High Precision Values Research Articles

A novel feature selection technique for enhancing performance of unbalanced text classification problem

Since the last few decades, Text Classification (TC) is being witnessed as an important research direction due to the availability of a huge amount of digital text documents on the web. It would be tedious to manually organize and label them by human experts. Again digging a large number of highly sparse terms and skewed categories present in the documents put a lot of challenges in the correct labeling of the unlabeled documents. Hence feature selection is an essential aspect in text classification, which aims to select more concise and relevant features for further mining of the documents. Additionally, if the text in the document set is associated with multiple categories and the distribution of classes in the dataset is unbalanced, it imposes more challenges on the suitable selection of features for text classification. In this paper, a Modified Chi-Square (ModCHI) based feature selection technique is proposed for enhancing the performance of classification of multi-labeled text documents with unbalanced class distributions. It is an improved version of the Chi-square (Chi) method, which emphasizes selecting maximum features from the classes with a large number of training and testing documents. Unlike Chi, in which the top features are selected with top Chi value, in this proposed technique a score is calculated by considering the total number of relevant documents corresponding to each class with respect to the total number of documents in the original dataset. According to the score the features related to the highly relevant classes as well as high Chi-square value are selected for further processing. The proposed technique is verified with four different classifiers such as Linear SVM (LSVM), Decision tree (DT), Multilevel KNN (MLKNN), Random Forest (RF) over Reuters benchmark multi-labeled, multi-class, unbalanced dataset. The effectiveness of the model is also tested by comparing it with four other traditional feature selection techniques such as term frequency-inverse document frequency (TF-IDF), Chi-square, and Mutual Information (MI). From the experimental outcomes, it is clearly inferred that LSVM with ModCHI produces the highest precision value of 0.94, recall value of 0.80, f-measure of 0.86 and the least hamming loss value of 0.003 with a feature size 1000. The proposed feature selection technique with LSVM produces an improvement of 3.33%, 2.19%, 16.25% in the average precision value, 3.03%, 33.33%, 21.42% in the average recall value, 4%, 34.48%, 14.70% in average F-measure value and 14%, 37.68%, 31.74% in average hamming loss value compared to TF-IDF, Chi and MI techniques respectively. These findings clearly interpret the better performance of the proposed feature selection technique compared to TF_IDF, Chi and MI techniques on the unbalanced Reuters Dataset.

Influence of definitive and interim restorative materials and surface finishing on the scanning accuracy of an intraoral scanner

PurposeTo analyze the influence of the restorative material type (definitive and interim) and its surface treatment (polished or glazed) on the scanning accuracy of an intraoral scanner. Material and methodsA mandibular dental typodont containing 3 typodont teeth (left second premolar and left first and second molars) was used for testing. Ten groups were created based on the crown material: typodont tooth (control group), gold (G group), zirconia (Z group), lithium disilicate (LD group), hybrid ceramic (HC group), composite resin (CR group), conventional PMMA (CNV-PMMA group), bis-acryl composite resin (CNV-BA group), milled PMMA (M-PMMA group), and additively manufactured bis-acryl-based polymer (AM-BA group). Except the G group, groups were subdivided into polished (P subgroups) or glazed (G subgroups). Each specimen was digitized by using an extraoral scanner (D1000; 3Shape A/G) and an intraoral scanner (TRIOS 4; 3Shape). Each reference scan was used to measure the discrepancy with the corresponding 15 intraoral scans by calculating the root mean square (RMS) error (Geomagic; 3D Systems). The Welch ANOVA and Games-Howell tests were selected to examine trueness (α=0.05). The F-test with Bonferroni correction was used to evaluate precision. ResultsSignificant trueness and precision differences were found (P<.001). The G-P subgroup had the lowest trueness values, while the CNV-PMMA-P, M-PMMA-P, and AM-BA-P subgroups had the highest trueness values. Significant RMS mean discrepancies were computed when comparing polished and glazed specimens fabricated with the same material (P<.001). The CNV-PMMA-G subgroup had the lowest precision values, while the CNV-BA-P subgroup had the highest precision values (P<.001). ConclusionsThe type and surface finishing of the restorative materials tested influenced the scanning accuracy of the IOS tested. The lowest trueness values were found in the high noble alloy specimens, while the highest trueness values were measured in conventional and milled PMMA and additively manufactured bis-acryl-based polymer polished specimens. Except for zirconia crowns, higher trueness values were found in polished specimens when compared with glazed crowns. The CNV-PMMA-G subgroup had the lowest precision values, while the highest precision values were measured in the CNV-BA-P subgroup. CLINICAL SIGNIFICANCEDefinitive and interim materials tested decrease intraoral scanning accuracy. Furthermore, polishing instead of glazing definitive and interim material assessed might be preferable to maximize intraoral scanning accuracy.

