Segmenting foreground objects in a multi-modal background using modified Z-score

Choudhury, Suman Kumar; Kumar, Pankaj; Choo, Kim‐Kwang Raymond; Bakshi, Sambit

doi:10.1007/s12652-017-0480-x

Cited by 6 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A modi ed 'robust' Z score formula (Eq. 2) was used (see Choudhury et al, 2017 andSrivastava, 2017), which simply replaces the mean and standard deviation in the well-known standardization procedure (Eq. 1) with the median slope value and MAD of the set of slopes (across space) for each rainfall component, respectively.…”

Section: -Estimating Relative Changes Using Standardized Z-score Valuesmentioning

confidence: 99%

Differential signal of change among multiple components of West African rainfall

Obarein

Lee

2022

Theor Appl Climatol

View full text Add to dashboard Cite

Rainfall components likely differ in the magnitude and direction of their long-term changes for any given location, and some rainfall components may carry a greater regional signal of change than rainfall totals. This study evaluates the magnitude of change of multiple rainfall components relative to other components, and the greatest regions of change across all rainfall components in West Africa. Hourly rainfall data from the ERA5 reanalysis dataset was used to derive twelve rainfall components, which were evaluated for long-term means, interannual variability, and long-term changes.For rainfall totals and rainfall intensity, the central Sahel is witnessing increasing trends while the western Sahel is experiencing signi cant decreasing trends. In general, decreasing trends predominate in the study domain, especially in the northwestern Congo Basin, where annual rainfall is decreasing by 120mm per decade. Importantly, rainfall frequency accounts for 49% of all signi cant grid-point trends for the whole domain. In contrast, rainfall totals account for 26% of all combined signi cant trends across the domain, while rainfall intensity (12.6%), rainy season length (9.5%), and seasonality (3.3%) account for the remaining signals of change. Most of the changes among the rainfall components are in the Tropical Wet and Dry regions (59% of all signi cant trends); the Saharan and Equatorial regions account for the least changes. This study nds evidence that rainfall frequency is changing more across the regions compared to rainfall totals and should be explored as rainfall inputs in climate models to potentially improve regional predictions of future rainfall.

show abstract

Section: -Estimating Relative Changes Using Standardized Z-score Valuesmentioning

confidence: 99%

Differential signal of change among multiple components of West African rainfall

Obarein

Lee

2022

Theor Appl Climatol

View full text Add to dashboard Cite

show abstract

“…But, the process has some limitations in handling with multiple actions at an instant. Hence, combined models including motion detection [10], background separation [11], HOG, etc.…”

Section: Related Workmentioning

confidence: 99%

Towards Enhanced Anomaly Object Detection and Face Recognition (EAODFR) in Surveillance Videos using Recurrent Neural Networks

Ragupathy*,

Vivekanandan

2019

IJRTE

View full text Add to dashboard Cite

In the present decade, anomaly object detection and face recognition from surveillance videos from diverse environments have become interesting and challenging research areas in computer vision. This paper works on developing an Enhanced Anomaly Object Detection and Face Recognition (EAODFR) model using Recurrent Neural Networks (RNN). Moreover, fractional derivative based background separation has been incorporated for framing efficient background subtraction model and foreground segmentation with appropriate pixel definitions on each frame of the surveillance videos. The Region of Interest detection has been done using optimal thresholding and for detecting anomaly objects. Further, efficient face recognition has been accomplished by designing the Recurrent Neural Networks (RNN), which is implemented with Long Short-Term Memory (LSTM). The recurrent NN are trained in terms of determining anomalous objects using the extracted features in the each frame of the video. The obtained results are analyzed in terms of precision, recall and f-measure and compared with some existing face recognition models. The comparative analysis provides better results and outperforms others.

show abstract

“…Z is expressed in terms of the number of standard deviations from the mean value. If the Z-score diverges from the mean by a large enough amount (usually >3.5 or <-3.5 (Choudhury, Sa, Choo, & Bakshi, 2017), the observation can be deemed an outlier, and can subsequently be removed from the dataset (Aggarwal, Gupta, Singh, Sharma, & Sharma, 2019). A total of 21 responses corresponded to Z-scores outside of the recommended threshold, leading to their removal.…”

Section: Response Analysis and Data Cleaningmentioning

confidence: 99%

“…By using standard deviation units, it approximates the difference of the score from the median (IBM, 2023). As recommended when implementing a modified Z-score to identify outliers, any scores above 3.5 or below -3.5 are categorised as outliers (Choudhury et al, 2017). 21 scores were outside of this threshold and were subsequently removed from the dataset.…”

Section: Assumptions Of Multivariate Variancementioning

confidence: 99%

“Fix All of Your Mental Problems”: Message Appeals and the Use Of Personalised Messaging in the Advertising of Digital Mental Health and Well-Being Services

Vallely

View full text Add to dashboard Cite

It is common practice for advertisements relating to digital mental health and well-being services to include very bold and vague (abstract) claims when portraying the app’s benefits, as opposed to more informative or specific messaging (concrete). This often translates to advertising messages such as “Relieve all of your stress”, “Live better”, or “Fix all of your mental problems”. Personalised features within advertisements are also occasionally used for some services in order to further attract the consumer’s attention.To date, no research has examined the effectiveness of concrete versus abstract message appeals and personalisation in advertisements for digital mental health and well-being services. This research categorises these digital mental health and well-being services as “self-appealing services” in relation to Belk’s (1988) theory of the self and the extended self.Building upon previously published literature on message appeals, construal level theory, and personalisation, this study examines the direct effect message appeals (concrete versus abstract) and personalisation have on consumers’ perceived intrusiveness and behavioural intentions to use the service. It also examines the moderating role of concrete message appeals and the mediating role of perceived intrusiveness on these direct effects. A 2 (message appeals: concrete versus abstract) x 2 (personalised versus non-personalised) between-subjects experimental design (n=158) was employed to test these relationships.Study findings demonstrated that the inclusion of a personalised message when advertising a digital mental health and well-being service lowers behavioural intentions to use the service and increases consumer perception of intrusiveness. Contrary to expectations, no significant difference was found in behavioural intentions when comparing the use of a concrete versus abstract message appeals in the advertising of a digital mental health and well-being service.Additionally, concrete message appeals did not moderate the effects of personalisation on behavioural intentions and perceived intrusiveness. Finally, perceived intrusiveness negatively mediated the relationship between personalisation and behavioural intentions.These findings offer several theoretical contributions to the body of knowledge on message appeals and personalised advertising in relation to self-appealing services. Study findings also have implications for managerial practice and social policy.

show abstract

Segmenting foreground objects in a multi-modal background using modified Z-score

Cited by 6 publications

References 44 publications

Differential signal of change among multiple components of West African rainfall

Differential signal of change among multiple components of West African rainfall

Towards Enhanced Anomaly Object Detection and Face Recognition (EAODFR) in Surveillance Videos using Recurrent Neural Networks

“Fix All of Your Mental Problems”: Message Appeals and the Use Of Personalised Messaging in the Advertising of Digital Mental Health and Well-Being Services

Contact Info

Product

Resources

About