Deep learning MRI signature to predict survival and treatment benefit from temozolomide in IDH-wildtype glioblastoma

BackgroundO⁶-methylguanine-DNA-methyltransferase (MGMT) methylation status does not correlate with temozolomide (TMZ) sensitivity in all IDH-wildtype glioblastoma (GBM) patients. New predictors of TMZ benefit are still in demand.MethodsBased on MR images, a deep learning image signature was constructed to predict the survival and benefit of temozolomide in patients with IDH wild-type glioblastoma.ResultsDiS signature was associated with OS as an independent prognostic factor in patients with IDH-wildtype glioblastoma. For high-risk group patients, TMZ was associated with improved OS for patients in MGMT-methylated subgroup (HR: 2.051, 95 % CI: 0.939–4.482, log-rank P = 0.034), but had not effect on MGMT-unmethylated patients. However, patients in the low- risk group did not benefit from TMZ.ConclusionDiS could offer complementary value beyond MGMT methylation status in predicting survival benefit from TMZ chemotherapy in patients with IDH-wildtype glioblastoma.     

面向图像内补与外推问题的迭代预测统一框架

目的 图像内补与外推可看做根据已知区域绘制未知区域的问题,是计算机视觉领域研究热点。近年来,深度神经网络成为解决内补与外推问题的主流方法。然而,当前解决方法多分别对待内补与外推问题,导致二者难以统一处理;且模型多采用卷积神经网络(convolutional neural network,CNN)构建,受到视野局部性限制,较难绘制远距离内容。针对这两个问题,本文按照分而治之思想联合CNN与Transformer构建深度神经网络,提出图像内补与外推统一处理框架及模型。方法 将内补与外推问题的解决过程分解为“表征、预测、合成”3个部分,表征与合成采用CNN完成,充分利用其局部相关性进行图像到特征映射和特征到图像重建;核心预测由Transformer实现,充分发挥其强大的全局上下文关系建模能力,并提出掩膜自增策略迭代预测特征,降低Transformer同时预测大范围未知区域特征的难度;最后引入对抗学习提升绘制图像逼真度。结果 实验给出在多种数据集下内补与外推对比评测,结果显示本文方法各项性能指标均超越对比方法。通过消融实验发现,模型相比采用非分解方式具有更佳表现,说明分而治之思路功效显著。此外,对掩膜自增策略进行详细的实验分析,表明迭代预测方法可有效提升绘制能力。最后,探究了Transformer关键结构参数对模型性能的影响。结论 本文提出一种迭代预测统一框架解决图像内补与外推问题,相较对比方法性能更佳,并且各部分设计对性能提升均有贡献,显示了迭代预测统一框架及方法在图像内补与外推问题上的应用价值与潜力。     

PPNNP: A privacy-preserving neural network prediction with separated data providers using multi-client inner-product encryption

In a neural network of deep learning, it needs a series of algorithms that endeavor to recognize underlying relationships in a set of data. In order to protect the privacy of user’s datasets, traditional schemes can perform the prediction task by setting only a single data provider in the system. However, the data may come from multiple separated data providers rather than single data source in real world since each data provider might hold partial features of a complete prediction sample. It requires that multiple data providers cooperate to perform the prediction for the neural networks by sending their own local data to a well-trained prediction model deployed on a remote cloud server to obtain a predictive label. However, the data owned by multiple data providers usually contain a large amount of private information, which can lead to serious security problems once leaked. To resolve the security and privacy issues of the data owned by multiple data providers, in this paper, we propose a Privacy-Preserving Neural Network Prediction model (PPNNP) that deploys multi-client inner-product functional encryption to the first layer of prediction model. Multiple data providers encrypt their data and upload it to a well-trained model deployed on cloud server, and the server makes predictions by calculating inner-products related to them. It can provide sufficient privacy and security for the data while deploying different neural network architectures with activation functions that are even non-linear on the remote server. We evaluate our scheme based on the real datasets and provide a comparison with the related schemes. Experimental results demonstrate that our scheme can reduce the computational cost of the whole process while significantly reducing the encryption time. It can obtain an accuracy of over 90% in different network architectures with even non-linear activation functions. Meanwhile, our solution can reduce communication overhead in the whole protocol.     

