Search

Background and Objective: Vitiligo is a chronic skin damage disease, triggered by differential melanocyte death. Vitiligo (0.5%–1% of the population) is one of the most severe skin conditions. In general, the foundation of the condition of vitiligo remains gradual patchy loss of skin pigmentation, overlying blood, and sometimes mucus. This paper provides a systematic review of the relevant publications and conference papers based on the subject of vitiligo diagnosis and confirmation through computer‐aided machine learning (ML) techniques. Materials and Methods: A search was conducted using a predetermined set of keywords across three databases, namely, Science Direct, PubMed, and IEEE Xplore. The selection process involved the application of eligibility criteria, which led to the inclusion of research published in reputable journals and conference proceedings up until June 2024. These selected papers were then subjected to full‐text screening for additional analysis. Research publications that involved application of ML techniques with targeted population of vitiligo were selected for further systematic review. Results: Ten selected and screened studies are included in this systematic review after applying eligibility criteria along with inclusion and exclusion criteria applied on initial search result which was 244 studies based on vitiligo. Priority is given to those studies only which use ML techniques to perform detection and diagnosis on vitiligo‐targeted population. Data analysis was carried out only from the selected and screened research articles that were published in authentic journals and conference proceedings. Conclusion: The importance of applying ML techniques in the clinical diagnosis of vitiligo can give more accurate results and at the same also eliminate the need of biased human judgement. Based on a comprehensive examination of the research, encompassing the methodologies employed and the metrics utilized to assess outcomes, it was determined that there is a need for further research and investigation regarding the application of ML algorithm for the detection and diagnosis of vitiligo with different datasets and more feature extraction. [ABSTRACT FROM AUTHOR]

Diagnosis on the basis of a computerized acoustic examination may play an incredibly important role in early diagnosis and in monitoring and even improving effective pathological speech diagnostics. Various acoustic metrics test the health of the voice. The precision of these parameters also has to do with algorithms for the detection of speech noise. The idea is to detect the disease pathology from the voice. First, we apply the feature extraction on the SVD dataset. After the feature extraction, the system input goes into the 27 neuronal layer neural networks that are convolutional and recurrent neural network. We divided the dataset into training and testing, and after 10 k-fold validation, the reported accuracies of CNN and RNN are 87.11% and 86.52%, respectively. A 10-fold cross-validation is used to evaluate the performance of the classifier. On a Linux workstation with one NVidia Titan X GPU, program code was written in Python using the TensorFlow package. [ABSTRACT FROM AUTHOR]

Automated handwritten digit identification has become essential for many daily operations such as verifying the authenticity of a cheque or deciphering a postal code. Researchers have been putting a lot of effort into figuring out how to automatically recognize and sort handwritten digits because of the advent of robotic technology in recent decades. Due to the complexity of the Arabic language and a lack of publicly available Arabic handwritten digit datasets, previous research has primarily concentrated on automating the recognition of English and European digits on availability of relevant datasets. Arabic handwritten recognition also plays a significant role in electronic-learning (e-learning) systems. It has not taken into account the recognition of handwritten Arabic digits. Arabic handwritten digits vary in size, form, slant, and image noise, which can cause changes in numeral topology. These factors make it difficult to classify and recognize Arabic handwritten digits. In order to overcome these challenges, we implemented a biologically plausible technique to classify Arabic handwritten digits. The objective of the research is to address the unique challenges of style, size, shape, slant variations, and image noise of Arabic handwritten digits in classification and recognition. To categorize Arabic handwritten digits, we employed convolutional spiking neural network (CSNN) and spike neural network (SNN) models. The reason for using SNN and SCNN is that the second-generation neural networks accumulate accolades on various computer vision tasks, i.e., pattern recognition, segmentation, and classification. However, there are certain challenges, i.e., energy inefficiency and computational cost, presented by these networks. The spiking neural network models also address these issues. These models are low-power, high-performance neural network models. We trained the spiking neural network model on Arabic digit datasets using a rate-based, non-spiking algorithm, i.e., backpropagation and soft-LIF, then integrated them with a spiking neural network. We have also used an STDP (spike time-dependent plasticity)-based spiking neural network for Arabic digit recognition. We attenuate the spiking variability in CSNN by adding noise during training, compensating the training errors, and bringing robustness against the spiking variability. We experimented with soft-LIF, a non-spiking version of the LIF neuron, and a variant of STDP rules for Arabic digit classification. Experimental results illustrate that CSNN achieves high performance at a significantly low energy and computational cost. We attained 98.98% and 91.16% recognition rates for the Arabic digit dataBase (ADBase) dataset using the convolutional spiking model and STDP spiking model, respectively. [ABSTRACT FROM AUTHOR]

