Recall Research Articles

A Machine Learning-Based Classification and Prediction Technique for DDoS Attacks

Distributed network attacks are referred to, usually, as Distributed Denial of Service (DDoS) attacks. These attacks take advantage of specific limitations that apply to any arrangement asset, such as the framework of the authorized organization’s site. In the existing research study, the author worked on an old KDD dataset. It is necessary to work with the latest dataset to identify the current state of DDoS attacks. This paper, used a machine learning approach for DDoS attack types classification and prediction. For this purpose, used Random Forest and XGBoost classification algorithms. To access the research proposed a complete framework for DDoS attacks prediction. For the proposed work, the UNWS-np-15 dataset was extracted from the GitHub repository and Python was used as a simulator. After applying the machine learning models, we generated a confusion matrix for identification of the model performance. In the first classification, the results showed that both Precision (PR) and Recall (RE) are <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim 89$ </tex-math></inline-formula> % for the Random Forest algorithm. The average Accuracy (AC) of our proposed model is ~89% which is superb and enough good. In the second classification, the results showed that both Precision (PR) and Recall (RE) are approximately 90% for the XGBoost algorithm. The average Accuracy (AC) of our suggested model is ~90%. By comparing our work to the existing research works, the accuracy of the defect determination was significantly improved which is approximately 85% and 79%, respectively.

Simple Multiscale UNet for Change Detection With Heterogeneous Remote Sensing Images

Change detection with heterogeneous remote sensing images (HRSIs) is attractive for observing the Earth’s surface when homogeneous images are unavailable. However, HRSIs cannot be compared directly because the imaging mechanisms for bitemporal HRSIs are different, and detecting change with HRSIs is challenging. In this letter, a simple yet effective deep learning approach based on the classical UNet is proposed. First, a pair of image patches are concatenated together to learn a shared abstract feature in both image patch domains. Then, a multiscale convolution module is embedded in a UNet backbone to cover the various sizes and shapes of ground targets in an image scene. Finally, a combined loss function, which incorporates the focal and dice losses with an adjustable parameter, was incorporated to alleviate the effect of the imbalanced quantity of positive and negative samples in the training progress. By comparisons with five state-of-the-art methods in three pairs of real HRSIs, the experimental results achieved by our proposed approach have the best overall accuracy (OA), average accuracy (AA), recall (RC), and F-Score that are more than 95%, 79%, 60%, and 61%, respectively. The quantitative results and visual performance indicated the feasibility and superiority of the proposed approach for detecting land cover change with HRSIs.

A Machine Intelligence Based Approach for the Classification of Human Face with Mask and without Mask

The importance of face mask (FM) is a major concern for the entire human society in the current circumstances. All peopleshould wear FM in order to lower the chance of infection due to several diseases. It is very much essential to track the peoplewho have not worn the FM in different crowded places, so that warning can be given to them to wear FM in order to lower thespread of infection of different diseases. So, the classification of human face images (HFIs) into human face with mask images(HFWMIs) and human face without mask images (HFWOMIs) types is an essential requirement in this situation. In this work, amachine intelligent (MI) based approach is proposed for the classification of HFIs into HFWMIs and HFWOMIs types. Theproposed approach is focused on the stacking (hybridization) of Logistic Regression (LRG), Support Vector Machine (SVMN),Random Forest (RFS) and Neural Network (NNT) methods to carry out such classification. The proposed method is comparedwith other machine learning (ML) based methods such as LRG, SVMN, RFS, NNT, Decision Tree (DTR), AdaBoost (ADB),Naïve Bayes (NBY), K-Nearest Neighbor (KNNH) and Stochastic Gradient Descent (SGDC) for performance analysis. Theproposed method and other ML based methods have been implemented using Python based Orange 3.26.0. In this work, 200HFWMIs and 200 HFWOMIs are taken from the Kaggle source. The performance of all the methods is assessed using theperformance parameters such as classification accuracy (CA), F1, Precision (PR) and Recall (RC). From the results, it is found that the proposed method is capable of providing better classification results in terms of CA,F1,PR and RC ascompared to other ML based methods such as LRG, SVMN,RFS, NNT,DTR,ADB, NBY, KNNHand SGD.

Morphological Based Medical Image Processing on Cervical Cytology Cancer Images Using Connected Component Techniques.

