In the competitive telecommunications industry, understanding and predicting customer churn-customers discontinuing service-is crucial for revenue and subscriber retention. Traditional customer churn prediction (CCP) ...
详细信息
ISBN:
(纸本)9798350370027;9798350370034
In the competitive telecommunications industry, understanding and predicting customer churn-customers discontinuing service-is crucial for revenue and subscriber retention. Traditional customer churn prediction (CCP) methods require extensive user data, raising privacy concerns when sharing data across different companies. This paper introduces a novel federated learning (FL) framework for CCP that enhances prediction accuracy while safeguarding privacy.
Given a machinelearning model and a record, membership inference attacks determine whether this record was used as part of the model's training dataset. This can raise privacy issues. There is a desideratum to pr...
详细信息
ISBN:
(纸本)9798350381993;9798350382006
Given a machinelearning model and a record, membership inference attacks determine whether this record was used as part of the model's training dataset. This can raise privacy issues. There is a desideratum to provide robust mitigation techniques against this attack that will not affect utility. One of the state-of-the-art frameworks in this area is SELENA, which has two phases: Split-AI and Self-Distillation to train a protected model. In this paper, we introduce a novel approach to the Split-AI phase, which tries to weaken the membership inference by using the Jacobian matrix norm and entropy. We experimentally demonstrate that our approach can decrease the memorization of the machine-learning model for three datasets: Purchase100, CIFAR-10, and SVHN, more than SELENA in the same range of utility in a setting in which we do not know any member of the training data.
In the modern era, the Internet of Things (IoT) has transformed connectivity, generating vast data that powers innovation across industries. The integration of Artificial Intelligence, precisely Natural Language Proce...
详细信息
ISBN:
(纸本)9798350304367;9798350304374
In the modern era, the Internet of Things (IoT) has transformed connectivity, generating vast data that powers innovation across industries. The integration of Artificial Intelligence, precisely Natural Language Processing (NLP), and machinelearning in IoT enhances human-device interactions, paving the way for more intuitive applications, while future prospects involve a deeper fusion of NLP, machinelearning, and artificial intelligence to elevate IoT capabilities and reshape digital interactions. In this paper, we explore the current challenges of different aspects of the Internet of Things (IoT) and the impact of artificial intelligence, NLP, and machinelearning to develop domain-specific and task-oriented solutions.
As quantum machinelearning (QML) emerges as a promising field at the intersection of quantum computing and artificial intelligence, it becomes crucial to address the biases and challenges that arise from the unique n...
详细信息
ISBN:
(纸本)9798331541378
As quantum machinelearning (QML) emerges as a promising field at the intersection of quantum computing and artificial intelligence, it becomes crucial to address the biases and challenges that arise from the unique nature of quantum systems. This research includes work on identification, diagnosis, and response to biases in Quantum machinelearning. This paper aims to provide an overview of three key topics: How does bias unique to Quantum machinelearning look? Why and how can it occur? What can and should be done about it?
Quantum computing is a rapidly evolving field with a wide range of applications in diverse industries. Hybrid quantum computing combines classical and quantum computing to solve complex problems, quantum machine learn...
详细信息
ISBN:
(纸本)9780998133171
Quantum computing is a rapidly evolving field with a wide range of applications in diverse industries. Hybrid quantum computing combines classical and quantum computing to solve complex problems, quantum machinelearning is a subset of machinelearning that leverages quantum computing for optimization, and quantum embeddings use quantum algorithms to process high dimensional data. Quantum computers have the potential to revoltionize finance, industry, production, drug research, and even consumer-facing services. With quantum computing's ability to handle massive amounts of data and perform complex calculations at incredible speeds, it holds great promise for addressing some of the world's most pressing problems in these areas.
The proceedings contain 38 papers. The topics discussed include: depth data based chroma keying using grab-cut segmentation;classification of diabetic retinopathy stages using histogram of oriented gradients and shall...
ISBN:
(纸本)9781538657416
The proceedings contain 38 papers. The topics discussed include: depth data based chroma keying using grab-cut segmentation;classification of diabetic retinopathy stages using histogram of oriented gradients and shallow learning;optimal PD tracking control of a quadcopter drone using adaptive PSO algorithm;animating DoF mechanism on simulation of a satellite trajectory around a planet in three celestial bodies system;machinelearning-based for automatic detection of corn-plant diseases using image processing;neuro-dynamic programming approach to optimal control of spreading of dengue viruses;and enhancing file security by using vigenere cipher and even rodeh code algorithm.
