检索结果-内蒙古大学图书馆

Communication & Computing (WCONF), World Conference on

作者： Ibna Soud Joy Faria Basher Nusrat Sultana Md. Ahnaf Tahmid Sayeda Rahnuma Akthar Mahady Hasan Sadita Ahmed Dept. of Computer Science & Engineering Independent University Bangladesh Dhaka Bangladesh

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

Agriculture stands as the cornerstone of global sustenance and economic prosperity, yet smallholder farmers face significant financial barriers. Despite advancements in agricultural technology and markets, access to financial services remains limited for smallholders. We've thoroughly examined 25 research papers in this field to assess the extent of existing research. Subsequently, we conducted a comprehensive market analysis and competitive review to shape the design of our platform. This study introduces an innovative fintech platform aimed at bridging this gap by facilitating connections between farmers and financial service providers. By leveraging precision risk analysis, inclusive microloans, comprehensive insurance coverage and democratized investment opportunities, our platform seeks to enhance sustainable farming practices and boost productivity for smallholder farmers. Our platform utilizes data analytics to assess risk factors specific to agricultural activities, thereby providing personalized financial solutions and mitigating risks inherent in farming operations.

关键词： Productivity Economics Data analysis Shape Reviews Insurance Risk analysis Faces Farming Investment

来源：评论

学校读者我要写书评

暂无评论

Detection of Dark Web Threats Using Machine Learning and Image Processing

arXiv

引用

arXiv 2024年

作者： Medipelly, Swetha Abosata, Nasr Dept. of Computer Science and Engineering Northumbria University London United Kingdom

kThis paper aimed to discover the risks associated with the dark web and to detect the threats related to human trafficking using image processing with OpenCV and Python. Apart from that, a development environment was set up by installing TensorFlow, OpenCV and Python. Through exploratory data analysis (EDA), significant insights into the distribution and interactions of dataset features were obtained, which are crucial for evaluating various cyberthreats. The construction and evaluation of logistic regression and support vector machine (SVM) models revealed that the SVM model outperforms logistic regression in accuracy. The paper delves into the intricacies of data preprocessing, EDA, and model development, offering valuable insights into network protection and cyberthreat response. © 2024, CC BY-NC-ND.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Enhancing Supply Chain Efficiency through IoT Integration: A Detailed Examination of the Chances and Difficulties

Enhancing Supply Chain Efficiency through IoT Integration: A...

引用

Advances in Computation, Communication and Information Technology (ICAICCIT), International Conference on

作者： Chaitanya Mehra Shaifali Sharma Jayant Arora Aakanksha Sharma Pranaya Mahajan Aryan Manhotra Dept. of Computer Science Engineering Chandigarh University Mohali Punjab India

ISBN: (数字)9798331541217

ISBN: (纸本)9798331541224

The adoption of Internet of Things (IoT) technology in supply chain management has brought about noteworthy transformations, boosting productivity, visibility, and evidence-based decision-making. This research investigates the primary reasons for implementing IoT in contemporary supply chains, tackling issues such as limited real-time monitoring, suboptimal inventory control, and the necessity for preemptive risk management. The investigation delves into the capabilities of IoT-driven solutions, including sensor technology, RFID systems, and data analysis tools, to confront these obstacles by enabling constant surveillance and anticipatory maintenance, taking into account the impact of innovative technologies such as blockchain and artificial intelligence. The results underscore the considerable effect of IoT in establishing robust, flexible, and eco-friendly supply chains, providing valuable insights for businesses aiming to improve their operational effectiveness in an increasingly digital landscape.

关键词： Supply chain management Data security Supply chains Inventory control Blockchains Maintenance Internet of Things Artificial intelligence Radiofrequency identification Edge computing

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Smart Parking System Using Artificial Intelligence and Optical Character Recognition

IoT-Enabled Smart Parking System Using Artificial Intelligen...

