Profiling of Urban Noise Using Artificial Intelligence

Noise pollution tends to receive less awareness compared to other types of pollution,however,it greatly impacts the quality of life for humans such as causing sleep disruption,stress or hearing impairment.Profiling urban sound through the identification of noise sources in cities could help to benefit livability by reducing exposure to noise pollution through methods such as noise control,planning of the soundscape environment,or selection of safe living space.In this paper,we proposed a self-attention long short-term memory(LSTM)method that can improve sound classification compared to previous baselines.An attention mechanism will be designed solely to capture the key section of an audio data series.This is practical as we only need to process important parts of the data and can ignore the rest,making it applicable when gathering information with long-term dependencies.The dataset used is the Urbansound8k dataset which specifically pertains to urban environments and data augmentation was applied to overcome imbalanced data and dataset scarcity.All audio sources in the dataset were normalized to mono signals.From the dataset above,an experiment was conducted to confirm the suitability of the proposed model when applied to the mel-spectrogram and MFCC(Mel-Frequency Cepstral Coefficients)datasets transformed from the original dataset.Improving the classification accuracy depends on the machine learning models as well as the input data,therefore we have evaluated different class models and extraction methods to find the best performing.By combining data augmentation techniques and various extraction methods,our classification model has achieved state-of-the-art performance,each class accuracy is up to 98%.

Anticancer effects of saponin and saponin–phospholipid complex of Panax notoginseng grown in Vietnam

Objective:To evaluate the antitumor activity both in vitro and in vivo of saponin–phospholipid complex of Panax notoginseng.Methods:The in vitro cytotoxic effect of saponins extract and saponin–phospholipid complex against human lung cancer NCI-H460 and breast cancer cell lines BT474 was examined using MTS assay.For in vivo evaluation of antitumor potential,saponin and saponin–phospholipid complex were administered orally in rats induced mammary carcinogenesis by 7,12-dimethylbenz(a)anthracene,for 30 days.Results:Our data showed that saponin–phospholipid complex had stronger anticancer effect compared to saponin extract.The IC50 values of saponin–phospholipid complex and saponin extract for NCI-H460 cell lines were 28.47 mg/m L and 47.97 mg/mL,respectively and these values for BT474 cells were 53.18 mg/mL and 86.24 mg/mL,respectively.In vivo experiments,administration of saponin,saponin–phospholipid complex and paclitaxel(positive control) effectively suppressed 7,12-dimethylbenz(a) anthracene-induced breast cancer evidenced by a decrease in tumor volume,the reduction of lipid peroxidation level and increase in the body weight,and elevated the enzymatic antioxidant activities of superoxide dismutase,catalase,glutathione peroxidase in rat breast tissue.Conclusions:Our study suggests that saponin extract from Panax notoginseng and saponin–phospholipid complex have potential to prevent cancer,especially breast cancer.

Investigation of Polymorphisms in Coding Region of OsHKT1in Relation to Salinity in Rice

Rice （Oryza sativa） is sensitive to salinity, but the salt tolerance level differs among cultivars,which might result from natural variations in the genes that are responsible for salt tolerance. High-affinitypotassium transporter （HKTs） has been proven to be involved in salt tolerance in plants. Therefore, wescreened for natural nucleotide polymorphism in the coding sequence of OsHKT1, which encodes the HKTprotein in eight Vietnamese rice cultivars differing in salt tolerance level. In total, seven nucleotidesubstitutions in coding sequence of OsHKT1 were found, including two non-synonymous and five synonymoussubstitutions. Further analysis revealed that these two non-synonymous nucleotide substitutions （G50Tand T1209A） caused changes in amino acids （Gly17Val and Asp403Glu） at signal peptide and the loop ofthe sixth transmembrane domain, respectively. To assess the potential effect of these substitutions on theprotein function, the 3D structure of HKT protein variants was modelled by using PHYRE2 webserver. Theresults showed that no difference was observed when compared those predicted 3D structure of HKTprotein variants with each other. In addition, the codon bias of synonymous substitutions cannot clearlyshow correlation with salt tolerance level. It might be interesting to further investigate the functional roles ofdetected non-synonymous substitutions as it might correlate to salt tolerance in rice.