Traveling time prediction in scheduled transportation with journey segments

Urban mobility impacts urban life to a great extent. To enhance urban mobility, much research was invested in traveling time prediction: given an origin and destination, provide a passenger with an accurate estimation of how long a journey lasts. In this work, we investigate a novel combination of methods from Queueing Theory and Machine Learning in the prediction process. We propose a prediction engine that, given a scheduled bus journey (route) and a ‘source/destination’ pair, provides an estimate for the traveling time, while considering both historical data and real-time streams of information that are transmitted by buses. We propose a model that uses natural segmentation of the data according to bus stops and a set of predictors, some use learning while others are learning-free, to compute traveling time. Our empirical evaluation, using bus data that comes from the bus network in the city of Dublin, demonstrates that the snapshot principle, taken from Queueing Theory, works well yet suffers from outliers. To overcome the outliers problem, we use Machine Learning techniques as a regulator that assists in identifying outliers and propose prediction based on historical data.     

Survival suit volume reduction associated with immersion: implications for buoyancy estimation in offshore workers of different size

Abstract

Rationale: It is currently unknown how body size affects buoyancy in submerged helicopter escape. Method: Eight healthy males aged 39.6 ± 12.6 year (mean ± SD) with BMI 22.0–40.0 kg m^?2 wearing a standard survival (‘dry’) suit undertook a normal venting manoeuvre and underwent 3D scanning to assess body volume (wearing the suit) before and after immersion in a swimming pool. Results: Immersion-induced volume loss averaged 14.4 ± 5.4 l, decreased with increasing dry density (mass volume^?1) and theoretical buoyant force in 588 UK offshore workers was found to be 264 ± 46 and 232 ± 60 N using linear and power functions, respectively. Both approaches revealed heavier workers to have greater buoyant force. Discussion: While a larger sample may yield a more accurate buoyancy prediction, this study shows heavier workers are likely to have greater buoyancy. Without free-swimming capability to overcome such buoyancy, some individuals may possibly exceed the safe limit to enable escape from a submerged helicopter.

Practitioner Summary: Air expulsion reduced total body volume of survival-suited volunteers following immersion by an amount inversely proportional to body size. When applied to 588 offshore workers, the predicted air loss suggested buoyant force to be greatest in the heaviest individuals, which may impede their ability to exit a submerged helicopter.     

Overcoming latency with motion prediction in directional autostereoscopic displays

Imaging delivering to correct retina assisted with tracking technique is a common practice for autostereoscopic displays with stereo two‐view data format. Due to various latencies produced in camera buffering, computer processing, data transmission, and illumination refreshing, delayed image delivery will give rise to a substantial degradation of the 3D display experience. This is particularly obvious for directional backlight 3D displays where significant flickering is resulted as a result of the inherent latency. This work systematically analyzes the source of latency by quantitatively measuring the exact latency value in a typical directional backlight autostereoscopic display. Based on accurate measurement, a motion prediction solution is proposed to improve the synchronization between the backlight illumination and viewer's eye location. Motion prediction helps overcome the lag between the center of illumination and viewer's eye, providing a flicker‐free viewing experience for both a stationary and a moving viewer.     