Cervical cancer is the fourth most common cancer in women. In 2018, it was estimated 570000 women were diagnosed with cervical cancer worldwide and about 311000 women died from the disease. An efficient technique is essential for solving the complication in the diagnosis of cervical cancer images. In this research, a new method is developed for cervical cancer image segmentation. First, the RGB image is converted into an HSI color model. The thresholding is applied to the saturation and intensity components to get binary images. These binary images are combined to get a new mask. Using the connected component concept nucleus and cytoplasm are segmented accurately. For the performance evaluation, peak signal-to-noise ratio (PSNR), mean square error (MSE), structural similarity index (SSIM), image quality index (IQI), structural content (SC), normalized cross-correlation (NK), precision (PR), recall (RC), the Average Difference (AD) and image fidelity (IF) are taken. The proposed techniques' highest PSNR values are 44.2341, 46.7953, 60.5925, and 61.4862, respectively. The proposed segmentation technique can attain a high PSNR (>40db) value at a threshold value equal to 0.1. Also proposed approach attains good precision, recall, and SSIM values. The lowest MSE values using proposed segmentation techniques are 0.0454, 0.0351, 0.0924, and 0.0271 individually. The AD, NK, SC, NAE, and LMSE values for the implemented approach are low, showing the segmented image's quality is very good. Thus, the proposed model performed better compared to other methods.

Diagnostic Value of SonoVue Contrast-Enhanced Ultrasonography in Nipple Discharge Based on Artificial Intelligence.

This paper aims to explore the application value of SonoVue contrast-enhanced ultrasonography based on deep unsupervised learning (DNS) in the diagnosis of nipple discharge. In this paper, a new model (ODNS) is proposed based on the unsupervised learning model and stack self-coding network. The ultrasonic images of 1,725 patients with breast lesions in the shared database are used as the test data of the model. The differences in accuracy (Acc), recall (RE), sensitivity (Sen), and running time between the two models before and after optimization and other algorithms are compared. A total of 48 female patients with nipple discharge are enrolled. The differences in SE, specificity (SP), positive predictive value (PPV), and negative predictive value (NPV) of conventional ultrasound and contrast-enhanced ultrasonography are analyzed based on pathological examination results. The results showed that when the number of network layers is 5, the classification accuracies of DNS and ODNS model data reached the highest values, which were 91.45% and 98.64%, respectively.

Cross-Model Attention-Guided Tumor Segmentation for 3D Automated Breast Ultrasound (ABUS) Images.

Tumor segmentation in 3D automated breast ultrasound (ABUS) plays an important role in breast disease diagnosis and surgical planning. However, automatic segmentation of tumors in 3D ABUS images is still challenging, due to the large tumor shape and size variations, and uncertain tumor locations among patients. In this paper, we develop a novel cross-model attention-guided tumor segmentation network with a hybrid loss for 3D ABUS images. Specifically, we incorporate the tumor location into a segmentation network by combining an improved 3D Mask R-CNN head into V-Net as an end-to-end architecture. Furthermore, we introduce a cross-model attention mechanism that is able to aggregate the segmentation probability map from the improved 3D Mask R-CNN to each feature extraction level in the V-Net. Then, we design a hybrid loss to balance the contribution of each part in the proposed cross-model segmentation network. We conduct extensive experiments on 170 3D ABUS from 107 patients. Experimental results show that our method outperforms other state-of-the-art methods, by achieving the Dice similarity coefficient (DSC) of 64.57%, Jaccard coefficient (JC) of 53.39%, recall (REC) of 64.43%, precision (PRE) of 74.51%, 95th Hausdorff distance (95HD) of 11.91mm, and average surface distance (ASD) of 4.63mm. Our code will be available online (https://github.com/zhouyuegithub/CMVNet).

A Two-Phase Approach using Mask R-CNN and 3D U-Net for High-Accuracy Automatic Segmentation of Pancreas in CT Imaging

