Software information sites (e.g., Jira, Stack Overflow) are now wide-ly used in software development. These online platforms for collaborative development preserve a large amount of Software Engineering (SE) texts. These texts enable researchers to detect developers’ attitudes toward their daily development by analyzing the sentiments expressed in the texts. Unfortunately, recent works reported that neither off-the-shelf tools nor SE-specified tools for sentiment analysis on SE texts can provide satisfying and reliable results. In this paper, we propose to incorporate pre-trained transformer models into the sentence-classification oriented deep learning framework named TextCNN to better capture the unique expression of sentiments in SE texts. Specifically, we introduce an optimized BERT model named RoBERTa as the word embedding layer of TextCNN, along with additional residual connections between RoBERTa and TextCNN for better cooperation in our training framework. An empirical evaluation based on four datasets from different software information sites shows that our training framework can achieve overall better accuracy and generalizability than the four baselines.

At present, computed tomography (CT) is widely used to assist disease diagnosis. Especially, computer aided diagnosis (CAD) based on artificial intelligence (AI) recently exhibits its importance in intelligent healthcare. However, it is a great challenge to establish an adequate labeled dataset for CT analysis assistance, due to the privacy and security issues. Therefore, this paper proposes a convolutional autoencoder deep learning framework to support unsupervised image features learning for lung nodule through unlabeled data, which only needs a small amount of labeled data for efficient feature learning. Through comprehensive experiments, it shows that the proposed scheme is superior to other approaches, which effectively solves the intrinsic labor-intensive problem during artificial image labeling. Moreover, it verifies that the proposed convolutional autoencoder approach can be extended for similarity measurement of lung nodules images. Especially, the features extracted through unsupervised learning are also applicable in other related scenarios.

In this paper, the concept of crowdsourcing is applied to the medical field and a health monitoring mechanism based on photo crowdsourcing is proposed. Specifically, with photo crowdsourcing by many participators, the routine circumstances of users may be represented. However, these photos may include other people than the user, such as the visibility requestor, the invisibility requestor, and the passerby. The visibility and invisibility requestor are the participators in the system, whose identity can be set as visible or invisible, while the passerbys do not participate in the system. Hence, a privacy protection mechanism is proposed for this system, which includes two categories: i) The image fuzzy processing is provided for the invisibility requestor, while the original image is reserved for the visibility requestor. ii) The passerby's image is directly fuzzy processed for privacy protection.

In this paper, we are trying to find the developmental tendencies and study hotspots of intelligent transportation systems technologies by theme classification and analysis of core articles from all papers published in IEEE Transactions on Intelligent Transportation Systems during 2010-2013. First, we classify theme categories by co-word analysis with different research domains and obtain 12 themes that include vehicle control technology, modeling and simulation, image processing, etc. Second, we find research focuses and directions of these themes by analyzing the trends of the article numbers published in each year of the TOP 5 themes. Finally, we identify TOP 5 core articles of these 12 themes and obtain their specific study hotspots by sorting the citations without self-citations of the articles in the Web of Science.

This paper describes experimental results for autonomous robotic rock excavation with fuzzy logic and neural networks. An excavation goal is decomposed into several tasks, whereas a take is accomplished by executing appropriate excavation behaviors. Finally, a behavior is carried out by a sequence of primitive, machine executing excavation actions. Excavation goals, tasks, and behaviors are specified using finite state machines (FSM) based on excavation heuristics and expertise from skilled human operators. The decision making in the FSMs are implemented using neural networks which are capable of improving their performance from previous task executions. Excavation actions are given using fuzzy logic rules acquired from human experience and heuristics. Several experiments are presented that demonstrate the system's ability to complete required excavation tasks effectively.