Software-defined network (SDN) and vehicular ad-hoc network (VANET) combined provided a software-defined vehicular network (SDVN). To increase the quality of service (QoS) of vehicle communication and to make the overall process efficient, researchers are working on VANET communication systems. Current research work has made many strides, but due to the following limitations, it needs further investigation and research: Cloud computing is used for messages/tasks execution instead of fog computing, which increases response time. Furthermore, a fault tolerance mechanism is used to reduce the tasks/messages failure ratio. We proposed QoS aware and fault tolerance-based software-defined V vehicular networks using Cloud-fog computing (QAFT-SDVN) to address the above issues. We provided heuristic algorithms to solve the above limitations. The proposed model gets vehicle messages through SDN nodes which are placed on fog nodes. SDN controllers receive messages from nearby SDN units and prioritize the messages in two different ways. One is the message nature way, while the other one is deadline and size way of messages prioritization. SDN controller categorized in safety and non-safety messages and forward to the destination. After sending messages to their destination, we check their acknowledgment; if the destination receives the messages, then no action is taken; otherwise, we use a fault tolerance mechanism. We send the messages again. The proposed model is implemented in CloudSIm and iFogSim, and compared with the latest models. The results show that our proposed model decreased response time by 50% of the safety and non-safety messages by using fog nodes for the SDN controller. Furthermore, we reduced the execution time of the safety and non-safety messages by up to 4%. Similarly, compared with the latest model, we reduced the task failure ratio by 20%, 15%, 23.3%, and 22.5%. [ABSTRACT FROM AUTHOR]

The present study uses observation-based gridded air temperature and precipitation datasets to investigate the spatiotemporal changes in meteorological drought from 1981 to 2020 in South Asia (SA). The drought characteristics i.e., duration, area, frequency, intensity, and severity are calculated using Run theory and the Standardized Precipitation Evapotranspiration Index (SPEI) on annual and seasonal timescales. SA is divided into four homogeneous subregions using the k-means clustering algorithm, while the trends were estimated using Sen's Slope estimator and modified Mann-Kendall (MMK) test. A state-of-the-art Bayesian Dynamic Linear (BDL) model was employed to assess the sub-regional drought variability and their possible links with large-scale atmospheric drivers such as the Indian Ocean Dipole (IOD), El Niño Southern Oscillation (ENSO), and the Pacific Decadal Oscillation (PDO). It is found that the SA winter season experienced a significant drying long-term trend, especially southwestern and northeastern parts of SA. Drought durations show dipolar patterns with longer drought duration in the southwestern compared to the northern parts of SA. Notably, arid and semi-arid regions have shown significant drying trends in terms of their area, frequency, and severity, implying that meteorological droughts are relatively more severe in those regions. Similarly, the relationship varies over time between drought variability and climate drivers. In particular, the IOD has an impact on drought episodes over southwest SA relative to the northern parts and is mostly affected by the Sea surface temperature (SST) variability. The study results contribute to a better understanding of the meteorological drought characteristics over SA, which is important for disaster risk managers and policymakers to mitigate drought impacts. [ABSTRACT FROM AUTHOR]

South Asia is home to one of the fastest-growing populations in Asia, and human activities are leaving indelible marks on the land surface. Yet the likelihood of successive observed droughts in South Asia (SA) and its four subregions (R-1: semi-arid, R-2: arid, R-3: subtropical wet, and R-4: tropical wet and dry) remains poorly understood. Using the state-of-the-art self-calibrated Palmer Drought Severity Index (scPDSI), we examined the impact of different natural ocean variability modes on the evolution, severity, and magnitude of observed droughts across the four subregions that have distinct precipitation seasonality and cover key breadbaskets and highly vulnerable populations. The study revealed that dryness had significantly increased in R-1, R-2, and R-4 during 1981–2020. Temporal analysis revealed an increase in drought intensity for R-1 and R-4 since the 2000s, while a mixed behavior was observed in R-2 and R-3. Moreover, most of the sub-regions witnessed a substantial upsurge in annual precipitation, but a significant decrease in vapor pressure deficit (VPD) during 1981–2020. The increase in precipitation and the decline in VPD partially contributed to a significant rise in Normalized Difference Vegetation Index (NDVI) and a decrease in dryness. In contrast, a strong positive correlation was found between drought index and precipitation, and NDVI across R-1, R-2, and R-4, whereas temperature and VPD exhibited a negative correlation over these regions. No obvious link was detected with El-Niño Southern Oscillation (ENSO) events, or Indian Ocean Dipole (IOD) and drought evolution, as explored for certain regions of SA. The findings showed the possibility that the precipitation changes over these regions had an insignificant relationship with ENSO, IOD, and drought onset. Thus, the study results highlight the need for considering interactions within the longer climate system in describing observed drought risks rather than aiming at drivers from an individual perspective. [ABSTRACT FROM AUTHOR]