Performance Comparison of Chemically Modified Sugarcane Bagasse for Removing Cd(II) in Water Environment

This paper evaluates the adsorption capacity of chemically sugarcane bagasses with sodium hydroxide(SHS),citric acid(CAS),tartaric acid(TAS)and unmodified sugarcane bagasse(SB)for cadmium adsorption in water environment.The results prove adsorption capacity for Cd(II)increases after chemical modification and the adsorption fits perfectly with the Langmuir isotherm.CAS had the highest maximum adsorption capacity of 45.45 mg/g followed by TAS with 38.46 mg/g and SHS with 29.41 at optimum pH 5.0 and 120 minutes equilibrium time while 1 g SB removed 18.8 mg Cd(II)in the same conditions.The kinetics study of the process followed a pseudo-secondorder rate expression,that indicated a strong interaction between the biosorbents and adsorbate.The sugarcane bagasse and modified sugarcane bagasse were characterized by scanning electron microscopy(SEM)and Fourier transform infrared spectroscopy(FTIR)analysis.The chemical modification was confirmed by the presence of carboxyl and esters groups created at 1,738 cm-1.The estimation of acid groups in modified materials shows the enhancement of this group after modification.On the other hand,desorption studies showed the high leaching of cadmium ion from the biosorbent leading to the efficient reutilization of materials.

DENSITY ESTIMATES FOR SOLUTIONS OF STOCHASTIC FUNCTIONAL DIFFERENTIAL EQUATIONS

In this article, we investigate the density of the solution to a class of stochastic functional differential equations by means of Malliavin calculus. Our aim is to provide upper and lower Gaussian estimates for the density.

Calibration of a neutron dose rate meter in various neutron standard fields

This paper presents the calibration of a neutron dose rate meter and the evaluation of its calibration factors(CFs)in several neutron standard fields(i.e.,two standard fields with bare sources of252Cf and241Am-Be,and five simulated workplace fields with241Am-Be moderated sources).The calibration in standard fields with bare sources was conducted by following the recommendations of the ISO 8529 standard.The measured total neutron ambient dose equivalent rates,denoted as H*(10)tot,were analyzed to obtain direct components,denoted as H*(10)dir,using a reduced fitting method.The CF was then calculated as the ratio between the conventional true value of the neutron ambient dose equivalent rate in a free field,denoted as H*(10)FF,and the value of H*(10)dir.In contrast,in the simulated workplace neutron fields,the calibration of the neutron dose rate meter was conducted by following the ISO 12789 standard.The CF was calculated as the ratio between the values of H*(10)totmeasured by a standard instrument(i.e.,Bonner sphere spectrometer)and the neutron dose rate meter.The CF values were obtained in the range of 0.88–1.0.The standard uncertainties(k=1)of the CFs were determined to be in the range of approximately 6.6–13.1%.

Taxonomic notes of three tea-plants(Camellia sect.Thea)recently described in Vietnam

Camellia sinensis var.dulcamara is a heterotypic synonym of C.sinensis var.pubilimba.Camellia flosculora and C.vidalii were excluded from sect.Thea.

