Certain small noncoding microRNAs (miRNAs) are differentially expressed in normal tissues and cancers, which makes them great candidates for biomarkers for cancer. Previously, a selected subset of miRNAs has been experimentally verified to be linked to breast cancer. In this paper, we validated the importance of these miRNAs using a machine learning approach on miRNA expression data. We performed feature selection, using Information Gain (IG), Chi-Squared (CHI2) and Least Absolute Shrinkage and Selection Operation (LASSO), on the set of these relevant miRNAs to rank them by importance. We then performed cancer classification using these miRNAs as features using Random Forest (RF) and Support Vector Machine (SVM) classifiers. Our results demonstrated that the miRNAs ranked higher by our analysis had higher classifier performance. Performance becomes lower as the rank of the miRNA decreases, confirming that these miRNAs had different degrees of importance as biomarkers. Furthermore, we discovered that using a minimum of three miRNAs as biomarkers for breast cancers can be as effective as using the entire set of 1800 miRNAs. This work suggests that machine learning is a useful tool for functional studies of miRNAs for cancer detection and diagnosis.

In this paper, the effectiveness of deep learning for automatic classification of grouper species by their vocalizations has been investigated. In the proposed approach, wavelet denoising is used to reduce ambient ocean noise, and a deep neural network is then used to classify sounds generated by different species of groupers. Experimental results for four species of groupers show that the proposed approach achieves a classification accuracy of around 90% or above in all of the tested cases, a result that is significantly better than the one obtained by a previously reported method for automatic classification of grouper calls.

Kidney cancer is one of the deadliest diseases and its diagnosis and subtype classification are crucial for patients’ survival. Thus, developing automated tools that can accurately determine kidney cancer subtypes is an urgent challenge. It has been confirmed by researchers in the biomedical field that miRNA dysregulation can cause cancer. In this paper, we propose a machine learning approach for the classification of kidney cancer subtypes using miRNA genome data. Through empirical studies we found 35 miRNAs that possess distinct key features that aid in kidney cancer subtype diagnosis. In the proposed method, Neighbourhood Component Analysis (NCA) is employed to extract discriminative features from miRNAs and Long Short Term Memory (LSTM), a type of Recurrent Neural Network, is adopted to classify a given miRNA sample into kidney cancer subtypes. In the literature, only a couple of kidney subtypes have been considered for classification. In the experimental study, we used the miRNA quantitative read counts data, which was provided by The Cancer Genome Atlas data repository (TCGA). The NCA procedure selected 35 of the most discriminative miRNAs. With this subset of miRNAs, the LSTM algorithm was able to group kidney cancer miRNAs into five subtypes with average accuracy around 95% and Matthews Correlation Coefficient value around 0.92 under 10 runs of randomly grouped 5-fold cross-validation, which were very close to the average performance of using all miRNAs for classification.

Intracranial Hemorrhage (ICH) has high rates of mortality, and risk factors associated with it are sometimes nearly impossible to avoid. Previous techniques to detect ICH using machine learning have shown some promise. However, due to a limited number of labeled medical images available, which often causes poor model accuracy in terms of the Dice coefficient, there is much to be improved. In this paper, we propose a modified u-net and curriculum learning strategy using a multi-task semi-supervised attention-based model, initially introduced by Chen et al., to segment ICH sub-groups from CT images. Using a modified inverse-sigmoid-based curriculum learning training strategy, we were able to stabilize Chen’s algorithm experimentally. This semi-supervised model produced higher Dice coefficient values in comparison to a supervised counterpart, regardless of the amount of labeled data used to train the model. Specifically, when training with 80% of the ground truth data, our semi-supervised model produced a Dice coefficient of 0.67, which was higher than 0.61, obtained by a comparable supervised model. This result also surpassed by a greater margin the one obtained by using the out-of-the-box u-net by Hssayeni et al.

A new approach to self-calibrate a camera-equipped robot manipulator is proposed in this paper. Self-calibration here means that the camera-robot system is capable of determining its geometric parameters without any external measurements and/or ground truth calibration data. With the proposed approach, one is able to identify all the rotational parameters and, up to a scale factor, all the translational parameters of a robotic system without any ground truth data. It is known from the computer vision literature that the extrinsic and intrinsic parameters of the camera can be obtained up to a scale factor by using the corresponding points of objects in a natural environment from an image sequence without knowing the positions of these object points. It is also well known that if the camera is treated as the tool of the robot, one is able to compute the corresponding robot pose directly from the camera-extrinsic parameters. An important question is how to determine the scale factors, which vary from one robot pose to another. It is discovered in this paper that if the robot pose measurement configurations follow a specially planned optimal trajectory, a unique scale factor can be used for all the poses measured along the trajectory. Thus, one is able to identify all the independent parameters of the robot with the poses measured in this manner with an inherently undetermined scale factor. One question remains: how do we obtain this unknown scale factor? Actually, the problem can be solved in a separate process. By two views of, say, a yardstick with the known length, the scale factor can be computed. If more than one measurement of the scale or measurements of multiple scales are provided from different viewing angles, the scale factor can be estimated with better accuracy in a least squares sense. Extensive simulation and experiment studies on a PUMA 560 robot reveal the convenience and effectiveness of the proposed approach.

An image processing technique called Local Binary Patterns (LBP) has been explored for its ability to generate feature vectors for dolphin vocalization classification. The LBP operator eliminates the need for contour tracing, denoising, and other prior processing. In an experimental study of classifying dolphin whistle types, the performance of the LBP operation was compared with that of the popular contour-based Time-Frequency Parameters (TFP) approach. The preliminary experimental results illustrate that the LBP method produces more consistent classifier accuracy of dolphin whistle calls even when the contour shapes are complex and populated with impulsive clicks and anthropogenic harmonics.