Long‐term drought monitoring and its assessment are of great importance for meteorological disaster risk management. The recurrent spells of heat waves and droughts have severely affected the environmental conditions worldwide, including Pakistan. The present work sought to investigate the spatiotemporal changes in drought characteristics over Pakistan during Rabi and Kharif cropping seasons. The role of large‐scale circulation and interannual mode of climate variability is further explored to identify the physical mechanisms associated with droughts in the region. Monthly precipitation and temperature data (1983–2019) from 53 meteorological stations were used to study drought characteristics, using the standardized precipitation evapotranspiration index (SPEI). The nonparametric Mann–Kendall, Sen's Slope, and Sequential Mann–Kendall tests were applied on the drought index to determine the statistical significance and magnitude of the historical trend. The state‐of‐the‐art Bayesian Dynamic Linear model was further used to analyse large‐scale climate drivers of droughts, revealed an increase in drought severity, mostly over arid to semiarid regions for both cropping seasons. While temperature played a significant role in defining droughts over dry and hot seasons, rainfall is influential over the western disturbances influenced region. The analysis of atmospheric circulation patterns revealed that large‐scale changes in wind speed, air temperature, relative humidity, and geopotential height anomalies are the likely drivers of droughts in the region. We found that Niño4, sea surface temperature, and multivariate El Niño‐Southern Oscillation (ENSO4.0) Index are the most influential factors for seasonal droughts across Pakistan. Overall, the findings provide a better understanding of drought‐prone areas in the region, and this information is of potential use for mitigating and managing drought risks. [ABSTRACT FROM AUTHOR]

Drought is one of the most frequent natural disasters occurring in Pakistan and has a great influence on livelihood, agriculture, and economy. The availability of long‐term high‐quality reanalysis products over Pakistan has been of great concern in recent decades. Here, we conduct drought assessment in Pakistan based on the standardized precipitation index (SPI) and the standardized precipitation evapotranspiration index (SPEI) at 3, 6, and 12 months timescales during 1983–2018. We use long‐term in situ observations to evaluate the accuracy of reanalysis products, including Climatic Research Unit (CRU TS), National Centers for Environmental Prediction version II (NCEP‐2), European Centre for Medium‐Range Weather Forecasts Version‐5 (ERA‐5), and Modern‐Era Retrospective analysis for Research and Applications version II (MERRA‐2). The main results are summarized as follows: (a) drought indices and drought areas assessed from reanalysis products are relatively more representative of historical droughts that had occurred in southern Pakistan and overestimation is evident for drought severity in western than eastern Pakistan; (b) statistically significant increasing trends (1984–1998 and 2000–2010) in monthly drought areas and occurrence are evident by CRU TS and MERRA‐2 in dominant arid and semiarid regions; (c) climate variables and drought features of southern Pakistan are best represented by CRU TS and MERRA‐2, while that of southwestern and western parts are best represented by ERA‐5; (d) the Nash–Sutcliffe efficiency (NSE) results range from −2 to 1, where the NSE of SPEI values (−1.0) show relatively weaker than SPI values (0.5) in most parts of the regions, specifically in the southern Pakistan; (e) a strong positive linear relationship on a monthly scale is evident in CRU TS, MERRA‐2, and ERA‐5 exhibiting relatively high correlation coefficient (0.84), except for NCEP‐2. Furthermore, the SPEI results are found to be better than SPI; thus, this study suggests SPEI may be more suitable than SPI in monitoring droughts under climate change. [ABSTRACT FROM AUTHOR]