Eye Strain Detection During Online Learning

The recent outbreak of the coronavirus disease of 2019(Covid-19)has been causing many disruptions among the education systems worldwide,most of them due to the abrupt transition to online learning.The sudden upsurge in digital electronic devices usage,namely personal computers,laptops,tablets and smart-phones is unprecedented,which leads to a new wave of both mental and physical health problems among students,for example eye-related illnesses.The overexpo-sure to electronic devices,extended screen time usage and lack of outdoor sun-light have put a consequential strain on the student’s ophthalmic health because of their young age and a relative lack of responsibility on their own health.Failure to take appropriate external measures to mitigate the negative effects of this pro-cess could lead to common ophthalmic illnesses such as myopia or more serious conditions.To remedy this situation,we propose a software solution that is able to track and capture images of its users’eyes to detect symptoms of eye illnesses while simultaneously giving them warnings and even offering treatments.To meet the requirements of a small and light model that is operable on low-end devices without information loss,we optimized the original MobileNetV2 model with depth-wise separable convolutions by altering the parameters in the last layers with an aim to minimize the resizing of the input image and obtained a new model which we call EyeNet.Combined with applying the knowledge distillation tech-nique and ResNet-18 as a teacher model to train the student model,we have suc-cessfully increased the accuracy of the EyeNet model up to 87.16%and support the development of a model compatible with embedded systems with limited computing power,accessible to all students.

Counter-Wind Deep Current in the Northern Beibu Gulf in Boreal Winter

The Beibu Gulf is at an important geographical location and rich in gas, oil and biological resources. The observed currents showed that the current in the upper layer was opposite to that in the lower layer in boreal winter in the northern Beibu Gulf and it was northeastward in the lower layer. This northeastward current was reproduced by a 3 D baroclinic model in this study. It's found that the counter-wind deep current(referred to as ‘CWDC' hereinafter) strengthened from September to November but weakened from December to the following February. A closed meridional circulation in vertical direction was found in the northern Beibu Gulf, including CWDC, surface southwestward current, an upwelling, and a downwelling. The temporal variation process of the meridional circulation was similar to that of CWDC, with strength and range stronger in November and December than in other four months. Similar to the variation process of CWDC, the monsoon wind changed from weak easterly wind in September to strong northeasterly wind in November and December, and it was transformed into weak southeasterly wind in February again. The sensitive experiments showed that CWDC and the meridional circulation were controlled by the monsoon wind and were adjusted by heat flux-and tide-induced mixing, respectively. According to the momentum balance equation, it can be revealed the counter-wind deep current is a compensation current which is induced by the surface elevation gradient balanced by the Coriolis force, vertical diffusion and baroclinic pressure gradient.

Improved flood susceptibility mapping using a best first decision tree integrated with ensemble learning techniques

Improving the accuracy of flood prediction and mapping is crucial for reducing damage resulting from flood events.In this study,we proposed and validated three ensemble models based on the Best First Decision Tree(BFT)and the Bagging(Bagging-BFT),Decorate(Bagging-BFT),and Random Subspace(RSS-BFT)ensemble learning techniques for an improved prediction of flood susceptibility in a spatially-explicit manner.A total number of 126 historical flood events from the Nghe An Province(Vietnam)were connected to a set of 10 flood influencing factors(slope,elevation,aspect,curvature,river density,distance from rivers,flow direction,geology,soil,and land use)for generating the training and validation datasets.The models were validated via several performance metrics that demonstrated the capability of all three ensemble models in elucidating the underlying pattern of flood occurrences within the research area and predicting the probability of future flood events.Based on the Area Under the receiver operating characteristic Curve(AUC),the ensemble Decorate-BFT model that achieved an AUC value of 0.989 was identified as the superior model over the RSS-BFT(AUC=0.982)and Bagging-BFT(AUC=0.967)models.A comparison between the performance of the models and the models previously reported in the literature confirmed that our ensemble models provided a reliable estimate of flood susceptibilities and their resulting susceptibility maps are trustful for flood early warning systems as well as development of mitigation plans.

