Accuracy Of System Research Articles

Online transaction fraud detection in the banking sector using machine learning techniques

In this paper Nowadays, online transactions are increasing rapidly and payment scams are also increasing. A hacker is a person who gains access to another person's financial information. Improving feature selection is important to detect transaction risk in large, multidimensional data. Fraud detection and classification performance is divided into two parts: training data and test data. During this process we have focused on data analysis and pre-processing. In a transaction’s dataset, the predictive variables influence how well a machine learning algorithm for transaction risk identification classifies and identifies fraudulent transactions. This study examines the application of machine learning techniques in improving fraud detection in the banking industry. Using advanced algorithms and historical transaction data, the model aims to identify anomalous patterns that indicate fraudulent activity. Feature engineering, ensemble methods, and anomaly detection algorithms are used to improve the accuracy and performance of fraud detection systems. reducing false positives and provides an adaptive security mechanism. By harnessing the power of machine learning, this approach aims to strengthen the banking sectors defines against sophisticated fraud schemes. This study not only contributes to the academic understanding of fraud detection, but also provides industry practitioners with a practical framework for implementing proactive measures. In navigating the complex landscape of financial security, this research serves as a guide for building agile and responsive systems that stay ahead of the threats that evolve in the ever-changing landscape of the banking industry.

Accuracy Validation of a Sensor-Based Inertial Measurement Unit and Motion Capture System for Assessment of Lower Limb Muscle Strength in Older Adults-A Novel and Convenient Measurement Approach.

(1) Background: The aim of this study was to assess lower limb muscle strength in older adults during the transfer from sitting to standing (STS) using an inertial measurement unit (IMU). Muscle weakness in this population can severely impact function and independence in daily living and increase the risk of falls. By using an IMU, we quantified lower limb joint moments in the STS test to support health management and individualized rehabilitation program development for older adults. (2) Methods: This study involved 28 healthy older adults (13 males and 15 females) aged 60-70 years. The lower limb joint angles and moments estimated using the IMU were compared with a motion capture system (Mocap) (pair t-test, ICC, Spearman correlations, Bland-Altman plots) to verify the accuracy of the IMU in estimating lower limb muscle strength in the elderly. (3) Results: There was no significant difference in the lower limb joint angles and moments calculated by the two systems. Joint angles and moments were not significantly different (p > 0.05), and the accuracy and consistency of the IMU system was comparable to that of the Mocap system. For the hip, knee, and ankle joints, the ICCs for joint angles were 0.990, 0.989, and 0.885, and the ICCs for joint moments were 0.94, 0.92, and 0.89, respectively. In addition, the results of the two systems were highly correlated with each other: the r-values for hip, knee, and ankle joint angles were 0.99, 0.99, and 0.96, and the r-values for joint moments were 0.92, 0.96, and 0.85. In the present study, there was no significant difference (p > 0.05) between the IMU system and the Mocap system in calculating lower limb joint angles and moments. (4) Conclusions: This study confirms the accuracy of the IMU in assessing lower limb muscle strength in the elderly. It provides a portable and accurate alternative for the assessment of lower limb muscle strength in the elderly.

Case-Based Deduction for Entailment Tree Generation

Maintaining logical consistency in structured explanations is critical for understanding and troubleshooting the reasoning behind a system’s decisions. However, existing methods for entailment tree generation often struggle with logical consistency, resulting in erroneous intermediate conclusions and reducing the overall accuracy of the explanations. To address this issue, we propose case-based deduction (CBD), a novel approach that retrieves cases with similar logical structures from a case base and uses them as demonstrations for logical deduction. This method guides the model toward logically sound conclusions without the need for manually constructing logical rule bases. By leveraging a prototypical network for case retrieval and reranking them using information entropy, CBD introduces diversity to improve in-context learning. Our experimental results on the EntailmentBank dataset show that CBD significantly improves entailment tree generation, achieving performance improvements of 1.7% in Task 1, 0.6% in Task 2, and 0.8% in Task 3 under the strictest Overall AllCorrect metric. These findings confirm that CBD enhances the logical consistency and overall accuracy of AI systems in structured explanation tasks.

