Detecting Natural Disasters with Unmanned Aerial Vehicles

Noman Khan,Samee Ullah Khan,Mi Young Lee,Sung Wook Baik 한국차세대컴퓨팅학회 2021 한국차세대컴퓨팅학회 학술대회 Vol.2021 No.11

Unmanned aerial vehicles (UAVs) or drones are versatile innovations that can capture pictures and videos and even collect air or soil samples. Natural disaster drones are especially critical, which help with understanding the damage after a disaster, locating people who need help, distributing resources and preparing for the next event. Computer vision, deep learning (DL), and drones can augment the existing sensors, thereby increasing the accuracy of natural disasters detector, and most importantly, allow people to take precautions, stay safe, and reduce the number of deaths and injuries that happens due to these disasters. Therefore, in this paper we propose a novel lightweight convolutional neural network (CNN) based framework to detect natural disasters including cyclone, flood, earthquake, and wildfire. The proposed CNN model is obtained by fine-tuning the MobileNetV2 that can be deployed on drones. Furthermore, the model is trained and evaluated using a publicly available natural disasters dataset by obtaining 83.4% accuracy. Similarly, the framework has ability to broad cast the notification in alarming situations, which makes our proposed framework a best fit for natural disasters detection in realworld surveillance settings.

Comparative Analysis of Solar Power Generation Forecasting Models for Identical Latitude Countries Data

Noman Khan,Waseem Ullah,Zulfiqar Ahmad Khan,Adnan Hussain,Min Je Kim,Sang Il Yoon,Sung Wook Baik 한국차세대컴퓨팅학회 2023 한국차세대컴퓨팅학회 학술대회 Vol.2023 No.12

Sustainable power systems should include solar energy generation. However, for effective grid management and the integration of renewable energy sources, accurate solar power generation predictions are essential. Therefore, this study compares the prediction of solar power forecasting in Italy and Bulgaria. These are two countries that have alike latitudes but different populations and solar energy production. The historical solar power generation and meteorological data from these countries are preprocessed and then used to apply four different deep learning models including Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The results are analyzed to gain insights into how the proximity of geographical locations and the quality and quantity of data impact the precision of prediction algorithms.

건물의 전력 소비 예측을 위한 어텐션 기반 이중 스트림 딥러닝 네트워크를 활용한 개선된 전력 소비 예측

Noman Khan,Samee Ullah Khan,Altaf Hussain,Sumin Lee,Mi Young Lee,Sung Wook Baik 한국차세대컴퓨팅학회 2023 한국차세대컴퓨팅학회 학술대회 Vol.2023 No.06

A crucial component of designing intelligent and ecologically friendly environments nowadays is electricity consumption forecasting. The generation of energy can be enhanced to effectively meet the population's rising requirements by using the prediction of future electricity consumption. Due to the broad variety of consumption patterns, it is difficult to anticipate the energy requirements of buildings. Therefore, this work uses a dual-steam approach with multi-head attention to anticipate the power consumption of the building to address this issue and produce precise predictions. The proposed network concurrently learns temporal representations through a Bidirectional Gated Recurrent Unit (BGRU) and spatial patterns through Atrous Convolutional Neural Network (ACNN). The obtained features are combined to create a single feature vector that is used as the input for the multi-head attention, which finds the features that are most suited to forecasting the electricity consumption of a building. Finally, the dense layer receives the effective features and uses them to forecast short-term power consumption. In this paper, the proposed dual-stream network with attention outperforms competing models, achieving the lowest error value for hourly building power consumption prediction, according to experimentation on the household electricity consumption dataset.

Leakage Current Energy Harvesting Application in a Photovoltaic (PV) Panel Transformerless Inverter System

Khan, Md. Noman Habib,Khan, Sheroz The Korean Institute of Electrical and Electronic 2017 Transactions on Electrical and Electronic Material Vol.18 No.4

Present-day solar panels incorporate inverters as their core components. Switching devices driven by specialized power controllers are operated in a transformerless inverter topology. However, some challenges associated with this configuration include the absence of isolation, causing leakage currents to flow through various components toward ground. This inevitably causes power losses, often being also the primary reason for the power inverters' analog equipment failure. In this paper, various aspects of the leakage currents are studied using different circuit analysis methods. The primary objective is to convert the leakage current energy into a usable DC voltage source. The research is focused on harvesting the leakage currents for producing circa 1.1 V, derived from recently developed rectifier circuits, and driving a $200{\Omega}$ load with a power in the milliwatt range. Even though the output voltage level is low, the harvested power could be used for charging small batteries or capacitors, even driving light loads.

