Mohammad Faleh Ahmmad Hunitie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohammad Faleh Ahmmad Hunitie has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Asokan Vasudevan
INTI International University
16 shared publications - Sulieman Ibraheem Mohammad
Al al-Bayt University
14 shared publications - Anber Abraheem Shlash Mohammad
Digital Marketing Department, Faculty of Administrative and Financial Sciences, University of Petra, Amman, Jordan
7 shared publications - Yogeesh Nijalingappa
School of Engineering, Architecture and Interior Design, Amity University Dubai, Dubai P.O. Box 345019, United Arab Emirates; Department of Mathematics, Government First Grade College, Tumakuru 572101, India
6 shared publications - Khaleel Ibrahim Al-Daoud
Al-Ahliyya Amman University
5 shared publications - Badrea Al Oraini
Qassim University
4 shared publications
Latest Publications
- Open Access
- 27 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Condition-based maintenance threshold determination for gearbox fault progression using vibration envelope features and accelerated life testing
Gearbox failures represent a critical problem faced by industrial machines, considering the impacts of such failures on machine reliability, efficiency, and maintenance cost. Despite the well-established use of vibration-based condition monitoring techniques for diagnosing the presence of faults, few attempts have been made in transforming information about fault progression into thresholds that could be used in making condition-based maintenance (CBM) decisions. In this work, a CBM system for analysing gearbox fault progression based on vibration envelope features is presented, alongside accelerated life testing. An experimental approach has been adopted, whereby accelerated life testing was performed to induce gearbox degradation progressively. Then, vibration data were analysed through the envelope technique, out of which six vibration envelope features, namely RMS Envelope, Kurtosis, Crest Factor, Peak Amplitude, Envelope Energy, and Sideband Energy Ratio, were derived and analysed based on their sensitivity through correlation, monotonicity, trendability, and separability tests. Thereafter, a composite health index based on the most sensitive features was formulated, and a multilevel maintenance threshold system consisting of Alert, Warning, and Critical levels was created. The findings show that Envelope Energy, Sideband Energy Ratio, and Kurtosis have the highest sensitivity to degradation and can accurately represent the evolution of gearbox faults. The composite health index shows a strong correlation with the extent of degradation (R2 = 0.962) and successfully discriminates between different health states of the gearbox. The developed framework for determining maintenance thresholds achieves an accuracy of 94.9%, which allows accurate identification of maintenance intervention phases.
- 27 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Open AccessCondition-based maintenance threshold determination for gearbox fault progression using vibration envelope features and accelerated life testing
Gearbox failures represent a critical problem faced by industrial machines, considering the impacts of such failures on machine reliability, efficiency, and maintenance cost. Despite the well-established use of vibration-based condition monitoring techniques for diagnosing the presence of faults, few attempts have been made in transforming information about fault progression into thresholds that could be used in making condition-based maintenance (CBM) decisions. In this work, a CBM system for analysing gearbox fault progression based on vibration envelope features is presented, alongside accelerated life testing. An experimental approach has been adopted, whereby accelerated life testing was performed to induce gearbox degradation progressively. Then, vibration data were analysed through the envelope technique, out of which six vibration envelope features, namely RMS Envelope, Kurtosis, Crest Factor, Peak Amplitude, Envelope Energy, and Sideband Energy Ratio, were derived and analysed based on their sensitivity through correlation, monotonicity, trendability, and separability tests. Thereafter, a composite health index based on the most sensitive features was formulated, and a multilevel maintenance threshold system consisting of Alert, Warning, and Critical levels was created. The findings show that Envelope Energy, Sideband Energy Ratio, and Kurtosis have the highest sensitivity to degradation and can accurately represent the evolution of gearbox faults. The composite health index shows a strong correlation with the extent of degradation (R2 = 0.962) and successfully discriminates between different health states of the gearbox. The developed framework for determining maintenance thresholds achieves an accuracy of 94.9%, which allows accurate identification of maintenance intervention phases.
