Layer Parameters Research Articles

Delineation of Saline/Fresh Water Interface and Mapping Ground-water Potential Zones using Spatial Resistivity Models in Bichpuri Block Agra, District UP, India

Abstract Pin-pointing freshwater within saline formations is of utmost importance as filtration and alternate means of public water supply are responsible for high expenditure. Vertical Electrical Sounding (VES) (n=49) was conducted at various locations in the Bichpuri block, Agra district. In this study for VES, the Schlumberger configuration was used. VES data were reconciled with the borehole well log, and drill sample cuttings were utilized to understand sub-surface configuration. Reconciled VES data displayed variation in resistivity layer parameters, i.e., layer thickness & true resistivity of sub-surface. True resistivity spatial models were developed at 25m intervals from the ground surface down to the depth of 150m, based on geo-electric parameters. Resistivity models reveal that freshwater is limited to 55m depth, beyond which groundwater is saline to brackish. The basement was encountered at a depth of 120m and further extended up to 150m. A groundwater potential map was prepared using GIS and divided into 3 categories – good, moderate, and poor. Major habitations of the study area lie in poor groundwater potential zone, which is a cause of concern with the intent on future development. Similar studies can be extended to areas with saline groundwater for mapping freshwater zones.

CLIMF2: A climatological model of the ionospheric F2 layer. Part 1: Model methodology

The ionospheric F2 layer is of key importance to systems dependent on the propagation of radio waves through the ionosphere, including over-the-horizon (OTH) radar, high frequency (HF) communications, global navigation satellite systems (GNSS), and low-frequency radio astronomy. The currently accepted F2 layer model, the International Reference Ionosphere (IRI), does not provide the variance in the parameters used to describe the layer and furthermore, was developed from a limited dataset. The newly developed model, CLIMF2, can be used in conjunction with IRI to overcome these limitations, and thereby improve applications such as the climatological modelling of OTH radar performance. CLIMF2 is an empirical climatological model of the F2 layer parameters derived from a global network of vertical incidence sounder (VIS) observations, consisting of 267 sites with data from the 1950s to 2021. CLIMF2 has the added functionality of providing the variance in the foF2 and hmF2 parameters.

A New Approach to the Ionosphere at Middle and Low Latitudes under the Geomagnetic Quiet Time of December 2019 by ICON and GOLD Observations

It has been found that the total electron content (TEC) and the ionospheric electric fields indicated by the geomagnetic data showed inconsistent changes with each other at the mid- and low latitudes in both the American and the Asian–Australian sectors during geomagnetic quiet time (GQT) from 30 November to 8 December 2019 (Kpmax = 1.7). Meanwhile, the effects of thermospheric compositions are still indistinct. In this work, we analyze the mid/low-latitude ionospheric variations during this period, utilizing multi-instrument observations. The vertical drift velocities from the Ionospheric Connection Explorer (ICON) show significant variations and are in line with the changes in TEC at low latitudes in both of the two sectors. The zonal electric fields are supposed to play the main role in the TEC changes. This is also confirmed by the ionospheric F2 layer parameters data from the ionosonde stations at Sanya in the Asian–Australian sectors. The correlation between the variations in the geomagnetic H component (ΔH) and ionospheric F-layer electric fields can be affected by solar activity levels. The geomagnetic data ΔH sometimes may not indicate the magnitude of the electric fields in the F-region ionosphere under geomagnetic quiet conditions. The column density ratio of atomic oxygen (O) to molecular nitrogen (N2) (∑O/N2) from the Global Scale Observations of the Limb and Disk (GOLD) showed a strong enhancement at mid-latitudes in the American sector on 30 November. It is speculated that the neutral compositions should make a minor contribution to the changes in TEC during this event, compared with the electric fields.

Finger vein identification system using capsule networks with hyperparameter tuning

<p>Safety and security systems are essential for personnel who need to be protected and valuables. The security and safety system can be supported using a biometric system to identify and verify permitted users or owners. Finger vein is one type of biometric system that has high-level security. The finger vein biometrics system has two primary functions: identification and verification. Safety and security technology development is often followed by hackers' development of science and technology. Therefore, the science and technology of safety and security need to be continuously developed. The paper proposes finger vein identification using capsule networks with hyperparameter tuning. The augmentation, convolution layer parameters, and capsule layers are optimized. The experimental results show that the capsule network with hyperparameter tuning successfully identifies the finger vein images. The system achieves an accuracy of 91.25% using the Shandong University machine learning and applications-homologous multimodal traits (SDUMLA-HMT) dataset.</p>

