Current state-of-the-art class-imbalanced loss functions for deep models require exhaustive tuning on hyperparameters for high model performance, resulting in low training efficiency and impracticality for nonexpert users. To tackle this issue, a parameter-free loss (PF-loss) function is proposed, which works for both binary and multiclass-imbalanced deep learning for image classification tasks. PF-loss provides three advantages: 1) training time is significantly reduced due to NO tuning on hyperparameter(s); 2) it dynamically pays more attention on minority classes (rather than outliers compared to the existing loss functions) with NO hyperparameters in the loss function; and 3) higher accuracy can be achieved since it adapts to the changes of data distribution in each mini-batch instead of the fixed hyperparameters in the existing methods during training, especially when the data are highly skewed. Experimental results on some classical image datasets with different imbalance ratios (IR, up to 200) show that PF-loss reduces the training time down to 1/148 of that spent by compared state-of-the-art losses and simultaneously achieves comparable or even higher accuracy in terms of both G-mean and area under receiver operating characteristic (ROC) curve (AUC) metrics, especially when the data are highly skewed.

Combing brain-computer interfaces (BCI) and virtual reality (VR) is a novel technique in the field of medical rehabilitation and game entertainment. However, the limitations of BCI such as a limited number of action commands and low accuracy hinder the widespread use of BCI-VR. Recent studies have used hybrid BCIs that combine multiple BCI paradigms and/or the multi-modal biosensors to alleviate these issues, which may become the mainstream of BCIs in the future. The main purpose of this review is to discuss the current status of multi-modal BCI-VR. This study first reviewed the development of the BCI-VR, and explored the advantages and disadvantages of incorporating eye tracking, motor capture, and myoelectric sensing into the BCI-VR system. Then, this study discussed the development trend of the multi-modal BCI-VR, hoping to provide a pathway for further research in this field.

The discovery of Wireless Power Transfer (WPT) technologies makes charging more convenient and reliable. Among all the existing WPT technologies, directional WPT is more efficient and has been successfully applied to supply energy for wireless rechargeable sensor networks (WRSNs). However, the state-of-the-art methods ignore the anisotropic energy receiving property of rechargeable sensors, resulting in energy wastage. In order to address this issue, in this paper, we point out that the received energy of a sensor is not only relative to the distance, but also relative to the angle between the sensor and the charger's orientation in directional WPT. Towards this end, we derive a pragmatic energy transfer model verified by experiments. In particular, we focus on a Minimal chArging Delay (MAD) problem to reduce charging delays. To obtain the optimal solution, we formulate the problem as a linear programming problem. Moreover, we introduce a method of charging power discretization, which significantly reduces the search space and bounds the performance gap to the optimal one with a 1/1-ϵ2approximation ratio. Besides, a merging method is introduced for a more practical application scenario. Finally, we demonstrate that our methods outperform the Set Cover baseline method by an average of 34.2% through simulations and experiments.

Partial charging in wireless rechargeable sensor networks (WRSNs) has been proposed recently, offering an new alternative in dealing with non-schedulable charging tasks. Most previous charging scheduling algorithms assume that a mobile charger must replenish a sensor to its full energy capacity in fulfilling every charging task (non-preemptive tasks). However, this charging manner degrades the charging efficiency and shortens the network lifetime to some extent. On the other hand, a partial-charging model is more effective and flexible. Although some previous works adopted a partial-charging model, they failed to theoretically formalize the schedulability of partial charging scheduling for WRSNs. To the best of our knowledge, this work first proposes a schedulability evaluation mechanism for such partial-charging scheduling. A partial charging scheme (PCS) based on schedulability evaluation for the on-demand charging architecture is given. Next, a simple case is presented for better comprehension and to demonstrate the merits of PCS. Additionally, test-bed experiments are conducted to compare the performance between the proposed scheme and previous schemes by applying different wireless energy transfer standards.

Recently, wireless power transfer is emerging as an enabling technology of wireless rechargeable sensor networks. Conventional methods that charge each sensor until its battery is full take unproportionally long time to finish, due to the limitation of charging efficiency and power transfer technologies. In this paper, we propose a mixed partial and full charge (MPF) scheme, including three specialized modules, i.e., evaluation module, adjustment module, and selection module. MPF allows nodes to be replenished "partially" by a mobile charging vehicle (MCV). When executing adjustment module, a concept of power and path adjustment window is proposed for determining a proper power allocation scheme as well as charging path. Then a scheduling strategy termed return mechanism is designed to further utilize the energy of the MCV and improve effective energy utilization. Finally, we build a high-accuracy charging test-bed and evaluate the applicability as well as performance of the proposed scheme. For large-scale networks, we also perform simulations to demonstrate the effectiveness of MPF in promoting survival rate and reducing traveling distance of the MCV.

