Dynamic Multi-Layer Perceptron for Fetal Health Classification Using Cardiotocography Data

Fetal health care is vital in ensuring the health of pregnant women and the fetus.Regular check-ups need to be taken by the mother to determine the status of the fetus’growth and identify any potential problems.To know the status of the fetus,doctors monitor blood reports,Ultrasounds,cardiotocography(CTG)data,etc.Still,in this research,we have considered CTG data,which provides information on heart rate and uterine contractions during pregnancy.Several researchers have proposed various methods for classifying the status of fetus growth.Manual processing of CTG data is time-consuming and unreliable.So,automated tools should be used to classify fetal health.This study proposes a novel neural network-based architecture,the Dynamic Multi-Layer Perceptron model,evaluated from a single layer to several layers to classify fetal health.Various strategies were applied,including pre-processing data using techniques like Balancing,Scaling,Normalization hyperparameter tuning,batch normalization,early stopping,etc.,to enhance the model’s performance.A comparative analysis of the proposed method is done against the traditional machine learning models to showcase its accuracy(97%).An ablation study without any pre-processing techniques is also illustrated.This study easily provides valuable interpretations for healthcare professionals in the decision-making process.

Digital modulation classification using multi-layer perceptron and time-frequency features

Considering that real communication signals corrupted by noise are generally nonstationary, and timefrequency distributions are especially suitable for the analysis of nonstationary signals, time-frequency distributions are introduced for the modulation classification of communication signals： The extracted time-frequency features have good classification information, and they are insensitive to signal to noise ratio （SNR） variation. According to good classification by the correct rate of a neural network classifier, a multilayer perceptron （MLP） classifier with better generalization, as well as, addition of time-frequency features set for classifying six different modulation types has been proposed. Computer simulations show that the MLP classifier outperforms the decision-theoretic classifier at low SNRs, and the classification experiments for real MPSK signals verify engineering significance of the MLP classifier.

Impact of Portable Executable Header Features on Malware Detection Accuracy

One aspect of cybersecurity,incorporates the study of Portable Executables(PE)files maleficence.Artificial Intelligence(AI)can be employed in such studies,since AI has the ability to discriminate benign from malicious files.In this study,an exclusive set of 29 features was collected from trusted implementations,this set was used as a baseline to analyze the presented work in this research.A Decision Tree(DT)and Neural Network Multi-Layer Perceptron(NN-MLPC)algorithms were utilized during this work.Both algorithms were chosen after testing a few diverse procedures.This work implements a method of subgrouping features to answer questions such as,which feature has a positive impact on accuracy when added?Is it possible to determine a reliable feature set to distinguish a malicious PE file from a benign one?when combining features,would it have any effect on malware detection accuracy in a PE file?Results obtained using the proposed method were improved and carried few observations.Generally,the obtained results had practical and numerical parts,for the practical part,the number of features and which features included are the main factors impacting the calculated accuracy,also,the combination of features is as crucial in these calculations.Numerical results included,finding accuracies with enhanced values,for example,NN_MLPC attained 0.979 and 0.98;for DT an accuracy of 0.9825 and 0.986 was attained.

Multi-Layer Feature Extraction with Deformable Convolution for Fabric Defect Detection

In the textile industry,the presence of defects on the surface of fabric is an essential factor in determining fabric quality.Therefore,identifying fabric defects forms a crucial part of the fabric production process.Traditional fabric defect detection algorithms can only detect specific materials and specific fabric defect types;in addition,their detection efficiency is low,and their detection results are relatively poor.Deep learning-based methods have many advantages in the field of fabric defect detection,however,such methods are less effective in identifying multiscale fabric defects and defects with complex shapes.Therefore,we propose an effective algorithm,namely multilayer feature extraction combined with deformable convolution(MFDC),for fabric defect detection.In MFDC,multi-layer feature extraction is used to fuse the underlying location features with high-level classification features through a horizontally connected top-down architecture to improve the detection of multi-scale fabric defects.On this basis,a deformable convolution is added to solve the problem of the algorithm’s weak detection ability of irregularly shaped fabric defects.In this approach,Roi Align and Cascade-RCNN are integrated to enhance the adaptability of the algorithm in materials with complex patterned backgrounds.The experimental results show that the MFDC algorithm can achieve good detection results for both multi-scale fabric defects and defects with complex shapes,at the expense of a small increase in detection time.

