In this paper, we introduce the problem of learning max-plus linear models from event data available through unlabeled logs. We present a method for obtaining these models when the logs contain input and output event ...
详细信息
ISBN:
(纸本)9798350358513;9798350358520
In this paper, we introduce the problem of learning max-plus linear models from event data available through unlabeled logs. We present a method for obtaining these models when the logs contain input and output event dates generated by a system in both normal conditions and abnormal conditions caused by failures. The properties of the method are presented, as well as results from a simulated example.
One of the biggest dangers to society today is terrorism, where attacks have become one of the most significantrisks to international peace and national security. Big data, information analysis, and artificial intelli...
详细信息
One of the biggest dangers to society today is terrorism, where attacks have become one of the most significantrisks to international peace and national security. Big data, information analysis, and artificial intelligence (AI) havebecome the basis for making strategic decisions in many sensitive areas, such as fraud detection, risk management,medical diagnosis, and counter-terrorism. However, there is still a need to assess how terrorist attacks are related,initiated, and detected. For this purpose, we propose a novel framework for classifying and predicting terroristattacks. The proposed framework posits that neglected text attributes included in the Global Terrorism database(GTD) can influence the accuracy of the model’s classification of terrorist attacks, where each part of the datacan provide vital information to enrich the ability of classifier learning. Each data point in a multiclass taxonomyhas one or more tags attached to it, referred as “related tags.” We appliedmachinelearning classifiers to classifyterrorist attack incidents obtained from the GTD. A transformer-based technique called DistilBERT extracts andlearns contextual features from text attributes to acquiremore information from text data. The extracted contextualfeatures are combined with the “key features” of the dataset and used to perform the final classification. Thestudy explored different experimental setups with various classifiers to evaluate the model’s performance. Theexperimental results show that the proposed framework outperforms the latest techniques for classifying terroristattacks with an accuracy of 98.7% using a combined feature set and extreme gradient boosting classifier.
machinelearning is a branch of computer science and has been applied to the field of artificial intelligence. It is a form of data analysis in which computers are used for learning without explicit programming. Machi...
详细信息
Mental health issues, including anxiety, stress, and depression, may remain untreated until they escalate to a severe level. The issues significantly impact an individual's overall well-being and productivity. Tim...
详细信息
In contemporary network environments, effective countermeasures against cybersecurity threats require highly effective Intrusion Detection Systems (IDS). This paper proposes an advanced methodology to enhance IDS by e...
详细信息
Decentralized applications (Dapps), based on smart contract technology, have been increasingly applied in various fields such as healthcare, industrial IoT, agriculture, financial services, supply chain management, an...
详细信息
ISBN:
(纸本)9798350376975;9798350376968
Decentralized applications (Dapps), based on smart contract technology, have been increasingly applied in various fields such as healthcare, industrial IoT, agriculture, financial services, supply chain management, and insurance. In certain complex business scenarios, blockchain may require machinelearning models to assist contract business. However, on-chain computations are often costly and slow, and there are limitations on contract size. Due to the transparency of on-chain data, there are also privacy concerns regarding user data during model training and inference. To address these challenges, we propose a trusted off-chain machinelearning solution that integrates ZK-SNARK and Oracle technologies. Following the principle of "off-chain computation, on-chain verification",our approach leverages ZK-SNARK to delegate the computation tasks of machinelearning models to a trusted environment under the Oracle off-chain server. This solution significantly reduces the computational costs of the blockchain. User data and models are executed off-chain, effectively safeguarding user privacy. The execution results generate zero-knowledge proofs returned for on-chain verification. We have implemented TOMLS-ZKSO and conducted relevant experiments on insurance contract business on the Chainmaker. Experimental results demonstrate the effectiveness of our approach, with model proof generation taking approximately 0.4 seconds and Dapp response time around 0.52 seconds.
In the realm of robotics, numerous downstream robotics tasks leverage machinelearning methods for processing, modeling, or synthesizing data. Often, this data comprises variables that inherently carry geometric const...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
In the realm of robotics, numerous downstream robotics tasks leverage machinelearning methods for processing, modeling, or synthesizing data. Often, this data comprises variables that inherently carry geometric constraints, such as the unit-norm condition of quaternions representing rigid-body orientations or the positive definiteness of stiffness and manipulability ellipsoids. Handling such geometric constraints effectively requires the incorporation of tools from differential geometry into the formulation of machinelearning methods. In this context, Riemannian manifolds emerge as a powerful mathematical framework to handle such geometric constraints. Nevertheless, their recent adoption in robot learning has been largely characterized by a mathematically-flawed simplification, hereinafter referred to as the "single tangent space fallacy". This approach involves merely projecting the data of interest onto a single tangent (Euclidean) space, over which an off-the-shelf learning algorithm is applied. This paper provides a theoretical elucidation of various misconceptions surrounding this approach and offers experimental evidence of its shortcomings. Finally, it presents valuable insights to promote best practices when employing Riemannian geometry within robot learning applications.
As part of a more global research effort towards greener aviation, the present study focuses on the prediction of noise impacts by the air traffic around major airports. To this end, a simple yet efficient data-driven...
详细信息
As part of a more global research effort towards greener aviation, the present study focuses on the prediction of noise impacts by the air traffic around major airports. To this end, a simple yet efficient data-driven model is developed which, relying on machinelearning (multivariable linear regression), allows assessing the noise levels and annoyance incurred by air traffic upon the sole knowledge of aircraft characteristics and operational features. This model is then applied to the air traffic occurring in Hong Kong city, which presents some unique specificities, e.g., complex airspace, non-standard aircraft types and/or operations, significant weather variations;Upon a prior training using a pre-existing experimental database of actual aircraft flying in and out of the Hong Kong international Airport (HKIA), the model proves efficient in predicting most flights' noise impacts, which are here quantified through three specific sound metrics. In a second stage, this model is further simplified via a systematic exploration and subsequent reduction of its constitutive variables, thereby leading to a reduced order model of similar accuracy and lower complexity. As a byproduct, this model reduction allows discriminating the main drivers underlying the noise impacts by aircraft. Overall, this study demonstrates how a datadriven model based on a relatively simple machinelearning approach can effectively predict the noise impacts of air traffic upon the sole knowledge of aircraft characteristics and operational features, even when they are non-standard as in Hong Kong.
Utilizing machinelearning (ML), a revolutionary trend in the fields of modern business and leadership, opens up new ways to improve leadership styles and propel company success. This research looks at how machine lea...
详细信息
Utilizing machinelearning (ML), a revolutionary trend in the fields of modern business and leadership, opens up new ways to improve leadership styles and propel company success. This research looks at how machinelearning techniques can be used to improve leadership strategies and the general efficiency of an organization. In the area of leadership development, this research looks at how machinelearning might be able to look at a lot of data and find trends, patterns, and insights that might not be seen with more traditional methods. In addition, it shows how important machinelearning algorithms are in predictive analytics, which helps managers see problems coming, lower risks, and take advantage of new opportunities. This research looks at how systems that use machinelearning might improve the openness, fairness, and responsibility of decision-making processes in order to build trust and teamwork. It also looks at the problems and moral issues that might come up when ML is used in leadership, emphasizing how important it is to have responsible ML governance and constant oversight to get rid of biases and make sure fair results. This research shows how machinelearning may have a big effect on leadership and the success of organizations. When leaders want to use AI-powered technology to stay ahead of the competition, boost innovation, and help their businesses grow in the digital age, our services can help.
Employers today are becoming more concerned about keeping their workforces, yet they mostly find it difficult to discover the actual causes of employee loss. Employee attrition can be caused by a variety of factors, i...
详细信息
暂无评论