Background and objectiveThe size, shape, and position of the pancreas are affected by the patient characteristics such as age, sex, adiposity. Owing to more complex anatomical structures (size, shape, and position) of the pancreas, specialists have some difficulties in the analysis of pancreatic diseases (diabetes, pancreatic cancer, pancreatitis). Therefore, the treatment of the disease requires enormous time and depends on the experience of specialists. In order to decrease the rate of pancreatic disease deaths and to assist the specialist in the analysis of pancreatic diseases, automatic pancreas segmentation techniques have been actively developed in the research article for many years. MethodsAlthough the rapid growth of deep learning and proving satisfactory performance in many medical image processing and computer vision applications, the maximum Dice Similarity Coefficients (DSC) value of these techniques related to automatic pancreas segmentation is only around 85% due to complex structure of the pancreas and other factors. Contrary to previous techniques which are required significantly higher computational power and memory, this paper suggests a novel two-phase approach for high-accuracy automatic pancreas segmentation in computed tomography (CT) imaging. The proposed approach consists of two phases; (1) Pancreas Localization, where the rough pancreas position is detected on the 2D CT slice by adopting Mask R-CNN model, (2) Pancreas Segmentation, where the segmented pancreas region is produced by refining the candidate pancreas region with 3D U-Net on the 2D sub-CT slices generated in the first phase. Both qualitative and quantitative assessments of the proposed approach are performed on the NIH data set. ResultsIn order to evaluate the achievement of the recommended approach, a total of 16 different automatic pancreas segmentation techniques reported in the literature are compared by utilizing performance assessment procedures which are Dice Similarity Coefficient (DSC), Jaccard Index (JI), Precision (PRE), Recall (REC), Pixel Accuracy (ACC), Specificity (SPE), Receiver Operating Characteristics (ROC) and Area under ROC curve (AUC). The average values of DSC, JI, REC and ACC are computed as 86.15%, 75.93%, 86.27%, 86.27% and 99.95% respectively, which are the best values among well-established studies for automatic pancreas segmentation. ConclusionIt is demonstrated with qualitative and quantitative results that our suggested two-phase approach creates more favorable results than other existing approaches.

Underwater hyperspectral imaging for in situ underwater microplastic detection

Abstract Microplastics (MPs) on the seabed threatening marine ecology or human health have drawn much attention. Most research focuses on the in situ detection of MPs in air, while the underwater environment, including light absorption and scattering of the water body, makes in situ MP detection challenging. This study proposed a method for in situ detection of underwater MPs (0.5–5 mm) using underwater VIS hyperspectral imaging (400–720 nm). The underwater spectral image correction model of the water body was calibrated by comparing the images of swatches in air and underwater. Different classifiers, including support vector machine (SVM), neural network (NN), least squares–support vector machine (LS–SVM), and partial least squares–discriminant analysis (PLS–DA), were investigated to identify MPs in air and underwater. Combined with the underwater spectral image correction model, all classifiers achieved promising results, and SVM outperformed all the other classifiers, with average precision (PR) = 0.9839, recall (RE) = 0.9859, and F1-score (F1) = 0.9849, for the identification of six types of MPs, where F1 increased by 3.01% over the raw underwater condition. The effects of particle size, color, and shape were studied, among which a detection limit of 0.5 mm was observed and proved to be possible to extend. MP identification on the lakebed verifies the potential of underwater hyperspectral imaging for in situ underwater MP detection, which may translate to seabed detection. Main findings Microplastics (MPs) on seabed can be detected using underwater hyperspectral imageries in turbid water, with the assistance of spectral image correction.

ArabicDialects: An Efficient Framework for Arabic Dialects Opinion Mining on Twitter Using Optimized Deep Neural Networks

The rapid development of tools for communication such as social networks, tweeting and Whatsapp has generated a large mass of important textual data. Also, the COVID-19 pandemic has inflamed social networks, hence the automatic analysis of opinions has become paramount. The purpose of this paper is to analyze Arabic tweets in terms of positivity, negativity, or neutrality.In analyzing the opinions of the Arabic language, a real challenge is encountered, which lies in the use of different dialects (Egyptian, Saudian, Maghrebian, Gulfian, Levantine, Syrian ⋯). In this paper, we introduce two major components: The first employs six machine learning (ML) methods, including Decision Trees (DT), Logistic Regression (LR), k Nearest Neighbors (K-NN), Random Forests (RF), Support Vector Machines (SVM), and Nave Bayes (NB), with the TF-IDF method acting as the feature extraction.While, the second part consists of testing three variants of Deep Learning (DL) based on multiplicative Long Short Term Memory (mLSTM), Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) by applying word embedding as the input vector. The experimental study was validated using three Arabic language corpora (TEAD, ATSAD, and ASTD) and two learning modes (Hold out and 10-folds cross validation). The obtained results in terms of Accuracy (ACC), Precesion (PREC), Recall (REC), and F1-score (F1) show a clear performance for DL techniques based on a 10-folds strategy compared to the state-of-the-art. The experiments shown in the paper reveal that the proposed DL models accomplished the best results.

