FakedBits- Detecting Fake Information on Social Platforms using Multi-Modal Features

Dilip Kumar Sharma,Bhuvanesh Singh,아가왈 사우랍,김현성,Raj Sharma 한국인터넷정보학회 2023 KSII Transactions on Internet and Information Syst Vol.17 No.1

Social media play a significant role in communicating information across the globe, connecting with loved ones, getting the news, communicating ideas, etc. However, a group of people uses social media to spread fake information, which has a bad impact on society. Therefore, minimizing fake news and its detection are the two primary challenges that need to be addressed. This paper presents a multi-modal deep learning technique to address the above challenges. The proposed modal can use and process visual and textual features. Therefore, it has the ability to detect fake information from visual and textual data. We used EfficientNet-B0 and a sentence transformer, respectively, for detecting counterfeit images and for textural learning. Feature embedding is performed at individual channels, whilst fusion is done at the last classification layer. The late fusion is applied intentionally to mitigate the noisy data that are generated by multi-modalities. Extensive experiments are conducted, and performance is evaluated against state-of-the-art methods. Three real-world benchmark datasets, such as MediaEval (Twitter), Weibo, and Fakeddit, are used for experimentation. Result reveals that the proposed modal outperformed the state-of-the-art methods and achieved an accuracy of 86.48%, 82.50%, and 88.80%, respectively, for MediaEval (Twitter), Weibo, and Fakeddit datasets.

What impacts the structural breaks in volatility transmission from crude oil to agricultural commodities?

Dilip Kumar 한양대학교 경제연구소 2019 JOURNAL OF ECONOMIC RESEARCH Vol.24 No.1

The paper examines the evolution of volatility transmission from thecrude oil market to agricultural commodities during the period from1983 to 2015 based on the unbiased version of Rogers and Satchell(1991) volatility estimator, hereafter referred as the AddRS estimator. Our findings indicate that the dynamics of volatility transmission fromcrude oil to the given agricultural commodity is structurally unstableand exhibits structural breaks. We find that the structural breaks involatility series play a tiny role in explaining the structural breaks inthe measured volatility transmission from crude oil to the givenagricultural commodities. However, we find that the conditionalheteroskedasticity plays a significant role in explaining the structuralbreaks in measured volatility transmission from crude oil toagricultural commodity. The economic significance analysis indicatesthat the information from the crude oil market can be used to earnsubstantial economic gain in returns by investing in agriculturalcommodities.

A Pilot Study on TeleBot, a Internet-based Teleoperated Robot

Dilip Kumar Limbu,Wong Hong Yee Alvin,Chua Yuanwei,Albertus Hendrawan Adiwahono,Tran Anh Dung,Han Boon Siew 제어로봇시스템학회 2013 제어로봇시스템학회 국제학술대회 논문집 Vol.2013 No.10

This paper presents a user study on an implemented Internet-based teleoperation robot named TeleBot. The objectives of the study were to: a) test the usability of TeleBot, b) compare two commonly used devices to control TeleBot, and c) understand further development and requirement of TeleBot by examining how operators use TeleBot to complete a specific task. A task-oriented user study that included navigating TeleBot to a specific location and use TeleBot’s arm to touch a “X” marking placed on the door, was designed. Eight participants performed the same task using two different types of device. Both objective and subjective data were collected during the study. The results indicated that a) TeleBot demonstrated a certain level of usability; b) showed that the gamepad was slightly easier to use for teleoperation and finally c) deduced further developmental area for TeleBot.

Hydrometallurgical recovery of critical metals from spent Li-ion batteries using simple leaching-precipitation techniques

Rajak Dilip Kumar,Guria Chandan,Gope Laldeep,Jibran Jahir Ahamad 한국자원공학회 2023 Geosystem engineering Vol.26 No.5

The rising demands for critical metals and the environmental impact of solid waste disposal have increased interest in recycling of spent lithium-ion batteries (LiBs). This study was focused on hydrometallurgical recycling of LCMO type cathode batteries for the recovery of critical metals (lithium, cobalt, and manganese). The process involves sulfuric acid leaching in the presence of a reducing agent (H2O2) followed by the precipitation recovery of critical metals. The influential parameters like pulp density, H2SO4 concentration, H2O2 addition, agitation time, and temperature were optimized, yielding >98% leaching in 2.0 M H2SO4 with 4 vol.% of H2O2 at a moderate temperature of 50°C. Reaction kinetics revealed that the leaching was governed by the mixedcontrol process. Furthermore, the separation and recovery of metals from leach liquor was conducted by simple precipitation techniques, where KMnO4, C2H2O4, and Na2CO3 were used as precipitating reagents to recover MnO2, CoC2O4, and Li2CO3, respectively.