Locally weighted learning based hybrid intelligence models for groundwater potential mapping and modeling: A case study at Gia Lai province, Vietnam

The groundwater potential map is an important tool for a sustainable water management and land use planning,particularly for agricultural countries like Vietnam.In this article,we proposed new machine learning ensemble techniques namely AdaBoost ensemble(ABLWL),Bagging ensemble(BLWL),Multi Boost ensemble(MBLWL),Rotation Forest ensemble(RFLWL)with Locally Weighted Learning(LWL)algorithm as a base classifier to build the groundwater potential map of Gia Lai province in Vietnam.For this study,eleven conditioning factors(aspect,altitude,curvature,slope,Stream Transport Index(STI),Topographic Wetness Index(TWI),soil,geology,river density,rainfall,land-use)and 134 wells yield data was used to create training(70%)and testing(30%)datasets for the development and validation of the models.Several statistical indices were used namely Positive Predictive Value(PPV),Negative Predictive Value(NPV),Sensitivity(SST),Specificity(SPF),Accuracy(ACC),Kappa,and Receiver Operating Characteristics(ROC)curve to validate and compare performance of models.Results show that performance of all the models is good to very good(AUC:0.75 to 0.829)but the ABLWL model with AUC=0.89 is the best.All the models applied in this study can support decision-makers to streamline the management of the groundwater and to develop economy not only of specific territories but also in other regions across the world with minor changes of the input parameters.

Modeling Election Problem by a Stochastic Differential Equation

The proportion of the favorable among voters to a nominee might change over times and depend on different factors for example: talent, reputation, party and even name order on election. The unobservable factors which might have minor impacts on the approval rate are modelized by random elements. The approval rate is initially described by the differential equation and then by the random differential equation including the above unobservable factors. We figure out the formula of the solution for the stochastic differential equation and simulate these solutions to identify the changes of the approval rate over time.

Jahn-Teller distortion assisted interstitial nitrogen engineering:Enhanced oxygen dehydrogenation activity of N-doped Mn_(x)Co_(3-x)O_(4) hierarchical micro-nano particles

Rational design of earth-abundant transition metal oxides catalysts is highly desirable for developing sustainable chemical processes.Herein,we demonstrate a prospective interstitial nitrogen engineering for fabricating oxygen vacancies(OVs)-rich nitrogen-doped-Mn_(x)Co_(3-x)O_(4)(N-Mn_(x)Co_(3-x)O_(4))oxide catalyst,in which the ratio of OVs concentration of N-Mn_(x)Co_(3-x)O_(4)to Mn species is as high as 1:1,according to the characterizations of X-ray absorption(XAS)and X-ray photoelectron(XPS)spectroscopies.The promising strategy of interstitial nitrogen engineering through lattice distortion caused by the Jahn-Teller effect can significantly increase the amount of interstitial nitrogen.The resulting catalyst enables an additive-free aerobic dehydrogenation coupling of aromatic amine to afford azo compounds with>99%yield and>99%selectivity at 60☆.We observed the superb catalytic activity is promoted by the enhanced oxygen mobility in OVs,which were created by the interstitial nitrogen in the catalyst matrix.The presence of interstitial nitrogen in transition metal oxides in this study shows how the manipulation of catalyst matrix can increase the OV sites to promote aerobic oxidation reaction.

Physical and mechanical properties of municipal solid waste incineration residues with cement and coal fly ash using X-ray Computed Tomography scanners

A significant volume of Municipal Solid Waste incineration bottom ash and fly ash (i.e.,incineration residues) are commonly disposed as landfill.Meanwhile,reclamation of landfill sites to create a new land space after their closure becomes an important goal in the current fewer and fewer land availability scenario in many narrow countries.The objective of this study is to reclaim incineration residue materials in the landfill site by using cement and coal fly ash as stabilizers aiming at performing quality check as new developed materials before future construction.Indeed,physical and mechanical properties of these new materials should be initially examined at the micro scale,which is the primary fundamental for construction at larger scale.This research examines quantitative influences of using the combination of cement and coal fly ash at different ratio on the internal structure and ability of strength enhancement of incineration residues when suffering from loading.Couple of industrial and micro-focus X-ray computed tomography (CT) scanners combined with an image analysis technique were utilized to characterize and visualize the behavior and internal structure of the incineration residues-cement-coal fly ash mixture under the series of unconfined compression test and curing period effect.Nine types of cement solidified incineration residues in term of different curing period (i.e.,7,14,28 days) and coal fly ash addition content (i.e.,0%,9%,18%) were scanned before and after unconfined compression tests.It was shown that incineration residues solidified by cement and coal fly ash showed an increase in compression strength and deformation modulus with curing time and coal fly ash content.Three-dimension computed tomography images observation and analysis confirmed that solidified incineration residues including incineration bottom and fly ash as well as cement and coal fly ash have the deliquescent materials.Then,it was studied that stabilized parts play a more important role than spatial void distribution in increment or reduction of compression strength.