SENet生成对抗网络在图像语义描述中的应用

针对图像语义描述过程中存在的语句描述不够准确及情感色彩涉及较少等问题,提出一种基于SENet生成对抗网络的图像语义描述方法。该方法在生成器模型特征提取阶段增加通道注意力机制,使网络能够更加充分和完整地提取图像中显著区域的特征,将提取后的图像特征输入到编码器中。在原始文本语料库中加入情感语料库且通过自然语言处理生成词向量,将词向量与编码后的图像特征相结合输入到解码器中,通过不断对抗训练生成一段符合该图像所示内容的情感描述语句。最后通过仿真实验与现有方法进行对比,该方法的BLEU指标相比SentiCap方法提高了15%左右,其他相关指标均有提升。在自对比实验中,该方法在CIDEr指标上提高3%左右。该网络能够很好地提取图像特征,使描述图像的语句更加准确,情感色彩更加丰富。

Tri-BERT-SENet:融合多特征的恶意网页识别

传统恶意网页识别缺乏全局性、系统性考量,没有将网页作为有机整体,而是独立针对标签结构、URL地址、文本内容等特定层面特征开展研究,导致准确率较低.虽然已有学者提出融合特征思想,但依旧使用机器学习算法予以实现,特征工程工作量巨大,识别效率低下.针对上述问题,提出一种基于多特征融合的Tri-BERT-SENet模型,用于完成恶意网页的识别任务.利用获取得到的HTML特征、网页URL特征以及网页文本特征,结合BERT模型的上下文感知能力,将特征转化为3个BERT模型输出;之后将模型输出作为特征通道,使用SENet进行加权计算,最终输出识别结果.实验结果表明,与传统机器学习模型以及使用BERT对单一特征的识别方法相比,该检测方法在恶意网页识别的准确率上有较大提升.

DM-L Based Feature Extraction and Classifier Ensemble for Object Recognition

Deep Learning is a powerful technique that is widely applied to Image Recognition and Natural Language Processing tasks amongst many other tasks. In this work, we propose an efficient technique to utilize pre-trained Convolutional Neural Network (CNN) architectures to extract powerful features from images for object recognition purposes. We have built on the existing concept of extending the learning from pre-trained CNNs to new databases through activations by proposing to consider multiple deep layers. We have exploited the progressive learning that happens at the various intermediate layers of the CNNs to construct Deep Multi-Layer (DM-L) based Feature Extraction vectors to achieve excellent object recognition performance. Two popular pre-trained CNN architecture models i.e. the VGG_16 and VGG_19 have been used in this work to extract the feature sets from 3 deep fully connected multiple layers namely “fc6”, “fc7” and “fc8” from inside the models for object recognition purposes. Using the Principal Component Analysis (PCA) technique, the Dimensionality of the DM-L feature vectors has been reduced to form powerful feature vectors that have been fed to an external Classifier Ensemble for classification instead of the Softmax based classification layers of the two original pre-trained CNN models. The proposed DM-L technique has been applied to the Benchmark Caltech-101 object recognition database. Conventional wisdom may suggest that feature extractions based on the deepest layer i.e. “fc8” compared to “fc6” will result in the best recognition performance but our results have proved it otherwise for the two considered models. Our experiments have revealed that for the two models under consideration, the “fc6” based feature vectors have achieved the best recognition performance. State-of-the-Art recognition performances of 91.17% and 91.35% have been achieved by utilizing the “fc6” based feature vectors for the VGG_16 and VGG_19 models respectively. The recognition performance has been achieved by considering 30 sample images per class whereas the proposed system is capable of achieving improved performance by considering all sample images per class. Our research shows that for feature extraction based on CNNs, multiple layers should be considered and then the best layer can be selected that maximizes the recognition performance.

融合多层特征SENet和多尺度宽残差的高光谱图像地物分类

提出了一种融合多层特征SENet和多尺度宽残差的高光谱图像地物分类的方法。实验选取Indian Pines和Pavia University为研究对象,结果表明,SE-Inception-Resnet-MSWideResnet(SEIR-MSWR)网络结构的总体分类精度为99.33%、99.52%,Kappa系数为0.98时,分类效果最优,相较于支持向量机(Support Vector Machine,SVM)、K最近邻法(K-NearestNeighbor,KNN),宽残差网络(Wide Resnet Network,WRN)以及InceptionV2-Resnet,总体分类精度分别提高了20.86%、20.09%、5.48%、3.39%、23.1%、16.89%、6.66%、2.58%,Kappa系数分别提高了0.18、0.17、0.06、0.04、0.22、0.17、0.07、0.03,均表现出良好的性能。该方法更好地提取了高光谱图像的本质特征,进而提高了高光谱图像地物的分类精度。

基于HoFiBiAFM的点击率预测模型

在推荐系统中,FiBiNET、AFM等深度学习模型能够关注特征的重要性进行点击率预测。其中FiBiNET的深层模型使用DNN网络相当隐式地对特征交互进行建模,但是使用DNN学习高阶特征可能导致低阶特征交叉被稀释。通过叠加多层SENET注意力机制的方式学习高阶重要性特征,并加入高阶注意力分解机共同更新特征表示,构成一种新的点击率预测模型HoFiBiAFM。通过在Movielens-100K和Movielens-1M数据集上分别与其他CTR预测模型进行分类任务和回归任务的对比实验,结果验证了HoFiBiAFM模型的点击率预测效果。