Prediction of the wall pressure spectrum over a curved structure excited by a non-homogeneous turbulent boundary layer in water

In the present study, we introduce a volume approach based on the Poisson equation solved using a Green's function and a semi-analytical turbulence model in space domain. This model can be built from either a Reynolds-Averaged Navier-Stokes (RANS) simulation or an estimation of the boundary layer parameters. Predictions for the power spectral density of the wall pressure fluctuations are compared against measured data obtained for various flow conditions inside a cavitation tunnel. Two geometries are considered. First, we use a NACA 0012 hydrofoil of constant chord length to validate predictions for different flow velocities and angles of attack. Then, we consider a NACA 0009 hydrofoil with a spanwise varying chord length to investigate the contribution of three-dimensional effects.

An ensemble deep learning approach for untrained compound fault diagnosis in bearings under unstable conditions

Based on the dimension invariance property of the data-driven bearing fault diagnosis method, unstable condition data can result in the loss of information and reduced diagnostic accuracy due to inconsistent data dimensions. Furthermore, the fixed parameters of the output layer restrict its ability to accurately diagnose faults beyond the training set, particularly compound faults with limited data. To address these challenges, this study proposes an ensemble deep learning approach for identifying untrained compound faults in bearings operating under non-stationary conditions. Firstly, a signal angular domain processing technique is employed to standardize the dimensionality of the bearing’s state information, effectively mitigating information loss. Secondly, a feature extraction model is established to dynamically capture local microscopic and multilevel features utilizing the adaptability of convolutional neural network (CNN), and it can mine the relevant features of compound faults through the single-fault features. In the verification process, the kmeans algorithm with scalable classification is used to optimize the classifier of CNN. Specifically, the number of cluster centers in kmeans is set to exceed the count of training fault categories. Identification of untrained compound faults is achieved by calculating the Euclidean distances between each feature and the cluster centers, based on the principle of minimum distance. It addresses the challenge of inadequate diagnostic rates for untrained compound faults. The diagnostic outcomes prove that the proposed method has a high diagnostic robustness and generalization ability, which can effectively solve the problem of insufficient fault data and provide a new way of diagnosing untrained compound faults.

Effect of Cobalt Doping on The Structural, Linear and Nonlinear Optical Parameters of Manganese Oxide Thin Layers

AbstractIn this study, undoped and cobalt‐doped manganese oxide Co:Mn3O4 (0, 2, and 4 at%) are elaborated by the spray pyrolysis procedure on glass substrates. The effect of cobalt doping concentrations on the structural, morphological, and optical features (linear and nonlinear) are investigated through the X‐ray diffractometer, Raman spectroscopy, Scanning Electron Microscopy with an attached energy dispersive X‐ray and UV–Vis‐NIR spectrophotometer. The XRD investigations exhibit a polycrystalline tetragonal structure for all Co:Mn3O4 and confirm by Raman results with the distinctive tetragonal mode A1g at 657 cm−1. The SEM images show an increase in roughness as cobalt doping concentration increases. The EDS quantitative analysis revealed the presence of manganese, oxygen, and cobalt. Furthermore, the optical investigation is pursued firstly through the linear optical that showed a decrease in the transmittance, and optical band gap energy as the cobalt concentration increased due to oxygen vacancies and defects and the increase of refractive index from 2.05 to 2.21. Second, the nonlinear optical parameters show a high value of the nonlinear refractive index 3.75 × 10−7 (esu) and the third‐order susceptibility χ3 = 2.2 × 10−8(esu) of Co:Mn3O4(2at%). These values put the Co:Mn3O4(2at%) thin layer as a candidate in the optoelectronic applications as a third‐order nonlinear medium.