- Open Access
- 27 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Closed-form topological and spectral invariants for periodic ladder-based vibration networks
This paper investigates two closely related network families, the open ladder graph and the cylindrical ladder graph, as exact test beds for degree-based, eccentricity-based, distance-based, and spectral descriptors. The two graphs can be seen as graph-theoretic two-rail models with and without periodic closure, allowing an exact comparison boundary effects versus cyclic-closure-effect. We obtain closed expressions for the Sombor index, reduced Sombor index, Sombor coindex, reduced Sombor coindex, first and second Zagreb indices, forgotten index, Randić index geometric-arithmetic index atom-bond connectivity index total eccentricity average eccentricity eccentric connectivity index Wiener Index radius diameter and total π-electron energy. For the energy part, we derive exact spectral sums and trigonometric closed forms using the Cartesian-product spectra of the underlying path and cycle graphs. Numerical tables and plots show that periodic closure increases all degree-regularity descriptors while sharply decreasing distance descriptors. In contrast, the total π-electron energy changes only by a small oscillatory amount, and both families share the same asymptotic energy density. The adjacency-based energy indeed can be interpreted explicitly as graph energy, instead of mechanical vibrational energy. An additional mass-spring formulation rooted on the graph Laplacian provides the analog equations of motion, natural-frequency spectra, dispersion samples and frequency-response operator for those analogous ladder topologies.
- 27 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Open AccessClosed-form topological and spectral invariants for periodic ladder-based vibration networks
This paper investigates two closely related network families, the open ladder graph and the cylindrical ladder graph, as exact test beds for degree-based, eccentricity-based, distance-based, and spectral descriptors. The two graphs can be seen as graph-theoretic two-rail models with and without periodic closure, allowing an exact comparison boundary effects versus cyclic-closure-effect. We obtain closed expressions for the Sombor index, reduced Sombor index, Sombor coindex, reduced Sombor coindex, first and second Zagreb indices, forgotten index, Randić index geometric-arithmetic index atom-bond connectivity index total eccentricity average eccentricity eccentric connectivity index Wiener Index radius diameter and total π-electron energy. For the energy part, we derive exact spectral sums and trigonometric closed forms using the Cartesian-product spectra of the underlying path and cycle graphs. Numerical tables and plots show that periodic closure increases all degree-regularity descriptors while sharply decreasing distance descriptors. In contrast, the total π-electron energy changes only by a small oscillatory amount, and both families share the same asymptotic energy density. The adjacency-based energy indeed can be interpreted explicitly as graph energy, instead of mechanical vibrational energy. An additional mass-spring formulation rooted on the graph Laplacian provides the analog equations of motion, natural-frequency spectra, dispersion samples and frequency-response operator for those analogous ladder topologies.
- Open Access
- 24 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Broadband vibration suppression of a nonlinear beam using a fractional-order inerter-assisted tuned mass damper
This study presents an analytical method for reducing broadband vibration in a simply supported nonlinear beam fitted with an inerter-assisted tuned mass damper. The first bending mode is obtained by Galerkin projection, geometric nonlinearity is represented by a cubic stiffness term, and beam damping is described by a fractional-order derivative. A single-harmonic balance formulation converts the coupled equations into an amplitude-dependent cubic equation that is solved directly over the forcing-frequency range. The absorber is optimized with respect to inertance ratio, tuning ratio, damping ratio, and fractional order. The objective is to minimize the largest beam amplitude between 7 and 14 Hz. For the beam considered, increasing the inertance ratio from 0 to 0.20 raises the peak-response reduction from about 4.5% to about 52%, while the physical absorber mass ratio remains 0.04. The optimal tuning ratio decreases as inertance increases, whereas the required absorber damping generally increases. A ±5% stiffness study shows that the optimized designs remain effective under moderate uncertainty. The results also clarify how fractional damping modifies the balance between effective stiffness and dissipation, enabling the proposed maps to support robust initial absorber selection before detailed high-fidelity validation. The resulting design maps and regression equations provide useful preliminary settings for later finite-element or experimental verification.