Effects of varying mixing ratios of components A and B on optical liquid silicone rubber

AbstractThe processing of optical liquid silicone rubber (LSR) formulations is associated with significant quality issues and high rejection rates. Often, the quality issues can be attributed to deviations in LSR dosing. To address these issues, specific mixing ratios of components A and B that deviate from the standard 1:1 ratio were intentionally created. These mixtures were characterized via differential scanning calorimetry, rheometer, and Fourier‐transform infrared spectroscopy. The mixtures were then processed via injection molding and mechanical properties such as shrinkage, density, hardness, and tensile properties were determined and analyzed. The results show that deviating mixing ratios for optical LSR have a significant influence on processing in terms of shifts in cross‐linking temperature and exothermic energy released, viscosity, and cavity pressure, as well as on the final component properties in terms of varying shrinkage, density, hardness, tensile strength, and elongation at break. This study shows that even small deviations have a major influence and should therefore be avoided. The requirements for the accuracy of the dosing system with regard to the mixing ratio must therefore be very high. In practice, such deviations in the mixing ratios are most likely to be detected in geometry via shrinkage, hardness, or tensile properties.Highlights More component A leads to faster but less dense cross‐linking Component B can be characterized by Fourier‐transform infrared spectroscopy via Si–H bending band at 905 cm−1. More component B leads to higher shrinkage, density, hardness, and strength. Deviations in the mixing ratio must be avoided as they lead to drastic changes. A general shift of the mixing ratio in favor of component B is less dramatic.

DGD-CNet: Denoising Gated Recurrent Unit with a Dropout-Based CSI Network for IRS-Aided Massive MIMO Systems.

For the deployment of Sixth Generation (6G) networks, integrating Massive Multiple-Input Multiple-Output (Massive MIMO) systems with Intelligent Reflecting Surfaces (IRS) is highly recommended due to its significant benefits in reducing communication losses for Non-Line-of-Sight (NLoS) conditions. However, the use of passive IRS presents challenges in channel estimation, mainly due to the significant feedback overhead required in Frequency Division Duplex (FDD)-based Massive MIMO systems. To address these challenges, this paper introduces a novel Denoising Gated Recurrent Unit with a Dropout-based Channel state information Network (DGD-CNet). The proposed DGD-CNet model is specifically designed for FDD-based IRS-aided Massive MIMO systems, aiming to reduce the feedback overhead while improving the channel estimation accuracy. By leveraging the Dropout (DO) technique with the Gated Recurrent Unit (GRU), the DGD-CNet model enhances the channel estimation accuracy and effectively captures both spatial structures and time correlation in time-varying channels. The results show that the proposed DGD-CNet model outperformed existing models in the literature, achieving at least a 26% improvement in Normalized Mean Square Error (NMSE), a 2% increase in correlation coefficient, and a 4% in system accuracy under Low-Compression Ratio (Low-CR) in indoor situations. Additionally, the proposed model demonstrates effectiveness across different CRs and in outdoor scenarios.

Fatigue Analysis of Shovel Body Based on Tractor Subsoiling Operation Measured Data

This paper aims to investigate the effects of soil penetration resistance, tillage depth, and operating speeds on the deformation and fatigue of the subsoiling shovel based on the real-time measurement of tractor-operating conditions data. Various types of sensors, such as force, displacement, and angle, were integrated. The software and hardware architectures of the monitoring system were designed to develop a field operation condition parameter monitoring system, which can measure the tractor’s traction force of the lower tie-bar, the real-time speed, the latitude and longitude, tillage depth, and the strain of the subsoiling shovel and other condition parameters in real-time. The time domain extrapolation method was used to process the measured data to obtain the load spectrum. The linear damage accumulation theory was used to calculate the load damage of the subsoiling shovel. The magnitude of the damage value was used to characterize the severity of the operation. The signal acquisition test and typical parameter test were conducted for the monitoring system, and the test results showed that the reliability and accuracy of the monitoring system met the requirements. The subsoiling operation test of the system was carried out, which mainly included two kinds of soil penetration resistances (1750 kPa and 2750 kPa), three kinds of tillage depth (250 mm, 300 mm, and 350 mm), and three kinds of operation speed (4 km/h low speed, 6 km/h medium speed, and 8 km/h high speed), totaling 18 kinds of test conditions. Eventually, the effects of changes in working condition parameters of the subsoiling operation on the overall damage of subsoiling shovels and the differences in damage occurring between the front and rear rows of subsoiling shovels under the same test conditions were analyzed. The test results show that under the same soil penetration resistance, the overall damage sustained by the subsoiling shovels increases regardless of the increase in the tillage depth or operating speed. In particular, the increase in the tillage depth increased the severity of subsoiling shovel damage by 19.73%, which was higher than the 17.48% increase due to soil penetration resistance and the 13.07% increase due to the operating speed. It should be noted that the front subsoiling shovels consistently sustained more damage than the rear, and the difference was able to reach 16.86%. This paper may provide useful information for subsoiling operations, i.e., the operational efficiency and the damage level of subsoiling shovels should be considered.