Geophysical Approach for Groundwater Resource Assessment: A Case Study of Oda Community Akure, Southwestern Nigeria

The geophysical investigation for groundwater was carried out at Oda town, Akure south local government area of Ondo State. Fourteen (14) points were sounded using a Schlumberger array with AB/2 of 80 m and the resulting geoelectric parameters were used in the estimation of the aquifer layer parameters of the subsurface. The first layer resistivity value ranges from 29 to 164 Ωm and thickness ranges from 0.6 to 2.5 m. The second layer has a resistivity value ranging from 21-1361 Ωm with a thickness ranging from 1.5 m to 14.6 m. The third layer resistivity value is from 68 to 297 Ωm with thickness ranging from 4 m to 12.4 m. The fourth layer which is the deepest layer has a resistivity value ranging from 180 to 4364 Ωm with depth ranging from 4 m to 19.5 m. The parameters interpreted from the geoelectric data were used to generate the aquifer thickness and resistivity maps, with bedrock relief which were combined to produce the groundwater potential map of the area. These maps were used to characterise the study area into low to high groundwater potential zones. The southwestern and eastern parts were identified as productive groundwater potential zones. The result was validated by taking water column depth from eight existing hand-dug wells. A significant correlation was obtained between the groundwater potential model and the well water column. The surveyed area is generally suitable for hand-dug well aside from the north-eastern part where groundwater potential is low and water volume is observed.

Electrical properties of silicon-implanted β-Ga2O3:Fe crystals

Ion implantation is a promising method for the development of β-Ga2O3-based technologies and devices. However, the physical principles of ion implantation for this particular semiconductor are still at the early stage of development. One of the primary tasks is the study of electrical properties of the ion-doped layers. In this work, we have investigated the electrical parameters of layers produced by ion implantation of a shallow donor impurity—silicon—into a semi-insulating β-Ga2O3 doped with iron and having a surface orientation of (−201). It is established that the activation efficiency of the implanted impurity significantly exceeds unity after post-implantation annealing at high temperatures. This indicates that not only silicon itself contributes to conductivity, but also defects formed with its (and, probably, iron) participation are involved. The temperature dependence of electron mobility is consistent with the theoretically calculated one under the assumption that, apart from shallow donors, there are also deep defect-associated donors and acceptors. It is assumed that the established properties are specific for the case of direct Si implantation into β-Ga2O3 doped with Fe.

Effect of Bergmeister papilla on disc parameters in spectral domain optical coherence tomography

ObjectivesTo investigate the morphological characteristics of Bergmeister papilla (BMP), a persistent hyaloid remnant tissue, and its effects on the measurements and repeatability of spectral-domain optical coherence tomography (OCT).Subjects/MethodsThe subjects of this prospective cross-sectional study including 83 patients with BMP and 76 unaffected individuals, all had open-angle structures. Images, including a 5-line raster and three consecutive optic disc cube scans centred on the optic disc, were acquired using the Cirrus high-definition OCT. BMP’s structural characteristics were classified based on the raster scan images, and repeatability of acquiring optic nerve head and retinal nerve fibre layer parameters acquisition was analysed by calculating the test-retest standard deviation (Sw), coefficient of variance (CV), and intraclass correlation coefficient.ResultsBMPs (n = 83) were categorised into lifting edge (LE) type (63.9%, n = 53), which partially covers the edge of the optic nerve head, and covering disc (CD) type (36.1%, n = 30), which completely covers the cupping area like a cap. The average cup-to-disc ratio (0.58 ± 0.21), vertical cup-to-disc ratio (0.55 ± 0.21), and cup volume (0.22 ± 0.22) of the CD type were lower than those of the LE type (0.66 ± 0.13, 0.64 ± 0.13, and 0.4 ± 0.27, respectively; all P < 0.05). Tolerability indices for repeatability of cup volume (Sw = 0.40 and CV = 0.36) and inferonasal (4 o’clock) retinal nerve fibre layer (Sw = 0.27 and CV = 0.25) in LE-type BMPs exceeded the cut-off value (0.22) and demonstrated stronger correlation with BMP location than that of the controls.ConclusionCaution should be exercised when interpreting OCT findings in eyes with BMP, as BMP can introduce a pitfall in OCT imaging.

Automatic shoreline detection by processing planview timex images using bi-LSTM networks

A new automatic shoreline detection method by using a bidirectional Long Short-Term Memory (bi-LSTM) Network that processes images column by column is presented. The model is trained on manually extracted shorelines from time-exposure video-images and is very robust against the selection of images for training. Thanks to the novelty of working with image columns, instead of with the whole image, the amount of labelled images for training is limited to a few tens or even less if the conditions are good. Moreover, this column approach makes the model to be robust to variable illuminated images and more easily interpretable, light and fast. There is a wide range of configuration parameters for the bi-LSTM layer by which the system works correctly, which facilitate to use the same network in different video stations. The highest accuracy is obtained by using CIELAB colour space. Without pre-processing the raw colour channels or defining a region of interest and without post-processing the obtained shorelines, the model demonstrates impressive accuracy with mean errors of 2.8 pixels (1.4 m) in Castelldefels and 1.7 pixels (0.85 m) in Barcelona. The method could also be effective for satellite shoreline detection by using as input channel the water index of the satellite detection techniques.