Vibration upshot of operating mechanical sewing machine

Prakash Kumar Yadav,Ram Lochan Yadav,Deepak Sharma,Dev Kumar Shah,Niraj Khatri Sapkota,Dilip Thakur,Nirmala Limbu,Md Nazrul Islam 대한직업환경의학회 2017 대한직업환경의학회지 Vol.29 No.-

Background: Most of the people associated with tailoring occupation in Nepal are still using mechanical sewing machine as an alternative of new technology for tailoring. Common peroneal nerves of both right and left legs are exposed to strenuous and chronic stress exerted by vibration and paddling of mechanical sewing machine. Methods: The study included 30 healthy male tailors and 30 healthy male individuals. Anthropometric variables as well as cardio respiratory variables were determined for each subject. Standard Nerve Conduction Techniques using constant measured distances were applied to evaluate common peroneal nerve (motor) in both legs of each individual. Data were analyzed and compared between study and control groups using Man Whitney U test setting the significance level p ≤ 0.05. Results: Anthropometric and cardio respiratory variables were not significantly altered between the study and control groups. The Compound muscle action potential (CMAP) latency of common peroneal nerves of both right [(11.29 ± 1.25 vs. 10.03 ± 1.37), P < 0.001] and left [(11.28 ± 1.38 vs. 10.05 ± 1.37), P < 0.01] legs was found to be significantly prolonged in study group as compared to control group. The Amp-CMAP of common peroneal nerves of both right [(4.57 ± 1.21 vs. 6.22 ± 1.72), P < 0.001] and left [(4.31 ± 1.55 vs. 6.25 ± 1.70), P < 0.001] legs was found significantly reduced in study group as compared to control group. Similarly, the motor nerve conduction velocity (MNCV) of common peroneal nerves of both right [(43.72 ± 3.25 vs. 47.49 ± 4.17), P < 0.001] and left [(42.51 ± 3.82 vs. 46.76 ± 4.51), P < 0.001] legs was also found to be significantly reduced in study group in comparison to control group. Conclusion: Operating mechanical sewing machine by paddling chronically and arduously could have attributed to abnormal nerve conduction study parameters due to vibration effect of the machine on right and left common peroneal nerves. The results of present study follow the trend towards presymptomatic or asymptomatic neuropathy similar to subclinical neuropathy.

Geo-spatial approach with frequency ratio method in landslide susceptibility mapping in the Busu River catchment, Papua New Guinea

Sujoy Kumar Jana,Tingneyuc Sekac,Dilip Kumar Pal 대한공간정보학회 2019 Spatial Information Research Vol.27 No.1

With the exacerbated kinetic energy of high volume of flowing water, the middle and lower catchment zones of a rugged terrain often become more prone to landslide. Almost half of Lae city, the second largest city in Papua New Guinea falling in the lower end of the catchment remains variably vulnerable to landslides. The study deliberates on the mapping of landslide sustainability, utilizing the geographical data sets such as terrain aspect and slope, land use land cover, site soil-geology, distance from river and distance from existing fault lines as input data for frequency ratio analysis culminating in delineation of susceptible landslide potential zones within the catchment area. The location of previous and recent landslide occurrence zones within the study region were identified and demarcated by dint of high resolution Google earth imagery complimented with the data gathered through field visit. All the thematic layers were prepared and organised for assignment of weights. The calculated frequency ratio values were assigned as weightage to each factor class. By using the weightage sum and raster calculator spatial analyst tool in ArcGIS 10.2.2 the results was generated. The result was then verified with known landslide occurrence and the cumulative % graph was constructed through calculated values. Furthermore the area under curve was calculated and validated with the ground truth information.

