This paper studies the application of machinelearning methods for the identification of ACARS (Aircraft Communications Addressing and Reporting System) signals in the field of intelligent communication. We first intr...
详细信息
ISBN:
(纸本)9798350391961;9798350391954
This paper studies the application of machinelearning methods for the identification of ACARS (Aircraft Communications Addressing and Reporting System) signals in the field of intelligent communication. We first introduce the characteristics, structure and transmission characteristics of ACARS signals, and then outline the basic knowledge of machinelearning, including supervised learning, unsupervised learning and semi-supervised learning. Then, the application of machinelearning method in ACARS signal recognition is discussed in detail, including data preprocessing, feature extraction and the application of different algorithms. Through experiments and results analysis, the effectiveness of the machinelearning method in ACARS signal recognition is verified, and the challenges and future directions are discussed.
The widespread use of social media has led to an increase in false and misleading information presented as legitimate news, also known as fake news. This poses a threat to societal stability and has led to the develop...
详细信息
ISBN:
(纸本)9798350364941;9798350364958
The widespread use of social media has led to an increase in false and misleading information presented as legitimate news, also known as fake news. This poses a threat to societal stability and has led to the development of fake news detectors that use machinelearning to flag suspicious information. However, existing fake news detection models are vulnerable to attacks by malicious actors who can manipulate data to change predictions. Research on attacks on news comments is limited, and current attack models are easily detectable. We propose two new attack strategies that instead use real, pre-existing comments from the same dataset as the news article to fool fake news detectors. Our experimental results show that fake news detectors are less robust to our proposed attack strategies than existing methods using pre-existing human-written comments, as well as a malicious synthetic comment generator.
Cardinality sketches are popular data structures that enhance the efficiency of working with large data sets. The sketches are randomized representations of sets that are only of logarithmic size but can support set m...
详细信息
Cardinality sketches are popular data structures that enhance the efficiency of working with large data sets. The sketches are randomized representations of sets that are only of logarithmic size but can support set merges and approximate cardinality (i.e., distinct count) queries. When queries are not adaptive, that is, they do not depend on preceding query responses, the design provides strong guarantees of correctly answering a number of queries exponential in the sketch size k. In this work, we investigate the performance of cardinality sketches in adaptive settings and unveil inherent vulnerabilities. We design an attack against the "standard" estimators that constructs an adversarial input by post-processing responses to a set of simple non-adaptive queries of size linear in the sketch size k. Empirically, our attack used only 4k queries with the widely used Hyper-LogLog (HLL++) (Flajolet et al., 2007b;Heule et al., 2013) sketch. The simple attack technique suggests it can be effective with post-processed natural workloads. Finally and importantly, we demonstrate that the vulnerability is inherent as any estimator applied to known sketch structures can be attacked using a number of queries that is quadratic in k, matching a generic upper bound.
Applying agile practices in datascience requires adaptations. This paper describes challenges and lessons learned in two appliedmachinelearning projects developed in the XP Lab course at University of Sao Paulo in ...
详细信息
ISBN:
(纸本)9783031485497;9783031485503
Applying agile practices in datascience requires adaptations. This paper describes challenges and lessons learned in two appliedmachinelearning projects developed in the XP Lab course at University of Sao Paulo in Brazil. It compiles six suggestions for educators and practitioners who want to bring agility to their datascience initiatives.
machinelearning applications are rapidly adopted by industry leaders in any field. The growth of investment in AI-driven solutions created new challenges in managing datascience and ML resources, people and projects...
详细信息
ISBN:
(纸本)9798400701030
machinelearning applications are rapidly adopted by industry leaders in any field. The growth of investment in AI-driven solutions created new challenges in managing datascience and ML resources, people and projects as a whole. The discipline of managing appliedmachinelearning teams, requires a healthy mix between agile product development tool-set and a long term research oriented mindset. The abilities of investing in deep research while at the same time connecting the outcomes to significant business results create a large knowledge based on management methods and best practices in the field. The Second KDD Workshop on appliedmachinelearning Management brings together applied research managers from various fields to share methodologies and case-studies on management of ML teams, products, and projects, achieving business impact with advanced AI-methods.
The proposed study realizes a novel quantum machinelearning (QML) architecture that allows heuristic function evaluation and can actually perform quantum circuits during massive data processing. The Quantum-Circuit f...
详细信息
Recent years have witnessed increasing privacy concerns towards machinelearning. To protect privacy in machinelearning, federated learning has been proposed as a decentralized privacy-preserving framework where clie...
详细信息
ISBN:
(纸本)9781728190549
Recent years have witnessed increasing privacy concerns towards machinelearning. To protect privacy in machinelearning, federated learning has been proposed as a decentralized privacy-preserving framework where clients upload the parameters rather than private data. However, training a fair federated learning model in heterogeneous environments is still challenging. First, heterogeneous data distributions lead the global model fail to show high accuracy on all distributions. Second, the federated learning training process exposes and exacerbates potential biases in heterogeneous training data. Third, the local bias of each client can be propagated through parameter sharing, biasing the global model. In this work, we propose a two-stage fairness-aware federated learning framework (HeteroFair) to achieve fairness under heterogeneous data distributions. Initially, we introduce the fairness constraint to the loss function and propose a local adaptive weighting algorithm to adjust the proportion of the fairness constraint, achieving fair training in heterogeneous environments. Then, we present a fairness-aware aggregation reweighting algorithm that reduces the mismatch between local and global fairness to achieve fair federated learning. Extensive evaluation results demonstrate the effectiveness of our proposed framework in achieving fairness and high accuracy under heterogeneous data distributions.
When applied to healthcare, machinelearning ushers in a new age of data-driven medical practice that holds great promise for better patient outcomes and individualized treatment. However, this evolution isn't wit...
详细信息
Cryptocurrencies, such as Bitcoin, Binance, Ethereum, FTX, and XRP, are decentralized digital assets known for their volatile nature and potential as investment instruments. Accurate price prediction is crucial for in...
详细信息
Traditional heat treatment methods require a significant amount of time and energy to affect atomic diffusion and enhance the spheroidization process of carbides in bearing steel, while pulsed current can accelerate a...
详细信息
Traditional heat treatment methods require a significant amount of time and energy to affect atomic diffusion and enhance the spheroidization process of carbides in bearing steel, while pulsed current can accelerate atomic diffusion to achieve ultra-fast spheroidization of carbides. However, the understanding of the mechanism by which different pulse current parameters regulate the dissolution behavior of carbides requires a large amount of experimental data to support, which limits the application of pulse current technology in the field of heat treatment. Based on this, quantify the obtained pulse current processing data to create an important dataset that could be applied to machinelearning. Through machinelearning, the mechanism of mutual influence between carbide regulation and various factors was elucidated, and the optimal spheroidization process parameters were determined. Compared to the 20 h required for traditional heat treatment, the application of pulsed electric current technology achieved ultra-fast spheroidization of GCr15 bearing steel within 90 min.
暂无评论