引用

International Conference on Communications, Signal Processing, and their Applications (ICCSPA)

作者： Mohammad Rafi Rashidi Chris Cherian Vipul Singh Negi Suchismita Chinara Dept. Computer Science and Engineering National Institute of Technology Rourkela India

ISBN: (数字)9798350384819

ISBN: (纸本)9798350384826

The Internet of Things (IoT) plays an important role in smart parking systems by addressing the growing problems of parking difficulties in urban areas, where traffic jams, air pollution, and parking time consumption are the main issues faced in our daily lives. To overcome these challenges, this paper presents a reliable IoT-enabled smart parking system based on automatic licence plate recognition (ALPR) using the optical character recognition (OCR) technique and Artificial Intelligence (AI). A three-module system has been implemented in real-time, where the first module is a computational device (Raspberry Pi) that receives data from IR sensor to provide information for parking slots availability. Camera-based optical character recognition is the second module, which recognizes license plates for a secured entry to the parking lot by validating the vehicle's plate number. The third module is a mobile application facilitating a convenient parking experience for slot reservations and paymentrelated services. Regarding plate recognition, the model is trained assuming various scenarios, such as different lighting conditions, partial occlusion, different angles and distances, and reduced inference time for recognizing the vehicle's plate number.

关键词： Urban areas Automated parking Signal processing Real-time systems Mobile applications Character recognition Internet of Things Reliability Artificial intelligence License plate recognition

来源：评论

学校读者我要写书评

暂无评论

1 AI-Powered Facial Expression Analysis In Real Time: Unveiling Emotions

1 AI-Powered Facial Expression Analysis In Real Time: Unveil...

引用

Electronics, Computing, Communication and Control Technology (ICECCC), International Conference on

作者： Aishwarya D Ponduru Sandeep Penmatsa V P S Akhilesh Varma Dept. of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Tamilnadu India

ISBN: (数字)9798350371802

ISBN: (纸本)9798350371819

This study introduces a novel facial deconstruction method for face emotion identification. After identifying facial landmarks with the IntraFace algorithm, seven regions of interest (ROI) are extracted, representing the principal featuresof the face: the mouth, nose, an area between the eyebrows, right and left eyes, and eyebrows. Next, a variety of local descriptors, such as Local Binary Patterns, Completed Local Binary Patterns. Local Ternary Patterns, and Dynamic Local Ternary Patterns, are employed to capture distinctive features. Inputting the feature vector which represents a face image into a multi-class support vector machine completes the recognition process. The suggested method outperforms previous facial deconstruction techniques, according on experimental findings on two publicly available datasets.

关键词： Support vector machines Accuracy Reviews Face recognition Computational modeling Feature extraction Vectors

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Nature-Inspired Paticle Bee Colony Deep Neural Network Technique for Event Detection in Video Sequences

An Adaptive Nature-Inspired Paticle Bee Colony Deep Neural N...

引用

Cognitive, Green and Ubiquitous Computing (IC-CGU), International Conference on

作者： Kumud Sachdeva Jasminder Kaur Sandhu Rakesh Sahu Dept. of Computer Science Engineering Chandigarh University Gharuan Punjab India

ISBN: (数字)9798350361780

ISBN: (纸本)9798350361797

Classifying and detecting difficult video events based on visual modalities remains an uncertain problem. Conventional video presentation approaches ineffectively extract each modality, hindering video event detection (VED) rates. The research methodology involves pre-processing steps: uploading video data samples, extracting video frames, converting to grayscale (rgb2gray), enhancing, and calculating smooth frames from the UCF -101 dataset. This pre-processing phase aims to deliver high-quality frames without data loss. Next, the feature extraction process employs the HoG method to extract feature vectors from refined video frames, facilitating the training process and efficiently reducing dimensions. An adaptive, nature-inspired PBC method is then implemented to select reliable and optimized feature sets from the extracted ones. These selected optimized feature vectors are input into different events of the deep neural network (DNN) classifier. Finally, reliable feature sets are identified through feature matching, and experimental outcomes demonstrate a significant 21.3% enhancement in VED and classification, assessed through accuracy rate, specificity (SP), sensitivity (SN), etc. Compared with traditional approaches using manually designed feature sets, the proposed approach proves more effective. Simulation outcomes on publicly available VED databases consistently outperform state-of-the-art video representation methods such as EFS-linear multi-support vector machine (MSVM), convolutional neural network (CNN), etc.