- 24 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Open AccessBroadband vibration suppression of a nonlinear beam using a fractional-order inerter-assisted tuned mass damper
This study presents an analytical method for reducing broadband vibration in a simply supported nonlinear beam fitted with an inerter-assisted tuned mass damper. The first bending mode is obtained by Galerkin projection, geometric nonlinearity is represented by a cubic stiffness term, and beam damping is described by a fractional-order derivative. A single-harmonic balance formulation converts the coupled equations into an amplitude-dependent cubic equation that is solved directly over the forcing-frequency range. The absorber is optimized with respect to inertance ratio, tuning ratio, damping ratio, and fractional order. The objective is to minimize the largest beam amplitude between 7 and 14 Hz. For the beam considered, increasing the inertance ratio from 0 to 0.20 raises the peak-response reduction from about 4.5% to about 52%, while the physical absorber mass ratio remains 0.04. The optimal tuning ratio decreases as inertance increases, whereas the required absorber damping generally increases. A ±5% stiffness study shows that the optimized designs remain effective under moderate uncertainty. The results also clarify how fractional damping modifies the balance between effective stiffness and dissipation, enabling the proposed maps to support robust initial absorber selection before detailed high-fidelity validation. The resulting design maps and regression equations provide useful preliminary settings for later finite-element or experimental verification.
- Open Access
- 23 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Lifecycle cost optimization of vibration mitigation in rotating machinery: Integrating measured transmissibility, finite element modeling, and downtime cost scenarios
Rotation devices play a vital role in industrial plants, where vibrations significantly affect efficiency, reliability, and the overall cost of operation. Vibrations cause wear and tear, failures, and high maintenance time, but previous studies have focused on machine efficiency without including financial factors. This paper provides a solution to this problem by developing an integrated approach to optimizing lifetime cost through vibration reduction in rotation devices. A numerical approach was used to quantify and analyse the phenomenon, including experimental measurement, finite element (FE) modelling, and economic analysis. Transmissibility measurement was used to describe vibration dynamics and validate the FE model. The response of the system was correlated to wear and tear, failure rates, and downtime. These factors were then used to formulate a lifetime cost model. The results have shown that there is a strong non-linear connection between the transmissibility factor and the lifecycle cost, where the higher the levels of vibrations, the greater the extent of wear and tear and downtime. The process of optimizing identified the optimum operating point where there is a perfect compromise between the vibration performance and the cost effectiveness. The sensitivity analysis has revealed that the transmissibility is the most significant factor affecting the lifecycle cost.
- 23 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Open AccessLifecycle cost optimization of vibration mitigation in rotating machinery: Integrating measured transmissibility, finite element modeling, and downtime cost scenarios
Rotation devices play a vital role in industrial plants, where vibrations significantly affect efficiency, reliability, and the overall cost of operation. Vibrations cause wear and tear, failures, and high maintenance time, but previous studies have focused on machine efficiency without including financial factors. This paper provides a solution to this problem by developing an integrated approach to optimizing lifetime cost through vibration reduction in rotation devices. A numerical approach was used to quantify and analyse the phenomenon, including experimental measurement, finite element (FE) modelling, and economic analysis. Transmissibility measurement was used to describe vibration dynamics and validate the FE model. The response of the system was correlated to wear and tear, failure rates, and downtime. These factors were then used to formulate a lifetime cost model. The results have shown that there is a strong non-linear connection between the transmissibility factor and the lifecycle cost, where the higher the levels of vibrations, the greater the extent of wear and tear and downtime. The process of optimizing identified the optimum operating point where there is a perfect compromise between the vibration performance and the cost effectiveness. The sensitivity analysis has revealed that the transmissibility is the most significant factor affecting the lifecycle cost.