Leakage Current Energy Harvesting Application in a Photovoltaic (PV) Panel Transformerless Inverter System

Md. Noman Habib Khan,Sheroz Khan 한국전기전자재료학회 2017 Transactions on Electrical and Electronic Material Vol.18 No.4

Present-day solar panels incorporate inverters as their core components. Switching devices driven by specialized powercontrollers are operated in a transformerless inverter topology. However, some challenges associated with this configurationinclude the absence of isolation, causing leakage currents to flow through various components toward ground. This inevitablycauses power losses, often being also the primary reason for the power inverters’ analog equipment failure. In this paper,various aspects of the leakage currents are studied using different circuit analysis methods. The primary objective is to convertthe leakage current energy into a usable DC voltage source. The research is focused on harvesting the leakage currentsfor producing circa 1.1 V, derived from recently developed rectifier circuits, and driving a 200 Ω load with a power in themilliwatt range. Even though the output voltage level is low, the harvested power could be used for charging small batteries orcapacitors, even driving light loads.

듀얼 스트림 CNN-LSTM 아키텍처를 사용한 태양광 발전 예측

Zulfiqar Ahmad Khan,Noman Khan,Su Min Lee,Sang Il Yoon,Mi Young Lee,Sung Wook Baik 한국차세대컴퓨팅학회 2022 한국차세대컴퓨팅학회 학술대회 Vol.2022 No.05

The integration of solar energy with a power system brings great economic and environmental benefits. However, the high penetration of solar power challenges the operation and planning of the existing power system owing to the intermittence and randomicity of solar power generation. Achieving accurate prediction for power generation is important to provide balanced electric energy for end-users. Therefore, in this paper, we introduce a deep learning-based dual stream Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network to learn spatial patterns using CNN and temporal features via the LSTM network. These features are then fused via a concatenation layer and then feed forward to Dense layers for optimal features selection and future solar power prediction. The performance of the proposed model is evaluated on benchmark datasets and achieved a new state-of-the-art on these datasets.

Dataset Standardization for Effective Solar Power Forecasting : A Comprehensive Analysis

Zulfiqar Ahmad Khan,Waseem Ullah,Hikmat Yar,Noman Khan,Min Je Kim,Sung Wook Baik 한국차세대컴퓨팅학회 2023 한국차세대컴퓨팅학회 학술대회 Vol.2023 No.12

This paper introduces a comprehensive approach to dataset standardization aimed at enhancing the effectiveness and reliability of solar power forecasting models. Leveraging multiple datasets, this study incorporates additional attributes such as atmospheric pressure and sunshine duration. These enrichments bridge critical gaps in meteorological and environmental data, facilitating more robust and precise solar power forecasting. The paper underscores the significance of these attributes, furnishes detailed equations for their computation, and presents the outcomes of their integration. It underscores their pivotal role in enabling solar energy stakeholders to make informed decisions and optimize energy production effectively.

Empowerment of People with Intellectual Disabilities

( A H M Noman Khan ) 대구대학교 한국특수교육문제연구소 2018 한국특수교육문제연구소 학술대회발표자료집 Vol.2018 No.1

Empowerment has different meanings in different contexts. According to the CBR Guidelines, empowerment is about ‘having a say and being listened to, self-power, own decision-making, having control or gaining further control, being free, independence, being capable of fighting for one’s rights, andbeing recognized and respected as equal citizens and human beings with a contribution make’. The World Bank defines Empowerment as“Increasing the capacity of individuals or groups to make a choice and to transform those choices into desired actions and outcomes”. Empowerment of persons with disabilities is often challenging and requires a contextualized social and rights based approach. Due to different factors, empowerment of persons with intellectual disabilities and/or other neuro-developmental disabilities has been experienced to be relatively more challenging. Due to ignorance and lack of awareness, families, communities and service providers are paying a negligible care to the specific needs of persons with intellectual disability. Besides, persons with intellectual disabilities often lack in required level of leadership skills and are not mobilized to raise voice and promote their rights. However, there are a number of good examples where persons with intellectual disabilities along with their organizations have achieved significant positive changes following systematic approaches and strategic interventions towards attaining the goal of empowerment. The key note discusses on the key issues concerning the state party’s obligation in terms of policies and practices in empowering persons with disabilities, especially as indicated in the global frameworks like UNCRPD and SDGs. This also discusses the challenges of empowerment of multi type of disability with specific focus to neuro developmental disability. Empowerment of the persons with intellectual disability can be achieved through a holistic approach to mainstreaming disability concerned issues in policy to practices at all levels of development. Systematic strategies for action in line with “Community Based Rehabilitation” guideline have been discussed bridging the link between awareness resigning, appropriate education, employment and livelihood, social integration and empowerment which will lead to better inclusion of persons with disabilities in all spheres of life.