Delphi: geometry-based connectivity prediction in triangle mesh compression

Delphi is a new geometry-guided predictive scheme for compressing the connectivity of triangle meshes. Both compression and decompression algorithms traverse the mesh using the EdgeBreaker state machine. However, instead of encoding the EdgeBreaker clers symbols that capture connectivity explicitly, they estimate the location of the unknown vertex, v , of the next triangle. If the predicted location lies sufficiently close to the nearest vertex, w , on the boundary of the previously traversed portion of the mesh, then Delphi estimates that v coincides with w . When the guess is correct, a single confirmation bit is encoded. Otherwise, additional bits are used to encode the rectification of that prediction. When v coincides with a previously visited vertex that is not adjacent to the parent triangle (EdgeBreaker S case), the offset, which identifies the vertex v , must be encoded, mimicking the cut-border machine compression proposed by Gumhold and Strasser. On models where 97% of Delphi predictions are correct, the connectivity is compressed down to 0.19 bits per triangle. Compression rates decrease with the frequency of wrong predictors, but remains below 1.50 bits per triangle for all models tested.     

Interest rate prediction: a neuro-hybrid approach with data preprocessing

The following research implements a differential evolution-based fuzzy-type clustering method with a fuzzy inference neural network after input preprocessing with regression analysis in order to predict future interest rates, particularly 3-month T-bill rates. The empirical results of the proposed model is compared against nonparametric models, such as locally weighted regression and least squares support vector machines, along with two linear benchmark models, the autoregressive model and the random walk model. The root mean square error is reported for comparison.     

Adoption of machine learning technology for failure prediction in industrial maintenance: A systematic review

Failure prediction is the task of forecasting whether a material system of interest will fail at a specific point of time in the future. This task attains significance for strategies of industrial maintenance, such as predictive maintenance. For solving the prediction task, machine learning (ML) technology is increasingly being used, and the literature provides evidence for the effectiveness of ML-based prediction models. However, the state of recent research and the lessons learned are not well documented. Therefore, the objective of this review is to assess the adoption of ML technology for failure prediction in industrial maintenance and synthesize the reported results. We conducted a systematic search for experimental studies in peer-reviewed outlets published from 2012 to 2020. We screened a total of 1,024 articles, of which 34 met the inclusion criteria. We focused on understanding the datasets analyzed, the preprocessing to generate features, and the training and evaluation of prediction models. The results reveal (1) a broad range of systems and domains addressed, (2) the adoption of up-to-date approaches to preprocessing and training, (3) some lack of performance evaluation mitigating the overfitting problem, and (4) considerable heterogeneity in the reporting of experimental designs and results. We identify opportunities for future research and suggest ways to facilitate the comparison and integration of evidence obtained from single studies.     

A genetic algorithm approach for SMEs bankruptcy prediction: Empirical evidence from Italy

Bankruptcy prediction is a topic, which affect the economic well being of all countries. Having an accurate company default prediction model, which can pick up on time the signs of financial distress, is vital for all firms, especially for small and medium-sized enterprises (SMEs). These firms represent the backbone of the economy of every country. Therefore, they need a prediction model easily adaptable to their characteristics. For this purpose, this study explores and compares the potential of genetic algorithms (GAs) with those of logistic regression (LR) and support vector machine (SVM). GAs are applied to a large sample of 3.100 Italian manufacturing SMEs, three, two and one year prior to bankruptcy. The results indicate that GAs are a very effective and promising instrument in assessing the likelihood of SMEs bankruptcy compared with LR and SVM, especially in reducing Type II misclassification rate. Of particular interest, results show that GAs prediction accuracy rate increases when the model is applied according to size and geographical area, with a marked improvement in the smallest sized firms and in the firms operating in north Italy.     