Hybrid features prediction model of movie quality using Multi-machine learning techniques for effective business resource planning

Quality prediction plays an essential role in the business outcome of the product. Due to the business interest of the concept, it has extensively been studied in the last few years. Advancement in machine learning (ML) techniques and with the advent of robust and sophisticated ML algorithms, it is required to analyze the factors influencing the success of the movies. This paper presents a hybrid features prediction model based on pre-released and social media data features using multiple ML techniques to predict the quality of the pre-released movies for effective business resource planning. This study aims to integrate pre-released and social media data features to form a hybrid features-based movie quality prediction (MQP) model. The proposed model comprises of two different experimental models; (i) predict movies quality using the original set of features and (ii) develop a subset of features based on principle component analysis technique to predict movies success class. This work employ and implement different ML-based classification models, such as Decision Tree (DT), Support Vector Machines with the linear and quadratic kernel (L-SVM and Q-SVM), Logistic Regression (LR), Bagged Tree (BT) and Boosted Tree (BOT), to predict the quality of the movies. Different performance measures are utilized to evaluate the performance of the proposed ML-based classification models, such as Accuracy (AC), Precision (PR), Recall (RE), and F-Measure (FM). The experimental results reveal that BT and BOT classifiers performed accurately and produced high accuracy compared to other classifiers, such as DT, LR, LSVM, and Q-SVM. The BT and BOT classifiers achieved an accuracy of 90.1% and 89.7%, which shows an efficiency of the proposed MQP model compared to other state-of-art- techniques. The proposed work is also compared with existing prediction models, and experimental results indicate that the proposed MQP model performed slightly better compared to other models. The experimental results will help the movies industry to formulate business resources effectively, such as investment, number of screens, and release date planning, etc.

Electrophysiological Correlates of Dream Recall During REM Sleep: Evidence from Multiple Awakenings and Within-Subjects Design.

PurposeIn the current study, we aimed to investigate the EEG correlates of dream recall (DR) monitoring both the homeostatic and state-trait like factors. We assessed the influence of the time of night on the EEG correlates of DR from REM sleep. Specifically, we tested the continuity-hypothesis (on the theta EEG band) and the activation-hypothesis (on the delta and beta bands).MethodsTwenty-seven subjects underwent polysomnography with multiple provoked awakenings during REM sleep. Only the subjects showing combinations of dream recall (REC) and non-REC (NREC) conditions in both first (1st–2nd sleep cycle) and second (3rd–4th sleep cycle) part of the night were included in the analyses. The final sample was composed of 10 subjects (mean age 24±0.70). EEG power spectra of the 5-min of REM sleep preceding each awakening were computed by a fast Fourier transform. The following frequency bands were considered: delta (0.50–4.75 Hz), theta (5.00–7.75 Hz), and beta (16.00–24.75 Hz). We also calculated the delta/beta power ratio as an integrated EEG index of activation.ResultsThe 2×2 within-subjects ANOVA recall × time revealed: a) no significant effect for time and no interaction; b) significant differences over the occipital area in the beta band; c) significant differences over the parietal area for the activation index values. Overall, the results indicated that DR is associated with higher activation regardless of homeostatic pressure across the night of sleep.ConclusionIn line with recent findings, we have shown that DR is predicted by desynchronized EEG activity during REM sleep, providing clear evidence in favor of the activation-hypothesis. We have also confirmed that the EEG pattern of DR can be ascribed to state-like factors. Further studies should assess whether homeostatic modulation may interact with some dream features and the related EEG predictors.

Automatic and Fast Recognition of On-Road High-Emitting Vehicles Using an Optical Remote Sensing System.