Adiponectin homolog novel osmotin protects obesity/diabetes-induced NAFLD by upregulating AdipoRs/PPARα signaling in <i>ob/ob</i> and <i>db/db</i> transgenic mouse models

Ahmad, Ashfaq,Ali, Tahir,Kim, Min Woo,Khan, Amjad,Jo, Myeung Hoon,Rehman, Shafiq Ur,Khan, Muhammad Sohail,Abid, Noman Bin,Khan, Mehtab,Ullah, Rahat,Jo, Min Gi,Kim, Myeong Ok Elsevier 2019 clinical and experimental Vol.90 No.-

<P><B>Abstract</B></P> <P><B>Background</B></P> <P>In metabolic disorders, adiponectin and adiponectin receptors (AdipoR1/R2) signaling has a key role in improving nonalcoholic fatty liver disease (NAFLD) in obesity-associated diabetes.</P> <P><B>Objective</B></P> <P>To the best of our knowledge, here, we reported for the first time the underlying mechanistic therapeutic efficacy of the novel osmotin, a homolog of mammalian adiponectin, against NAFLD in leptin-deficient <I>ob/ob</I> and <I>db/db</I> mice.</P> <P><B>Methods</B></P> <P>The <I>ob/ob</I> and <I>db/db</I> mice were treated with osmotin at a dose of 5 μg/g three times a week for two weeks. To co-relate the <I>in vivo</I> results we used the human liver carcinoma HepG2 cells, subjected to knockdown with small siRNAs of AdipoR1/R2 and PPARα genes and treated with osmotin and palmitic acid (P.A.). MTT assay, Western blotting, immunohistofluorescence assays, and plasma biochemical analyses were applied.</P> <P><B>Results</B></P> <P>Osmotin stimulated AdipoR1/R2 and its downstream APPL1/PPAR-α/AMPK/SIRT1 pathways in <I>ob/ob</I> and <I>db/db</I> mice, and HepG2 cells exposed to P.A. Mechanistically, we confirmed that knockdown of AdipoR1/R2 and PPARα by their respective siRNAs abolished the osmotin activity in HepG2 cells exposed to P.A. Overall, the <I>in vivo</I> and <I>in vitro</I> results suggested that osmotin protected against NAFLD through activation of AdipoR1/R2 and its downstream APPL1/PPAR-α/AMPK/SIRT1 pathways as shown by the reduced body weight, blood glucose level and glycated hemoglobin, improved glucose tolerance, attenuated insulin resistance and hepatic glucogenesis, regulated serum lipid parameters, and increased fatty acid oxidation and mitochondrial functions.</P> <P><B>Conclusion</B></P> <P>Our findings strongly suggest that novel osmotin might be a potential novel therapeutic tool against obesity/diabetes-induced NAFLD and other metabolic disorders.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Osmotin <I>via</I> AdipoRs dependently reduced palmitic acid-induced toxicity <I>in vitro</I>. </LI> <LI> Osmotin regulated AdipoRs/APPL1/PPAR-α/AMPK/SIRT1 pathways in <I>ob/ob</I> and <I>db/db</I> mice. </LI> <LI> Osmotin regulated AdipoRs/APPL1/PPAR-α/AMPK/SIRT1 pathways in HepG2 cells. </LI> <LI> Osmotin regulated the impaired insulin signaling both <I>in vivo</I> and <I>in vitro</I> studies. </LI> <LI> Osmotin treatment regulated plasma chemistry associated with metabolic disorders. </LI> </UL> </P>

Deep Learning framework for intelligent surveillance video analytics

Su Min Lee,Min Je Kim,Khan Samee Ullah,Khan Zulfiqar Ahmad,Khan Noman,Mi Young Lee,Sung Wook Baik 한국차세대컴퓨팅학회 2021 한국차세대컴퓨팅학회 학술대회 Vol.2021 No.11

Recently, in computer vision behavior recognition is an active research area that plays a significant role in smart cities for crime prevention and urban safety. However, without base knowledge of Artificial Intelligence (AI) designing an efficient model is very difficult because we need data and programing skills for implementing the system. To tackle this problem, we designed and implemented a system that allows a user having no professional knowledge to easily and conveniently create a deep learning model. The interface of this system consists of Data Selection, Model Training and Testing, and Model Parameter values according to domains and categories. In addition, we designed a function to check the test results for the model selected by the user. This system allows users to quickly and easily create and test models.