High Prediction Rate Research Articles

Lorenz Chaotic System-Based Carbon Nanotube Physical Unclonable Functions

Physical unclonable function (PUF) is an advanced hardware security technology. Most conventional encryption approaches rely on the secure keys stored in nonvolatile memory, which are vulnerable to physical attacks. In contrast, PUF exploits the hardware fabrication variations to generate secure keys. As there are significant fabrication induced variations in carbon nanotube (CNT)-based circuits, they are natural candidates for building highly secure PUFs. However, existing PUFs are reported to be vulnerable to machine learning modeling attacks. In this paper, we develop a novel CNT PUF design through leveraging Lorenz chaotic system. Lorenz chaotic system magnifies the differences among responses of similar challenges. This salient feature gives the superior security performance, making the PUF design resistant to machine learning modeling attacks. Our experimental results demonstrate that these attacking methods can achieve very high bit-wise prediction rates for the standard CNT PUF. In contrast, when hacking the proposed Lorenz chaotic system-based CNT PUF, they become much less effective, where only up to 55% bit-wise prediction rates can be achieved.

Ensemble swarm behaviour based feature selection and support vector machine classifier for chronic kidney disease prediction

Kidney Disease and kidney failure is the one of the complicated and challenging health issues regarding human health. Without having any symptoms few diseases are detected in later stages which results in dialysis. Advanced excavating technologies can always give various possibilities to deal with the situation by determining important realations and associations in drilling down health related data. The prediction accuracy of classification algorithms depends upon appropriate Feature Selection (FS) algorithms decrease the number of features from collection of data. FS is the procedure of choosing the most relevant features, removing irrelevant features. To identify the Chronic Kidney Disease (CKD), Hybrid Wrapper and Filter based FS (HWFFS) algorithm is proposed to reduce the dimension of CKD dataset. Filter based FS algorithm is performed based on the three major functions: Information Gain (IG), Correlation Based Feature Selection (CFS) and Consistency Based Subset Evaluation (CS) algorithms respectively. Wrapper based FS algorithm is performed based on the Enhanced Immune Clonal Selection (EICS) algorithm to choose most important features from the CKD dataset. The results from these FS algorithms are combined with new HWFFS algorithm using classification threshold value. Finally Support Vector Machine (SVM) based prediction algorithm be proposed in order to predict CKD and being evaluated on the MATLAB platform. The results demonstrated with the purpose of the SVM classifier by using HWFFS algorithm provides higher prediction rate in the diagnosis of CKD when compared to other classification algorithms.

Predictability and success rate of short implants

In oral rehabilitation with dental implants, severely resorbed alveolar ridges are a challenging problem due to the reduced height of the residual bone. Continuous search for minimally invasive procedures has resulted in the conception of reduced-length dental implants, decreasing the necessary amount of bone for implantation, thereby reducing the need of bone-grafts. Given the growing demand in the field of implant dentistry and the continuous development of surgical techniques, this study aimed to review the current literature on the predictability and success rate of short implants. Relevant articles published in the PubMed database between the years of 2004 and 2014 were selected using the following key-words: short dental implants, extra-short implants, survival rate, implant, mandible, maxilla, prognosis, implant survival, implant length. Based on the literature review, we concluded that short implants showed high predictability and high success rate in the short term, therefore they are one of the current options for the rehabilitation of atrophic alveolar ridges. Further longitudinal studies are necessary to define more reliably parameters for their proper use, ensuring the achievement of high success rates and survival rates with the use of this type of implant.o assess the attitude and practice of dental professionals towards using of advance radiographic technique.

Cyber security methods for aerial vehicle networks: taxonomy, challenges and solution

Aerial vehicle networks (AVNs) compose a large number of heterogeneous aerial nodes, such as unmanned aerial vehicles, aircrafts and helicopters. The main characteristics of these networks are the high mobility of aerial nodes and the dynamic network topology. AVNs represent attractive targets for attackers due to the fact that aerial nodes could be connected to an untrusted network and hence lead the attackers to launch lethal threats, e.g., aircraft crash. Therefore, the security of AVNs is mandatory. In this article, we examine the challenges of cyber detection methods to secure AVNs and review exiting security schemes proposed in the current literature. Furthermore, we propose a security framework to protect an aircraft (SFA) against malicious behaviors that target aircrafts communication systems. Numerical results show that SFA achieves a high accuracy detection and prediction rates as compared to the current intrusion detection for aircrafts communication system.