Two-loop hexa-box integrals for non-planar five-point one-mass processes

We present the calculation of the three distinct non-planar hexa-box topologies for five-point one-mass processes. These three topologies are required to obtain the two-loop virtual QCD corrections for two-jet-associated W, Z or Higgs-boson production. Each topology is solved by obtaining a pure basis of master integrals and efficiently constructing the associated differential equation with numerical sampling and unitarity-cut techniques. We present compact expressions for the alphabet of these non-planar integrals, and discuss some properties of their symbol. Notably, we observe that the extended Steinmann relations are in general not satisfied. Finally, we solve the differential equations in terms of generalized power series and provide high-precision values in different regions of phase space which can be used as boundary conditions for subsequent evaluations.

AuSR1: Authentication and self-recovery using a new image inpainting technique with LSB shifting in fragile image watermarking

With the rapid development of multimedia technology, editing and manipulating digital images have become more accessible than ever. This paper proposed color image authentication based on blind fragile image watermarking for tamper detection and self-recovery named AuSR1. The AuSR1 divides each channel of the cover image into non-overlapping blocks with the size of 2 × 2 pixels. The authentication data is embedded into the original block location, while the recovery data is embedded into the distant location from the original location based on the block mapping algorithm. The watermark data is then embedded into the 2 LSB to achieve high quality of the recovered image under tampering attacks. In addition, the permutation algorithm is applied to ensure the security of the watermark data. The AuSR1 utilizes a three-layer authentication algorithm to achieve a high detection rate.The experimental results show that the scheme produced a PSNR value of 45.57 dB and an SSIM value of 0.9972 of the watermarked images. Furthermore, the AuSR1 detected the tampered area of the images with a high precision value of 0.9943. In addition, the recovered image achieved a PSNR value of 27.64 dB and an SSIM value of 0.9339 on a 50% tampering rate.

Measurement of the hyperfine coupling constants and absolute energies of the 12s 2S1/2, 13s 2S1/2 , and 11d 2DJ levels in atomic cesium

We report measurements of the absolute energies of the hyperfine components of the $12s{\phantom{\rule{0.16em}{0ex}}}^{2}{S}_{1/2}$ and $13s{\phantom{\rule{0.16em}{0ex}}}^{2}{S}_{1/2}$ levels of atomic cesium, $^{133}\mathrm{Cs}$. Using the frequency difference between these components, we determine the hyperfine coupling constants for these states, and report these values with a relative uncertainty of $\ensuremath{\sim}0.06$%. We also examine the hyperfine structure of the $11d{\phantom{\rule{0.16em}{0ex}}}^{2}{D}_{J}$ ($J=3/2,5/2$) states, and resolve the sign ambiguity of the hyperfine coupling constants from previous measurements of these states. We also derive new, high precision values for the state energies of the $12s{\phantom{\rule{0.16em}{0ex}}}^{2}{S}_{1/2}, 13s{\phantom{\rule{0.16em}{0ex}}}^{2}{S}_{1/2}$, and $11d{\phantom{\rule{0.16em}{0ex}}}^{2}{D}_{J}$ states of cesium.

