Early Detection of Alzheimer’s Disease Based on Laplacian Re-Decomposition and XGBoosting

The precise diagnosis of Alzheimer’s disease is critical for patient treatment,especially at the early stage,because awareness of the severity and progression risks lets patients take preventative actions before irreversible brain damage occurs.It is possible to gain a holistic view of Alzheimer’s disease staging by combining multiple data modalities,known as image fusion.In this paper,the study proposes the early detection of Alzheimer’s disease using different modalities of Alzheimer’s disease brain images.First,the preprocessing was performed on the data.Then,the data augmentation techniques are used to handle overfitting.Also,the skull is removed to lead to good classification.In the second phase,two fusion stages are used:pixel level(early fusion)and feature level(late fusion).We fused magnetic resonance imaging and positron emission tomography images using early fusion(Laplacian Re-Decomposition)and late fusion(Canonical Correlation Analysis).The proposed system used magnetic resonance imaging and positron emission tomography to take advantage of each.Magnetic resonance imaging system’s primary benefits are providing images with excellent spatial resolution and structural information for specific organs.Positron emission tomography images can provide functional information and the metabolisms of particular tissues.This characteristic helps clinicians detect diseases and tumor progression at an early stage.Third,the feature extraction of fused images is extracted using a convolutional neural network.In the case of late fusion,the features are extracted first and then fused.Finally,the proposed system performs XGB to classify Alzheimer’s disease.The system’s performance was evaluated using accuracy,specificity,and sensitivity.All medical data were retrieved in the 2D format of 256×256 pixels.The classifiers were optimized to achieve the final results:for the decision tree,the maximum depth of a tree was 2.The best number of trees for the random forest was 60;for the support vector machine,the maximum depth was 4,and the kernel gamma was 0.01.The system achieved an accuracy of 98.06%,specificity of 94.32%,and sensitivity of 97.02%in the case of early fusion.Also,if the system achieved late fusion,accuracy was 99.22%,specificity was 96.54%,and sensitivity was 99.54%.

Efficient Computer Aided Diagnosis System for Hepatic Tumors Using Computed Tomography Scans

One of the leading causes of mortality worldwide is liver cancer.The earlier the detection of hepatic tumors,the lower the mortality rate.This paper introduces a computer-aided diagnosis system to extract hepatic tumors from computed tomography scans and classify them into malignant or benign tumors.Segmenting hepatic tumors from computed tomography scans is considered a challenging task due to the fuzziness in the liver pixel range,intensity values overlap between the liver and neighboring organs,high noise from computed tomography scanner,and large variance in tumors shapes.The proposed method consists of three main stages;liver segmentation using Fast Generalized Fuzzy C-Means,tumor segmentation using dynamic thresholding,and the tumor’s classification into malignant/benign using support vector machines classifier.The performance of the proposed system was evaluated using three liver benchmark datasets,which are MICCAI-Sliver07,LiTS17,and 3Dircadb.The proposed computer adided diagnosis system achieved an average accuracy of 96.75%,sensetivity of 96.38%,specificity of 95.20%and Dice similarity coefficient of 95.13%.

Alzheimer’s Disease Diagnosis Based on a Semantic Rule-Based Modeling and Reasoning Approach

Alzheimer’s disease(AD)is a very complex disease that causes brain failure,then eventually,dementia ensues.It is a global health problem.99%of clinical trials have failed to limit the progression of this disease.The risks and barriers to detecting AD are huge as pathological events begin decades before appearing clinical symptoms.Therapies for AD are likely to be more helpful if the diagnosis is determined early before the final stage of neurological dysfunction.In this regard,the need becomes more urgent for biomarker-based detection.A key issue in understanding AD is the need to solve complex and high-dimensional datasets and heterogeneous biomarkers,such as genetics,magnetic resonance imaging(MRI),cerebrospinal fluid(CSF),and cognitive scores.Establishing an interpretable reasoning system and performing interoperability that achieves in terms of a semantic model is potentially very useful.Thus,our aim in this work is to propose an interpretable approach to detect AD based on Alzheimer’s disease diagnosis ontology(ADDO)and the expression of semantic web rule language(SWRL).This work implements an ontology-based application that exploits three different machine learning models.These models are random forest(RF),JRip,and J48,which have been used along with the voting ensemble.ADNI dataset was used for this study.The proposed classifier’s result with the voting ensemble achieves a higher accuracy of 94.1%and precision of 94.3%.Our approach provides effective inference rules.Besides,it contributes to a real,accurate,and interpretable classifier model based on various AD biomarkers for inferring whether the subject is a normal cognitive(NC),significant memory concern(SMC),early mild cognitive impairment(EMCI),late mild cognitive impairment(LMCI),or AD.

Enhancing Task Assignment in Crowdsensing Systems Based on Sensing Intervals and Location