- Open Access
- 22 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Hybrid analytical–numerical–experimental study of low-frequency transformer noise control using stacked Helmholtz resonator panels
Low frequency noise produced by electrical transformers is one of the most resilient problems, since such types of noises are highly resistant to standard techniques of noise suppression. Absorption panels do not provide sufficient protection below 500 Hz; hence, alternative techniques based on resonance have been developed in the field of passive acoustic control. This research considers stacked Helmholtz resonators as a possible method of attenuating low frequency noises produced by transformer equipment in the range from 20 Hz to 500 Hz. A combination of analytical, numerical, and experimental techniques is utilized to estimate the effectiveness of the proposed method. Experimental tests have shown that proper configuration of Helmholtz resonators can help to attenuate sounds up to 7.5 dB and provide 9.2 dB of transmission loss. The highest efficiency of attenuation has been estimated at 11.5%. Numerical estimates demonstrated a high level of correspondence with experiments, with an error margin of smaller than 3.2% for all tested configurations. An increase in the volume of cavities, neck lengths, and layering significantly increased the efficiency of low frequency attenuation. It can be concluded that the application of stacked Helmholtz resonator panels is one of the most energy-efficient ways to suppress noise in the considered low-frequency band.
- 22 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Open AccessHybrid analytical–numerical–experimental study of low-frequency transformer noise control using stacked Helmholtz resonator panels
Low frequency noise produced by electrical transformers is one of the most resilient problems, since such types of noises are highly resistant to standard techniques of noise suppression. Absorption panels do not provide sufficient protection below 500 Hz; hence, alternative techniques based on resonance have been developed in the field of passive acoustic control. This research considers stacked Helmholtz resonators as a possible method of attenuating low frequency noises produced by transformer equipment in the range from 20 Hz to 500 Hz. A combination of analytical, numerical, and experimental techniques is utilized to estimate the effectiveness of the proposed method. Experimental tests have shown that proper configuration of Helmholtz resonators can help to attenuate sounds up to 7.5 dB and provide 9.2 dB of transmission loss. The highest efficiency of attenuation has been estimated at 11.5%. Numerical estimates demonstrated a high level of correspondence with experiments, with an error margin of smaller than 3.2% for all tested configurations. An increase in the volume of cavities, neck lengths, and layering significantly increased the efficiency of low frequency attenuation. It can be concluded that the application of stacked Helmholtz resonator panels is one of the most energy-efficient ways to suppress noise in the considered low-frequency band.
- Open Access
- 21 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Possibility-based transfer-matrix optimization of a graded double-cavity micro-perforated partition with fuzzy parameters for broadband sound transmission loss
This study proposes a possibility-based transfer-matrix optimization and assessment framework for fuzzy geometric parameters in a graded double-cavity micro-perforated partition. The system consists of a front limp panel, a first air cavity, a micro-perforated panel, a second air cavity, and a back limp panel. The two cavities are graded over three equal parallel strips, so the local depths of the two cavities differ from strip to strip. Fuzzy numbers model each uncertain design quantity as a triangular fuzzy number and propagate through alpha-cuts. The acoustic model consists of explicit transfer matrices, an area-averaged transmission coefficient, and normal-incidence sound transmission loss. The specific novelty is the direct use of exact alpha-cut corner propagation inside the graded strip-wise transfer-matrix objective, where guaranteed band-average sound transmission loss, guaranteed low-band minimum, and fuzzy width are evaluated together rather than only after a deterministic design is selected. A fuzzy width penalty and guaranteed band-average transmission loss with guaranteed low-band minimum transmission loss are included in the objective function. This is analyzed with a detailed numerical study from 250 Hz to 2,000 Hz. The selected graded design realizes a guaranteed average sound transmission loss of 78.085 dB and a guaranteed low-band minimum of 41.323 dB, while the central design gives 81.425 dB and 43.406 dB, respectively. Compared with a uniform-cavity reference evaluated under the same fuzzy setting, the graded design improves the guaranteed low-band average and minimum while maintaining a comparable uncertainty width. This study focuses on mathematical formulation, tabulated numerical output, and an accessible interpretation of design rather than a long theoretical discussion.
