Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

The impact of different negative training data on regulatory sequence predictions.

In PloS one ; h5-index 176.0

Regulatory regions, like promoters and enhancers, cover an estimated 5-15% of the human genome. Changes to these sequences are thought to underlie much of human phenotypic variation and a substantial proportion of genetic causes of disease. However, our understanding of their functional encoding in DNA is still very limited. Applying machine or deep learning methods can shed light on this encoding and gapped k-mer support vector machines (gkm-SVMs) or convolutional neural networks (CNNs) are commonly trained on putative regulatory sequences. Here, we investigate the impact of negative sequence selection on model performance. By training gkm-SVM and CNN models on open chromatin data and corresponding negative training dataset, both learners and two approaches for negative training data are compared. Negative sets use either genomic background sequences or sequence shuffles of the positive sequences. Model performance was evaluated on three different tasks: predicting elements active in a cell-type, predicting cell-type specific elements, and predicting elements' relative activity as measured from independent experimental data. Our results indicate strong effects of the negative training data, with genomic backgrounds showing overall best results. Specifically, models trained on highly shuffled sequences perform worse on the complex tasks of tissue-specific activity and quantitative activity prediction, and seem to learn features of artificial sequences rather than regulatory activity. Further, we observe that insufficient matching of genomic background sequences results in model biases. While CNNs achieved and exceeded the performance of gkm-SVMs for larger training datasets, gkm-SVMs gave robust and best results for typical training dataset sizes without the need of hyperparameter optimization.

Krützfeldt Louisa-Marie, Schubach Max, Kircher Martin

2020

General General

The influence of machine learning-based knowledge management model on enterprise organizational capability innovation and industrial development.

In PloS one ; h5-index 176.0

The aims are to explore the construction of the knowledge management model for engineering cost consulting enterprises, and to expand the application of data mining techniques and machine learning methods in constructing knowledge management model. Through a questionnaire survey, the construction of the knowledge management model of construction-related enterprises and engineering cost consulting enterprises is discussed. First, through the analysis and discussion of ontology-based data mining (OBDM) algorithm and association analysis (Apriori) algorithm, a data mining algorithm (ML-AR algorithm) on account of ontology-based multilayer association and machine learning is proposed. The performance of the various algorithms is compared and analyzed. Second, based on the knowledge management level, analysis and statistics are conducted on the levels of knowledge acquisition, sharing, storage, and innovation. Finally, according to the foregoing, the knowledge management model based on engineering cost consulting enterprises is built and analyzed. The results show that the reliability coefficient of this questionnaire is above 0.8, and the average extracted value is above 0.7, verifying excellent reliability and validity. The efficiency of the ML-AR algorithm at both the number of transactions and the support level is better than the other two algorithms, which is expected to be applied to the enterprise knowledge management model. There is a positive correlation between each level of knowledge management; among them, the positive correlation between knowledge acquisition and knowledge sharing is the strongest. The enterprise knowledge management model has a positive impact on promoting organizational innovation capability and industrial development. The research work provides a direction for the development of enterprise knowledge management and the improvement of innovation ability.

Zhou Zhigang, Liu Yanyan, Yu Hao, Ren Lihua

2020

Radiology Radiology

A Deep-Learning Diagnostic Support System for the Detection of COVID-19 Using Chest Radiographs: A Multireader Validation Study.

In Investigative radiology ; h5-index 46.0

** : The aim of this study was to compare a diagnosis support system to detect COVID-19 pneumonia on chest radiographs (CXRs) against radiologists of various levels of expertise in chest imaging.

MATERIALS AND METHODS : Five publicly available databases comprising normal CXR, confirmed COVID-19 pneumonia cases, and other pneumonias were used. After the harmonization of the data, the training set included 7966 normal cases, 5451 with other pneumonia, and 258 CXRs with COVID-19 pneumonia, whereas in the testing data set, each category was represented by 100 cases. Eleven blinded radiologists with various levels of expertise independently read the testing data set. The data were analyzed separately with the newly proposed artificial intelligence-based system and by consultant radiologists and residents, with respect to positive predictive value (PPV), sensitivity, and F-score (harmonic mean for PPV and sensitivity). The χ test was used to compare the sensitivity, specificity, accuracy, PPV, and F-scores of the readers and the system.

RESULTS : The proposed system achieved higher overall diagnostic accuracy (94.3%) than the radiologists (61.4% ± 5.3%). The radiologists reached average sensitivities for normal CXR, other type of pneumonia, and COVID-19 pneumonia of 85.0% ± 12.8%, 60.1% ± 12.2%, and 53.2% ± 11.2%, respectively, which were significantly lower than the results achieved by the algorithm (98.0%, 88.0%, and 97.0%; P < 0.00032). The mean PPVs for all 11 radiologists for the 3 categories were 82.4%, 59.0%, and 59.0% for the healthy, other pneumonia, and COVID-19 pneumonia, respectively, resulting in an F-score of 65.5% ± 12.4%, which was significantly lower than the F-score of the algorithm (94.3% ± 2.0%, P < 0.00001). When other pneumonia and COVID-19 pneumonia cases were pooled, the proposed system reached an accuracy of 95.7% for any pathology and the radiologists, 88.8%. The overall accuracy of consultants did not vary significantly compared with residents (65.0% ± 5.8% vs 67.4% ± 4.2%); however, consultants detected significantly more COVID-19 pneumonia cases (P = 0.008) and less healthy cases (P < 0.00001).