Vibration energy characters study of a soft-core beam system coupled through nonlinear coupling layers

To ascertain the potential impact of nonlinear coupling layers on the vibration control of composite beam systems, this study develops a vibration analysis model of a nonlinear coupling-layered soft-core beam system. Ascertain the accuracy of the vibration responses computed by the soft-core beam system using the Galerkin truncation method (GTM) in comparison to the results obtained through alternative methods. The correct calculation results indicate that nonlinear coupling layers are the cause of nonlinear phenomena in the soft-core beam system. Nonlinear coupling layers are responsible for nonlinear phenomena of the soft-core beam system, such as peak-jumping and the region with multiple continuous amplitudes, according to numerical results. To reduce vibrations in the soft-core beam system's resonance regions, reasonable parameters for the nonlinear coupling layers are advantageous. When the soft-core beam system is excited at a single frequency, the kinetic energy responses include converted values of nonlinear coupling layers. Using nonlinear coupling layers, it is possible to establish an effective parameter range for the vibration energy control of the soft-core beam system. The utilization of reasonable parameters in nonlinear coupling layers can effectively mitigate the vibration energy of a soft-core beam system that is excited at a single frequency. The soft-core beam system induces the desired energy transfer phenomena at specific time intervals and under particular conditions.

Mechanical Performance of Adhesive Connections in Structural Applications.

Adhesive bonding is an excellent candidate for realising connections for secondary structures in structural applications such as offshore wind turbines and installations, avoiding the risk and associated welding problems. The strength of the adhesive layer is an important parameter to consider in the design process it being lower than the strength capacity of the bonding material. The presence of defects in the adhesive materials undoubtedly influences the mechanical behaviour of bonded composite structures. More specifically, the reduction in strength is more pronounced as the presence of defects (voids) increases. For this reason, a correct evaluation of the presence of defects, which can be translated into damage parameters, has become essential in predicting the actual behaviour of the bonded joints under different external loading conditions. In this paper, an extensive experimental programme has been carried out on adhesively bonded connections subjected to Mode I and Mode II loading conditions in order to characterise the mechanical properties of a commercial epoxy resin and to define the damage parameters. The initial damage parameters of the adhesive layer have been identified according to the Kachanov-Sevostianov material definition, which is able to take into account the presence of diffuse initial cracking.

Seasonal Evolution of Stable Thermal Stratification in Central Area of Lake Ladoga

The complete climatic courses of the parameters of stable thermal stratification for the central part of Lake Ladoga, the largest European lake, are presented on the basis of empirical relationships, taking into account the physical processes governing water temperature variations. For the first time, the seasonal cycle of the surface water temperature, the temperature and the depth of the thermocline, and the hypolimnion temperature are calculated using the vertical profiles of the temperature obtained from the central area of Lake Ladoga. Temperature data are used for the period of in situ observations from 1897 to the present. The proposed functional forms of the temporal temperature cycle and the course of thermocline’s boundaries deepening are useful for examination and simulation of the heat vertical transport from air to water. Approximation curves for the parameters of heating and cooling periods were developed with high significant determination coefficients. Time dependencies of the climatic rates of change in water temperature and the depth of the thermocline boundaries were determined from the onset of stable stratification to its dissipation. The highest rate of water temperature change in the heating stage takes place in late June–early July, which at the water surface, is 0.32 °C/day, while in the thermocline layer, it is 0.18 °C/day. The peak velocity during the cooling stage at the surface occurs in late August–early September and is 0.14 °C/day, whereas in the thermocline, it is 0.08 °C/day and takes place between September and early October. During the period of heating, the deepening parameters of the thermocline layer do not fluctuate very much, only within the range of 0.1–0.3 m/day. During the cooling period, under the influence of free convection, rates increase drastically. The maximum rates of deepening during the period of full autumn mixing reach 1.8 m/day. When the autumn overturn occurs, the epilimnion thickness equals the bottom depth, and the bottom temperature reaches its maximum during the annual cycle. Climatic norms of the stratification parameters against which it is necessary to assess climate change are calculated.