Arterial enhancing local tumor progression detection on CT images using convolutional neural network after hepatocellular carcinoma ablation: a preliminary study

To evaluate the performance of a deep convolutional neural network (DCNN) in detecting local tumor progression (LTP) after tumor ablation for hepatocellular carcinoma (HCC) on follow-up arterial phase CT images. The DCNN model utilizes three-dimensional (3D) patches extracted from three-channel CT imaging to detect LTP. We built a pipeline to automatically produce a bounding box localization of pathological regions using a 3D-CNN trained for classification. The performance metrics of the 3D-CNN prediction were analyzed in terms of accuracy, sensitivity, specificity, positive predictive value (PPV), area under the receiver operating characteristic curve (AUC), and average precision. We included 34 patients with 49 LTP lesions and randomly selected 40 patients without LTP. A total of 74 patients were randomly divided into three sets: training (n = 48; LTP: no LTP = 21:27), validation (n = 10; 5:5), and test (n = 16; 8:8). When used with the test set (160 LTP positive patches, 640 LTP negative patches), our proposed 3D-CNN classifier demonstrated an accuracy of 97.59%, sensitivity of 96.88%, specificity of 97.65%, and PPV of 91.18%. The AUC and precision–recall curves showed high average precision values of 0.992 and 0.96, respectively. LTP detection on follow-up CT images after tumor ablation for HCC using a DCNN demonstrated high accuracy and incorporated multichannel registration.

A novel deep learning-based method for detection of weeds in vegetables.

Precision weed control in vegetable fields can substantially reduce the required weed control inputs. Rapid and accurate weed detection in vegetable fields is a challenging task due to the presence of a wide variety of weed species at various growth stages and densities. This paper presents a novel deep-learning-based method for weed detection that recognizes vegetable crops and classifies all other green objects as weeds. The optimal confidence threshold values for YOLO-v3, CenterNet, and Faster R-CNN were 0.4, 0.6, and 0.4/0.5, respectively. These deep-learning models had average precision (AP) above 97% in the testing dataset. YOLO-v3 was the most accurate model for detection of vegetables and yielded the highest score of 0.971, along with high precision and recall values of 0.971 and 0.970, respectively. The inference time of YOLO-v3 was similar to CenterNet, but significantly shorter than that of Faster R-CNN. Overall, YOLO-v3 showed the highest accuracy and computational efficiency among the deep-learning architectures evaluated in this study. These results demonstrate that deep-learning-based methods can reliably detect weeds in vegetable crops. The proposed method avoids dealing with various weed species, and thus greatly reduces the overall complexity of weed detection in vegetable fields. Findings have implications for advancing site-specific robotic weed control in vegetable crops.

Optimal Deep Reinforcement Learning for Intrusion Detection in UAVs

In recent years, progressive developments have been observed in recent technologies and the production cost has been continuously decreasing. In such scenario, Internet of Things (IoT) network which is comprised of a set of Unmanned Aerial Vehicles (UAV), has received more attention from civilian to military applications. But network security poses a serious challenge to UAV networks whereas the intrusion detection system (IDS) is found to be an effective process to secure the UAV networks. Classical IDSs are not adequate to handle the latest computer networks that possess maximum bandwidth and data traffic. In order to improve the detection performance and reduce the false alarms generated by IDS, several researchers have employed Machine Learning (ML) and Deep Learning (DL) algorithms to address the intrusion detection problem. In this view, the current research article presents a deep reinforcement learning technique, optimized by Black Widow Optimization (DRL-BWO) algorithm, for UAV networks. In addition, DRL involves an improved reinforcement learning-based Deep Belief Network (DBN) for intrusion detection. For parameter optimization of DRL technique, BWO algorithm is applied. It helps in improving the intrusion detection performance of UAV networks. An extensive set of experimental analysis was performed to highlight the supremacy of the proposed model. From the simulation values, it is evident that the proposed method is appropriate as it attained high precision, recall, F-measure, and accuracy values such as 0.985, 0.993, 0.988, and 0.989 respectively.

Quality monitoring of blind fasteners installation: An approach from the manufacturing chain and visual analytics

Fastening is a recurrent assembly operation at the aerospace industry. Among the many different types of fasteners being used blind ones offer particular advantages but there is yet a lack of reliable installation monitoring methods for their massive adoption. The present paper proposes an installation evaluation solution for blind fasteners that integrates the effect of the previous drilling operation and allows the visualization of the relationships between hole quality parameters, installation variables and installation quality. The results show high precision values of 0.95 and accuracy of 0.9.

