In the contemporary world, artificial intelligence and machinelearning algorithms are an important driver for decision-making, by leveraging real-world data for future predictions. Despite clearly improving efficienc...
详细信息
ISBN:
(纸本)9798350384048;9798350384031
In the contemporary world, artificial intelligence and machinelearning algorithms are an important driver for decision-making, by leveraging real-world data for future predictions. Despite clearly improving efficiency, the lack of transparency in their predictions raises concerns about the degree of fairness of machinelearning models, well highlighted by recent instances of algorithmic unfairness, from automated decisions on criminal recidivism to disease prediction. Increased user awareness of algorithmic fairness is met with a deficiency in systems guiding data analysts and practitioners in comprehending the implications of their outputs. To tackle the challenge of fairness interpretability, we propose FairnessFriend, a chatbot solution that combines data science with a human-computer interaction perspective. Given a dataset and a trained machinelearning model with established fairness metrics, our system facilitates users in understanding these metrics and their significance in the context of the training data. FairnessFriend provides meanings for various statistical fairness metrics, and presents the resulting metrics values with detailed explanations, offering specific insights into their implications.
This special section of the IEEE Journal of Solidstate Circuits (JSSC) highlights outstanding papers presented at the 2023 IEEE international Solid-State Circuits conference (ISSCC), which was held from February 19 to...
详细信息
This special section of the IEEE Journal of Solidstate Circuits (JSSC) highlights outstanding papers presented at the 2023 IEEE international Solid-State Circuits conference (ISSCC), which was held from February 19 to 23, 2023 in San Francisco, USA, under the conference theme “Building on 70 years of Innovation in Solid-State Circuit Design.” ISSCC is the foremost global forum for the presentation of advances in solid-state circuits and systems-on-a-chip (SoCs) and offers a unique opportunity for engineers working at the cutting edge of integrated circuit (IC) design and application. The conference includes several technical programs ranging from analog, digital, memory, wireline (WLN)/wireless, and power management circuits and systems with applications in various fields. This JSSC special section highlights selected papers from ISSCC, specifically on topics related to WLN circuits, digital circuit techniques (DCTs), digital architecture and systems (DASs), machinelearning (ML) accelerators, and memory circuits.
The phenomenon of supercooling in phase change materials has been a major obstacle to the effective use of these materials in thermal energy storage systems. Numerous studies have shown that nanoparticles display sign...
详细信息
The phenomenon of supercooling in phase change materials has been a major obstacle to the effective use of these materials in thermal energy storage systems. Numerous studies have shown that nanoparticles display significant advantages over other methods of supercooling inhibition in terms of increased nucleation rate, enhanced thermal conductivity, reduced supercooling, and improved cycling stability. Yet, the mechanism of supercooling inhibition by nanoparticles has not been comprehensively discussed or reviewed in published articles. The objective of this review is to provide a comprehensive analysis of the mechanisms by which nano- particles promote nucleation and reduce supercooling in phase change materials, as well as to discuss the most influential factors such as the type, concentration, and size of the nanoparticles, as well as ultrasonic and synergistic effects. Additionally, the paper focuses on an overview of recent advances in the application of machinelearning to control the supercooling of nanofluid phase change materials. The potential for practical applications of machinelearning techniques to enhance the thermophysical properties of phase change materials and suppress phase change material supercooling is one of our major findings.
The disease known as lung cancer, which is common and frequently deadly, starts in the cells of the lungs and causes symptoms like exhaustion, chest pain, and persistent coughing. Since small cell lung cancer (SCLC) i...
详细信息
This paper presents an Artificial intelligence (AI)-driven approach designed to provide a sophisticated decision support tool for companies. The main goal of this machinelearning (ML) model is to aid companies in ele...
详细信息
ISBN:
(纸本)9798350367607;9798350367591
This paper presents an Artificial intelligence (AI)-driven approach designed to provide a sophisticated decision support tool for companies. The main goal of this machinelearning (ML) model is to aid companies in elevating their Industry 4.0 maturity level by guiding strategic decision-making processes, drawing insights from successful companies that have attained high maturity levels in similar contexts.
This thesis introduces an innovative machinelearning solution to a prevalent healthcare challenge in Bangladesh: the legibility of handwritten prescriptions. Where 97.1% of Bangladeshi doctors relying on handwritten ...
详细信息
Ensuring the quality of software systems is essential for effective and efficient usage in complex software development procedures. A vital component of the whole procedure is the early identification and forecasting ...
详细信息
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.
Worldwide healthcare systems have faced enormous hurdles because of the COVID-19 pandemic, especially when it comes to treating individuals who already have pre-existing disorders such as cardiovascular diseases (CVDs...
详细信息
Worldwide healthcare systems have faced enormous hurdles because of the COVID-19 pandemic, especially when it comes to treating individuals who already have pre-existing disorders such as cardiovascular diseases (CVDs). Prioritizing medical therapies and resources for COVID-19 patients who are at increased risk of mortality from underlying CVDs requires early identification. In this work, we investigate how well three machinelearning algorithms-, Random Forest, XGBoost, and Logistic Regression-predict death in COVID-19 patients who already have cardiovascular disease. We performed grid search and cross-validation using a dataset of clinical and demographic features of COVID-19 patients with and without CVDs to reduce overfitting and maximize model performance. Our findings show that among patients with CVDs, Logistic Regression had the best accuracy in predicting COVID-19 fatality, followed by Random Forest and Decision Tree coming in a close second. These results highlight how machinelearning algorithms can help clinical professionals detect high-risk COVID-19 patients who have underlying cardiovascular diseases (CVDs), enable prompt interventions, and enhance patient outcomes.
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
暂无评论