Pose Generation for Social Robots in Conversational Group Formations

We study two approaches for predicting an appropriate pose for a robot to take part in group formations typical of social human conversations subject to the physical layout of the surrounding environment. One method is model-based and explicitly encodes key geometric aspects of conversational formations. The other method is data-driven. It implicitly models key properties of spatial arrangements using graph neural networks and an adversarial training regimen. We evaluate the proposed approaches through quantitative metrics designed for this problem domain and via a human experiment. Our results suggest that the proposed methods are effective at reasoning about the environment layout and conversational group formations. They can also be used repeatedly to simulate conversational spatial arrangements despite being designed to output a single pose at a time. However, the methods showed different strengths. For example, the geometric approach was more successful at avoiding poses generated in nonfree areas of the environment, but the data-driven method was better at capturing the variability of conversational spatial formations. We discuss ways to address open challenges for the pose generation problem and other interesting avenues for future work.

Shear Wave Elastography-Assisted Ultrasound Breast Image Analysis and Identification of Abnormal Data

In this paper, shear wave elastography was used to study and analyze the images of the breast in-depth and identify the abnormal image data. Sixty breast lesions were evaluated, and quantitative metrics were reproducible in the static and dynamic modes of shear wave elastography with a higher interobserver agreement in dynamic qualitative metrics than in the static mode. There were no statistically significant differences between the two modes of imaging in quantitative metrics, and quantitative metrics were more effective than qualitative metrics. Postoperative immunohistochemical expression of ER, PR, HER-2, Ki-67, molecular typing, pathological type, histological grading, and axillary lymph node status of breast cancer was obtained based on pathological results. The correlation between mass size, patient age, and WiMAX values of breast cancer masses was analyzed using Pearson correlation, and the differences in SWVmax values of breast cancer masses between different expressions of immunohistochemical parameters ER, PR, HER-2, Ki-67, and axillary lymph node status were compared using tests. The variables with correlations and differences were included in the multiple linear regression analysis to assess the factors influencing the SWVmax values. The performance of TDPM, SPM, and TSPM was compared using PVA body models with different freeze-thaw cycles. The results showed that TSPM performed better than SPM in general, and TDPM showed excellent performance because of high temporal resolution and low random error, especially when the number of freeze-thaw cycles increased and the hardness of the PVA body mold increased. Measurements at different depths of inhomogeneous body models also showed that the TDPM method was less affected by depth, and the results were more stable. Finally, the reliability of the shear wave velocity (SWS) measured by the TDPM and SPM methods was investigated using porcine ligament tissue, and the results showed that the mean values of SWS goodness of fit for TDPM and SPM were 0.94 and 0.87, respectively, and the estimated elastic modulus of TDPM was very close to the mechanical test results.

Is Synthetic The New Real? Performance Analysis of Time Series Generation Techniques with Focus on Network Load Forecasting

This paper explores whether Generative Adversarial Networks (GANs) can produce realistic network load data that can be utilized to train machine learning models in lieu of real data. In this regard, we evaluate the performance of three recent GAN architectures on the Telecom Italia data set across a set of qualitative and quantitative metrics. Our results show that GAN generated synthetic data is indeed similar to real data and forecasting models trained on this data achieve similar performance to those trained on real data.

Is Synthetic The New Real? Performance Analysis of Time Series Generation Techniques with Focus on Network Load Forecasting

This paper explores whether Generative Adversarial Networks (GANs) can produce realistic network load data that can be utilized to train machine learning models in lieu of real data. In this regard, we evaluate the performance of three recent GAN architectures on the Telecom Italia data set across a set of qualitative and quantitative metrics. Our results show that GAN generated synthetic data is indeed similar to real data and forecasting models trained on this data achieve similar performance to those trained on real data.

Habitat Integrity in Protected Areas Threatened by LULC Changes and Fragmentation: A Case Study in Tehran Province, Iran

The integration and connection of habitats in protected areas (PAs) are essential for the survival of plant and animal species and attaining sustainable development. Investigating the integrity of PAs can be useful in developing connections among patches and decreasing the fragmentation of a habitat. The current study has analyzed spatial and temporal changes to habitat to quantify fragmentation and structural destruction in PAs in Tehran Province, Iran. To achieve this purpose, the trends in land use/land cover (LULC) changes and the quantitative metrics of the landscape ecology approach have been examined. The results revealed that in Lar National Park, low-density pasture has the top increasing trend with 4.2% from 1989 to 2019; in Jajrud PA, built-up has the top increasing trend with 1.5% during the studied years; and among the land uses in TangehVashi Natural Monument, bare land has the top increasing trend with 0.6% from 1989 to 2019. According to the findings, habitat fragmentation and patch numbers have expanded in the studied areas due to the development of economic and physical activities. The results also indicate that the current trend of habitat fragmentation in PAs will have the highest negative impacts, especially in decreasing habitat integrity, changing the structure of patterns and spatial elements, and increasing the edge effect of patches.