CONCLUSIONS : The system showed robust accuracy for COVID-19 pneumonia detection on CXR and surpassed radiologists at various training levels.

Fontanellaz Matthias, Ebner Lukas, Huber Adrian, Peters Alan, Löbelenz Laura, Hourscht Cynthia, Klaus Jeremias, Munz Jaro, Ruder Thomas, Drakopoulos Dionysios, Sieron Dominik, Primetis Elias, Heverhagen Johannes T, Mougiakakou Stavroula, Christe Andreas

2020-Nov-30

General General

Multikernel Capsule Network for Schizophrenia Identification.

In IEEE transactions on cybernetics

Schizophrenia seriously affects the quality of life. To date, both simple (e.g., linear discriminant analysis) and complex (e.g., deep neural network) machine-learning methods have been utilized to identify schizophrenia based on functional connectivity features. The existing simple methods need two separate steps (i.e., feature extraction and classification) to achieve the identification, which disables simultaneous tuning for the best feature extraction and classifier training. The complex methods integrate two steps and can be simultaneously tuned to achieve optimal performance, but these methods require a much larger amount of data for model training. To overcome the aforementioned drawbacks, we proposed a multikernel capsule network (MKCapsnet), which was developed by considering the brain anatomical structure. Kernels were set to match partition sizes of the brain anatomical structure in order to capture interregional connectivities at the varying scales. With the inspiration of the widely used dropout strategy in deep learning, we developed capsule dropout in the capsule layer to prevent overfitting of the model. The comparison results showed that the proposed method outperformed the state-of-the-art methods. Besides, we compared performances using different parameters and illustrated the routing process to reveal characteristics of the proposed method. MKCapsnet is promising for schizophrenia identification. Our study first utilized the capsule neural network for analyzing functional connectivity of magnetic resonance imaging (MRI) and proposed a novel multikernel capsule structure with the consideration of brain anatomical parcellation, which could be a new way to reveal brain mechanisms. In addition, we provided useful information in the parameter setting, which is informative for further studies using a capsule network for other neurophysiological signal classification.

Wang Tian, Bezerianos Anastasios, Cichocki Andrzej, Li Junhua

2020-Dec-01

General General

Density-Aware Curriculum Learning for Crowd Counting.

In IEEE transactions on cybernetics

Recently, crowd counting draws much attention on account of its significant meaning in congestion control, public safety, and ecological surveys. Although the performance is improved dramatically due to the development of deep learning, the scales of these networks also become larger and more complex. Moreover, a large model also entails more time to train for better performance. To tackle these problems, this article first constructs a lightweight model, which is composed of an image feature encoder and a simple but effective decoder, called the pixel shuffle decoder (PSD). PSD ends with a pixel shuffle operator, which can display more density information without increasing the number of convolutional layers. Second, a density-aware curriculum learning (DCL) training strategy is designed to fully tap the potential of crowd counting models. DCL gives each predicted pixel a weight to determine its predicting difficulty and provides guidance on obtaining better generalization. Experimental results exhibit that PSD can achieve outstanding performance on most mainstream datasets while training under the DCL training framework. Besides, we also conduct some experiments about adopting DCL on existing typical crowd counters, and the results show that they all obtain new better performance than before, which further validates the effectiveness of our method.

Wang Qi, Lin Wei, Gao Junyu, Li Xuelong

2020-Dec-01

General General

Semisupervised Learning via Axiomatic Fuzzy Set Theory and SVM.

In IEEE transactions on cybernetics

In this article, we present a semantic semisupervised learning (Semantic SSL) approach targeted at unifying two machine-learning paradigms in a mutually beneficial way, where the classical support vector machine (SVM) learns to reveal primitive logic facts from data, while axiomatic fuzzy set (AFS) theory is utilized to exploit semantic knowledge and correct the wrongly perceived facts for improving the machine-learning model. This novel semisupervised method can easily produce interpretable semantic descriptions to outline different categories by forming a fuzzy set with semantic explanations realized on the basis of the AFS theory. Besides, it is known that disagreement-based semisupervised learning (SSL) can be viewed as an excellent schema so that a co-training approach with SVM and the AFS theory can be utilized to improve the resulting learning performance. Furthermore, an evaluation index is used to prune descriptions to deliver promising performance. Compared with other semisupervised approaches, the proposed approach can build a structure to reflect data-distributed information with unlabeled data and labeled data, so that the hidden information embedded in both labeled and unlabeled data can be sufficiently utilized and can potentially be applied to achieve good descriptions of each category. Experimental results demonstrate that this approach can offer a concise, comprehensible, and precise SSL frame, which strikes a balance between the interpretability and the accuracy.

Jia Wenjuan, Liu Xiaodong, Wang Yuangang, Pedrycz Witold, Zhou Juxiang

2020-Dec-01