In-situ recognition of hand gesture via Enhanced Xception based single-stage deep convolutional neural network

In-situ detection and recognition of handgestures in an unconstrained environment is a crucial task in the field of machine vision and video recognition. Hand gesture recognizing task is perhaps more complicated, with varying lighting conditions and background. Robust, accurate hand detection and classification becomes necessary to facilitate the Graphical User Interface, Tele-surgery, etc. In this paper, a Convolutional Neural Network (CNN) based Hybrid Single Stage Recognition (Hybrid-SSR) framework is proposed for real-time hand gesture recognition. The time-efficient Enhanced Xception (E-Xception) CNN model is proposed for feature extraction. The framework is evaluated using three separate datasets (NUSHP-II, Senz-3D, and MITI-HD). The performance of the framework is evaluated for the range of IoU from 0.5 to 0.95. In comparison with the conventional single-stage hand gesture recognition system, the Hybrid-SSR model resulted in higher precision values (99.60 % on AP0.5, 97.80 % on AP0.75, and 88.20 % on AP0.5:0.95) for the MITI-HD dataset. The Hybrid-SSR model with Adam Optimizer surpasses the other optimization techniques. The proposed model achieved comparatively higher precision and recall values for focusing parameter (γ) = 2 and weighting parameter (α) = 0.5. The misclassification problem encountered by the conventional single-stage models is mitigated by implementing the focal loss function in the classification sub-network. The computation cost of Hybrid-SSR (12 ms) is significantly lower compared to other single-stage hand gesture recognition frameworks.

Application of dynamic programming approach to computation of atomic functions

The special class of atomic functions is considered. The atomic function is a solution with compact support of linear differential functional equation with constant coefficients and linear transformations of the argument. The functions considered are used in discrete atomic compression (DAC) of digital images. The algorithm DAC is lossy and provides better compression than JPEG, which is de facto a standard for compression of digital photos, with the same quality of the result. Application of high precision values of atomic functions can improve the efficiency of DAC, as well as provide the development of new technologies for data processing and analysis. This paper aims to develop a low complexity algorithm for computing precise values of the atomic functions considered. Precise values of atomic functions at the point of dense grids are the subject matter of this paper. Formulas of V. O. Rvachev and their generalizations are used. Direct application of them to the computation of atomic functions on dense grids leads to multiple calculations of a great number of similar expressions that should be reduced. In this research, the reduction required is provided. The goal is to develop an algorithm based on V. O. Rvachev’s formulas and their generalizations. The following tasks are solved: to convert these formulas to reduce the number of arithmetic operations and to develop a verification procedure that can be used to check results. In the current research, methods of atomic function theory and dynamic programming algorithms development principles are applied. A numerical scheme for computation of atomic functions at the points of the grid with the step, which is less than each predetermined positive real number, is obtained and a dynamic algorithm based on it is developed. Also, a verification procedure, which is based on the properties of atomic functions, is introduced. The following results are obtained: 1) the algorithm developed provides faster computation than direct application of the corresponding formulas; 2) the algorithm proposed provides precise computation of atomic functions values; 3) procedure of verification has linear complexity in the number of values to be checked. Moreover, the algorithms proposed are implemented using Python programming language and a set of tables of atomic functions values are obtained. Conclusions: results of this research are expected to improve existing data processing technologies based on atomic functions, especially the algorithm DAC, and accelerate the development of new ones.

COMPARISON OF TREE IMPLEMENTATION, REGRESSION LOGISTICS, AND RANDOM FOREST TO DETECT IRIS TYPES

Iris is a genus of 260-300 species of flowering plants with striking flower colors and has a dominant color in each region. The name iris is taken from the Greek word for rainbow, which is also the name for the Greek goddess of the rainbow, Iris. The number of types of iris plants with almost the same physical characteristics, especially in the pistil and crown, causes the misdetection of iris plant types. Iris plants are deliberately used because data is already available digitally on the internet and software such as orange and is widely used as a material for classifying objects. This research was conducted to classify iris plant types using three algorithms, namely Tree algorithm, Regression Logistics, and Random Forest. Classification algorithms are a learning method for predicting the value of a group of attributes in describing and distinguishing a class of data or concepts that aim to predict a class of objects whose class labels are unknown. The results showed the largest AUC (Area Under Curve) value obtained by the Random Forest method. AUC accuracy is said to be perfect when the AUC value reaches 1,000 and the accuracy is poor if the AUC value is below 0.500. As for the precision value of the three models used Random Forest has the highest precision value. From the data tests that have been done training and testing can be seen that the level of accuracy of testing of the three models where the Random Forest model is superior as a method for classification of irises.