Edge systems are undergoing a groundbreaking computing evolution to support artificial intelligence, deep learning, and complex computational algorithms. Using cloud servers to perform deep learning model inference po...
详细信息
ISBN:
(纸本)9798350350494;9798350350500
Edge systems are undergoing a groundbreaking computing evolution to support artificial intelligence, deep learning, and complex computational algorithms. Using cloud servers to perform deep learning model inference poses challenges such as response delays, increased communication costs, and data privacy concerns. Therefore, significant efforts have been made to push the processing of deep learning models to edge systems, which has led to the creation of edge intelligence as the intersection of learning and edge computing. learning models, especially deep convolutional neural networks, have made significant achievements in machine vision, which provide high accuracy and predictability by spending computing power and memory. If these models are optimized and deployed on edge systems, there will be a revolution in the applications of edge systems in real time. In this paper, by using optimization techniques such as quantization, weight pruning, and weight clustering, the possibility of deploying a typical convolutional neural network model on edge systems that have limited computing resources and memory is investigated. The results show that by using a collaborative algorithm, despite the slight decrease in the accuracy of the model, it is possible to achieve a small-sized model that can even be deployed on microcontrollers.
This research presents a novel wavelet transform and machinelearning-based method to microgrid protection, with a focus on the Unified Power Flow Controller (UPFC). Microgrid components such as distribution generator...
详细信息
ISBN:
(纸本)9798350385939;9798350385922
This research presents a novel wavelet transform and machinelearning-based method to microgrid protection, with a focus on the Unified Power Flow Controller (UPFC). Microgrid components such as distribution generators are critical to enhancing the reliability of electricity networks. For different sources and loads to integrate smoothly, effective defect identification is required. The technique uses wavelet transform to extract meaningful information from failure signals, which is then fed into a machinelearning model for real-time identification. This method analyzes current signals from both ends of the transmission line using wavelet-based multi-resolution analysis, and then compares the results to preset thresholds to generate fault indices. This approach offers a reliable microgrid protection solution with lower losses and increased dependability.
The proceedings contain 132 papers. The topics discussed include: nearest neighbor outperforms kernel-kernel methods for distribution regression;a multi-objective topology optimization method used in simultaneous cons...
ISBN:
(纸本)9781665482905
The proceedings contain 132 papers. The topics discussed include: nearest neighbor outperforms kernel-kernel methods for distribution regression;a multi-objective topology optimization method used in simultaneous constraints of natural frequency and static stiffness;a continuous evaluation method and model of product storage lifetime;a correlation filter tracking algorithm with adaptive model update strategy;a decentralized frequency restoration control for cascaded-type microgrid in islanded mode;a dimensional learning squirrel search algorithm based on roulette strategy;a fast detection method for infrared small targets in complex sea and sky background;a quantum learning approach based on hidden Markov models for failure scenarios generation;a robust framework for deep learning approaches to facial emotion recognition and evaluation;a study of Mongolian emotion classification incorporating emojis;a synergic neural network for medical image classification based on attention mechanism;adaptive multi-tasking framework for video action proposal localization;algorithmic design of autonomous housekeeping robots through imitation learning and model predictive control;and an algorithm for terrain recognition of heavy duty diesel vehicles using Chinese regulatory standard data.
The widespread utilization of Internet of Things (IoT) devices has resulted in an exponential increase in data at the Internet's edges. This trend, combined with the rapid growth of machinelearning (ML) applicati...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
The widespread utilization of Internet of Things (IoT) devices has resulted in an exponential increase in data at the Internet's edges. This trend, combined with the rapid growth of machinelearning (ML) applications, necessitates the execution of learning tasks across the entire spectrum of computing resources - from the device, to the edge, to the cloud. This paper investigates the execution of machinelearning algorithms within the edge-cloud continuum, focusing on their implications from a distributed computing perspective. We explore the integration of traditional ML algorithms, leveraging edge computing benefits such as low-latency processing and privacy preservation, along with cloud computing capabilities offering virtually limitless computational and storage resources. Our analysis offers insights into optimizing the execution of machinelearning applications by decomposing them into smaller components and distributing these across processing nodes in edge-cloud architectures. By utilizing the Apache Spark framework, we define an efficient task allocation solution for distributing ML tasks across edge and cloud layers. Experiments on a clustering application in an edgecloud setup confirm the effectiveness of our solution compared to highly centralized alternatives, in which cloud resources are extensively used for handling large volumes of data from IoT devices.
暂无评论