Open Education Platforms have revolutionized learning by providing accessible and flexible education to a vast number of learners. However, understanding learner behaviour in such environments remains a challenge due ...
详细信息
For the current multimodal classification, there is the drawback that can not cope the any combination of modalities. So, this paper proposes a novel unified convolutional classification model for overcoming the disad...
详细信息
ISBN:
(纸本)9798400707032
For the current multimodal classification, there is the drawback that can not cope the any combination of modalities. So, this paper proposes a novel unified convolutional classification model for overcoming the disadvantage. We propose the Giant Multi-Scale Dilation Block (GMSDB) for enhancing Spatial Attention Block, including Large Separable Kernel Attention (LSKA) and Multiscale Swelling Attention Block (MSAB), For LSKA, GMSDB can obtain a larger sensory field via an ultra large kernel, and decompose the 2D convolutional kernel of the deep convolutional layer into cascaded horizontal 1D and vertical 1D kernels, which effectively converts the long text and video data into an ultra large vector matrix representation. For MSDA, with multi-head design, the channels of the feature map can be divided into n different heads, and Sliding Window Expansion of Attention (SWDA) can be performed through different dilation rates at different heads. Based on the above model, the semantic information at various scales within the attended sensory field can be aggregated, and the redundancy of the self-attention mechanism can be reduced effectively. In this way, the long-range dependence problem is successfully solved and the ability on adapting to inputs of different scales from different modes is effectively improved.
Automated speech recognition (ASR) systems struggle with Bengali, which is the fifth most spoken language. Bengali has a varied morphology, many dialects, and limited high-quality annotated voice data. Traditional voi...
详细信息
This document introduces the 1stinternational Virtual Conference on Visual pattern Extraction and recognition for Cultural Heritage Understanding (VIPERC 2022), a premier forum for presenting the state-of-the-art, ne...
详细信息
Among the many methods of analysing correlation coefficient, the two classical methods are the Spearman correlation coefficient and Pearson correlation coefficient. For the Spearman method, the time complexity is larg...
详细信息
ISBN:
(纸本)9798400707032
Among the many methods of analysing correlation coefficient, the two classical methods are the Spearman correlation coefficient and Pearson correlation coefficient. For the Spearman method, the time complexity is larger because of the sorting data. For the Pearson method, there are also some limited conditions, such as the data are needed to linearly related and continuous, normally distributed or near-normally distributed with a single peak and independent. To avoid the disadvantages about the above correlation coefficients, we propose a novel method about correlation calculation based on an inequation, which derives from inventory model theory and risk pooling theory. Firstly, for the whole dataset, we calculate the sample mean and standard deviation of sub elements and whole datasets respectively. Then, using the inventory model theory, we calculate the total standard deviation of the whole dataset and the sum of standard deviation about sub elements of whole dataset, and obtain the novel inequality. Then, judge this inequality: when "=" is true, conclude that there is no correlation data in the entire dataset X;when ">" is true, it is judged that the entire dataset X has relevant data, furthermore, the bigger the difference of left value subtracts right value, the stronger the correlation. The proposed algorithm owns the lower time complexity and much wider range of uses. Finally, the GDP experiment and Gini index experiment demonstrate the effectiveness of the novel method.
The black box nature of current AI models has raised serious concerns about accountability, bias and trust in the models that might undermine their relevance and usefulness in the field of medicine where human lives a...
详细信息
ISBN:
(纸本)9783031543029;9783031543036
The black box nature of current AI models has raised serious concerns about accountability, bias and trust in the models that might undermine their relevance and usefulness in the field of medicine where human lives are at risk. AI in medicine has the ability to derive meaningful inferences from real world data - an emerging school of thought namely Real World Evidence (RWE) studies - that can assist medical practitioners to improve evidence based quality of care. In the field of oncology, the accuracy and performance of inference models are as important as clinically relevant and sound explanations of the inference. In this paper, we present an Explainable AI (XAI) framework for our AI model that predicts the suitability of a chemotherapy treatment at the time of its prescription based on RWE. The framework provides explanations both for a specific patient and also for the model. It provides explanations like feature analysis, counterfactual, and top risk factors that contribute to a treatment failure. As a result, the framework adds an explainability layer between treatment failure predictive model and oncologists, thereby enabling evidence based assistance to oncologists in designing chemotherapy plans.
In order to resist network attacks on IoT devices, identifying IoT devices is the firststep for ensuring device security. The traditional passive method identifies IoT devices by mining the potential relationship bet...
详细信息
ISBN:
(纸本)9798350350128
In order to resist network attacks on IoT devices, identifying IoT devices is the firststep for ensuring device security. The traditional passive method identifies IoT devices by mining the potential relationship between traffic characteristics and devices. However, the form of selected traffic features are too singular without considering device behavioral characteristics and the classifier used is too specific with simple structure in these methods. This paper proposes a stacking ensemble learning approach for IoT device identification, ENSIOT, which fully considering the behavioral characteristics of devices and integrating the advantages of various machinelearning methods to achieve efficient identification of IoT devices. Firstly, in the process of traffic processing, our method selects features from activity cycles, port numbers, signalling patterns, and cipher suites. Then, in model integration, many machinelearning methods are used as base models to learn features selected, and output preliminary recognition results. Finally, the meta model learns the relationship between label and the recognition results of each base model and outputs the final device identification result. This stacking structure stacks the base models and the meta model to make a classifier with strong identification and generalization ability. Incremental learning is used to improve identification accuracy when traffic pattern changing. Comparative experiments are conducted on two datasets of UNSW and TMA-2021. The experimental results verify the effectiveness of ENSIOT, which achieve the accuracy of over 98% on two dataset and bring a noticeable improvement in terms of both accuracy and macro F1 score.
Recent studies showed the possibility of extracting SoS information from pulse-echo ultrasound raw data (a.k.a. RF data) using deep neural networks that are fully trained on simulated data. These methods take sensor d...
详细信息
ISBN:
(纸本)9783031476785;9783031476792
Recent studies showed the possibility of extracting SoS information from pulse-echo ultrasound raw data (a.k.a. RF data) using deep neural networks that are fully trained on simulated data. These methods take sensor domain data, i.e., RF data, as input and train a network in an end-to-end fashion to learn the implicit mapping between the RF data domain and the SoS domain. However, such networks are prone to overfitting to simulated data which results in poor performance and instability when tested on measured data. We propose a novel method for SoS mapping employing learned representations from two linked autoencoders. We test our approach on simulated and measured data acquired from human breast mimicking phantoms. We show that SoS mapping is possible using the learned representations by linked autoencoders. The proposed method has a Mean Absolute Percentage Error (MAPE) of 2.39% on the simulated data. On the measured data, the predictions of the proposed method are close to the expected values (MAPE of 1.1%). Compared to an end-to-end trained network, the proposed method shows higher stability and reproducibility.
Air pollution has been shown to have serious negative effects on people’s health, the environment, and the economy. It is becoming more and more crucial to model, predict, and monitor air quality, particularly in urb...
详细信息
In the era of big data, sentiment analysis on social media platforms presents unique challenges due to the noisy and unstructured nature of the data. This study introduces a novel deep learning approach for discoverin...
详细信息
暂无评论