Vibration Friction Investigation on the NCS of Joints of the CNC Machine Tools Considering Friction Factor

Machine tool vibrations play a significant role in hindering productivity during machining. The growing vibrations accelerate tool wear and chipping, cause a poor wave surface finish, and may damage the spindle bearing. Some research showed that tribological properties such as friction factors can have obvious influences on the topography of rough surfaces and the nonlinear dynamic characteristics of machine tool systems. Therefore, studying the vibration friction dynamic characteristics on the normal contact stiffness (NCS) of joints of CNC machine tools is absolutely necessary for improving the machining accuracy and precision of the whole system. The study results of NCS of joints of the CNC and the friction coefficient are discussed in this paper. The model of NCS based on fractal parameters was obtained. The models of deformations of the rough surfaces and contact surfaces were deduced. The results showed that the NCS based on the calculation method considering the elastic–plastic deformation of the asperity is much higher in precision than the methods considering only elastic or plastic deformation separately. The observations this paper described suggest that in the CNC machine tools system, higher D and G and higher friction coefficients lead to higher normal contact stresses (NCSs).

Formation mechanism and luminescence properties of silicon carbide nanowires with core-shell structure

For the preparation of SiC nanowires (SiC NWs) by carbothermal reduction, it is of great significance to study the formation mechanism of sic nanowires for process optimization and the controllable preparation. Although first-principles molecular dynamics (FPMD) can simulate systems of hundreds of atoms on a picosecond time scale, the results of FPMD are still insufficient to elucidate the formation mechanism of core-shell SiC nanowires. To make up this deficiency, this article has conducted Deep Potential Molecular Dynamics (DPMD) simulation on nanoseconds timescales with near FPMD accuracy for systems containing thousands of atoms, the results more concretively show the formation process of core-shell SiC nanowires. DPMD simulation results show when CO molecules react with SiO molecules, CO molecules are wrapped by SiO molecules to form agglomerates, SiO molecules in the agglomerates that can come into contact with the wrapped CO molecules will react with wrapped CO molecules to form the SiC core, and SiO molecules that in the outer layer of the agglomerates will disproportionate into the amorphous SiO2 shell. Furthermore, the formation mechanism of SiC nanowires was validated in combination with thermodynamics and experimental methods. Thermodynamic results show that vacuum conditions are favorable for the formation of SiO and CO and lower the temperature of SiC preparation. Finally, the core-shell structure of SiC NWs with good luminescence properties were successfully prepared by carbothermal reduction method using carbon black and silicon dioxide as raw materials under the pressure of less than 5 kPa.

A novel color-aided system for diagnosis of early gastric cancer using magnifying endoscopy with narrow-band imaging.

The Pink Zone Pattern (PP) sign is a typical color alteration of early gastric cancer (EGC) under magnifying endoscopic narrow-band imaging (ME-NBI). By integrating the color changes (PP sign) with the "vessel plus surface (VS)" classification system, we developed an innovative diagnostic system for EGC and named it "Pink Microsurface Microvascular (PSV)" system. Here, we aimed to elucidate the diagnostic performance of the PSV system for EGC. We conducted a single-center prospective clinical study (before-after design) consisting of 2 cross-sectional studies at 2 separate periods. In the before phase, 184 suspected lesions were evaluated using the VS system under ME-NBI; in the after phase, 183 suspected lesions were evaluated using the PSV system. We compared the diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) between the VS group and the PSV group. The accuracy, sensitivity, specificity, PPV, and NPV of the VS system for EGC were 84.6%, 87.0%, 83.6%, 67.8%, and 94.2%, respectively, and those for the PSV system were 93.0%, 92.0%, 93.4%, 85.2%, and 96.6%, respectively. The accuracy, specificity, and PPV of the PSV system were superior to those of the VS system. However, the sensitivity and NPV did not significantly differ between the VS system and the PSV system. The VS system was inconclusive for 22 lesions (12.0%) and the PSV system was inconclusive for 11 lesions (6.0%). The PSV system could identify more suspicious lesions than the VS system. We propose a new PSV diagnostic system by combining the VS system and the PP sign. Compared with the VS system, the PSV system could identify more suspected lesions and improve the diagnostic performance of EGC.

