The role of artificial neural network and machine learning in utilizing spatial information

Akash Goel,Amit Kumar Goel,Adesh Kumar 대한공간정보학회 2023 Spatial Information Research Vol.31 No.3

In this age of the fourth industrial revolution 4.0, the digital world has a plethora of data, including the internet of things, mobile, cybersecurity, social media, forecasts, health data, and so on. The expertise of machine learning and artificial intelligence (AI) is required to soundly evaluate the data and develop related smart and automated applications, These fields use a variety of machine learning techniques including supervised, unsupervised, and reinforcement learning. The objective of the study is to present the role of artificial neural networks and machine learning in utilizing spatial information. Machine learning and AI play an increasingly important role in disaster risk reduction from hazard mapping and forecasting severe occurrences to real-time event detection, situational awareness, and decision assistance. Some of the applications employed in the study to analyze the various ANN domains included weather forecasting, medical diagnosis, aerospace, facial recognition, stock market, social media, signature verification, forensics, robotics, electronics hardware, defense, and seismic data gathering. Machine learning determines the many prediction models for problems involving classification, regression, and clustering using known variables and locations from the training dataset, spatial data that is based on tabular data creates different observations that are geographically related to one another for unknown factors and places. The study presents that the Recurrent neural network and convolutional neural network are the best method in spatial information processing, healthcare, and weather forecasting with greater than 90% accuracy.

Robust Motion Control using Novel First Order Sliding Modes

Akash Panhale,Shailaja Kurode 제어로봇시스템학회 2020 제어로봇시스템학회 국제학술대회 논문집 Vol.2020 No.10

Sliding Mode Control (SMC) assures finite time convergence of sliding variables and constrains it to zero thereafter leading to robustness with respect to internal and external disturbances during sliding. This is achieved by discontinuous term in the control. The discontinuity in the control leads to undesirable chattering which limits its practical applicability. This paper proposes novel simple chatter-free first order sliding mode control philosophy. The mathematical proof of the proposed algorithm is illustrated. The investigated algorithm is validated in simulation for the motion control system.

Using Statistical and Machine Learning Methods to Evaluate the Prognostic Accuracy of SIRS and qSOFA

Akash Gupta,Tieming Liu,Scott Shepherd,William Paiva 대한의료정보학회 2018 Healthcare Informatics Research Vol.24 No.2

Objectives: The objective of this study was to compare the performance of two popularly used early sepsis diagnostic criteria, systemic inflammatory response syndrome (SIRS) and quick Sepsis-related Organ Failure Assessment (qSOFA), using statistical and machine learning approaches. Methods: This retrospective study examined patient visits in Emergency Department (ED) with sepsis related diagnosis. The outcome was 28-day in-hospital mortality. Using odds ratio (OR) and modeling methods (decision tree [DT], multivariate logistic regression [LR], and naïve Bayes [NB]), the relationships between diagnostic criteria and mortality were examined. Results: Of 132,704 eligible patient visits, 14% died within 28 days of ED admission. The association of qSOFA ≥2 with mortality (OR = 3.06; 95% confidence interval [CI], 2.96–3.17) greater than the association of SIRS ≥2 with mortality (OR = 1.22; 95% CI, 1.18–1.26). The area under the ROC curve for qSOFA (AUROC = 0.70) was significantly greater than for SIRS (AUROC = 0.63). For qSOFA, the sensitivity and specificity were DT = 0.39, LR = 0.64, NB = 0.62 and DT = 0.89, LR = 0.63, NB = 0.66, respectively. For SIRS, the sensitivity and specificity were DT = 0.46, LR = 0.62, NB = 0.62 and DT = 0.70, LR = 0.59, NB = 0.58, respectively. Conclusions: The evidences suggest that qSOFA is a better diagnostic criteria than SIRS. The low sensitivity of qSOFA can be improved by carefully selecting the threshold to translate the predicted probabilities into labels. These findings can guide healthcare providers in selecting risk-stratification measures for patients presenting to an ED with sepsis.

Correction: Using Statistical and Machine Learning Methods to Evaluate the Prognostic Accuracy of SIRS and qSOFA

Akash Gupta,Tieming Liu,Scott Shepherd,William Paiva 대한의료정보학회 2018 Healthcare Informatics Research Vol.24 No.3

Effect of Functional Status on the Quality of Bowel Preparation in Elderly Patients Undergoing Screening and Surveillance Colonoscopy

Akash Kumar,Lisa Lin,Oren Bernheim,Emilia Bagiella,Lina Jandorf,Steven H. Itzkowitz,Brijen J. Shah 거트앤리버 소화기연관학회협의회 2016 Gut and Liver Vol.10 No.4

Background/Aims: Optimal bowel preparation is essential for successful screening or for surveillance colonoscopy (SC). Inadequate bowel preparation is associated with older age, the male gender, and the presence of certain comorbidities. However, the association between patients’ functional status and bowel preparation quality has not been studied. We prospectively examined the relationship between functional status, namely, the ability to perform activities of daily living (ADLs) and ambulate, and the quality of bowel preparation in elderly patients undergoing SC. Methods: Before undergoing SC, 88 elderly patients were surveyed regarding their functional status, specifically regarding their ability to perform ADLs and ambulate a quarter of a mile. Gastroenterologists then determined the quality of the bowel preparation, which was classified as either adequate or inadequate. Then, the frequency of inadequate bowel preparation in patients who did or did not experience difficulty performing ADLs and ambulating was calculated. Results: Difficulty ambulating (unadjusted odds ratio [OR], 4.83; p<0.001), difficulty performing ADLs (OR, 2.93; p=0.001), and history of diabetes (OR, 2.88; p=0.007) were significant univariate predictors of inadequate bowel preparation. After adjusting for the above variables, only difficulty ambulating (adjusted OR, 5.78; p=0.004) was an independent predictor of inadequate bowel preparation. Conclusions: Difficulty with ambulation is a strong predictor of inadequate bowel preparation in elderly patients undergoing SC.