The popularity of mobile devices with sensors is captivating the attention of researchers to modern techniques,such as the internet of things(IoT)and mobile crowdsensing(MCS).The core concept behind MCS is to use the power of mobile sensors to accomplish a difficult task collaboratively,with each mobile user completing much simpler micro-tasks.This paper discusses the task assignment problem in mobile crowdsensing,which is dependent on sensing time and path planning with the constraints of participant travel distance budgets and sensing time intervals.The goal is to minimize aggregate sensing time for mobile users,which reduces energy consumption to encourage more participants to engage in sensing activities and maximize total task quality.This paper introduces a two-phase task assignment framework called location time-based algorithm(LTBA).LTBA is a framework that enhances task assignment in MCS,whereas assigning tasks requires overlapping time intervals between tasks and mobile users’tasks and the location of tasks and mobile users’paths.The process of assigning the nearest task to the mobile user’s current path depends on the ant colony optimization algorithm(ACO)and Euclidean distance.LTBA combines two algorithms:(1)greedy online allocation algorithm and(2)bio-inspired traveldistance-balance-based algorithm(B-DBA).The greedy algorithm was sensing time interval-based and worked on reducing the overall sensing time of the mobile user.B-DBA was location-based and worked on maximizing total task quality.The results demonstrate that the average task quality is 0.8158,0.7093,and 0.7733 for LTBA,B-DBA,and greedy,respectively.The sensing time was reduced to 644,1782,and 685 time units for LTBA,B-DBA,and greedy,respectively.Combining the algorithms improves task assignment in MCS for both total task quality and sensing time.The results demonstrate that combining the two algorithms in LTBA is the best performance for total task quality and total sensing time,and the greedy algorithm follows it then B-DBA.

Identification and Classification of Crowd Activities

The identification and classification of collective people’s activities are gaining momentum as significant themes in machine learning,with many potential applications emerging.The need for representation of collective human behavior is especially crucial in applications such as assessing security conditions and preventing crowd congestion.This paper investigates the capability of deep neural network(DNN)algorithms to achieve our carefully engineered pipeline for crowd analysis.It includes three principal stages that cover crowd analysis challenges.First,individual’s detection is represented using the You Only Look Once(YOLO)model for human detection and Kalman filter for multiple human tracking;Second,the density map and crowd counting of a certain location are generated using bounding boxes from a human detector;and Finally,in order to classify normal or abnormal crowds,individual activities are identified with pose estimation.The proposed system successfully achieves designing an effective collective representation of the crowd given the individuals in addition to introducing a significant change of crowd in terms of activities change.Experimental results onMOT20 and SDHA datasets demonstrate that the proposed system is robust and efficient.The framework achieves an improved performance of recognition and detection peoplewith a mean average precision of 99.0%,a real-time speed of 0.6ms non-maximumsuppression(NMS)per image for the SDHAdataset,and 95.3%mean average precision for MOT20 with 1.5ms NMS per image.

Overlapping Shadow Rendering for Outdoor Augmented Reality

Realism rendering methods of outdoor augmented reality(AR)is an interesting topic.Realism items in outdoor AR need advanced impacts like shadows,sunshine,and relations between unreal items.A few realistic rendering approaches were built to overcome this issue.Several of these approaches are not dealt with real-time rendering.However,the issue remains an active research topic,especially in outdoor rendering.This paper introduces a new approach to accomplish reality real-time outdoor rendering by considering the relation between items in AR regarding shadows in any place during daylight.The proposed method includes three principal stages that cover various outdoor AR rendering challenges.First,real shadow recognition was generated considering the sun’s location and the intensity of the shadow.The second step involves real shadow protection.Finally,we introduced a shadow production algorithm technique and shades through its impacts on unreal items in the AR.The selected approach’s target is providing a fast shadow recognition technique without affecting the system’s accuracy.It achieved an average accuracy of 95.1%and an area under the curve(AUC)of 92.5%.The outputs demonstrated that the proposed approach had enhanced the reality of outside AR rendering.The results of the proposed method outperformed other state-of-the-art rendering shadow techniques’outcomes.

Timing and Classication of Patellofemoral Osteoarthritis Patients Using Fast Large Margin Classifier

:Surface electromyogram(sEMG)processing and classication can assist neurophysiological standardization and evaluation and provide habitational detection.The timing of muscle activation is critical in determining various medical conditions when looking at sEMG signals.Understanding muscle activation timing allows identication of muscle locations and feature validation for precise modeling.This work aims to develop a predictive model to investigate and interpret Patellofemoral(PF)osteoarthritis based on features extracted from the sEMG signal using pattern classication.To this end,sEMG signals were acquired from ve core muscles over about 200 reads from healthy adult patients while they were going upstairs.Onset,offset,and time duration for the Transversus Abdominus(TrA),Vastus Medialis Obliquus(VMO),Gluteus Medius(GM),Vastus Lateralis(VL),and Multidus Muscles(ML)were acquired to construct a classication model.The proposed classication model investigates function mapping from real-time space to a PF osteoarthritis discriminative feature space.The activation feature space of muscle timing is used to train several large margin classiers to modulate muscle activations and account for such activation measurements.The fast large margin classier achieved higher performance and faster convergence than support vector machines(SVMs)and other state-of-the-art classiers.The proposed sEMG classication framework achieved an average accuracy of 98.8%after 7 s training time,improving other classication techniques in previous literature.

Diagnosis of Various Skin Cancer Lesions Based on Fine-Tuned ResNet50 Deep Network

With the massive success of deep networks,there have been signi-cant efforts to analyze cancer diseases,especially skin cancer.For this purpose,this work investigates the capability of deep networks in diagnosing a variety of dermoscopic lesion images.This paper aims to develop and ne-tune a deep learning architecture to diagnose different skin cancer grades based on dermatoscopic images.Fine-tuning is a powerful method to obtain enhanced classication results by the customized pre-trained network.Regularization,batch normalization,and hyperparameter optimization are performed for ne-tuning the proposed deep network.The proposed ne-tuned ResNet50 model successfully classied 7-respective classes of dermoscopic lesions using the publicly available HAM10000 dataset.The developed deep model was compared against two powerful models,i.e.,InceptionV3 and VGG16,using the Dice similarity coefcient(DSC)and the area under the curve(AUC).The evaluation results show that the proposed model achieved higher results than some recent and robust models.