Optical remote sensing systems (RSSs) for monitoring vehicle emissions can be installed on any road and provide non-contact on-road measurements, that allow law enforcement departments to monitor emissions of a large number of on-road vehicles. Although many studies in different research fields have been performed using RSSs, there has been little research on the automatic recognition of on-road high-emitting vehicles. In general, high-emitting vehicles and low-emitting vehicles are classified by fixed emission concentration cut-points, that lack a strict scientific basis, and the actual cut-points are sensitive to environmental factors, such as wind speed and direction, outdoor temperature, relative humidity, atmospheric pressure, and so on. Besides this issue, single instantaneous monitoring results from RSSs are easily affected by systematic and random errors, leading to unreliable results. This paper proposes a method to solve the above problems. The automatic and fast-recognition method for on-road high-emitting vehicles (AFR-OHV) is the first application of machine learning, combined with big data analysis for remote sensing monitoring of on-road high-emitting vehicles. The method constructs adaptively updates a clustering database using real-time collections of emission datasets from an RSS. Then, new vehicles, that pass through the RSS, are recognized rapidly by the nearest neighbor classifier, which is guided by a real-time updated clustering database. Experimental results, based on real data, including the Davies-Bouldin Index (DBI) and Dunn Validity Index (DVI), show that AFR-OHV provides faster convergence speed and better performance. Furthermore, it is not easily disturbed by outliers. Our classifier obtains high scores for Precision (PRE), Recall (REC), the Receiver Operator Characteristic (ROC), and the Area Under the Curve (AUC). The rates of different classifications of excessive emissions and self-adaptive cut-points are calculated automatically in order to provide references for law enforcement departments to establish evaluation criterion for on-road high-emitting vehicles, detected by the RSS.

MP50-18 RELATIVE VALIDITY OF A DIETARY SCREENING TOOL TO IDENTIFY RISK FACTORS FOR UROLITHIASIS

You have accessJournal of UrologyStone Disease: Epidemiology & Evaluation II1 Apr 2018MP50-18 RELATIVE VALIDITY OF A DIETARY SCREENING TOOL TO IDENTIFY RISK FACTORS FOR UROLITHIASIS Kristina L. Penniston, Mariana M. Coughlin, Emma J. Leister, and R. Allan Jhagroo Kristina L. PennistonKristina L. Penniston More articles by this author , Mariana M. CoughlinMariana M. Coughlin More articles by this author , Emma J. LeisterEmma J. Leister More articles by this author , and R. Allan JhagrooR. Allan Jhagroo More articles by this author View All Author Informationhttps://doi.org/10.1016/j.juro.2018.02.1629AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookTwitterLinked InEmail INTRODUCTION AND OBJECTIVES The identification of specific dietary risk factors for urolithiasis enables tailored nutrition intervention that is capable of reducing stone risk. We developed a stone-specific food screener (SFS) and assessed its relative validity. METHODS The SFS, designed to ascertain patients′ habitual eating patterns, was developed via an iterative process involving identification of foods, nutrients, and other dietary factors that influence calcium (Ca) stones; pilot testing; modification; and statistical evaluation. Patients (n=26, 52±12 y; 57% female) and healthy volunteers (n=38, 33±14 y; 68% female) completed the SFS and, within 30 d, a 3-d weighed diet record (DR), a telephone-administered dietitian-assisted 24-h food recall (RC), or both. DRs and RCs were analyzed with nutrient analysis software. Results and agreement between measures were assessed. RESULTS The SFS compared favorably with DRs and RCs for fruit/vegetable intake (F/V, 5.3±2.4 vs. 5.7±3.0 and 5.2±2.8 servings/d, respectively; P>0.36), calcium (960±510 vs. 1,025±431 and 954±474 mg/d; P>0.08), and oxalate (239±96 vs. 221±172 and 274±230 mg/d; P>0.22). But for sodium (Na) and fluids, the SFS compared best with DRs (3,299±1,441 vs. 2,831±959 mg/d and 64±37 vs. 69±38 ozs/d; P>0.25); SFS vs. RCs for same comparisons differed significantly (P<0.02). While paired correlations were high for most SFS-to-DR comparisons (figure), it was low for Na (R2=0.01) due to highly divergent responses from some individuals. Within-person coefficients of variation (CV) for the above factors were lowest when the SFS was compared to DRs: 46% of individuals had CVs <20% for fluids, F/V, oxalate, Ca, and Na compared to only 29% when the SFS was compared to RCs. There was disagreement between DRs and RCs for fluids, oxalate, and Na (P<0.03 for all) due to inconsistent and variable intake of these dietary factors over multiple days. On average, the SFS took 6.5 minutes to complete. CONCLUSIONS The SFS compared well with 3-d weighed DRs for specific stone-related dietary factors (fluids, F/V, oxalate, Ca, and Na) and could be used in clinic to identify patients′ habitual dietary risk factors and to stratify those requiring more detailed nutritional evaluation, both of which could result in more appropriate individualized nutrition recommendations for stone prevention. © 2018FiguresReferencesRelatedDetails Volume 199Issue 4SApril 2018Page: e682-e683 Advertisement Copyright & Permissions© 2018MetricsAuthor Information Kristina L. Penniston More articles by this author Mariana M. Coughlin More articles by this author Emma J. Leister More articles by this author R. Allan Jhagroo More articles by this author Expand All Advertisement Advertisement PDF downloadLoading ...