Crystallinity Dependent Gas-Sensing Abilities of ZnO Hollow Fibers

Akash Katoch,Zain Ul Abideen,김재훈,Sang Sub Kim 대한금속·재료학회 2016 METALS AND MATERIALS International Vol.22 No.5

The grain size and crystallinity are important factors in considering the gas sensing properties of metal oxide based miniaturized gas sensors. This study reports the effects of the grain size and crystallinity on the CO sensing abilities of ZnO hollow fibers (HFs) synthesized by electrospinning. The grain size and crystallinity of the HFs were controlled by changing the heat treatment time during their synthesis and were characterized by SEM, TEM and XRD. Both the nanograin size and crystallinity of the HFs change significantly with increasing heat treatment time. Longer heat treatments result in improved sensing abilities irrespective of the evolution of larger-sized nanograins. Sensing measurements were carried out at various temperatures in the range 300- 400 °C. The improved crystallinity likely compensates the adverse effects of grain growth in terms of the sensor response. That is, crystallinity rather than grain size, is the dominant factor determining the sensing abilities of HFs. This result provides useful guidelines for the fabrication of HF-based chemiresistive-type gas sensors.

Optimization and Monitoring of Water Soluble Substrate for Synthesis of Mannosylerythritol Lipids by Pseudozyma antarctica (ATCC 32657)

Akash Bhangale,Sushant Wadekar,Sandeep Kale,Amit Pratap 한국생물공학회 2013 Biotechnology and Bioprocess Engineering Vol.18 No.4

Biosurfactants are amphipathic molecules,consisting of hydrophobic and hydrophilic domains, which can partition at the interfaces between different fluid phases,such as oil/water or water/air interfaces. Mannosylerithritol lipids (MELs) are a type of glycolipid. The yeast Candida (Pseudozyma) antarctica (ATCC 32657) secretes an extracellular MEL, with biosurfactant properties, when grown on a water soluble and insoluble substrate, such as glycerine or oils. Value added MEL was biologically synthesized, by using two different types of honey as natural and newer water soluble carbon source. Those types of honey as a carbon source were optimized at different concentration of total carbohydrate present in the honey. Further optimized substrate concentration of honey was monitored for 15 days,for studies of MEL yield and cell growth concentration per day on shake flask batch culture. Surfactant properties,such as surface tension, interfacial tension, foaming,emulsification and wetting of MEL, were observed. Produced MEL was confirmed by thin layer chromatography (TLC),Fourier Transform Infrared (FTIR) spectra, and 1H Nuclear Magnetic Resonance (NMR) techniques.

A Novel Approach to Generate Chirped Waveform by using Chirped Lithium Niobate Mach-Zehnder Modulator

Akash Srivastav,Sanjeev Kumar Raghuwanshi 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.7

A novel technique to generate an arbitrary chirped waveform by harnessing features of Lithium Niobate Mach-Zehnder analog intensity Modulator is suggested and verified by mathematical analysis. The most important application of chirped microwave waveform is that, it improves the range- resolution of radar. In the proposed approach, two electrical drive signal of opposite gain is used to modulate light coming out from the continuous-wave (CW) laser in LiNb Mach-Zehnder modulator (MZM). The output of the MZM is chirped optical waveform due to the dependence of the mach-zehnder modulators chirp on the form of signals applied to the drive electrode. In our simple and straight forward method of producing chirped waveform, is basically based on the concept of change in phase at the two arms of Lithium Niobate Mach-Zehnder modulator due to change in refractive index at the respective arms when electric drive voltage is applied. The chirping phenomenon is expressed in terms of an intrinsic chirp parameter of the MZM. The proposed design is simple, easy to implement and cost effective than the previously proposed model of chirped waveform generation uses the MZM and chirped fiber Bragg grating.

SENSITIZATION OF PERIODONTITIS DISEASE CAUSING BACTERIA BY LOW POWER He-Ne LASER RADIATION

Akash Tripathi Satsangi,Guru Prasad 한국광과학회 2004 Journal of Photosciences Vol.11 No.2

Growth and Characterization of MgxZn1-xO Thin Films by Aerosol-Assisted Chemical Vapor Deposition (AACVD)

Akash Shukla,Vipin K. Kaushik,Dixit Prasher 대한금속·재료학회 2014 ELECTRONIC MATERIALS LETTERS Vol.10 No.1

The growth and characterization of MgxZn1-xO thin films by aerosol-assisted chemical vapor deposition (AACVD) technique is reported in this paper. We have grown the thin films of ZnO by adding varying concentrations of magnesium (Mg) on a glass substrate. The precursor from which the MgxZn1-xO thin films were grown was made up of a mixture of zinc acethylacetonate and magnesium acetate tetrahydrate in boiled isopropyl alcohol. Oxygen gas was used as a carrier gas and substrate temperature was maintained at 400°C. MgxZn1-xO thin films were finally characterized by x-ray diffraction (XRD), atomic force microscopy (AFM) and UV-VIS-NIR spectroscopy. XRD results show that MgxZn1-xO thin films displayed a wurtzite structure and addition of Mg leads to a slight shift towards higher 2-theta values. AFM results show that MgZnO thin films were uniformly covered with nano flakes and their size decreases with an increase in Mg content. Optical studies show that with the increase of Mg content, transparency as well energy band gap of the MgxZn1-xO thin films increases, which also agrees with the reported values.