Differentially categorized structural brain hubs are involved in different microstructural, functional, and cognitive characteristics and contribute to individual identification.

Very little is known regarding whether structural hubs of human brain networks that enable efficient information communication may be classified into different categories. Using three multimodal neuroimaging data sets, we construct individual structural brain networks and further identify hub regions based on eight widely used graph-nodal metrics, followed by comprehensive characteristics and reproducibility analyses. We show the three categories of structural hubs in the brain network, namely, aggregated, distributed, and connector hubs. Spatially, these distinct categories of hubs are primarily located in the default-mode system and additionally in the visual and limbic systems for aggregated hubs, in the frontoparietal system for distributed hubs, and in the sensorimotor and ventral attention systems for connector hubs. These categorized hubs exhibit various distinct characteristics to support their differentiated roles, involving microstructural organization, wiring costs, topological vulnerability, functional modular integration, and cognitive flexibility; moreover, these characteristics are better in the hubs than nonhubs. Finally, all three categories of hubs display high across-session spatial similarities and act as structural fingerprints with high predictive rates (100%, 100%, and 84.2%) for individual identification. Collectively, we highlight three categories of brain hubs with differential microstructural, functional and, cognitive associations, which shed light on topological mechanisms of the human connectome.

Landslide susceptibility assessment in the Nantian area of China: a comparison of frequency ratio model and support vector machine

It is significant to do landslide susceptibility assessment (LSA) accurately and efficiently using an appropriate model for landslide prediction and prevention. This article aims to compare the frequency ratio (FR) model with the support vector machine (SVM), for mapping the landslide susceptibility of Nantian area in southeastern hilly area, China. To begin, 70 recorded landslides are identified through field investigation and the land and recourse department, 50% of the landslide grid cells are used to train the models and the remaining 50% of the landslide grid cells are used to test the models. Ten environmental factors are used in the modeling of LSA, including the elevation, slope, aspect, plan curvature, profile curvature, relief amplitude, lithology factor, distance to river, Normalized Difference Build-up Index (NDBI) and Normalized Difference Vegetation Index (NDVI). Then the landslide susceptibility maps of Nantian area are produced by the FR and SVM models, respectively. Finally, the accuracies and efficiencies of both two models are evaluated and compared. The results show that the landslide susceptibility distribution characteristics of Nantian area are explored well by the two models, and the FR model has higher prediction rate and is considerably more efficient than SVM for LSA.

Complications and Failures of Implants

Although the high predictability and long-term success rate of dental implants is well documented, complications and failures do occur. Some complications may be relatively minor and easy to correct, while others will be major and result in the loss of the implant or prosthesis. The aim of this paper is to discuss complications and failures of dental implants.

The clinical value of C-reactive protein and procalcitonin in early prediction of pancreatic fistula after pancreaticoduodenectomy