- 21 July 2026
- Published by Academic Publishing Pte. Ltd. in Sound & Vibration
Open AccessPossibility-based transfer-matrix optimization of a graded double-cavity micro-perforated partition with fuzzy parameters for broadband sound transmission loss
This study proposes a possibility-based transfer-matrix optimization and assessment framework for fuzzy geometric parameters in a graded double-cavity micro-perforated partition. The system consists of a front limp panel, a first air cavity, a micro-perforated panel, a second air cavity, and a back limp panel. The two cavities are graded over three equal parallel strips, so the local depths of the two cavities differ from strip to strip. Fuzzy numbers model each uncertain design quantity as a triangular fuzzy number and propagate through alpha-cuts. The acoustic model consists of explicit transfer matrices, an area-averaged transmission coefficient, and normal-incidence sound transmission loss. The specific novelty is the direct use of exact alpha-cut corner propagation inside the graded strip-wise transfer-matrix objective, where guaranteed band-average sound transmission loss, guaranteed low-band minimum, and fuzzy width are evaluated together rather than only after a deterministic design is selected. A fuzzy width penalty and guaranteed band-average transmission loss with guaranteed low-band minimum transmission loss are included in the objective function. This is analyzed with a detailed numerical study from 250 Hz to 2,000 Hz. The selected graded design realizes a guaranteed average sound transmission loss of 78.085 dB and a guaranteed low-band minimum of 41.323 dB, while the central design gives 81.425 dB and 43.406 dB, respectively. Compared with a uniform-cavity reference evaluated under the same fuzzy setting, the graded design improves the guaranteed low-band average and minimum while maintaining a comparable uncertainty width. This study focuses on mathematical formulation, tabulated numerical output, and an accessible interpretation of design rather than a long theoretical discussion.
- 26 February 2026
- Published by Institute of Society Transformation sp. z o.o. in Economic Annals-ХХI
- Vol. 219 (1-2) , 86-91
Machine learning models for financial market volatility prediction: comparative economic forecasting accuracy
The ability to forecast volatility precisely plays an important role in risk management in financial markets. In this paper, we performed a comparative analysis of forecasting accuracy of machine learning approaches and the traditional GARCH model in the case of the Amman Stock Exchange in Jordan. Historical daily index data from 2010 to March 2025 were used to compare the forecasting performance of the LSTM algorithm, support vector machine algorithm, and random forest algorithm for one-day out-of-sample horizon (January-March 2025) to GARCH(1,1)-t model. According to the MSE and MAE measures, the LSTM model demonstrated the lowest forecasting errors and performed significantly better by the Diebold-Mariano test. In economic terms, this finding implies that more accurate volatility forecasts directly translate into better risk-adjusted portfolio performance and more efficient capital allocation. The LSTM model provided up to 30% MSE reduction compared to GARCH during the periods of high volatility regimes. As such, from the economic analysis, the LSTM forecast portfolio is observed to have a Sharpe ratio of 0.89 with a maximum drawdown of -4.15%, which is a better performance compared to the GARCH forecast portfolio, proving the economic benefit of using machine learning models for forecasting volatility in emerging markets. In summary, it can be seen that the use of machine learning, especially the LSTM method, does not only improve forecast accuracy but also has strong economic benefits. As such, the problem of choosing the best volatility forecasting model is well solved in the Jordanian financial market.