Ensemble of Machine Learning Algorithms for Rice Grain Yield Prediction Using UAV-Based Remote Sensing

Sarkar Tapash Kumar,Roy Dilip Kumar,강예성,전새롬,박준우,류찬석 한국농업기계학회 2024 바이오시스템공학 Vol.49 No.1

Purpose Accurately estimating rice yield before harvesting is crucial for eff ective crop management, food trade assessment, and national food policy planning to ensure food security. Remotely sensed spectral information such as vegetation index (VI)-based approaches for yield prediction are adequate during mid-stage growth but not during ripening due to leaf senescence, canopy coverage, panicle abundance, and other factors. To fi ll this research gap, this study aims to predict rice yield during ripening stage using an ensemble of machine learning (ML) algorithms. Methods A fi xed-wing unmanned aerial vehicle (UAV) was employed to acquire spectral features from red-green-blue, nearinfrared, and red-edge images. In this study, we utilized state-of-the-art ML-based algorithms, such long short term memory (LSTM), bi-directional LSTM (Bi-LSTM), Gaussian process regression (GPR), fuzzy inference system (FIS), adaptive neuro FIS (ANFIS), M5 model tree (M5 Tree), support vector regression (SVR), random forest (RF), and the powerful ensemble techniques based on Bayesian model averaging (BMA), and simple averaging (SA) to aid in improving rice yield prediction more precisely at the ripening stage. Results The fi ndings demonstrate that the ensemble model based on BMA excelled all other models on all evaluation criteria. BMA accomplished the most accurate yield prediction with correlation coeffi cient, root mean squared error (RMSE), normalized RMSE, mean absolute error, median absolute deviation, index of agreement, and a-10 values of 0.958, 0.187 t ha −1 , 0.031, 0.158 t ha −1 , 0.088 t ha −1 , 0.957, and 1.00, respectively. Conclusion Employing a combination of ML algorithms for predicting rice grain yield using UAV-based remote sensing proves to be a powerful and eff ective approach. The ensemble method improves forecast accuracy, mitigates individual algorithm limitations, and produces trustworthy outcomes for smart agricultural decisions by integrating the strengths of multiple algorithms. This comprehensive technique has the potential to adapt rice yield estimation and contribute to sustainable food production systems.

Short Communication : High-Frequency in Vitro Flowering in Six Species of Ceropegia

( Aneesh Kumar Nair ),( Naik Dhiraj Dilip ),( Pandit Sagar Subhash ) 한국식물학회 2007 Journal of Plant Biology Vol.50 No.3

Geospatial modeling of solar radiation to explore solar energy potential in Papua New Guinea

Sailesh Samanta,Dilip Kumar Pal,Sammy Samun Aiau,Babita Palsamanta 대한공간정보학회 2016 Spatial Information Research Vol.24 No.5

Climatology and meteorology are essentially driven by the incoming solar radiation and the latter’s latitudinal distribution. The total amount of incoming solar radiation, duration or day-length and the seasonal distribution of radiation have also the leading implication in researches in agricultural sciences. With the reality of climate change looming large, with its plausible para- phernalia on the humankind, it is obvious that the rising demand for clean energy sources will swing the needle of research towards ‘the optimum harnessing of solar energy’ regime. In a specified latitudinal expanse, topography is a major factor that determines the spatial

Nickel(II) Determination by Spectrophotometry Coupled with Preconcentration Technique in Water and Alloy Samples

Rekha, Dasari,Kumar, Jengiti. Dilip,Jayaraj, Bellum,Lingappa, Y.,Chiranjeevi, Pattium Korean Chemical Society 2007 Bulletin of the Korean Chemical Society Vol.28 No.3

A micro organism Agrobacterium tumifacient as an immobilized cell on a solid support was presented as a new biosorbent in a simple and sensitive spectrophotometry determination of Ni(II) in various samples using 4-hydroxy benzaldehyde-4-bromophenyl hydrazone as a color developing agent (λmax 497 nm) at pH 4.0 ± 0.2. Beer's law was obeyed over the range of 0.01-0.1 μg L-1. The molar absorptivity and Sandell's sensitivity were 1.285 × 105 L mol-1cm-1 and 0.007245 μg cm-2 respectively. Under these conditions, the preconcentration factor obtained was 82, and the detection limit achieved was 0.05 μg L-1. The detailed study of various interfering ions made the method more sensitive and selective. The recovery of Ni(II) from various samples range from 97.75 to 99.35%. The present method was successfully applied for the determination of Ni(II) in spiked, natural water and alloy samples. The proposed method was compared with reported methods in terms of Student's ‘t'-test and Variance ratio ‘f'-test which indicates that there is no significant difference between proposed and literature method at 95% confidence level.