IoT-Fog-Cloud Centric Earthquake Monitoring and Prediction

Earthquakes are among the most inevitable natural catastrophes. The uncertainty about the severity of the earthquake has a profound effect on the burden of disaster and causes massive economic and societal losses. Although unpredictable, it can be expected to ameliorate damage and fatalities, such as monitoring and predicting earthquakes using the Internet of Things (IoT). With the resurgence of the IoT, an emerging innovative approach is to integrate IoT technology with Fog and Cloud Computing to augment the effectiveness and accuracy of earthquake monitoring and prediction. In this study, the integrated IoT-Fog-Cloud layered framework is proposed to predict earthquakes using seismic signal information. The proposed model is composed of three layers: (i) at sensor layer, seismic data are acquired, (ii) fog layer incorporates pre-processing, feature extraction using fast Walsh–Hadamard transform (FWHT), selection of relevant features by applying High Order Spectral Analysis (HOSA) to FWHT coefficients, and seismic event classification by K-means accompanied by real-time alert generation, (iii) at cloud layer, an artificial neural network (ANN) is employed to forecast the magnitude of an earthquake. For performance evaluation, K-means classification algorithm is collated with other well-known classification algorithms from the perspective of accuracy and execution duration. Implementation statistics indicate that with chosen HOS features, we have been able to attain high accuracy, precision, specificity, and sensitivity values of 93.30%, 96.65%, 90.54%, and 92.75%, respectively. In addition, the ANN provides an average correct magnitude prediction of 75%. The findings ensured that the proposed framework has the potency to classify seismic signals and predict earthquakes and could therefore further enhance the detection of seismic activities. Moreover, the generation of real-time alerts further amplifies the effectiveness of the proposed model and makes it more real-time compatible.

Computed Tomography Image Based on Intelligent Segmentation Algorithm in the Diagnosis of Ovarian Tumor

This study was to explore the application of computed tomography (CT) images based on intelligent segmentation algorithms in the analysis of ovarian tumors, so as to provide a theoretical basis for clinical diagnosis of ovarian tumors. In this study, 100 patients with ovarian tumors were selected as the research objects and performed CT imaging examinations; a convolutional neural networks (CNN) algorithm model was constructed and applied to CT diagnostic image segmentation of patients with ovarian tumors, so as to analyze the effectiveness of the proposed algorithm for CT image segmentation. As a result, the image was segmented three times under the CNN algorithm, and the numbers of true positives (TP) were 50, 49, and 50, respectively; the numbers of false positives (FP) were 1, 2, and 1, respectively; the numbers of false negatives (FN) were 2, 3, and 2, respectively; and the numbers of true negatives (TN) were 47, 46, and 47, respectively. Thus, there was no great difference in the three measured values P ≥ 0.05 . The accuracy of the CNN algorithm was 0.97, 0.95, and 0.97, respectively, for the three times of segmentation; the precision was 0.98, 0.96, and 0.98, respectively; the recall was 0.96, 0.94, and 0.96, respectively. Thus, the accuracy, precision, and recall of the three measurements were not greatly different P ≥ 0.05 . In addition, the F1 values of three measurements were 0.97, 0.94, and 0.97, respectively, which all were close to 1, showing no statistically great difference P ≥ 0.05 . The segmentation accuracy, precision, and recall of the algorithm in this study were greatly greater than the SE-Res Block U-shaped CNN algorithm, and the density peak clustering algorithm, and the differences were statistically significant P &lt; 0.05 . In short, the CNN algorithm showed high accuracy, precision, recall, and comprehensive evaluation values for CT image segmentation, which made the diagnosis of malignant or benign ovarian tumors more effective and provided reliable theoretical guidance for clinical analysis of ovarian tumors.