Multi-layer additive manufacturing on nickel-based superalloy by optimization of pulsed mode process parameters of single-layer bead geometry

Recent advancements in the wire arc additive manufacturing (WAAM) process for nickel-based superalloys have had a substantial impact on metal additive manufacturing industries such as aerospace, energy, and construction. The input process parameters influence the WAAM part's dimensional accuracy, process stability, and other critical impacts. The quality of each weld layers in WAAM can be controlled by various process parameters. In this study, a single-layer bead was deposited from Hastelloy C-22 using the pulsed mode gas tungsten arc welding (PC-GTAW) process. The chosen input process parameters include pulse frequency (X1), peak current (X2), and pulse on time (X3). The design of experiments (DoE) statistical quality tool was used to optimize the parameters, and the response surface m`ethodology (RSM) technique was used to develop the design matrix. The experiments were conducted based on central composite design (CCD), and their resulting responses bead width (Y1), height (Y2), and depth of penetration (Y3) were evaluated using optical microscopy. The results of the geometrical analysis have revealed a significant correlation between the characteristics of the layer and the parameters of the process. The analysis of variance (ANOVA) method was employed to verify the validity of the actual and predicted models. The model was experimentally validated using the established optimal process parameters, and the mechanical and metallurgical performance was evaluated. The microstructure of the single-layer exhibits equiaxed, cellular, and columnar structures at various regions. The pulse mode process was found to effectively reduce elemental segregation, improve the microstructure, and enhance the mechanical properties of the weld layer. The multi-layer experiments were carried out using the optimal process parameters of a single layer. According to metallographic investigations, the multi-layer that has been deposited exhibits a lack of cracks and porosity. This study provides new insights into the stabilized properties necessary to achieve optimal process parameters and metallurgical characteristics in the robust wire arc additive manufacturing of Hastelloy C-22.

Application of Vertical Electrical Sounding (VES) for the Determination of Water-Bearing Zone in Karaworo, Lokoja Kogi State, Nigeria

The importance of water in our various communities and the difficulties faced so far to get good and clean water for both domestic consumption and industrial purposes can never be overemphasized. For these purposes to be accomplished, it is necessary to survey the area of study to know more about the geology of the area, which is characterized by the Lokoja Formation, Patti Formation, and Agbaja Ironstone and the possible reasons why there is a lack of water in the area. The geoelectric survey was conducted at Karaworo with the objective of determining the sedimentary formation's geoelectrical features and analyzing the potential of the groundwater in the study area. The most frequently used type of array for Vertical Electrical Sounding (VES) is the Schlumberger array, which needs a lot of space at both ends to yield deeper subsurface information. The Schlumberger configuration was used for data acquisition. About fifteen (15) VES points were acquired at different locations within the study area. For the different VES positions, the maximum AB/2 is within 100m to 180m. Partial curve matching was used to determine the layer parameters as part of the quantitative interpretation of the VES curves. The IP2WIN software was used in the final data analysis. The depth sounding interpretation revealed subsurface layers which comprises of topsoil/clay with a resistivity range between 1.42 ohm-m to 81.0ohm-m and a thickness of 0.253 m to 70.4 m, lateritic clay with a resistivity range between 01.06ohm-m to 1730 ohm-m and a thickness of 0.236 m to 19.2 m, siltstone with resistivity range between 0.423 ohm-m to 5069 ohm-m and a thickness of 4.09 m to 28 m and sandstone with resistivity range between 0.664 ohm-m to 137 ohm-m with the thickness at infinity. Sandstone constituted the aquiferous zone. In conclusion, different types of curves which include HA-type, H-type, KH-type, QH-type and HAK-type characterize the area and hence it is suggested that boreholes be placed in low resistivity zones and considerable depth and thickness as revealed in VES 4 and VES 8 but those with low resistivity without considerable depth, for example, VES 2, VES 5, VES 6, VES 7, etc. can be developed into a hand dug well.