Objective To study the relationship of early postoperative CRP and PCT with pancreatic fistula after pancreaticoduodenectomy (PD); to study whether the combination of CRP and PCT can be used as an early predictor of pancreatic fistula; and to determine the optimal cut-off values of CRP and PCT for early diagnosis of pancreatic fistula after PD. Methods Postoperative pancreatic fistula and other complications were recorded in 82 patients after PD carried out at the Anshan Iron and Steel Group General Hospital from January 2013 to May 2017. PCT and CRP were measured on the 1st to the 5th postoperative day (POD). CRP and PCT were compared between the pancreatic fistula group and the non-complication group on pancreatic fistula prediction. The sensitivity, specificity, and combined sensitivity, combined specificity, negative predictive value, positive predictive value and optimal cut-off value were calculated. Results 56 patients developed postoperative complications, including 17 patients with pancreatic fistula, and 39 patients with non-pancreatic fistula. The postoperative CRP and PCT were correlated with postoperative pancreatic fistula and with other complications. The higher the CRP and PCT, the higher the risk of postoperative pancreatic fistula. The ROC curves suggested that CRP and PCT had a high predictive value for pancreatic fistula, especially on POD 2. The optimal cut-off value of CRP was 189.05 mg/L, the sensitivity was 94.1%, the specificity was 81.5%, the positive predictive value was 94.7%, and the negative predictive value was 24.4%. The optimal cut-off value of PCT was 0.89 mg/dl, the sensitivity was 88.2%, the specificity was 84.6%, the positive predictive value was 91.3%, and the negative predictive value was 20.5%. The sensitivity and specificity of combined CRP with PCT on POD 2 in predicting pancreatic fistula after operations were 100% and 69.1%, respectively. Conclusion Combined CRP and PCT had a high early predictive rate in the identification of pancreatic fistula after PD. Key words: Pancreaticoduodenectomy; Postoperative pancreatic fistula; C-reactive protein; Procalcitonin; Predictor

Early wound infection identification using the WIRE tool in community health care settings: An audit report.

Wound infection is proving to be a challenge for health care professionals. The associated complications and cost of wound infection is immense and can lead to death in extreme cases. Current management of wound infection is largely subjective and relies on the knowledge of the health care professional to identify and initiate treatment. In response, we have developed an infection prediction and assessment tool. The Wound Infection Risk-Assessment and Evaluation tool (WIRE) and its management strategy is a tool with the aim to bring objectivity to infection prediction, assessment and management. A local audit carried out indicated a high infection prediction rate. More work is being done to improve its effectiveness.

Feature reduction for classification of daily activities through kinematic data from smartphones

Abstract Linear acceleration and angular rotation data measured from a human body can provide insights on how a person moves. These kinematic data are typically analyzed and used to understand disease progression associated with movement disorders. Time and frequency domain features extracted from such data are often of large dimensions and not feasible for implementation on resource-constraint devices. In this paper, we propose two optimal feature selection schemes that can better characterize the kinematic measurements to distinguish the movements of a person. One of the proposed approach is based on principal component analysis and the other is based on combinatorial high frequency feature selection from multi-classification algorithms to reduce the features required to maintain high activity prediction rate. We apply three classification algorithms to differentiate the activities a subject was engaged in. Results show the features can be reduced from 561 to 15 with above 84% activity prediction accuracy.

Near infrared chemo-responsive dye intermediaries spectra-based in-situ quantification of volatile organic compounds

Volatile organic compounds (VOCs) detection and measurement in materials with near infrared spectroscopy (NIRS) have been an unresolved constraint till date. This paper focused on the use of NIRS for rapid detection and quantification of pure VOCs (ethanol, ethyl acetate and acetic acid) in mixed VOCs via employing sensitive intermediary chemo-responsive dyes as capture probes, whose NIRS spectra were scanned, preprocessed and used to build partial least squares (PLS) prediction models. Average predicted rates based on the PLS-built prediction models for the pure VOCs in the mixed VOCs yielded 98.60±17.41%. 78.26% of the pure VOCs prediction rates ranged between 85 and 114% and normally distributed. The high prediction rates achieved imply the technique may be deployed as a panacea to widen the usage scope of NIRS and e-nose based colorimetric sensors for rapid detection and quantification of VOCs content in materials which hitherto had been a constraint for both systems.