Klasifikasi SMS Spam Berbahasa Indonesia Menggunakan Algoritma Multinomial Naïve Bayes

Based on a report submitted by Truecaller Insights Report 2020, Indonesia placed sixth position with the most spam messages, one of the spam applications is SMS. Spam SMS contains unwanted or unsolicited messages, including advertisements, scams and so on. The existence of this spam message causes inconvenience from the user's side when receiving spam SMS, and some even become victims of crime after responding to the SMS. To minimize inconvenience and crime caused by spam messages, the purpose of this study is to filter SMS spam or SMS filtering by classifying SMS spam using the Multinomial Naïve Bayes algorithm by looking for the best combination of parameters to improve the performance of the model that is formed. The results of model testing get the highest precision value in the MNB and SVM models by 93%, the highest recall value in the SVM model at 94%, the highest f1-score value in the SVM model at 94%, the highest accuracy value in the SVM model at 95%, and the fastest test time on the MNB model is 2.66 ms

Activated carbon derived from Azolla filiculoides fern: a high-adsorption-capacity adsorbent for residual ampicillin in pharmaceutical wastewater.

In this study, the effectiveness of activated carbon prepared from the Azolla filiculoides fern (ACAF) in order to remove ampicillin from aqueous solution was examined. The preparation of the ACAF was performed through chemical and physical activation processes with the presence of ZnCl2 and at a temperature of 450 °C. The ACAF yield was 44.7% of the fresh Azolla filiculoides. The results obtained from the characterization study indicate that the prepared ACAF has excellent surface and internal properties to be used as an adsorbent. The surface area, porosity, and pore volume were estimated to be 716.4 m2/g, 51.2%, and 0.621 cm3/g, respectively. The functional groups in ACAF that were responsible for the adsorption of ampicillin molecules were detected using FTIR analyses. The maximum efficiency (96.84%) and uptake (114.3 mg/g) of ACAF to remove ampicillin were achieved under the following conditions: ACAF dose = 0.8 g/L, pH = 7, concentration of ampicillin = 100 mg/L, contact time = 60 min, and temperature = 45 °C. It was found that the kinetic and isotherm data matched the pseudo-second-order and Langmuir models with high precision values, respectively. Considering the thermodynamics of the adsorption, the endothermic and spontaneous nature of the ampicillin adsorption onto ACAF was approved. The ampicillin adsorption capacity by ACAF was not significantly affected by the presence of different concentrations of NaNO3 competitor ion. The considerably higher adsorption capacity of the ACAF for ampicillin (114.3 mg/g) than other previously used adsorbents with excellent regeneration level (five cycles) depicts the superior performance of ACAF in the adsorption systems.Supplementary InformationThe online version contains supplementary material available at 10.1007/s13399-021-01962-4.

Protein Classification Using Machine Learning and Statistical Techniques

Background: In the recent era, the prediction of enzyme class from an unknown protein is one of the challenging tasks in bioinformatics. Day-to-day, the number of proteins increases which causes difficulties in clinical verification and classification; as a result, the prediction of enzyme class gives a new opportunity to bioinformatics scholars. The machine learning classification technique helps in protein classification and predictions. But it is imperative to know which classification technique is more suited for protein classification. This study used human proteins data that is extracted from the UniProtKB databank. A total of 4368 protein data with 45 identified features were used for experimental analysis. Objective: The prime objective of this article is to find an appropriate classification technique to classify the reviewed as well as un-reviewed human enzyme class of protein data. Also, find the significance of different features in protein classification and prediction. Methods: In this article, the ten most significant classification techniques such as CRT, QUEST, CHAID, C5.0, ANN, SVM, Bayesian, Random Forest, XgBoost, and CatBoost have been used to classify the data and discover the importance of features. To validate the result of different classification techniques, accuracy, precision, recall, F-measures, sensitivity, specificity, MCC, ROC, and AUROC were used. All experiments were done with the help of SPSS Clementine and Python. Results: Above discussed classification techniques give different results and found that the data are imbalanced for class C4, C5, and C6. As a result, all of the classification techniques give acceptable accuracy above 60% for these classes of data, but their precision value is very less or negligible. The experimental results highlight that the Random forest gives the highest accuracy as well as AUROC among all, i.e., 96.84% and 0.945, respectively, and also has high precision and recall value. Conclusion: The experiment conducted and analyzed in this article highlights that the Random Forest classification technique can be used for protein of human enzyme classification and predictions.