关键词： Training Visualization Adaptive systems Sensitivity Event detection Video sequences Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DevOps 2.0: Embracing AI/ML, Cloud-Native Development, and a Culture of Continuous Transformation

DevOps 2.0: Embracing AI/ML, Cloud-Native Development, and a...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： V. Hemanth Das Chowdary A. Shanmukh T. Phaneendra Nikhil B. Sandeep Kumar Feroz Khan Dept. of Computer Science Engineering Koneru Lakshmiah University Vaddeswaram India

ISBN: (数字)9798350386349

ISBN: (纸本)9798350386356

This research study investigates the emerging domain of DevOps, assessing its capacity to fundamentally transform the processes of software development and delivery. A notable advancement in the field of DevOps is the amalgamation of AI/ML and artificial intelligence. These technologies possess significant potential to revolutionize the DevOps domain through the automation of tedious duties, including provisioning infrastructure, managing configurations, and identifying anomalies. This study highlights the increasing need for streamlined solutions. By harnessing the capabilities of AI and ML-driven tools, DevOps teams will have the ability to streamline their processes, enabling them to allocate resources to more strategic approaches such as nurturing innovation, addressing complex challenges, and making decisions based on data. This study will investigate the precise methods by which AI/ML can enhance DevOps practices, resulting in a software development environment that is more secure, efficient, and agile.

关键词： Industries Technological innovation DevOps Automation Social networking (online) Microservice architectures Transforms

来源：评论

学校读者我要写书评

暂无评论

Designing Energy-Efficient PATH-based Decision Tree Memristor Crossbar Circuits

Designing Energy-Efficient PATH-based Decision Tree Memristo...

引用

IEEE Conference on Nanotechnology

作者： Pranav Sinha Akash Chavan Sunny Raj Dept. of Computer Science and Engineering Oakland University Rochester MI USA

ISBN: (数字)9798350386240

ISBN: (纸本)9798350386257

We propose an approach to designing energy-efficient in-memory decision tree (DT) machine-learning circuits using memristors and PATH-based computing. DT machine learning (ML) algorithms are computationally simple, and they require fewer data to train compared to other ML algorithms, making them an attractive option for edge computing. Existing work on creating energy-efficient DT circuits has utilized FLOW-based computing. However, these approaches require costly write operations before every inference, leading to high energy utilization. In this paper, we propose an algorithm to generate PATH-based DT in-memory crossbar circuit designs that only require a write during circuit synthesis and not before every inference, leading to highly energy-efficient inference. We test the performance of our PATH-based design on multiple standard machine learning datasets and demonstrate that our approach achieves a 47% reduction in energy consumption, on average, compared to the state-of-the-art.

关键词： Machine learning algorithms Memristors Machine learning Energy efficiency Inference algorithms Circuit synthesis Decision trees

来源：评论

学校读者我要写书评

暂无评论

Eva: Python-based Desktop Virtual Assistant for Visually Impaired

Eva: Python-based Desktop Virtual Assistant for Visually Imp...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： Anishamol Abraham Benita Susan Mathew Dona Lisa Mathew Fiaz S Mohammad Gokul Krishnan Dept. of Computer Science Amal Jyothi College of Engineering Kottayam India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

Virtual assistants have become essential resources in the digital age, providing users with a wide range of functionalities to expedite work and increase productivity. In this research, we provide a complete examination of Eva, a virtual assistant created using Python, and compare it to other virtual assistants such as Cortana and Copilot. Through a meticulous examination of Eva’s features, we demonstrate its superiority in versatility and effectiveness. By embracing Eva’s strengths and capitalizing on its competitive advantages, we push for a future in which digital experiences are inclusive and empowering for all users.

关键词： Productivity computers Codes Automation Virtual assistants Information age Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Photovoltaic Interleaved Boost Integrated CL Resonant Converter for Magnetron Application

A Photovoltaic Interleaved Boost Integrated CL Resonant Conv...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Aref Molaei Kajanan Kanathipan John Lam Dept. of Electrical Engineering and Computer Science York University Toronto Canada

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376074

A new single-stage high-gain interleaved boost modular CL resonant converter is proposed in this paper for photovoltaic-powered magnetron application. The proposed converter is able to provide high voltage gain for the magnetron which is a device for microwave applications. Perturb and Observe (P&O) method was used to achieve Maximum Power Point Tracking (MPPT) in the integrated interleaved boost stage by controlling the duty-cycle of the two primary leg switches. The operational principles of the converter are briefly discussed in this paper. Results on a 1.7kW, 230V/3.8kV design are presented to verify the proposed converter performance.

关键词： Photovoltaic systems Maximum power point trackers Legged locomotion Magnetic resonance Magnetic devices Resonant converters Microwave devices High-voltage techniques Energy conversion Microwave theory and techniques

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：