Fully automatic, multiorgan segmentation in normal whole body magnetic resonance imaging (MRI), using classification forests (CFs), convolutional neural networks (CNNs), and a multi-atlas (MA) approach.

As part of a program to implement automatic lesion detection methods for whole body magnetic resonance imaging (MRI) in oncology, we have developed, evaluated, and compared three algorithms for fully automatic, multiorgan segmentation in healthy volunteers. The first algorithm is based on classification forests (CFs), the second is based on 3D convolutional neural networks (CNNs) and the third algorithm is based on a multi-atlas (MA) approach. We examined data from 51 healthy volunteers, scanned prospectively with a standardized, multiparametric whole body MRI protocol at 1.5 T. The study was approved by the local ethics committee and written consent was obtained from the participants. MRI data were used as input data to the algorithms, while training was based on manual annotation of the anatomies of interest by clinical MRI experts. Fivefold cross-validation experiments were run on 34 artifact-free subjects. We report three overlap and three surface distance metrics to evaluate the agreement between the automatic and manual segmentations, namely the dice similarity coefficient (DSC), recall (RE), precision (PR), average surface distance (ASD), root-mean-square surface distance (RMSSD), and Hausdorff distance (HD). Analysis of variances was used to compare pooled label metrics between the three algorithms and the DSC on a 'per-organ' basis. A Mann-Whitney U test was used to compare the pooled metrics between CFs and CNNs and the DSC on a 'per-organ' basis, when using different imaging combinations as input for training. All three algorithms resulted in robust segmenters that were effectively trained using a relatively small number of datasets, an important consideration in the clinical setting. Mean overlap metrics for all the segmented structures were: CFs: DSC = 0.70 ± 0.18, RE = 0.73 ± 0.18, PR = 0.71 ± 0.14, CNNs: DSC = 0.81 ± 0.13, RE = 0.83 ± 0.14, PR = 0.82 ± 0.10, MA: DSC = 0.71 ± 0.22, RE = 0.70 ± 0.34, PR = 0.77 ± 0.15. Mean surface distance metrics for all the segmented structures were: CFs: ASD = 13.5 ± 11.3 mm, RMSSD = 34.6 ± 37.6 mm and HD = 185.7 ± 194.0 mm, CNNs; ASD = 5.48 ± 4.84 mm, RMSSD = 17.0 ± 13.3 mm and HD = 199.0 ± 101.2 mm, MA: ASD = 4.22 ± 2.42 mm, RMSSD = 6.13 ± 2.55 mm, and HD = 38.9 ± 28.9 mm. The pooled performance of CFs improved when all imaging combinations (T2w + T1w + DWI) were used as input, while the performance of CNNs deteriorated, but in neither case, significantly. CNNs with T2w images as input, performed significantly better than CFs with all imaging combinations as input for all anatomical labels, except for the bladder. Three state-of-the-art algorithms were developed and used to automatically segment major organs and bones in whole body MRI; good agreement to manual segmentations performed by clinical MRI experts was observed. CNNs perform favorably, when using T2w volumes as input. Using multimodal MRI data as input to CNNs did not improve the segmentation performance.

Comparative analysis of two methods for measuring sales volumes during malaria medicine outlet surveys