- 26 February 2026
- Published by Institute of Society Transformation sp. z o.o. in Economic Annals-ХХI
- Vol. 219 (1-2) , 86-91
Machine learning models for financial market volatility prediction: comparative economic forecasting accuracy
The ability to forecast volatility precisely plays an important role in risk management in financial markets. In this paper, we performed a comparative analysis of forecasting accuracy of machine learning approaches and the traditional GARCH model in the case of the Amman Stock Exchange in Jordan. Historical daily index data from 2010 to March 2025 were used to compare the forecasting performance of the LSTM algorithm, support vector machine algorithm, and random forest algorithm for one-day out-of-sample horizon (January-March 2025) to GARCH(1,1)-t model. According to the MSE and MAE measures, the LSTM model demonstrated the lowest forecasting errors and performed significantly better by the Diebold-Mariano test. In economic terms, this finding implies that more accurate volatility forecasts directly translate into better risk-adjusted portfolio performance and more efficient capital allocation. The LSTM model provided up to 30% MSE reduction compared to GARCH during the periods of high volatility regimes. As such, from the economic analysis, the LSTM forecast portfolio is observed to have a Sharpe ratio of 0.89 with a maximum drawdown of -4.15%, which is a better performance compared to the GARCH forecast portfolio, proving the economic benefit of using machine learning models for forecasting volatility in emerging markets. In summary, it can be seen that the use of machine learning, especially the LSTM method, does not only improve forecast accuracy but also has strong economic benefits. As such, the problem of choosing the best volatility forecasting model is well solved in the Jordanian financial market.
- 27 December 2025
- Published by Institute of Society Transformation sp. z o.o. in Economic Annals-ХХI
- Vol. 218 (11-12)
Macroeconomic impact of digital currency adoption: panel data econometrics with fixed effects in accounting system
This research intends to investigate empirically the implications of the growth of digital money on inflation, economic growth, and foreign exchange rate volatility at the state level in Malaysia. In doing so, a panel data model was constructed involving 16 states and territories from the year 2015 to 2024. The key explanatory variable in the regression model is the composite Digital Currency Acceptance Index (DCI), which consists of per capita volume of transactions made through digital wallets and internet penetration. This regression model has been estimated employing the fixed effect method along with robust clustered standard errors at the state level. According to the estimation results, a one-point increment in the acceptance index lowers the inflation by 1.82 percentage points and raises GDP growth by 1.94 percentage points. They both are significant at the 0.1% significance level. On the other hand, the impact of DCI on the foreign exchange rate (MYR/USD) volatility was found to be rather minor and insignificant. Robustness testing through alternative indices’ use with a one-year lag and using proxies like mobile payment transaction volume and electronic card payments corroborated the main results. The Hausman test also supported the superiority of fixed effects model over random effects in all cases. Such results have significant policy implications for monetary authorities as they indicate that digital payment systems’ construction will help achieve price stability and economic growth without the creation of foreign exchange volatility.
- 27 December 2025
- Published by Institute of Society Transformation sp. z o.o. in Economic Annals-ХХI
- Vol. 218 (11-12)
Macroeconomic impact of digital currency adoption: panel data econometrics with fixed effects in accounting system
This research intends to investigate empirically the implications of the growth of digital money on inflation, economic growth, and foreign exchange rate volatility at the state level in Malaysia. In doing so, a panel data model was constructed involving 16 states and territories from the year 2015 to 2024. The key explanatory variable in the regression model is the composite Digital Currency Acceptance Index (DCI), which consists of per capita volume of transactions made through digital wallets and internet penetration. This regression model has been estimated employing the fixed effect method along with robust clustered standard errors at the state level. According to the estimation results, a one-point increment in the acceptance index lowers the inflation by 1.82 percentage points and raises GDP growth by 1.94 percentage points. They both are significant at the 0.1% significance level. On the other hand, the impact of DCI on the foreign exchange rate (MYR/USD) volatility was found to be rather minor and insignificant. Robustness testing through alternative indices’ use with a one-year lag and using proxies like mobile payment transaction volume and electronic card payments corroborated the main results. The Hausman test also supported the superiority of fixed effects model over random effects in all cases. Such results have significant policy implications for monetary authorities as they indicate that digital payment systems’ construction will help achieve price stability and economic growth without the creation of foreign exchange volatility.