3GPP LTE系统中结合位置预测的切换算法

针对3GPP LTE系统中因频繁切换而导致的系统吞吐量降低的问题,提出了基于用户运动机制及其方向改变概率的预测模型,并将其与标准的长期演进(LTE)切换算法相结合。模型使用方向改变概率计算各个可能位置的接收信号强度的权重,再求和得到预测的接收信号强度。经过仿真对比,使用结合位置预测的切换算法后,切换次数没有明显变化,但系统吞吐量有所提高。相比于传统的数据挖掘预测模型,提出的预测模型效果更好。     

A Kolmogorov-Smirnov statistic based segmentation approach to learning from imbalanced datasets: With application in property refinance prediction

Classification is an important task in data mining. Class imbalance has been reported to hinder the performance of standard classification models. However, our study shows that class imbalance may not be the only cause to blame for poor performance. Rather, the underlying complexity of the problem may play a more fundamental role. In this paper, a decision tree method based on Kolmogorov-Smirnov statistic (K-S tree), is proposed to segment the training data so that a complex problem can be divided into several easier sub-problems where class imbalance becomes less challenging. K-S tree is also used to perform feature selection, which not only selects relevant variables but also removes redundant ones. After segmentation, a two-way re-sampling method is used at the segment level to empirically determine the optimal sampling percentage and the rebalanced data is used to fit logistic regression models, also at the segment level. The effectiveness of the proposed method is demonstrated through its application on property refinance prediction.     

PITAGORAS-PSP: Including domain knowledge in a multi-objective approach for protein structure prediction

Whenever evolutionary algorithms are used to solve certain classes of problems such as those that present a huge search space, the incorporation of problem-specific knowledge is required to achieve adequate levels of performance. In this paper, we propose a multi-objective optimization-based procedure that includes such a domain-specific knowledge to cope with a difficult problem, the protein structure prediction (PSP). This problem is considered to be an open problem as there is no recognized “best” procedure to find solutions. It presents a vast search space and the analysis of each protein conformation requires significant amount of computing time. In our procedure, we provide a reduction of the search space by using the dependent rotamer library and include new heuristics to improve a multi-objective approach to PSP based on the PAES algorithm. As it is shown in the paper, by using benchmark proteins from the CASP8 set, this hybrid PSP procedure provides competitive results when it is compared with some of the better proposals appeared up to now.     

Learning machines: Rationale and application in ground-level ozone prediction

Multilayer perceptron (MLP) and support vector machine (SVM), two popular learning machines, are increasingly being used as alternatives to classical statistical models for ground-level ozone prediction. However, employing learning machines without sufficient awareness about their limitations can lead to unsatisfactory results in modeling the ozone evolving mechanism, especially during ozone formation episodes. With the spirit of literature review and justification, this paper discusses, with respect to the concerning of ozone prediction, the recently developed algorithms/technologies for treating the most prominent model-performance-degradation limitations. MLP has the “black-box” property, i.e., it hardly provides physical explanation for the trained model, overfitting and local minima problems, and SVM has parameters identification and class imbalance problems. This commentary article aims to stress that the underlying philosophy of using learning machines is by no means as trivial as simply fitting models to the data because it causes difficulties, controversies or unresolved problems. This article also aims to serve as a reference point for further technical readings for experts in relevant fields.     

改进的CART算法在煤层底板突水预测中的应用

针对基于传统CART算法建立的煤层底板突水预测模型存在运行时间较长、准确率不高等缺点,介绍了一种改进的CART算法决策树模型,并将其用于煤层底板突水预测模型的建立。实验结果表明,采用改进的CART算法建立的煤层底板突水预测模型运行时间由1.041 1s减少到了0.612 5s,突水预测正确率由88.78%提高到了95.54%。     

IBGSS: An Improved Binary Gravitational Search Algorithm based search strategy for QoS and ranking prediction in cloud environments

Quality of Service (QoS) value prediction and QoS ranking prediction have their significance in optimal service selection and service composition problems. QoS based service ranking prediction is an NP-Complete problem which examines the order of ranked service sequence with respect to the unique QoS requirements. To address the NP-Complete problem, greedy and optimization-based strategies such as CloudRank and PSO have been widely employed in service oriented environments. However, they pose several challenges with respect to the similarity measure based QoS prediction, trap at local optima, and near optimal solution. Hence, this paper presents Improved Binary Gravitational Search Strategy (IBGSS), an optimization based search strategy to address the challenges in the state-of-the-art QoS value prediction and service ranking prediction techniques. IBGSS employs improved cosine similarity measure, and Newton–Raphson inspired Binary Gravitational Search Algorithm (NR-BGSA) for accurate QoS value prediction and optimal service ranking prediction respectively. The effectiveness of IBGSS over the state-of-the-art QoS value prediction and ranking prediction techniques was validated using two real world QoS datasets, namely WSDream#1 and web service QoS dataset in terms of various statistical measures (Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Average Precision Correlation (APC)).     