Multiparametric Magnetic Resonance Imaging of the Prostate for Tumour Detection and Local Staging: Imaging in 1.5T and Histopathologic Correlation

PurposeThe study sought to prospectively evaluate which technique among T2-weighted images, dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI), diffusion-weighted (DW) MRI, or a combination of the 2, is best suited for prostate cancer detection and local staging. MethodsTwenty-seven consecutive patients with biopsy-proven adenocarcinoma of the prostate underwent MRI on a 1.5T scanner with a surface phased-array coil prior radical prostatectomy. Combined anatomical and functional imaging was performed with the use of T2-weighted sequences, DCE MRI, and DW MRI. We compared the imaging results with whole mount histopathology. ResultsFor the multiparametric approach, significantly higher sensitivity values, that is, 53% (95% confidence interval [CI]: 41.0-64.1) were obtained as compared with each modality alone or any combination of the 3 modalities (P < .05). The specificity for this multiparametric approach, being 90.3% (95% CI: 86.3-93.3) was not significantly higher (P < .05) as compared with the values of the combination of T2+DCE MRI, DW+DCE MRI, or DCE MRI alone. Among the 3 techniques, DCE had the best performance for tumour detection in both the peripheral and the transition zone. High negative predictive value rates (>86%) were obtained for both tumour detection and local staging. ConclusionsThe combination of T2-weighted sequences, DCE MRI, and DW MRI yields higher diagnostic performance for tumour detection and local staging than can any of these techniques alone or even any combination of them.

Role of MRI in predicting meniscal tear reparability.

To elucidate the role of MRI in predicting meniscal tear reparability according to tear type and location in relation to vascular zones. In this retrospective study, two readers evaluated 79 pre-surgical MRIs of meniscal tears arthroscopically treated with meniscectomy or meniscal repair. Tears were classified according to type into vertical, horizontal, radial, complex, flaps and bucket handle and were considered reparable if the distance measured from the tear to the menisco-capsular junction was less than or equal to 5mm. Predictions were compared with the surgical procedure performed in arthroscopy. We assessed the diagnostic performance of MRI, agreement between MRI and arthroscopy, and interrater agreement. Then, we conducted an ROC analysis on the distances measured by the first reader and built a multivariate logistic regression model. MRI had a sensitivity, specificity, PPV, NPV and accuracy, respectively, of 85%, 79%, 86%, 76% and 83% in predicting meniscal tear reparability. Correct predictions for the specific tear pattern were 76% for vertical, 84% for horizontal, 88% for radial, 86% for complex, 84% for flaps and 86% for bucket handle. Agreement between the two readers' predictions and arthroscopy was good (k=0.65 and 0.61, respectively). Inter-rater agreement was almost excellent (k=0.79). The ROC analysis revealed sensitivity and specificity of 73% and 83% with a cutoff value of <4mm (p<0.001). Anterior cruciate ligament injury and medial meniscal tear increased the likelihood of meniscal tear reparability. MRI can be a reliable and accurate tool to predict the reparability of meniscal tears, with higher prediction rates for bucket-handle tears.

How Manual Object Exploration is Associated with 7‐ to 8‐Month‐Old Infants’ Visual Prediction Abilities in Spatial Object Processing

The present experiment examined whether infants’ visual prediction performance of the appearance of objects moving in space is related to their manual object exploration ability. Fifty‐five 7‐ to 8‐month‐old infants were tested. A visual object prediction paradigm was developed during which a three‐dimensional object was presented in a live eye‐tracking setting. During familiarization, the object rotated back and forth along the vertical axis. While the object was moving, two target parts of it were briefly occluded from view and uncovered again as the object changed its direction of motion. In the test phase, the entire object was rotated around 90° and now rotated along the horizontal axis. We recorded infants’ eye movements directed at the target locations and analyzed the prediction rates. All of the infants also participated in a manual object exploration task, in which they freely explored five toy blocks. Infants with a higher level of object exploration skill had higher prediction rates during test trials as compared to infants with less proficient object exploratory actions. The results support the interpretation that advanced manual object exploration experience is associated with infants’ advanced visual prediction ability of the appearance of objects moving in space.

Prediction of the aquatic toxicity of aromatic compounds to tetrahymena pyriformis through support vector regression.

