Robust Probabilistic Discriminative Model Prediction Tracker via Improved Model Update Strategy

In the visual object tracking, the tracking algorithm based on discriminative model prediction have shown favorable performance in recent years. Probabilistic discriminative model prediction (PrDiMP) is a typical tracker based on discriminative model prediction. The PrDiMP evaluates tracking results through output of the tracker to guide online update of the model. However, the tracker output is not always reliable, especially in the case of fast motion, occlusion or background clutter. Simply using the output of the tracker to guide the model update can easily lead to drift. In this paper, we present a robust model update strategy which can effectively integrate maximum response, multi-peaks and detector cues to guide model update of PrDiMP. Furthermore, we have analyzed the impact of different model update strategies on the performance of PrDiMP. Extensive experiments and comparisons with state-of-the-art trackers on the four benchmarks of VOT2018, VOT2019, NFS and OTB100 have proved the effectiveness and advancement of our algorithm.

MultiMirror: Neural Cross-lingual Word Alignment for Multilingual Word Sense Disambiguation

Word Sense Disambiguation (WSD), i.e., the task of assigning senses to words in context, has seen a surge of interest with the advent of neural models and a considerable increase in performance up to 80% F1 in English. However, when considering other languages, the availability of training data is limited, which hampers scaling WSD to many languages. To address this issue, we put forward MultiMirror, a sense projection approach for multilingual WSD based on a novel neural discriminative model for word alignment: given as input a pair of parallel sentences, our model -- trained with a low number of instances -- is capable of jointly aligning, at the same time, all source and target tokens with each other, surpassing its competitors across several language combinations. We demonstrate that projecting senses from English by leveraging the alignments produced by our model leads a simple mBERT-powered classifier to achieve a new state of the art on established WSD datasets in French, German, Italian, Spanish and Japanese. We release our software and all our datasets at https://github.com/SapienzaNLP/multimirror.

Super Resolution MRI Using Generative Adversarial Networks

This paper proposes a new frame for MRI Image Enhancement from a low-resolution (LR) image obtain from an early used MRI machine to generate a high-resolution (HR) MRI image. For this we use Generative Adversarial Networks, which have proven well in image recovery task. Here we simultaneously train two models which is Generative model that captures the data distribution in the LR MRI images, and a discriminative model that estimates the probability that a sample came from the training data rather than generator. For training generator, we have to maximize the probability of discriminator of making a mistake in comparing the fake image. For discriminator the adversarial loss uses least squares in order to stabilize the training and for generator the function is a combination of a least square adversarial loss and a content term based on mean square error and image gradient to improve the quality of generated images of MRI.

A Discriminative Model to Generate Melodies through Evolving LSTM Recurrent Neural Networks

The paper describes a method that uses evolving LSTM recurrent neural networks to generate melodic music through a discriminative model. The approach enclosed has achieved an accuracy level of over 90%, thus enabling our model to understand & generate music as per the input parameters. The input expected from the user is minimal and can be provided by a layman. The experiments presented here demonstrate how LSTM can successfully learn a form of training music data and compose a novel (and pleasing) melody based on that style of training. LSTM can play melodies with good timing and appropriate structure if the parameters have been set appropriately. The RNN Model presented in this paper leverages the benefits of LSTM networks and demonstrates how this feat can be achieved.

Wheelchair Movement Based on Convolution Neural Network

This paper intends to develop a methodology for helping amputees and crippled people old, by ongoing voice direction and association between patient and personal computer (PC) where these blends offer a promising response for helping the debilitated people. The major objective of this work is accurately detected audio orders via a microphone of an English language (go, stop, right and left) in a noisy environment by the proposed system. Thus, a patient that utilizes the proposed system can be controlling a wheelchair movement. The venture depends on preparing an off-line dataset of audio files are included 10000 orders and background noise. The proposed system has two important steps of preprocessing to get accurate of specific audio orders, accordingly, the accurate direction of wheelchair movement. Firstly, a dataset was preprocessed to reduce ambient noise by using Butterworth (cutoff 500-5000 Hz) and Wiener filter. Secondly, in the input (a microphone) of the proposed discriminative model put a procedure of infinite impulse response filter (Butterworth), passband filter for cutoff input microphone from 150-7000 Hz for back-off the loud and environment noise and local polynomial approximation (Savitzky-Golay) smoothing filter that plays out a polynomial regression on the signal values. Thus, a better for filtering from ambient noise and keeping on a waveform from distortion that makes the discriminative model accurate when voice orders were recognized. The proposed system can work with various situations and speeds for steering; forward, stop, left and right. All datasets are trained by using deep learning with specific parameters of...

Pancreatic hormones response-generated machine learning model to help distinguish sporadic pancreatic cancer from new-onset diabetes cohort.

e16235 Background: Diabetes mellitus (DM), a paraneoplastic phenomenon, can develop earlier than other symptoms in pancreatic cancer (PaC) patients. Enhanced surveillance is encouraged on all elderly patients with new-onset DM. However, it is a challenge to differentiate newly developed PaCDM from type 2 DM (T2DM). Thus, we investigated the differences of pancreatic hormones responses and functions between PaCDM and T2DM patients, and developed discriminative model by machine learning algorithms. Methods: PaC patients with normal blood glucose (PaCNG) or with new-onset DM (PaCDM) were recruited. For each case, age and gender matched newly developed T2DM patients and healthy volunteers were selected as controls. After ≥10 hours fasting, all participants underwent a mixed meal stimulation test (MMTT). Blood samples were collected at 0, 15, 30, 60 and 120 min to measure insulin, C-peptide, glucagon, and pancreatic polypeptide (PP). Indices of insulin sensitivity (HOMA-IS, HOMA-IR) and insulin secretion (HOMA-β, insulinogenic index 30’ and 120’) were calculated. Increases in hormone levels were compared among groups with repeated measure analysis. Four machine learning algorithms (Random Forest, Logistic Regression, Support Vector Machines, Naïve bayes) were used to develop quadri-separated discriminative models of PaCDM based on baseline characteristics, pancreatic hormones and insulin indices listed above. Results: Insulin and C-peptide responses to MMTT were blunted in PaCDM patients compared to T2DM. The AUC of insulin were comparatively lower in PaCDM; between-group differences were observed at the fasting (197.15 ± 16.59 pg/mL to 537.96 ± 118.69 pg/mL; P = 0.040) and 15 min (523.94 ± 81.15 pg/mL to 1182.51 ± 219.35 pg/mL; P = 0.036) time-points. No statistical differences among groups were found for glucagon. The mean peak PP concentration after MMTT in PaCDM group (466.67 ± 79.05 pg/mL) was higher than control group (258.54 ± 31.36 pg/mL, P = 0.034), but not statistically different to T2DM patients (452.34 ± 62.96 pg/mL, P = 0.892). PaCDM patients had lower insulin secretion capacity but better insulin sensitivity compared to T2DM patients. Eight indices (age, HbA1c, CA19-9, peak concentration of glucose, area above basal of PP, HOMA-IR, HOMA-IS, HOMA-β) were recruited for model development. And the discriminative model generated by random forest algorithm obtained best performance (AUC = 1.000, CA = 0.963, F-1 = 0.941, Precision = 0.889, Recall = 1.000, Specificity = 0.947; model verified). Conclusions: PaCDM patients tend to present with lower β-cell function and better insulin resistance compared to T2DM patients. As our model based on machine learning algorithm generates a good result for discrimination, the above findings may help with early screening for sporadic PaC in new-onset DM. Clinical trial information: ChiCTR1800018247.