一种改进CycleGAN的素描头像彩色化算法

针对现阶段由素描头像生成的彩色头像图像清晰度低、人脸识别率不高和视觉质量不佳等问题,提出一种改进CycleGAN的素描头像彩色化算法:对U-Net自编码器的第一个特征提取模块进行优化,设计一种多尺度自注意力机制特征提取模块,从多个尺度提取输入图像以减少输入图像的细节信息丢失,将提取的特征用通道堆叠的方式进行特征融合,对融合的特征嵌入SENet自注意力机制,以引导模型对特征重点区域的关注度,最后再降低融合特征的通道维数;对生成头像与真实头像添加L1像素损失和感知损失,以进一步提升生成头像的质量.实验结果表明:较基础模型CycleGAN生成的彩色头像,在CUHK数据集FID值降低了22.23、Rank-1值提高了16%,在AR数据集FID值降低了15.34、Rank-1值提高了9.3%.

基于SE-SAE特征融合和BiLSTM的锂电池寿命预测

预测锂电池剩余使用寿命(RUL)时,针对电池外部特性参量电流、电压等单一的健康因子(HI)对电池退化特性无法完整覆盖的问题,提出一种结合通道注意力机制(SENet)和栈式自编码(SAE)进行特征融合并引入双向长短期记忆(BiLSTM)实现锂电池RUL的预测方法。充分提取锂电池电压、电流等HI。利用SAE对多个锂电池HI特征进行特征融合,并结合SENet通道注意力机制,增加重要特征在提取过程中的表现能力。利用BiLSTM网络对融合HI进行训练预测。采用NASA和马里兰大学计算机辅助寿命周期工程中心(CALCE)锂电池数据集进行验证,训练预测数据均采用50%的比例划分,预测结果的均方根误差(RMSE)平均值达到0.017。

Automatic Sentimental Analysis by Firefly with Levy and Multilayer Perceptron

The field of sentiment analysis(SA)has grown in tandem with the aid of social networking platforms to exchange opinions and ideas.Many people share their views and ideas around the world through social media like Facebook and Twitter.The goal of opinion mining,commonly referred to as sentiment analysis,is to categorise and forecast a target’s opinion.Depending on if they provide a positive or negative perspective on a given topic,text documents or sentences can be classified.When compared to sentiment analysis,text categorization may appear to be a simple process,but number of challenges have prompted numerous studies in this area.A feature selection-based classification algorithm in conjunction with the firefly with levy and multilayer perceptron(MLP)techniques has been proposed as a way to automate sentiment analysis(SA).In this study,online product reviews can be enhanced by integrating classification and feature election.The firefly(FF)algorithm was used to extract features from online product reviews,and a multi-layer perceptron was used to classify sentiment(MLP).The experiment employs two datasets,and the results are assessed using a variety of criteria.On account of these tests,it is possible to conclude that the FFL-MLP algorithm has the better classification performance for Canon(98%accuracy)and iPod(99%accuracy).

Feature aggregation for nutrient deficiency identification in chili based on machine learning

Macronutrient deficiency inhibits the growth and development of chili plants.One of the non-destructive methods that plays a role in processing plant image data based on specific characteristics is computer vision.This study uses 5166 image data after augmentation process for six plant health conditions.But the analysis of one feature cannot represent plant health condition.Therefore,a careful combination of features is required.This study combines three types of features with HSV and RGB for color,GLCM and LBP for texture,and Hu moments and centroid distance for shapes.Each feature and its combination are trained and tested using the same MLP architecture.The combination of RGB,GLCM,Hu moments,and Distance of centroid features results the best performance.In addition,this study compares the MLP architecture used with previous studies such as SVM,Random Forest Technique,Naive Bayes,and CNN.CNN produced the best performance,followed by SVM and MLP,with accuracy reaching 97.76%,90.55%and 89.70%,respectively.Although MLP has lower accuracy than CNN,the model for identifying plant health conditions has a reasonably good success rate to be applied in a simple agricultural environment.

Intelligent Detection Method of Substation Environmental Targets Based on MD-Yolov7

The complex operating environment in substations, with different safety distances for live equipment, is a typical high-risk working area, and it is crucial to accurately identify the type of live equipment during automated operations. This paper investigates the detection of live equipment under complex backgrounds and noise disturbances, designs a method for expanding lightweight disturbance data by fitting Gaussian stretched positional information with recurrent neural networks and iterative optimization, and proposes an intelligent detection method for MD-Yolov7 substation environmental targets based on fused multilayer feature fusion (MLFF) and detection transformer (DETR). Subsequently, to verify the performance of the proposed method, an experimental test platform was built to carry out performance validation experiments. The results show that the proposed method has significantly improved the performance of the detection accuracy of live devices compared to the pairwise comparison algorithm, with an average mean accuracy (mAP) of 99.2%, which verifies the feasibility and accuracy of the proposed method and has a high application value.