Toxicity evaluation is an extremely important process during drug development. It is usually initiated by experiments on animals, which is time-consuming and costly. To speed up such a process, a quantitative structure-activity relationship (QSAR) study was performed to develop a computational model for correlating the structures of 581 aromatic compounds with their aquatic toxicity to tetrahymena pyriformis. A set of 68 molecular descriptors derived solely from the structures of the aromatic compounds were calculated based on Gaussian 03, HyperChem 7.5, and TSAR V3.3. A comprehensive feature selection method, minimum Redundancy Maximum Relevance (mRMR)-genetic algorithm (GA)-support vector regression (SVR) method, was applied to select the best descriptor subset in QSAR analysis. The SVR method was employed to model the toxicity potency from a training set of 500 compounds. Five-fold cross-validation method was used to optimize the parameters of SVR model. The new SVR model was tested on an independent dataset of 81 compounds. Both high internal consistent and external predictive rates were obtained, indicating the SVR model is very promising to become an effective tool for fast detecting the toxicity.

Elemental classification of the tusks of dugong (Dugong dugong) by HH-XRF analysis and comparison with other species

The elemental composition was investigated and applied for identifying the sex and habitat of dugongs, in addition to distinguishing dugong tusks and teeth from other animal wildlife materials such as Asian elephant (Elephas maximus) tusks and tiger (Panthera tigris tigris) canine teeth. A total of 43 dugong tusks, 60 dugong teeth, 40 dolphin teeth, 1 whale tooth, 40 Asian elephant tusks and 20 tiger canine teeth were included in the study. Elemental analyses were conducted using a handheld X-ray fluorescence analyzer (HH-XRF). There was no significant difference in the elemental composition of male and female dugong tusks, whereas the overall accuracy for identifying habitat (the Andaman Sea and the Gulf of Thailand) was high (88.1%). Dolphin teeth were able to be correctly predicted 100% of the time. Furthermore, we demonstrated a discrepancy in elemental composition among dugong tusks, Asian elephant tusks and tiger canine teeth, and provided a high correct prediction rate among these species of 98.2%. Here, we demonstrate the feasible use of HH-XRF for preliminary species classification and habitat determination prior to using more advanced techniques such as molecular biology.

Rough cognitive ensembles

Rough Cognitive Networks are granular classifiers stemming from the hybridization of Fuzzy Cognitive Maps and Rough Set Theory. Such cognitive neural networks attempt to quantify the impact of rough granular constructs (i.e., the positive, negative and boundary regions of a target concept) over each decision class for the problem at hand. In rough classifiers, determining the precise granularity level is crucial to compute high prediction rates. Regrettably, learning the similarity threshold parameter requires reconstructing the information granules, which may be time-consuming. In this paper, we put forth a new multiclassifier system classifier named Rough Cognitive Ensembles. The proposed ensemble employs a collection of Rough Cognitive Networks as base classifiers, each operating at a different granularity level. This allows suppressing the requirement of learning a similarity threshold. We evaluate the granular ensemble with 140 traditional classification datasets using different heterogeneous distance functions. After comparing the proposed model to 15 well-known classifiers, the experimental evidence confirms that our scheme yields very promising classification rates.

DynaDom: structure-based prediction of T cell receptor inter-domain and T cell receptor-peptide-MHC (class I) association angles

BackgroundT cell receptor (TCR) molecules are involved in the adaptive immune response as they distinguish between self- and foreign-peptides, presented in major histocompatibility complex molecules (pMHC). Former studies showed that the association angles of the TCR variable domains (Vα/Vβ) can differ significantly and change upon binding to the pMHC complex. These changes can be described as a rotation of the domains around a general Center of Rotation, characterized by the interaction of two highly conserved glutamine residues.MethodsWe developed a computational method, DynaDom, for the prediction of TCR Vα/Vβ inter-domain and TCR/pMHC orientations in TCRpMHC complexes, which allows predicting the orientation of multiple protein-domains. In addition, we implemented a new approach to predict the correct orientation of the carboxamide endgroups in glutamine and asparagine residues, which can also be used as an external, independent tool.ResultsThe approach was evaluated for the remodeling of 75 and 53 experimental structures of TCR and TCRpMHC (class I) complexes, respectively. We show that the DynaDom method predicts the correct orientation of the TCR Vα/Vβ angles in 96 and 89% of the cases, for the poses with the best RMSD and best interaction energy, respectively. For the concurrent prediction of the TCR Vα/Vβ and pMHC orientations, the respective rates reached 74 and 72%. Through an exhaustive analysis, we could show that the pMHC placement can be further improved by a straightforward, yet very time intensive extension of the current approach.ConclusionsThe results obtained in the present remodeling study prove the suitability of our approach for interdomain-angle optimization. In addition, the high prediction rate obtained specifically for the energetically highest ranked poses further demonstrates that our method is a powerful candidate for blind prediction. Therefore it should be well suited as part of any accurate atomistic modeling pipeline for TCRpMHC complexes and potentially other large molecular assemblies.