Scientific Basis for the Substantiation of Process Regulations for the Micro-Cutting of Hardened Gears

Abstract The paper considers scientific principles of technological procedure development for the selection and assignment of parameters of velocity machining by blade tool at gear milling with due regard to the required parameters of the gear surface layer. Optimum micro-cutting conditions are determined when full participation in stock removal of all mill teeth is provided. Technological regulation of selection and setting of machining parameters is spread for gear hobbing of the spur gear wheels with fine-modular and coarse-modular hardness (220...320 HV) and after heat treatment (HRC46...63). Correlation with essential parameters of the surface layer, cutting depth, feed, speed and radius of rounding of the cutting edge of milling cutters’ teeth is established. It is scientifically grounded, tested, and proved at what modes of cutting, the radius of rounding of cutting edge of the cutting tool is made metal removal at oncoming and passing high-speed micro milling. The process of determining of minimal sliding angle, or maximum value (without the use of coolant and with coolant), in which there is no micro-cutting process taking into account variation of variable parameters of cutting conditions and geometrical parameters of hobbing cutters is modelled. For the first time, we ascertained the relation between the sliding angle and the maximum contact angle of the mill tooth with the work surface, which allowed determine the efficiency of the shaping process through coefficient (without coolant and with coolant).

Fault diagnosis method of multi-rotor UAV based on one-dimensional convolutional neural network with adaptive batch normalization algorithm

In this paper, we propose a one-dimensional convolutional neural network model based on the adaptive batch normalization (AdaBN) algorithm to improve the CNN model, which is difficult to extract features from multi-rotor unmanned aerial vehicle (UAV) rotor structural faults under variable conditions and has poor fault diagnosis performance. The method accomplishes fault diagnosis and classification by feature extraction from lower dimensional multi-rotor UAV data. The AdaBN algorithm adjusts the parameters of the BN layer in the model during the testing phase to improve the domain adaptive capability of the model in scenarios with variable operating conditions. Also, to improve the robustness of the model under noisy conditions, the first layer of convolutional kernel dropout operation is introduced to improve the noise immunity of the model. To reduce the complexity of manual tuning and to find the optimal combination of hyperparameters for the network model more effectively, the grey wolf optimizer algorithm is used to optimize the hyperparameters and further improve the model performance. Finally, the effectiveness of the proposed method is verified through comparison tests, and it shows good diagnostic effects in noise and variable conditions compared with several commonly used fault diagnosis methods.

Vision Image Monitoring on Transportation Infrastructures: A Lightweight Transfer Learning Approach

Vision monitoring of distress has emerged as a new trend in intelligent transportation infrastructure systems, including roads and bridges. Recently, transfer learning methods and lightweight networks have been used to realize efficient distress identification without large amount of human-labor work. This paper proposed an engineering approach that integrated transfer learning with lightweight models to classify and detect concrete bridge distresses. Two datasets named Distress Dataset of Asphalt Pavement (DDAP) with 2500 asphalt pavement distresses images and Distress Dataset of Concrete Bridge (DDCB) with 906 concrete bridge distresses images were used. The lightweight models MobileNet and MobileNet-SSD were employed to conduct 6 comparative experiments for exploring the model performance with different transfer learning modes (Mode I and II) and procedures (one-step and two-step procedure) in classification and detection tasks. Based on the comparison of the results, the optimum model for two tasks was respectively recognized. For classification task, the model directly transferred specific parameters of partial convolution layers from ImageNet-based model achieved the highest accuracy of 97.8%. For detection task, the two-step transfer learning model using an intermediate transfer learning step trained by DDAP reached a mean average precision of 87.16%. The proposed approach has the application potential for practical road inspection work in intelligent transportation infrastructure maintenance.

Multi-objective Stochastic Gradient Based ADR Mechanism for Throughput and Latency Optimization in LoRaWAN

Background: In Long Range Wide Area Networks (LoRaWAN), the goal of Adaptive Data Rate (ADR) is to allocate resources to End Devices (ED) like Transmission Power (TP) and Spreading Factor (SF). The EDs are designed in a way that they can choose optimal configuration resource parameters from a set of LoRa physical layer parameters. The SF parameter has to be chosen correctly, as an incorrect one may cause collisions and interference if multiple nodes have the same SF. This paper focuses on throughput and latency optimization using an effective ADR mechanism for LoRaWAN-based IoT networks. Objective: The objective of this study is to maximize the total throughput. SF should be used by multiple nodes as it will have less Time on Air (ToA), but it may cause collision, contention, and co-spreading factor interference problems. The idea is to find an optimal SF allocation to end devices and the optimal number of total devices using the same SF to avoid collision and interference. Methods: This paper proposes a multi-objective stochastic gradient descent method to solve the constrained optimization problem for optimizing throughput and latency. Results: This work compares throughput and latency results for the static, quasi-static, and dynamic environments. Trade-offs between latency and throughput for the simulated scenarios are also presented. Conclusion: The simulation results show that the throughput obtained using this technique is higher than the naive ADR approach and the existing gradient descent methods.