注意力机制和Faster RCNN相结合的绝缘子识别

针对利用Faster RCNN识别绝缘子图像过程中定位不够准确的问题,提出一种注意力机制和Faster RCNN相结合的绝缘子识别方法。在特征提取阶段引入基于注意力机制的挤压与激励网络(Squeeze-and-Excitation Networks,SENet)结构,使模型能够关注与目标相关的特征通道并弱化其他无关的特征通道;根据绝缘子的特点,对区域建议网络(region proposal network,RPN)生成锚点(anchor)的比例和尺度进行调整;在全连接层运用注意力机制对周围建议框的特征向量赋予不同权重并进行融合,更新目标建议框的特征向量。实验结果表明:与传统的Faster RCNN算法相比,改进后的算法能够较好地识别出绝缘子。

双向特征融合与注意力机制结合的目标检测

目标检测使用特征金字塔检测不同尺度的物体时,忽略了高层信息和低层信息之间的关系,导致检测效果差;此外,针对某些尺度的目标,检测中容易出现漏检。本文提出双向特征融合与注意力机制结合的方法进行目标检测。首先,对SSD(single shot multibox detector)模型深层特征层与浅层特征层进行特征融合,然后将得到的特征与深层特征层进行融合。其次,在双向融合中加入了通道注意力机制,增强了语义信息。最后,提出了一种改进的正负样本判定策略,降低目标的漏检率。将本文提出的算法与当前主流算法在VOC数据集上进行了比较,结果表明,本文提出的算法在对目标进行检测时,目标平均准确率有较大提高。

一种用于石油化工厂环境下的仪表自动检测方法

针对石油化工厂中人工抄表导致的低效、高误差和成本高等弊端,以及仪表图像拍摄条件场景复杂等问题,提出了一种基于改进Faster RCNN模型的工业数字表检测方法。首先,在特征提取网络阶段对卷积层低层和高层的网络特征进行融合,提高模型对细粒度细节和小目标的敏感度;其次,结合SENet网络结构,使模型关注不同通道的重要程度,通过分配不同的学习权重来强化对目标的关注度;最后,利用RPN网络进行最后处理,提取出数字表图像的边界框位置信息。结果表明,本文提出的模型检测精度为97.3%,相对于传统目标检测算法来说能更精准地识别出数字表。

嵌套网络模型下的相似图像检索方法

对深度学习领域的稠密卷积网络(dense convolutional network,DenseNet)进行改进,提出了一种嵌套网络模型下的相似图像检索方法。该方法主要通过嵌入压缩和激励网络(squeeze-and-excitation network,SENet),调整原DenseNet网络结构,优化特征提取模块,从而提高图像检索的准确率。在整个深度学习的过程中,给图像特征通道设置合理的权值,抑制图像中的无效特征,能够进一步提高图像的检索速度。实验结果表明,所提算法能够加强图像有效特征的传递,无论从精度和速度方面均可得到较好的图像检索结果。

改进的多尺度火焰检测方法

网络层数的加深会造成对火焰目标深层特征细节信息表征能力减弱,同时提取了低相关度的冗余特征,导致火焰识别精度不高。针对该问题,提出了一种基于改进Faster R-CNN的火焰检测方法,以提高在深层网络下的火焰识别精度。首先利用ResNet50网络提取火焰特征,并添加SENet模块降低火焰目标冗余特征;然后将深层特征和浅层特征进行多尺度特征融合,增强深层特征的细节信息;最后训练网络,实现对火焰目标的识别定位。实验通过构建VOC火焰数据集进行网络训练,使用测试集进行检测,并进行特征图可视化对比,相比于改进前模型,本文模型平均精度提高了7.78%,召回率提高了9.05%,精确率提高了12.54%。本文提出的火焰目标检测模型,通过结合注意力机制模块和多尺度特征融合机制,能够有效进行火焰目标特征提取,火焰目标的检测结果更加准确。

机器人目标抓取区域实时检测方法

针对目前机器人目标抓取区域检测方法无法兼顾检测准确率和实时性的问题,提出一种基于SE-RetinaGrasp神经网络模型的机器人目标抓取区域实时检测方法。该方法首先以一阶目标检测模型RetinaNet为基础提取抓取框位置及抓取角度;针对抓取检测任务采用SENet结构确定重要的特征通道;结合平衡特征金字塔设计思想,充分融合高低层的特征信息,以加强小抓取框的检测性能;在Cornell数据集上进行实验验证,结果表明该方法在取得更高检测准确率的同时,提高了抓取检测的效率,达到实时检测的要求。