer and network layer,our EECLP protocol(Energy Efficient Cross-Layer Protocol for Wireless Sensor Networks)integrates these two layers to satisfy energy efficiency *** gain access to the transmission channel,we implement a communication regime at the MAC layer based on CSMA/CA(Carrier Sense Multiple Access/Collision Avoidance)***,depending on the activity and a standby period,we employ the RTS/CTS(Request to Send/Clear to Send)method to prevent collisions and resolve hidden node concerns by utilizing the network allocation vector(NAV)to calculate the transmission *** a greedy strategy,we establish chains amongst cluster members to mitigate the issue of high energy consumption in routing *** objective function was utilized to determine the optimal cross-chain path based on the distances to the base station(BS)and residual energy(RE).The simulation,testing,and comparison of the proposed protocol to peer protocols have shown superior outcomes and a prolonged network *** the suggested protocol,the network lifetime increases by 10%compared to FAMACO(Fuzzy and Ant Col

关键词： WSN energy consumption MAC layer network layer EECLP energy-efficient lifespan

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-Assisted Semi-Federated Learning Framework for Industrial Edge Intelligence

引用

China Communications 2024年第5期21卷 314-329页

作者： Wu Xiongyue Tang Jianhua Marie Siew Shien-Ming Wu School of Intelligent Engineering South China University of TechnologyGuangzhou 511442China Electrical and Computer Engineering Department Carnegie Mellon UniversityPittsburghPA 15213United States

The rapid development of emerging technologies,such as edge intelligence and digital twins,have added momentum towards the development of the Industrial Internet of Things(IIo T).However,the massive amount of data generated by the IIo T,coupled with heterogeneous computation capacity across IIo T devices,and users’data privacy concerns,have posed challenges towards achieving industrial edge intelligence(IEI).To achieve IEI,in this paper,we propose a semi-federated learning framework where a portion of the data with higher privacy is kept locally and a portion of the less private data can be potentially uploaded to the edge *** addition,we leverage digital twins to overcome the problem of computation capacity heterogeneity of IIo T devices through the mapping of physical *** formulate a synchronization latency minimization problem which jointly optimizes edge association and the proportion of uploaded nonprivate *** the joint problem is NP-hard and combinatorial and taking into account the reality of largescale device training,we develop a multi-agent hybrid action deep reinforcement learning(DRL)algorithm to find the optimal *** results show that our proposed DRL algorithm can reduce latency and have a better convergence performance for semi-federated learning compared to benchmark algorithms.

关键词： digital twin edge association industrial edge intelligence(IEI) semi-federated learning

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in ECG using Deep Learning 18

Anomaly Detection in ECG using Deep Learning

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Rajput, Ashish Patel, Neetesh Raj Bhati, Rohan Singh Singh, Amit Pratap Fatima, Hoor Sharda University School of Engineering and Technology Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9789380544519

Electrocardiogram (ECG) signals play a very important role in the detection of heart irregularities. Early detection of abnormalities is essential for better patient care and improved medical outcomes. Recent years have witnessed a surge in the application of deep learning techniques, such as autoencoders, long short-term memory (LSTM) networks, and convolutional neural networks (CNNs), for automated ECG signal detection. Our research study utilizes a large-scale ECG database encompassing various types of cardiac diseases. We individually trained and employed autoencoders, LSTM networks, and CNNs to identify abnormal ECG patterns. Autoencoders enhance the dataset by revealing subtle features that might otherwise go unnoticed due to attention limitations. LSTM networks effectively model the temporal relationships between individual elements within the dataset. CNNs, on the other hand, focus primarily on spatial features and waveform graphs. The performance of these algorithms is evaluated based on accuracy, precision, and F1-score, ensuring high scores in sensitivity, predictive value, specificity, and overall classification accuracy, with minimal false positives or negatives. Beyond accuracy, we also consider practical aspects such as generalization approaches and computational efficiency. Understanding the strengths and limitations of each deep learning algorithm is crucial for ECG detection. Comparative studies of this nature hold immense value for the healthcare sector and academia, guiding the selection of the most effective deep learning algorithm for abnormality detection. Moreover, it illustrates how the combined approach may enhance performance, leading to improved diagnostics and treatment of patients. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Anomaly Detection Autoencoder Comparative Analysis Convolutional Neural Network Deep Learning Diagnostic Tools Healthcare LSTM Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Detection Approach based on Colour Fundus Pictures 18

Glaucoma Detection Approach based on Colour Fundus Pictures

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Afshan, Roshni Chakraverti, Ashish Kumar Chhabra, Megha Sharda University School of Engineering and Technology Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9789380544519

Glaucoma is a common retinal disorder that has an impact on the optic nerve, resulting in irreversible sight loss if left untreated. Although early detection is crucial for optimal management, manual detection is difficult and needs highly competent ophthalmologists. To overcome this issue, this study Employ Convolutional Neural Networks (CNNs) and further deep learning techniques, to detect glaucoma automatically. The study employs a standardization technique on a dataset of 5000 retinal pictures to ensure that all images are uniform at 256× 256 pixels. Data augmentation techniques such as rescaling, rotation, vertical and horizontal shifts are used consistently to improve dataset variety and model resilience. The MobileNetV3 architecture is used for glaucoma detection, and two optimizers, Stochastic Gradient Descent (SGD) and Adam are used during model training. Pre-processing refines incoming pictures further by turning them to greyscale, adding Gaussian noise, and ensuring pixel values are inside the [0, 255] range. Accuracy, precision, recall, specificity, and F-measure are all part of performance evaluation. Comparative analyses evaluate the suggested model's efficacy, assuring its dependability and quality. The results show that the model is proficient in detecting glaucoma due to its excellent classification accuracy. This work improves automated glaucoma detection, perhaps assisting in early diagnosis and treatment, so protecting patients from irreparable vision loss caused by this 'silent thief of vision.' © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Convolutional neural network Deep learning Glucoma image Machine learning

来源：评论

学校读者我要写书评

暂无评论

Empowering Students and Enabling Accessibility- A survey on Personal Voice Assistant for Students Education and Enhanced Accessibility 15

Empowering Students and Enabling Accessibility- A survey on ...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Yadav, Shreya Dhingra, Gauri Gupta, Sarang Paulraj, Betty Department of Computer Science and Engineering Amity School of Engineering and Technology Uttar Pradesh Noida India

ISBN: (纸本)9798331300579

Personal voice assistants have revolutionized how people interact with technology by enabling effortless access to a variety of services by making the user experience natural and more effective using Artificial Intelligence (AI) and Natural language processing (NLP) technologies to understand spoken instructions and reply the information with the most appropriate information or actions that are appropriate to the current context. The voice assistant can now be the ultimate time saver thanks to its wide range of functionalities, which range from basic tasks like setting alarms and playing music on YouTube to more advanced ones like understanding text through paragraphs and responding to any questions inside it using NLP. Personal voice assistants have shown great promise in changing human-computer interaction and promoting a more comfortable, personalized, and natural experience with computing. © Grenze Scientific Society, 2024.

关键词： Students

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：