Removal of Multiplicative Gamma Noise from Images via SRAD Model Amelioration

In this paper, an improved Speckle Reducing Anisotropic Diffusion (SRAD), destined to remove multiplicative gamma noise applied to different images is proposed. The basic idea is to divide the image into several riddled areas and then calculate the Equivalent Number of Look (ENL) of each region. The largest value of the ENL is the best optimal homogeneous region of the image. This optimal choice allows us to solve the major problem of the SRAD algorithm articulated around a visual choice of the homogeneous region which is not satisfactory and causes non-uniformity in this area. To give more validity to the proposed method, several experimentations were conducted using different kinds of images and were approved by some quantitative metrics like PSNR, SNR, VSNR, and SSIM. The computer simulation results confirm the efficiency of the proposed method which outperformances the classical SRAD method.

Hybrid Sharpening Transformation Approach for Multifocus Image Fusion Using Medical and Nonmedical Images

In this study, we introduced a preprocessing novel transformation approach for multifocus image fusion. In the multifocus image, fusion has generated a high informative image by merging two source images with different areas or objects in focus. Acutely the preprocessing means sharpening performed on the images before applying fusion techniques. In this paper, along with the novel concept, a new sharpening technique, Laplacian filter + discrete Fourier transform (LF + DFT), is also proposed. The LF is used to recognize the meaningful discontinuities in an image. DFT recognizes that the rapid change in the image is like sudden changes in the frequencies, low-frequency to high-frequency in the images. The aim of image sharpening is to highlight the key features, identifying the minor details, and sharpen the edges while the previous methods are not so effective. To validate the effectiveness the proposed method, the fusion is performed by a couple of advanced techniques such as stationary wavelet transform (SWT) and discrete wavelet transform (DWT) with both types of images like grayscale and color image. The experiments are performed on nonmedical and medical (breast medical CT and MRI images) datasets. The experimental results demonstrate that the proposed method outperforms all evaluated qualitative and quantitative metrics. Quantitative assessment is performed by eight well-known metrics, and every metric described its own feature by which it is easily assumed that the proposed method is superior. The experimental results of the proposed technique SWT (LF + DFT) are summarized for evaluation matrices such as RMSE (5.6761), PFE (3.4378), MAE (0.4010), entropy (9.0121), SNR (26.8609), PSNR (40.1349), CC (0.9978), and ERGAS (2.2589) using clock dataset.

JLAN: medical code prediction via joint learning attention networks and denoising mechanism

Background Clinical notes are documents that contain detailed information about the health status of patients. Medical codes generally accompany them. However, the manual diagnosis is costly and error-prone. Moreover, large datasets in clinical diagnosis are susceptible to noise labels because of erroneous manual annotation. Therefore, machine learning has been utilized to perform automatic diagnoses. Previous state-of-the-art (SOTA) models used convolutional neural networks to build document representations for predicting medical codes. However, the clinical notes are usually long-tailed. Moreover, most models fail to deal with the noise during code allocation. Therefore, denoising mechanism and long-tailed classification are the keys to automated coding at scale. Results In this paper, a new joint learning model is proposed to extend our attention model for predicting medical codes from clinical notes. On the MIMIC-III-50 dataset, our model outperforms all the baselines and SOTA models in all quantitative metrics. On the MIMIC-III-full dataset, our model outperforms in the macro-F1, micro-F1, macro-AUC, and precision at eight compared to the most advanced models. In addition, after introducing the denoising mechanism, the convergence speed of the model becomes faster, and the loss of the model is reduced overall. Conclusions The innovations of our model are threefold: firstly, the code-specific representation can be identified by adopted the self-attention mechanism and the label attention mechanism. Secondly, the performance of the long-tailed distributions can be boosted by introducing the joint learning mechanism. Thirdly, the denoising mechanism is suitable for reducing the noise effects in medical code prediction. Finally, we evaluate the effectiveness of our model on the widely-used MIMIC-III datasets and achieve new SOTA results.

Functional and structural phenotyping of cardiomyocytes in the 3D organization of embryoid bodies exposed to arsenic trioxide

Chronic exposure to environmental pollutants threatens human health. Arsenic, a world-wide diffused toxicant, is associated to cardiac pathology in the adult and to congenital heart defects in the foetus. Poorly known are its effects on perinatal cardiomyocytes. Here, bioinformatic image-analysis tools were coupled with cellular and molecular analyses to obtain functional and structural quantitative metrics of the impairment induced by 0.1, 0.5 or 1.0 µM arsenic trioxide exposure on the perinatal-like cardiomyocyte component of mouse embryoid bodies, within their 3D complex cell organization. With this approach, we quantified alterations to the (a) beating activity; (b) sarcomere organization (texture, edge, repetitiveness, height and width of the Z bands); (c) cardiomyocyte size and shape; (d) volume occupied by cardiomyocytes within the EBs. Sarcomere organization and cell morphology impairment are paralleled by differential expression of sarcomeric α-actin and Tropomyosin proteins and of acta2, myh6 and myh7 genes. Also, significant increase of Cx40, Cx43 and Cx45 connexin genes and of Cx43 protein expression profiles is paralleled by large Cx43 immunofluorescence signals. These results provide new insights into the role of arsenic in impairing cytoskeletal components of perinatal-like cardiomyocytes which, in turn, affect cell size, shape and beating capacity.