Influence of phytochemicals in piper betle linn leaf extract on wound healing

Background:Wound healing has being extensively investigated over the world.Healing impairment is caused by many reasons including increasing of free-radicals-mediated damage,delaying in granulation tissue formation,reducing in angiogenesis and decreasing in collagen reorganization.These facts consequently lead to chronic wound healing.Piper betle Linn(Betle)leaves have been folklore used as an ingredient of drugs for cutaneous wound treatment.However,the effect of betle leaf on wound healing is not yet well elucidated.In this study,we aimed to investigate the healing efficacy of methanol leaf extract of Piper betle Linn on proliferation of fibroblast NIH3T3 cells as well as full-thickness burn and excision wounds in swiss mice.Methods:Scratch wound healing assays were conducted to examine the effects of betle leaf extract on healing activity of fibroblast cells.Burn and excision wounds on swiss mouse skins were created for investigating the wound healing progress caused by the betle leaf extract.Malondialdehyde(MDA)was also evaluated to examine the products of lipid hydroperoxide(LPO)under conditions of with or without betle leaf extract treatment.Results:The results of this study showed that Piper betle Linn leaf extract in methanol increased proliferation of NIH3T3 cells and promoted wound healing in vitro and in vivo with both burn wound and excision wound models.In addition,this extract significant decreased level of malondialdehyde(MDA)in liver of treated-mice compared with that in non-treated mice.Conclusions:Our results suggest that Piper betle Linn can be used as an ingredient in developing natural origin drugs for treatment of cutaneous wounds.

Revealing efficient catalytic performance of N-CuO_(x) for aerobic oxidative coupling of aliphatic alkynes:A Langmuir-Hinshelwood reaction mechanism

O_(x)idative couplings of aliphatic alkynes are crucial for the production of naturally occurring 1,3-diynes.Herein we report the novel approach for effective synthesis of unsaturated coordinated N doped copper oxides(N-CuO_(x))catalyst,and uncover that N-CuO_(x) catalyst as an additive-free and cost-effective heterogeneous catalyst has highly catalytic performance for directly oxidative coupling of aliphatic alkynes.The key to achieve efficient oxidative coupling of aliphatic alkynes is the synergistic effect of N species and uncoordinated O/Cu species caused by N dopants,which undergoes the Langmuir–Hinshelwood reaction mechanism.The N-CuO_(x) catalyst displays~89.1%yield for hexadeca-7,9-diyne under mild conditions and stable reusability(5 cycles),showing significant advances compared with the traditionally copper oxides.These findings highlight the heteroatom dopants that provide a new methodology for designing efficient copper catalysts in synthesis of naturally occurring 1,3-diynes.

Comprehensive evaluation of dioxins and dioxin-like compounds in surface soils and river sediments from e-waste-processing sites in a village in northern Vietnam:Heading towards the environmentally sound management of e-waste