Credit card fraud detection using asexual reproduction optimization

PurposeThe best algorithm that was implemented on this Brazilian dataset was artificial immune system (AIS) algorithm. But the time and cost of this algorithm are high. Using asexual reproduction optimization (ARO) algorithm, the authors achieved better results in less time. So the authors achieved less cost in a shorter time. Their framework addressed the problems such as high costs and training time in credit card fraud detection. This simple and effective approach has achieved better results than the best techniques implemented on our dataset so far. The purpose of this paper is to detect credit card fraud using ARO.Design/methodology/approachIn this paper, the authors used ARO algorithm to classify the bank transactions into fraud and legitimate. ARO is taken from asexual reproduction. Asexual reproduction refers to a kind of production in which one parent produces offspring identical to herself. In ARO algorithm, an individual is shown by a vector of variables. Each variable is considered as a chromosome. A binary string represents a chromosome consisted of genes. It is supposed that every generated answer exists in the environment, and because of limited resources, only the best solution can remain alive. The algorithm starts with a random individual in the answer scope. This parent reproduces the offspring named bud. Either the parent or the offspring can survive. In this competition, the one which outperforms in fitness function remains alive. If the offspring has suitable performance, it will be the next parent, and the current parent becomes obsolete. Otherwise, the offspring perishes, and the present parent survives. The algorithm recurs until the stop condition occurs.FindingsResults showed that ARO had increased the AUC (i.e. area under a receiver operating characteristic (ROC) curve), sensitivity, precision, specificity and accuracy by 13%, 25%, 56%, 3% and 3%, in comparison with AIS, respectively. The authors achieved a high precision value indicating that if ARO detects a record as a fraud, with a high probability, it is a fraud one. Supporting a real-time fraud detection system is another vital issue. ARO outperforms AIS not only in the mentioned criteria, but also decreases the training time by 75% in comparison with the AIS, which is a significant figure.Originality/valueIn this paper, the authors implemented the ARO in credit card fraud detection. The authors compared the results with those of the AIS, which was one of the best methods ever implemented on the benchmark dataset. The chief focus of the fraud detection studies is finding the algorithms that can detect legal transactions from the fraudulent ones with high detection accuracy in the shortest time and at a low cost. That ARO meets all these demands.

Movie Recommendation System to Solve Data Sparsity Using Collaborative Filtering Approach

With the increase in numbers of multimedia technologies around us, movies and videos on social media and OTT platforms are growing, making it confusing for users to decide which one to watch for. For this, movie recommendation systems are widely used. It has been observed that two-thirds of the films watched on Netflix are the recommended ones to its users. The target of this work is to use implicit feedback given by other users to recommend movies, i.e., ratings given by them. Implicit feedback will help to enhance Data Sparsity as for a replacement logged-in user, the system won't have details of their past liked movies. So, matching the similarity with other users is often a plus point to recommend movies that they would like. The anticipated result will depend upon the positive attitude; i.e., if the predicted rating is high, then it'll be recommended; otherwise it'll not be recommended. The performance of the methodology is measured with accuracy and precision values for different strategies. It gives the best accuracy and highest precision values using Logistic Regression (LR) and lowest recall value as compared to other algorithms. This technique gives an accuracy, precision, and recall value of 81.9%, 69.82%, and 32.5%, respectively, using LR.

FractalCovNet architecture for COVID-19 Chest X-ray image Classification and CT-scan image Segmentation

Precise and fast diagnosis of COVID-19 cases play a vital role in early stage of medical treatment and prevention. Automatic detection of COVID-19 cases using the chest X-ray images and chest CT-scan images will be helpful to reduce the impact of this pandemic on the human society. We have developed a novel FractalCovNet architecture using Fractal blocks and U-Net for segmentation of chest CT-scan images to localize the lesion region. The same FractalCovNet architecture is also used for classification of chest X-ray images using transfer learning. We have compared the segmentation results using various model such as U-Net, DenseUNet, Segnet, ResnetUNet, and FCN. We have also compared the classification results with various models like ResNet5-, Xception, InceptionResNetV2, VGG-16 and DenseNet architectures. The proposed FractalCovNet model is able to predict the COVID-19 lesion with high F-measure and precision values compared to the other state-of-the-art methods. Thus the proposed model can accurately predict the COVID-19 cases and discover lesion regions in chest CT without the manual annotations of lesions for every suspected individual. An easily-trained and high-performance deep learning model provides a fast way to identify COVID-19 patients, which is beneficial to control the outbreak of SARS-II-COV.