Design and Implementation of Touch Display Accuracy Optimization Software Based on Deep Learning

This paper mainly introduces the touch display accuracy optimization software based on convolutional neural network to enhance the touch accuracy of the smart board system. Convolutional neural networks are used to train touch data, which enables the software to automatically correct the position of touch points and reduce touch bias. The system architecture includes a data acquisition module, a deep learning model training module, and a touch accuracy optimization module, which is expected to be applied to more fields with the continuous application and development of technology. On the whole, the launch of the software provides a new technical way to realize the smart board book system.

Examining the accuracy of an unmediated OER course marking system

As the open educational resources (OER) textbook movement continues to grow in the United States, librarians and other campus advocates are working to help students reduce course costs by identifying courses using free OER textbooks in lieu of commercial textbooks. The systems used for marking which courses are using OER are variable in their design and not always consistent in how they mark materials. This study investigates one OER course marking system at a public university in Texas. Specifically, it examines courses marked as using only OER to determine how accurately the course marker reflects the materials assigned on course syllabi. Study findings reveal that there are substantial discrepancies between the course marking designation and the actual materials used. This finding has implications for students relying on course marking systems to make registration decisions. It also has implications for librarians and administrators assessing the impact of campus textbook affordability efforts.

A Robust Tri-Electromagnet-Based 6-DoF Pose Tracking System Using an Error-State Kalman Filter.

Magnetic pose tracking is a non-contact, accurate, and occlusion-free method that has been increasingly employed to track intra-corporeal medical devices such as endoscopes in computer-assisted medical interventions. In magnetic pose-tracking systems, a nonlinear estimation algorithm is needed to recover the pose information from magnetic measurements. In existing pose estimation algorithms such as the extended Kalman filter (EKF), the 3-DoF orientation in the S3 manifold is normally parametrized as unit quaternions and simply treated as a vector in the Euclidean space, which causes a violation of the unity constraint of quaternions and reduces pose tracking accuracy. In this paper, a pose estimation algorithm based on the error-state Kalman filter (ESKF) is proposed to improve the accuracy and robustness of electromagnetic tracking systems. The proposed system consists of three electromagnetic coils for magnetic field generation and a tri-axial magnetic sensor attached to the target object for field measurement. A strategy of sequential coil excitation is developed to separate the magnetic fields from different coils and reject magnetic disturbances. Simulation and experiments are conducted to evaluate the pose tracking performance of the proposed ESKF algorithm, which is also compared with standard EKF and constrained EKF. It is shown that the ESKF can effectively maintain the quaternion unity and thus achieve a better tracking accuracy, i.e., a Euclidean position error of 2.23 mm and an average orientation angle error of 0.45°. The disturbance rejection performance of the electromagnetic tracking system is also experimentally validated.

An identification method of LBL underwater positioning systematic error with optimal selection criterion

Unlike the space targets such as satellites whose observation distance is about the order of 100 km, the measurement distance of long baseline (LBL) underwater positioning system is much shorter. If the noncoincidence between the multiple beacons and the target center is not considered, this systematic error will cause a little larger positioning error. Therefore, aiming at the situation that multiple beacons are installed outside the target and the distance between the beacons and the target center is significant, a multi-beacon positioning model of the LBL underwater system is constructed in this paper. Furthermore, for the sound speed systematic error and the time of arrival (TOA) systematic error in the multi-beacon LBL system positioning measurement data, three identification models of systematic error are constructed. According to the positioning process of the LBL underwater system, the expression of the optimal test statistic D is derived based on the TOA residual. Finally, the optimal selection criterion is given, and the underwater target position and systematic error can be accurately estimated. Both of the numerical simulation and the underwater positioning test show that the appropriate identification model of systematic error in the measurement data can be selected according to the optimal selection criterion, and the underwater target positioning accuracy of the LBL system can be improved.