Adaptive transfer learning in deep neural networks: Wind power prediction using knowledge transfer from region to region and between different task domains

Transfer learning (TL) in deep neural networks is gaining importance because, in most of the applications, the labeling of data is costly and time consuming. Additionally, TL also provides an effective weight initialization strategy for deep neural networks. This paper introduces the idea of adaptive TL in deep neural networks (ATL‐DNN) for wind power prediction. Specifically, we show in case of wind power prediction that adaptive TL of the deep neural networks system can be adaptively modified as regards training on a different wind farm is concerned. The proposed ATL‐DNN technique is tested for short‐term wind power prediction, where continuously arriving information has to be exploited. Adaptive TL not only helps in providing good weight initialization, but also in utilizing the incoming data for effective learning. Additionally, the proposed ATL‐DNN technique is shown to transfer knowledge between different task domains (wind power to wind speed prediction) and from one region to another region. The simulation results show that the proposed ATL‐DNN technique achieves average values of 0.0637, 0.0986, and 0.0984 for the mean absolute error, root mean squared error, and standard deviation error, respectively.     

Co-evolutionary multi-population genetic programming for classification in software defect prediction: An empirical case study

Evolving diverse ensembles using genetic programming has recently been proposed for classification problems with unbalanced data. Population diversity is crucial for evolving effective algorithms. Multilevel selection strategies that involve additional colonization and migration operations have shown better performance in some applications. Therefore, in this paper, we are interested in analysing the performance of evolving diverse ensembles using genetic programming for software defect prediction with unbalanced data by using different selection strategies. We use colonization and migration operators along with three ensemble selection strategies for the multi-objective evolutionary algorithm. We compare the performance of the operators for software defect prediction datasets with varying levels of data imbalance. Moreover, to generalize the results, gain a broader view and understand the underlying effects, we replicated the same experiments on UCI datasets, which are often used in the evolutionary computing community. The use of multilevel selection strategies provides reliable results with relatively fast convergence speeds and outperforms the other evolutionary algorithms that are often used in this research area and investigated in this paper. This paper also presented a promising ensemble strategy based on a simple convex hull approach and at the same time it raised the question whether ensemble strategy based on the whole population should also be investigated.     

Evolutions in machine learning technology for financial distress prediction: A comprehensive review and comparative analysis

In recent years, financial distress prediction (FDP), also known as corporate failure prediction or bankruptcy prediction, has gained significant importance due to its impact on organizations, especially during unexpected events like pandemics and wars. Machine learning (ML) models have emerged as innovative and essential tools in predicting financial distress, leveraging the ever-increasing volume of databases and computing power. This study utilizes bibliographic techniques to contribute to the field's literature review to address the disorganized nature of the existing literature on FDP, reduce confusion, and provide clarity to domain researchers. These techniques enable identifying the progress of articles published over the years, influential authors, and highly cited articles. Additionally, the study examines crucial aspects of data preprocessing, such as missing data, imbalanced data, feature selection, and outliers, as they significantly impact the robustness and performance of ML models. Furthermore, it discusses essential models employed in FDP, focusing on recent advancements that represent promising trends. In conclusion, this study contributes to the field by uncovering novel trends and proposing possible directions for advancing FDP research. These findings will guide researchers, practitioners, and stakeholders in their quest for improved prediction and decision-making in financial distress.