Search results

ß-thalassemia is a hereditary disorder due to mutation in the ß-globin gene on chromosome 11. Out of 200 known ß-globin gene chain mutations recognized, it is better to identify the most common mutation in specific regions and ethnicity for cost-effective molecular diagnosis of this disorder. Therefore, this study aims to practice multiplex-amplification refractory mutation system (ARMS) PCR on patients with thalassemia in Khyber Pakhtunkhwa (KP) to investigate the most common mutations in the ß-globin chain gene.

Twenty-two individuals (patients, their parents and non-affected siblings) with signed consent were studied from six consanguineous families of ß-thalassemia. Blood samples were collected for DNA isolation. For the detection of mutations in the ß-globin gene, ARMS-PCR was used. The amplicon was visualized through 2% Agarose Gel.

The most common mutations among different ethnic groups in the study area residents were Fr 8-9 (+G) and IVS 1-5 (G> C). The prominent enhancing factors for ß-thalassemia are inter-family marriages and lack of awareness.

Multiplex ARMS_PCR is the most valuable technique for assessing multiple mutations in a single reaction tube.

Due to extensively found ethnic and regional variations and a high rate of consanguinity, the Pashtun population has a great risk of mutations in their genome. Therefore, ARMS-PCR is a cost-effective mutational diagnostic strategy that can help to control disease burden.

Limited studies using ARMS-PCR for mutational analysis in the ß-globin gene are conducted. This study is unique as it targeted consanguineous families of KP Pakistan.

This paper aims to examine the presence of momentum profit in the Indian stock market and seeks to explore the sources of momentum profit employing both risk based and behavioral models. R2, idiosyncratic volatility, and delay measures are employed in order to test behavioral models.

The paper follows Jegadeesh and Timan's methodology in constructing momentum portfolios.

The study finds strong presence of momentum profits in India during 1995‐2006. The risk based models such as CAPM and Fama‐French fail to account for the phenomenon. Idiosyncratic risk exhibits a positive relation with momentum, lending support to behavioural factors as source of momentum phenomenon.

In forming portfolios, selecting the stocks which have been winners in the last three and six months can help investors and fund mangers earn substantial profit.

The study employs behavioral variables to explain the momentum phenomenon. In the Indian context it is an unexplored area.

This paper aims to investigate the association of COVID-19 confirmed cases and deaths with mental health, unemployment and financial markets-related search terms for the USA, the UK, India and worldwide using Google Trends.

The authors use Spearman’s rank correlation coefficients to assess the relationship between relative search volumes (RSVs) and mental health, unemployment and financial markets-related search terms, with the total confirmed COVID-19 cases as well as deaths in the USA, UK, India and worldwide. The sample period starts from the day 100 cases were reported for the first time, which is 7 March 2020, 13 March 2020, 23 March 2020 and 28 January 2020 for the US, the UK, India and worldwide, respectively, and ends on 25 June 2020.

The results indicate a significant increase in anxiety, depression and stress leading to sleeping disorders or insomnia, further deteriorating mental health. The RSVs of employment are negatively significant, implying that people are hesitant to search for new jobs due to being susceptible to exposure, imposed lockdown and social distancing measures and changing employment patterns. The RSVs for financial terms exhibit the varying associations of COVID-19 cases and deaths with the stock market, loans, rent, etc.

This study has implications for the policymakers, health experts and the government. The state governments must provide proper medical facilities and holistic care to the affected population. It may be noted that the findings of this study only lead us to conclude about the relationship between COVID-19 cases and deaths and Google Trends searches, and do not as such indicate the effect on actual behaviour.

To the best of the authors’ knowledge, this is the first attempt to investigate the relationship between the number of COVID-19 cases and deaths in the USA, UK and India and at the global level and RSVs for mental health-related, job-related and financial keywords.

The new customer churn prediction (CCP) utilizing deep learning is developed in this work. Initially, the data are collected from the WSDM-KKBox’s churn prediction challenge dataset. Here, the time-varying data and the static data are aggregated, and then the statistic features and deep features with the aid of statistical measures and “Visual Geometry Group 16 (VGG16)”, accordingly, and the features are considered as feature 1 and feature 2. Further, both features are forwarded to the weighted feature fusion phase, where the modified exploration of driving training-based optimization (ME-DTBO) is used for attaining the fused features. It is then given to the optimized and ensemble-based dilated deep learning (OEDDL) model, which is “Temporal Context Networks (DTCN), Recurrent Neural Networks (RNN), and Long-Short Term Memory (LSTM)”, where the optimization is performed with the aid of ME-DTBO model. Finally, the predicted outcomes are attained and assimilated over other classical models.

The features are forwarded to the weighted feature fusion phase, where the ME-DTBO is used for attaining the fused features. It is then given to the OEDDL model, which is “DTCN, RNN, and LSTM”, where the optimization is performed with the aid of the ME-DTBO model.

The accuracy of the implemented CCP system was raised by 54.5% of RNN, 56.3% of deep neural network (DNN), 58.1% of LSTM and 60% of RNN + DTCN + LSTM correspondingly when the learning percentage is 55.

The proposed CCP framework using the proposed ME-DTBO and OEDDL is accurate and enhances the prediction performance.