The lack of schedulability evaluation of previous charging schemes in wireless rechargeable sensor networks (WRSNs) degrades the charging efficiency, leading to node exhaustion. We propose an Optimal Path Planning Charging scheme, namely OPPC, for the on-demand charging architecture. OPPC evaluates the schedulability of a charging mission, which makes charging scheduling predictable. It provides an optimal charging path which maximizes charging efficiency. When confronted with a non-schedulable charging mission, a node discarding algorithm is developed to enable the schedulability. Experimental simulations demonstrate that OPPC can achieve better performance in successful charging rate as well as charging efficiency.

Traditional coverage metrics in verification focus on controllability without taking observability into account, which may result in an artificially high coverage and a false sense of confidence. In this paper, we present a path constraint solving based test generation method at register-transfer level (RTL) for observability-enhanced branch coverage. The branches executed but not observed by a test sequence are identified as our target branches. The test generation for each target branch is converted to the process of covering multiple intermediate sub-target states sequentially to guarantee the execution and observation of the target branch. Valid input vectors are automatically generated by multicycle path constraint solving and simulation is guided by the abstract distance information to reach the sub-target states. Experimental results show that our approach can reduce the gap between branch coverage and observability-enhanced branch coverage.

Test generation for hard-to-reach states is important in functional verification. In this paper, we present a path constraint solving-based test generation method (PACOST) which operates in an abstraction-guided semiformal verification framework to cover hard-to-reach states. PACOST combines concrete simulation and symbolic simulation on the design under verification for path constraint extraction and mutation, and uses a sequential path constraint extractor to generate a set of valid input vectors for exploring different simulation paths with different next states. It then works on a target state-oriented abstract model to select the next state with the smallest abstract distance. In addition, the value of register variables in control logic can be controlled by analyzing the data dependence between variables, which helps the simulation converge to the target states. Experimental results show that PACOST can generate shorter traces reaching hard-to-reach states, in comparison with previous abstraction-guided semiformal methods.

Test generation for hard-to-reach states has been one of the hardest tasks in functional verification. In this paper, we present PACOST, a PAth Constraint Solving based Test generation method which operates in an abstraction-guided simulation framework to cover hard-to-reach states. PACOST combines concrete simulation and symbolic simulation in a path constraint solver to generate a set of valid input vectors for exploring different simulation paths, followed by next state selection considering abstract distances. In addition, two backtracking strategies are proposed to alleviate the dead end problem and ensure fast converge to the target state. Experimental results show that PACOST is effective in covering hard-to-reach states.

Drosha is a class of RNase III enzyme plays important roles in the microRNA (miRNA) generation by cleaving primary miRNAs to release hairpin-shaped miRNA precursors. Accurately predicting the Drosha cleavage positions (i.e., processing sites) is helpful for the identification of miRNAs and the understanding of miRNA biogenesis mechanisms. In this study, we presented a Drosha processing site predictor, termed DroshaPSP, with a two-step prediction model by integrating structure and sequence features. Testing results on the Drosophila melanogaster miRNA data showed that DroshaPSP obtained a sensitivity of 0.859, a specificity of 0.999, and a Matthew's Correlation Coefficient of 0.864. We also found that the Shannon entropy is a powerful structure feature for DroshaPSP to distinguish true Drosha processing sites from the nearby pseudo processing sites effectively.

Bioinformatics has become an important subject in computer science (CS). While it is an active research area, bioinformatics is still of infancy in CS education. E-learning labs are emerging as important educational tools for bioinformatics. We consider that it can be improved with case study and simulated virtual environment. In this study we present a dedicated case-study e-learning lab for bioinformatics (CELB). It is publicly accessible at http://bioinfo.hust.edu.cn:8080/blast4/. The evaluation results reveal that this e-learning lab is suitable for training students' problem-solving ability in bioinformatics.

Collaborative tagging systems have emerged as an ubiquitous way to annotate and organize online resources. The users' tagging actions over time reflect the changing of their interests. In this paper, we propose to detect bursty tagging event, which captures the relations among a group of correlated tags where the tags are either bursty or associated with bursty tag co-occurrence. We exploit the sliding time intervals to extract bursty features from large tag corpora as the first step, and then adopt graph clustering techniques to group bursty features into meaningful bursty events. An experimental study demonstrates the superiority of our approach.

Online forums contain huge amounts of valuable user-generated content. In current forum systems, users have to passively wait for other users to visit the forum systems and read/answer their questions. The user experience for question answering suffers from this arrangement. In this paper, we address the problem of "pushing" the right questions to the right persons, the objective being to obtain quick, high-quality answers, thus improving user satisfaction. We propose a framework for the efficient and effective routing of a given question to the top-k potential experts (users) in a forum, by utilizing both the content and structures of the forum system. First, we compute the expertise of users according to the content of the forum system--this is to estimate the probability of a user being an expert for a given question based on the previous question answering of the user. Specifically, we design three models for this task, including a profile-based model, a thread-based model, and a cluster-based model. Second, we re-rank the user expertise measured in probability by utilizing the structural relations among users in a forum system. The results of the two steps can be integrated naturally in a probabilistic model that computes a final ranking score for each user. Experimental results show that the proposals are very promising.