A comparative study of landslide susceptibility maps produced using support vector machine with different kernel functions and entropy data mining models in China

The main aim of this study was to apply and compare two GIS-based data mining models, namely support vector machine (SVM) by four kernel functions (linear-SVM, polynomial-SVM, radial basic function-SVM, and sigmoidal-SVM) and entropy models in landslide susceptibility mapping, in Shangzhou District, China. Initially, 145 landslide locations were mapped using early reports, aerial photographs, and supported by field surveys. Subsequently, landslides in the study area were divided randomly into training and validation datasets (70/30) using ArcGIS 10.0 software. In the current study, 14 landslide conditioning factors, namely, slope aspect, slope angle, profile curvature, plan curvature, altitude, topographic wetness index (TWI), stream power index (SPI), sediment transport index (STI), normalized difference vegetation index (NDVI), distance from roads, distance from rivers, distance from faults, rainfall, and lithology, were exploited to detect the most susceptible areas. In the next step, landslide susceptibility maps generated by four types of SVM or entropy models were produced. Finally, validation of the landslide susceptibility maps produced by different models was evaluated using receiver operating characteristics (ROC) curves. The results showed that the entropy model exhibited the highest success rate (0.7610), followed by polynomial-SVM (0.7526), the sigmoidal-SVM (0.7518), radial basic function-SVM (0.7446), and linear-SVM (0.7390) models. Similarly, the ROC plots also showed that the prediction rates gave almost similar results. The entropy model had the highest prediction rate (0.7599), followed by polynomial-SVM (0.7259), sigmoidal-SVM (0.7203), radial basic function-SVM (0.7149), and linear-SVM (0.7009) models. Hence, it can be concluded that the five models used in this study gave close results, with the entropy model exhibiting best performance in landslide susceptibility mapping.

Prioritization of landslide conditioning factors and its spatial modeling in Shangnan County, China using GIS-based data mining algorithms

The main objective of the current study is to apply a random forest (RF) data-driven model and prioritization of landslide conditioning factors according to this method and its comparison to a multivariate adaptive regression spline (MARS) model for landslide susceptibility mapping in China. For this purpose, at first, landslide locations were identified by earlier reports, aerial photographs, and field surveys and a total of 348 landslides were mapped from various sources in GIS. Then, the landslide inventory was randomly split into a training dataset (70% = 244 landslides) and the remaining (30% = 104 landslides) were used for validation. In this study, 12 landslide conditioning factors were applied to detect the most susceptible areas. These factors were slope aspect, altitude, distance to faults, lithology, normalized difference vegetation index, plan curvature, profile curvature, distance to rivers, distance to roads, slope angle, stream power index, and topographic wetness index. The relationship between each conditioning factor and landslide was finalized using a frequency ration (FR) model. Subsequently, landslide-susceptible areas were mapped using the MARS and RF models. The results revealed that the most important conditioning factors according to the accuracy measure (mean decrease) of the RF model are lithology (23.47%), distance to faults (22.21%), and altitude (19.58%). We also notice that altitude (19.04%), distance to faults (18.83%), and distance to roads (15.29%) have the highest importance according to the Gini measure. Finally, the accuracy of the landslide susceptibility maps produced from the two models was verified using a receiver operating characteristics curve. The results showed that the landslide susceptibility map produced using the MARS model has a higher prediction rate than RF by area under the curve values of 87.51 and 77.32%, respectively. According to the validation results, the map produced by the MARS model exhibits the better accuracy and could be proposed for land-use planning in the study area.