The management of electronic waste(e-waste),which can be a source of both useful materials and toxic substances,depending on the processing method,is important for promoting material cycling.In this study,we used the dioxin-responsive chemical-activated luciferase gene expression(DR-CALUX)assay combined with gas chromatographyehigh-resolution mass spectrometry to evaluate the levels of dioxin-like compounds in surface soils and river sediments collected in and around an e-waste-processing village in northern Vietnam.The WHO-TEQs(Toxic equivalents)of polychlorinated dibenzo-p-dioxins and dibenzofurans(PCDD/Fs),coplanar polychlorinated biphenyls(Co-PCBs),and polybrominated dibenzo-pdioxins and dibenzofurans(PBDD/Fs)in soils collected in January 2012 ranged from 0.29 to 310 pg/g(median 2.9 pg/g,n=32),and the WHO-TEQs in sediments ranged from 0.96 to 58 pg/g(median 4.4 pg/g,n=8).Dioxin-like activities(CALUX-TEQs[2,3,7,8-TCDD equivalent])in soils collected in January 2012,2013,and 2014 ranged from<30 to 4300 pg/g(median<30 pg/g,n=96),and the activities in sediments ranged from<30 to 4000 pg/g(median 33 pg/g,n=24).Dioxin-like compounds accumulated in samples collected around e-waste-processing areas such as open-burning sites and e-waste-processing workshops,and the compounds may be transported from their sources to surrounding areas over the course of several years.Some of the CALUX-TEQs,but not WHO-TEQs,values were higher than the maximum acceptable WHO-TEQs promulgated by various authorities,indicating that all dioxin-like compounds should be evaluated in samples collected from e-waste-processing areas.Our findings suggest that open burning and open storage of e-waste should be prohibited and that wastewater treatment should be implemented at each workshop to reduce contamination by dioxin-like compounds from e-waste.

Hybrid model to optimize object-based land cover classification by meta-heuristic algorithm:an example for supporting urban management in Ha Noi,Viet Nam

This study proposed a novel object-based hybrid classification model named GMNN that combines Grasshopper Optimization Algorithm(GOA)and the multiple-class Neural network(MNN)for urban pattern detection in Hanoi,Vietnam.Four bands of SPOT 7 image and derivable NDVI,NDWI were used to generate image segments with associated attributes by PCI Geomatics software.These segments were classified into four urban surface types(namely water,impervious surface,vegetation and bare soil)by the proposed model.Alternatively,three training and validation datasets of different sizes were used to verify the robustness of this model.For all tests,the overall accuracies of the classification were approximately 87%,and the Area under Receiver Operating Characteristic curves for each land cover type was 0.97.Also,the performance of this model was examined by comparing several statistical indicators with common benchmark classifiers.The results showed that GMNN out-performed established methods in all comparable indicators.These results suggested that our hybrid model was successfully deployed in the study area and could be used as an alternative classification method for urban land cover studies.In a broader sense,classification methods will be enriched with the active and fast-growing contribution of metaheuristic algorithms.

Analysis of monomeric and oligomeric organophosphorus flame retardants in fish muscle tissues using liquid chromatographyeelectrospray ionization tandem mass spectrometry:Application to Nile tilapia(Oreochromis niloticus)from an e-waste processing area in northern Vietnam

Using electrospray ionization tandem mass spectrometry combined with liquid chromatography(LC),a novel analytical method was developed to quantify eight monomeric organophosphorus flame retardants(m-PFRs)and three oligomeric organophosphorus flame retardants(o-PFRs)in fish muscle samples.The optimization and validation experiments indicate that the developed method can determine accurately the concentrations of analytes in fish muscle samples.The recoveries of analytes in fish muscle samples were in the range of 74-105%.The coefficients of variation of the concentrations of analytes in fish muscle samples were 0.6-8.9%.The concentrations of analytes in procedural blanks were below the limit of quantification(LOQ)values.Furthermore,the developed method was applied to the analysis of m-PFRs and o-PFRs in the muscle samples of tilapias collected from an electronic waste(ewaste)processing area in northern Vietnam.The concentrations of m-PFRs such as tris(2-chloroethyl)phosphate(TCEP),tris(2-chloroisopropyl)phosphate(TCIPP),and triphenyl phosphate(TPHP)were dominant among the investigated m-PFRs.The respective concentrations of TCEP,TCIPP,and TPHP were up to 160,300,and 230 ng g^-1 lipid weight,respectively,whereas those of o-PFRs were up to 10 ng g^-1 lipid weight.The results of this study indicate lower accumulation potential of o-PFRs compared with m-PFRs for the first time.