BackgroundThere is increased interest in using commercial providers for improving access to quality malaria treatment. Understanding their current role is an essential first step, notably in terms of the volume of diagnostics and anti-malarials they sell. Sales volume data can be used to measure the importance of different provider and product types, frequency of parasitological diagnosis and impact of interventions. Several methods for measuring sales volumes are available, yet all have methodological challenges and evidence is lacking on the comparability of different methods.MethodsUsing sales volume data on anti-malarials and rapid diagnostic tests (RDTs) for malaria collected through provider recall (RC) and retail audits (RA), this study measures the degree of agreement between the two methods at wholesale and retail commercial providers in Cambodia following the Bland-Altman approach. Relative strengths and weaknesses of the methods were also investigated through qualitative research with fieldworkers.ResultsA total of 67 wholesalers and 107 retailers were sampled. Wholesale sales volumes were estimated through both methods for 62 anti-malarials and 23 RDTs and retail volumes for 113 anti-malarials and 33 RDTs. At wholesale outlets, RA estimates for anti-malarial sales were on average higher than RC estimates (mean difference of four adult equivalent treatment doses (95% CI 0.6-7.2)), equivalent to 30% of mean sales volumes. For RDTs at wholesalers, the between-method mean difference was not statistically significant (one test, 95% CI −6.0-4.0). At retail outlets, between-method differences for both anti-malarials and RDTs increased with larger volumes being measured, so mean differences were not a meaningful measure of agreement between the methods. Qualitative research revealed that in Cambodia where sales volumes are small, RC had key advantages: providers were perceived to remember more easily their sales volumes and find RC less invasive; fieldworkers found it more convenient; and it was cheaper to implement than RA.Discussion/conclusionsBoth RA and RC had implementation challenges and were prone to data collection errors. Choice of empirical methods is likely to have important implications for data quality depending on the study context.

Recovery sleep after sleep deprivation almost completely abolishes dream recall

The study investigated the effect of one night of sleep deprivation on dream recall at morning awakening after recovery sleep. Forty healthy subjects were studied after adaptation (A) and baseline nights (B), and a recovery (R) night following 40h of prolonged wakefulness. Parallel to the well-known recovery sleep changes (slow-wave sleep – SWS – rebound, decreased number of awakenings and of REM sleep amount), an almost complete abolition of dream recall was found, with an around 75% decrease with respect to the adaptation and baseline nights. The number of dreams recalled by those subjects with successful recall (REC) did not significantly differ between nights. Moreover, gender and sleep stage at awakening did not affect either the proportion of REC subjects or the number of dreams recalled by REC subjects during each night. Finally, the drastic impairment of dream recall after R night was associated to a larger increase of SWS and a shorter REM sleep duration. We suggest that dream recall could have been impaired during R night because: (i) the lower number of spontaneous awakenings over the night reduced the contents available in memory as possible cues for the retrieval of dream experiences at morning; (ii) mental experiences, having been elaborated during SWS more than in the other nights, were less dreamlike (i.e., perceptually vivid and bizarre) and, thus less accessible at morning recall than those elaborated during the nights with a higher proportion of REM sleep; (iii) dream contents, as a peculiar type of episodic information, were less consolidated because of the lower effectiveness of declarative memory during recovery sleep.

Test-expectancy and word-frequency effects in recall and recognition.

To determine if people who expect a recall (RCL) test encode a list of to-beremembered (TBR) words differently than those who expect a recognition (RON) test, people were first induced to expect a RCL or a RON test and then were asked to remember a critical list consisting of both high-frequency (HF) and low-frequency (LF) words. Following presentation of the critical list, different groups received either an expected RCL test, an unexpected RCL test, an expected RON test, or an unexpected RON test. There were two main results: (a) People who expected RCL did better in both RCL and RON than did people who expected RON, but to a much greater degree for HF than LF words, (b) The standard word-frequency effect was obtained; namely, HF words were better recalled but more poorly recognized than LF words. These data were interpreted within the framework of Anderson and Bower's generaterecognize theory as indicating that, compared to people expecting a RON test, people expecting a RCL test more variably encode the semantic interpretations of the TBR word. The implications that these data have for Glanzer and Bowies' theory of the word-frequency effect and for classroom examinations were also discussed.

Interaction of Task Difficulty on Recall and Anticipation Methods in Paired-Associate Learning

Summary Within-Ss 2×3 factorial design, with two methods—recall (REC) and anticipation (ANT)—and three levels of list difficulty, was used for testing the hypothesis that ANT is superior to REC only if the learning task is comparatively difficult. Each of 20 male university students learned, both by the methods of REC and ANT, pairs of 10 words and digits (WD), eight CVCs of moderate and six CCCs of low association values. Analysis of variance, except for the main effect of method, yielded high significance for all the main effects and interactions. In learning paired-associate lists for comparatively easier tasks (WD and CVC lists), no significant difference was found between the two methods. For CCC pairs, however, a significant difference was found (t = 2.50, p < .02), which supported the hypothesis. A tentative modification was suggested in W. K. Estes's theory of reinforcement in human learning.