Validation of DDC-3D code system for neutronics and thermal-hydraulics coupling analysis using BEAVRS benchmark

The direct whole-core calculations can provide accurate results and insights to the physics phenomena of the reactor. It can also capture the local effects of temperature and density fields on fuel depletion. However, the computational cost of the direct whole-core calculations is expensive. To compromise between computational cost and accuracy, the DDC-3D code system has been developed to perform neutronics and thermal-hydraulics coupling analysis. The DDC-3D code system couples the open-source codes DRAGON & DONJON based on two-step method and subchannel code COBRA-EN. The Picard iteration method is applied to ensure the stability of numerical calculation. Then the BEAVRS benchmark is used to validate the computational capabilities of DDC-3D code system. The critical boron concentrations, control rod worths and fission rate distributions are calculated in HZP condition. The results show a good agreement with measured data. The results demonstrate that the two-step method is applicable and valid for multiphysics simulations. For the result of HFP condition for cycle 1, the results also agree well with measured data, including the trend of the critical boron concentrations and power distributions throughout the cycle 1. Although the detailed thermal–hydraulic experimental values are not available, the thermal-hydraulics analysis of the hot fuel assemblies indicates that the calculation results are reasonable. In general, the results demonstrate the feasibility and accuracy of DDC-3D code system for neutronics and thermal-hydraulics coupling calculations and life cycle simulation of PWRs.

Experimental validation and analysis of hybrid adaptive iterative learning sliding mode control for PMSM seeker coordinator

High-order nonlinearity, strong coupling, and external disturbances constrain the high-precision servo tracking control of the missile seeker coordinator, which compromises the guidance accuracy of guided weapons. The individual differences in the seekers cause model parameter perturbations, leading to uncertainty and time-varying disturbances, which reduces the tracking performance of the seeker servo system. To cope with these uncertainties various traditional Iterative learning control (ILC) strategies have been designed to suppress high-order nonlinear disturbances. However, these are very sensitive to system uncertainties, external disturbances and model parametric perturbations. In response to this challenge, this paper proposes a hybrid adaptive iterative learning sliding mode control (AILS) methodology. The iterative learning sliding mode control (ILSMC) strategy is used to reduce the impact of periodic disturbances in the system, ensuring a rapid system response. The enhanced adaptive learning law (EAL) strategy offers an estimation of the lumped disturbances of the system, encapsulating both parameter shifts and residual disturbances. Through this appropriate adaptive control, both disturbances compensation and the chattering effect due to sliding mode control are simultaneously minimized. Simulation and experimental results show that compared with the traditional open-loop iterative learning control, the learning convergence speed and convergence accuracy of the proposed hybrid AILS are highly significant. Experimental results also show that the control algorithm designed in this paper can also perform adaptively, has fast learning capability and ensures convergence while guaranteeing the tracking accuracy of the seeker coordinator servo system.

Accuracy of Speech Sound Analysis: Comparison of an Automatic Artificial Intelligence Algorithm With Clinician Assessment.

Automatic speech analysis (ASA) and automatic speech recognition systems are increasingly being used in the treatment of speech sound disorders (SSDs). When utilized as a home practice tool or in the absence of the clinician, the ASA system has the potential to facilitate treatment gains. However, the feedback accuracy of such systems varies, a factor that may impact these gains. The current research analyzes the feedback accuracy of a novel ASA algorithm (Amplio Learning Technologies), in comparison to clinician judgments. A total of 3,584 consonant stimuli, produced by 395 American English-speaking children and adolescents with SSDs (age range: 4-18 years), were analyzed with respect to automatic classification of the ASA algorithm, clinician-ASA agreement, and interclinician agreement. Further analysis of results as related to phoneme acquisition categories (early-, middle-, and late-acquired phonemes) was conducted. Agreement between clinicians and ASA classification for sounds produced accurately was above 80% for all phonemes, with some variation based on phoneme acquisition category (early, middle, late). This variation was also noted for ASA classification into "acceptable," "unacceptable," and "unknown" (which means no determination of phoneme accuracy) categories, as well as interclinician agreement. Clinician-ASA agreement was reduced for misarticulated sounds. The initial findings of Amplio's novel algorithm are promising for its potential use within the context of home practice, as it demonstrates high feedback accuracy for correctly produced sounds. Furthermore, complexity of sound influences consistency of perception, both by clinicians and by automated platforms, indicating variable performance of the ASA algorithm across phonemes. Taken together, the ASA algorithm may be effective in facilitating speech sound practice for children with SSDs, even in the absence of the clinician.

