Accurate reading and comprehension of medical prescriptions are crucial for healthcare providers to ensure appropriate treatment for the patients. However, with the growing volume of prescriptions and increasingly com...
详细信息
Cooperative search and tracking of multiple Unmanned Aerial Vehicle(UAV) systems is becoming a key application paradigm for realizing efficient coordination missions. This paper proposes a multiple UAV cooperative sea...
详细信息
Due to the wealth of information it contains, ship radiated noise plays a crucial role in underwater acoustic signal processing for ship identification. The traditional approach to ship radiated noise detection is ext...
详细信息
In recent days most people who are disabled are not able to make proper communication with others. Deaf people frequently communicate through sign language, a kind of manual communication. There are many different sig...
详细信息
In reality, it is laborious to obtain complete label degrees, giving birth to Incomplete Label Distribution Learning (InLDL), where some degrees are missing. Existing InLDL methods often assume that degrees are unifor...
ISBN:
(纸本)9781956792041
In reality, it is laborious to obtain complete label degrees, giving birth to Incomplete Label Distribution Learning (InLDL), where some degrees are missing. Existing InLDL methods often assume that degrees are uniformly random missing. However, it is often not the case in practice, which arises the first issue. Besides, they often adopt explicit regularization to compensate the incompleteness, leading to burdensome parameter tuning and extra computation, causing the second issue. To address the first issue, we adopt a more practical setting, i.e., small degrees are more prone to be missing, since large degrees are likely to catch more attention. To tackle the second issue, we argue that label distribution itself already contains abundant knowledge, such as label correlation and ranking order, thus it may have provided enough prior for learning. It is precisely because existing methods overlook such a prior that leads to the forced adoption of explicit regularization. By directly utilizing the label degrees prior, we design a properly weighted objective function, exempting the need from explicit regularization. Moreover, we provide rigorous theoretical analysis, revealing in principle that the weighting plays an implicit regularization role. To sum up, our method has four advantages, it is 1) model selection free;2) with closed-form solution (sub-problem) and easy-to-implement (a few lines of codes);3) with linear computational complexity in the number of samples, thus scalable to large datasets;4) competitive with state-of-the-arts in both random and non-random missing scenarios.
With the rapid development of artificial intelligence and machine vision technology, power grid inspection system based on vision is widely used. However, the power grid intelligent inspection system has the problem o...
详细信息
Power communication network is an important infrastructure in power system, and its security and stability are very important to ensure the normal operation of power system. With the development and application of pow...
详细信息
Building pattern informs urban spatial structure understanding and modeling. However, previous studies showed limitations on the identification of building groups which has complex spatial distribution. Specifically, ...
详细信息
The widespread use of social media has opened the door to new forms of harassment and abuse, such as cyberbullying, that have a serious impact on individuals39; psychological health. Therefore, research communities ...
详细信息
ISBN:
(纸本)9789819712731;9789819712748
The widespread use of social media has opened the door to new forms of harassment and abuse, such as cyberbullying, that have a serious impact on individuals' psychological health. Therefore, research communities have recently developed detection approaches using Natural Language Processing (NLP) combined with machine learning algorithms to identify instances of cyberbullying in social media texts. However, they are unable to determine the type of cyberbullying and the reasons why victims may be targeted. This paper develops a novel detection approach that can identify the type of cyberbullying based on characteristics such as gender, religion, age, and ethnicity, even if the original records in the training dataset do not include such information or features. This paper has accomplished this objective by utilizing Explainable Artificial intelligence (XAI) technology alongside machine learning models to justify and explain the classification of text as cyberbullying. Technically speaking, XAI technology enables machine learning models to capture and highlight the most influential words that affect the decision to classify a text as cyberbullying. Those influential words are utilized to re-label and update the training data. The machine learning models are then re-trained using the updated data. To evaluate the performance of the proposed approach, a simulation experiment has been conducted on a large dataset containing texts from Twitter. Simulation results show that XAI technology provides convincing explanations for classifying a text as cyberbullying. It also enables machine learning models to identify various types of cyberbullying and enhances their performance in terms of classification accuracy.
Adherence to procedures and rules is essential in order to obtain the best results in medicine and sports. However, traditional clinical setups can induce stress in patients, hindering recovery. Meanwhile, advancement...
详细信息
暂无评论