The trend of “Deep Learning for Internet of Things (IoT)” has gained fresh momentum with enormous upcoming applications employing these models as their processing engine and Cloud as their resource giant. But this picture leads to underutilization of ever-increasing device pool of IoT that has already passed 15 billion mark in 2015. Thus, it is high time to explore a different approach to tackle this issue, keeping in view the characteristics and needs of the two fields. Processing at the Edge can boost applications with real-time deadlines while complementing security.

This review paper contributes towards three cardinal directions of research in the field of DL for IoT. The first section covers the categories of IoT devices and how Fog can aid in overcoming the underutilization of millions of devices, forming the realm of the things for IoT. The second direction handles the issue of immense computational requirements of DL models by uncovering specific compression techniques. An appropriate combination of these techniques, including regularization, quantization, and pruning, can aid in building an effective compression pipeline for establishing DL models for IoT use-cases. The third direction incorporates both these views and introduces a novel approach of parallelization for setting up a distributed systems view of DL for IoT.

DL models are growing deeper with every passing year. Well-coordinated distributed execution of such models using Fog displays a promising future for the IoT application realm. It is realized that a vertically partitioned compressed deep model can handle the trade-off between size, accuracy, communication overhead, bandwidth utilization, and latency but at the expense of an additionally considerable memory footprint. To reduce the memory budget, we propose to exploit Hashed Nets as potentially favorable candidates for distributed frameworks. However, the critical point between accuracy and size for such models needs further investigation.

To the best of our knowledge, no study has explored the inherent parallelism in deep neural network architectures for their efficient distribution over the Edge-Fog continuum. Besides covering techniques and frameworks that have tried to bring inference to the Edge, the review uncovers significant issues and possible future directions for endorsing deep models as processing engines for real-time IoT. The study is directed to both researchers and industrialists to take on various applications to the Edge for better user experience.

Localization of the nodes is crucial for gaining access of different nodes which would provision in extreme areas where networks are unreachable. The feature of localization of nodes has become a significant study where multiple features on distance model are implicated on predictive and heuristic model for each set of localization parameters that govern the design on energy minimization with proposed adaptive threshold gradient feature (ATGF) model. A received signal strength indicator (RSSI) model with node estimated features is implicated with localization problem and enhanced with hybrid cumulative approach (HCA) algorithm for node optimizations with distance predicting.

Using a theoretical or empirical signal propagation model, the RSSI (known transmitting power) is converted to distance, the received power (measured at the receiving node) is converted to distance and the distance is converted to RSSI (known receiving power). As a result, the approximate distance between the transceiver node and the receiver may be determined by measuring the intensity of the received signal. After acquiring information on the distance between the anchor node and the unknown node, the location of the unknown node may be determined using either the trilateral technique or the maximum probability estimate approach, depending on the circumstances using federated learning.

Improvisation of localization for wireless sensor network has become one of the prime design features for estimating the different conditional changes externally and internally. One such feature of improvement is observed in this paper, via HCA where each feature of localization is depicted with machine learning algorithms imparting the energy reduction problem for each newer localized nodes in Section 5. All affected parametric features on energy levels and localization problem for newer and extinct nodes are implicated with hybrid cumulative approach as in Section 4. The proposed algorithm (HCA with AGTF) has implicated with significant change in energy levels of nodes which are generated newly and which are non-active for a stipulated time which are mentioned and tabulated in figures and tables in Section 6.

Localization of the nodes is crucial for gaining access of different nodes which would provision in extreme areas where networks are unreachable. The feature of localization of nodes has become a significant study where multiple features on distance model are implicated on predictive and heuristic model for each set of localization parameters that govern the design on energy minimization with proposed ATGF model. An RSSI model with node estimated features is implicated with localization problem and enhanced with HCA algorithm for node optimizations with distance predicting.

This paper aims to introduce the weighted squared Euclidean distance between points in signal space, to improve the performance of the Wi-Fi indoor positioning. Nowadays, the received signal strength-based Wi-Fi indoor positioning, a low-cost indoor positioning approach, has attracted a significant attention from both academia and industry.

The local principal gradient direction is introduced and used to define the weighting function and an average algorithm based on k-means algorithm is used to estimate the local principal gradient direction of each access point. Then, correlation distance is used in the new method to find the k nearest calibration points. The weighted squared Euclidean distance between the nearest calibration point and target point is calculated and used to estimate the position of target point.

Experiments are conducted and the results indicate that the proposed Wi-Fi indoor positioning approach considerably outperforms the weighted k nearest neighbor method. The new method also outperforms support vector regression and extreme learning machine algorithms in the absence of sufficient fingerprints.

Weighted k nearest neighbor approach, support vector regression algorithm and extreme learning machine algorithm are the three classic strategies for location determination using Wi-Fi fingerprinting. However, weighted k nearest neighbor suffers from dramatic performance degradation in the presence of multipath signal attenuation and environmental changes. More fingerprints are required for support vector regression algorithm to ensure the desirable performance; and labeling Wi-Fi fingerprints is labor-intensive. The performance of extreme learning machine algorithm may not be stable.

The new weighted squared Euclidean distance-based Wi-Fi indoor positioning strategy can improve the performance of Wi-Fi indoor positioning system.

The received signal strength-based effective Wi-Fi indoor positioning system can substitute for global positioning system that does not work indoors. This effective and low-cost positioning approach would be promising for many indoor-based location services.

A novel Wi-Fi indoor positioning strategy based on the weighted squared Euclidean distance is proposed in this paper to improve the performance of the Wi-Fi indoor positioning, and the local principal gradient direction is introduced and used to define the weighting function.