Monitoring and Predicting Air Quality with IoT Devices

The growing concern about air quality and its influence on human health has prompted the development of sophisticated monitoring and forecast systems. This article gives a thorough investigation into forecasting the air quality index (AQI) with an Internet of Things (IoT) device that analyzes temperature, humidity, PM10, and PM2.5 levels. The dataset used for this analysis comprises 5869 data points across six critical parameters essential for accurate air quality prediction. The data from these sensors is sent to the ThingSpeak cloud platform for storage and preliminary analysis. The system forecasts AQI using a TensorFlow-based regression model, delivering real-time insights. The combination of IoT technology and machine learning improves the accuracy and responsiveness of air quality monitoring systems, making it a useful tool for environmental management and public health protection. This work presents comparatively the effectiveness of feedforward neural network models trained with the ‘adam’ and ‘RMSprop’ optimizers over different epochs, as well as the machine learning algorithm random forest with varying numbers of estimators to forecast AQI. The models were trained using both types of regression analysis: linear regression and random forest regression. The findings show that the model achieves a high degree of accuracy, with the predictions closely aligning with the actual AQI values, thus having the potential to significantly reduce the negative health impact associated with poor air quality, protecting public health and alerting users when pollution levels are higher than allowed. Specifically, the random forest model with 100 estimators delivers the best overall performance for both AQI 10 and AQI 2.5, achieving the lowest Mean Absolute Error (MAE) of 0.2785 for AQI 10 and 0.2483 for AQI 2.5. This integration of IoT technology and advanced predictive analysis addresses the significant worldwide issue of air pollution by identifying the pollution hotspots and allowing decision-makers for quick reactions, and the development of effective strategies to reduce pollution sources.

Development of an alternative method to quantify H2S: application in wine fermentation.

A colorimetric method for the quantification of hydrogen sulfide (H₂S) produced in microbial fermentations was developed using lead gelled alginate microparticles packed in glass columns. The formation of a lead sulfide complex, between H₂S and lead ion (Pb2+) immobilized on the microparticles, allowed simple and accurate quantification by colorimetry. The microparticle-loaded columns were calibrated and showed significant analytical sensitivity. The calibration curve of the system showed a correlation coefficient (r2) of 0.995 and a detection limit of 1.29 ± 0.02 μg L-1. The application of the columns in laboratory wine fermentations was able to detect variations in H2S production from 10.6 to 23.5 μg L-1 by increasing the sugar content in the medium, and from 10.6 to 3.2 μg L-1 with decreasing nitrogen content in the medium. Validation of the proposed method was carried out by determining H₂S in a vinic fermentation model, the results of which were compared with those obtained using a reference chemical method. The data obtained showed no statistically significant differences between the two methods, confirming the reliability and accuracy of the developed system. © 2024 Society of Chemical Industry.

Developing a Microsatellite Polymerase Chain Reaction System for Small Yellow Croaker (Larimichthys polyactis) and Its Application in Parentage Assignment.

(1) Background: The small yellow croaker, an economically important fish in East Asia, has been subjected to population declines due to overfishing and environmental pressures. The development of effective breeding programs is considered crucial for the species, and accurate parentage assignment is deemed essential for such programs. (2) Methods: The assembled reference genome of the small yellow croaker was utilized to select highly polymorphic microsatellite markers. A multiplex PCR system was optimized for the simultaneous amplification of these markers. The system's accuracy was validated using controlled mating pairs and subsequently applied to a group mating scenario. (3) Results: The developed multiplex PCR system demonstrated high accuracy in assigning offspring to their parents in both the controlled and group mating scenarios. (4) Conclusions: The system is presented as a valuable tool for pedigree management, selective breeding, and conservation efforts for the small yellow croaker, facilitating sustainable aquaculture practices and genetic improvement.

AVaTER: Fusing Audio, Visual, and Textual Modalities Using Cross-Modal Attention for Emotion Recognition.

Multimodal emotion classification (MEC) involves analyzing and identifying human emotions by integrating data from multiple sources, such as audio, video, and text. This approach leverages the complementary strengths of each modality to enhance the accuracy and robustness of emotion recognition systems. However, one significant challenge is effectively integrating these diverse data sources, each with unique characteristics and levels of noise. Additionally, the scarcity of large, annotated multimodal datasets in Bangla limits the training and evaluation of models. In this work, we unveiled a pioneering multimodal Bangla dataset, MAViT-Bangla (Multimodal Audio Video Text Bangla dataset). This dataset, comprising 1002 samples across audio, video, and text modalities, is a unique resource for emotion recognition studies in the Bangla language. It features emotional categories such as anger, fear, joy, and sadness, providing a comprehensive platform for research. Additionally, we developed a framework for audio, video and textual emotion recognition (i.e., AVaTER) that employs a cross-modal attention mechanism among unimodal features. This mechanism fosters the interaction and fusion of features from different modalities, enhancing the model's ability to capture nuanced emotional cues. The effectiveness of this approach was demonstrated by achieving an F1-score of 0.64, a significant improvement over unimodal methods.