- Open Access
- 20 June 2025
- Published by Innovative Research Publishing in International Journal of Innovative Research and Scientific Studies
- Vol. 8 (5) , 2198-2208
AI-powered accounting: Analysing accuracy and efficiency using machine learning algorithms and predictive models
With each passing day, AI and ML continue to revolutionize the world of industry. For that reason, accounting too cannot stay behind. The ever-evolving technologies of artificial intelligence and machine learning are being widely applied to automate regular activities, reduce human error, and ensure better precision in financial reporting by deploying AI accounting systems. Recent AI-based accounting systems apply advanced machine learning algorithms to transaction classification, error detection, and financial trend predictions instead of manual accounting practices. This paper has evaluated accuracy, development in efficiency, and anomaly detection while assessing the performance of AI compared to conventional manual practices of accounting systems. This work seeks to find out how AI-human interfaces, machine learning models that include some supervised learning algorithms, predictive analytics, and clustering techniques, can significantly enhance financial reporting reliability while simplifying accounting processes. The survey results also show that AI-driven systems provide higher levels of accuracy and faster speed, and may also offer superior mechanisms for identifying anomalies in financial information. These insights underscore the transformative potential of AI in accounting: AI will undoubtedly be crucial in advancing both operational efficiencies and financial decisions.
- 20 June 2025
- Published by Innovative Research Publishing in International Journal of Innovative Research and Scientific Studies
- Vol. 8 (5) , 2198-2208
Open AccessAI-powered accounting: Analysing accuracy and efficiency using machine learning algorithms and predictive models
With each passing day, AI and ML continue to revolutionize the world of industry. For that reason, accounting too cannot stay behind. The ever-evolving technologies of artificial intelligence and machine learning are being widely applied to automate regular activities, reduce human error, and ensure better precision in financial reporting by deploying AI accounting systems. Recent AI-based accounting systems apply advanced machine learning algorithms to transaction classification, error detection, and financial trend predictions instead of manual accounting practices. This paper has evaluated accuracy, development in efficiency, and anomaly detection while assessing the performance of AI compared to conventional manual practices of accounting systems. This work seeks to find out how AI-human interfaces, machine learning models that include some supervised learning algorithms, predictive analytics, and clustering techniques, can significantly enhance financial reporting reliability while simplifying accounting processes. The survey results also show that AI-driven systems provide higher levels of accuracy and faster speed, and may also offer superior mechanisms for identifying anomalies in financial information. These insights underscore the transformative potential of AI in accounting: AI will undoubtedly be crucial in advancing both operational efficiencies and financial decisions.
- Open Access
- 13 June 2025
- Published by Bilingual Publishing Group in Forum for Linguistic Studies
- Vol. 7 (6) , 895–909
Quantifying Metaphorical Language in Literature Using Fuzzy Semantics
Using fuzzy semantics—a framework derived within cognitive linguistics that defines the way in which entities relate to objects—we introduce empirical justification for our parameter weights (0.3, 0.4, 0.3) based on a pilot study of 50 metaphor instances. We present a new approach for quantifying metaphorical language in centuries of literary writings. We deal with the inherent gradience of metaphoric expression by computing Fuzzy Membership Values (FMVs) from three core parameters: literalness, vividness, and abstraction. The analysis was complemented with the Metaphor Identification Procedure (MIP), and expert evaluations reveal insights into metaphoric use for a small-scale case study of selected verses by Sylvia Plath, Emily Dickinson, and an Indian English poet. Extended metaphors, novel sensory mappings, and conventional metaphors each produce different FMV ranges, offering an objective metric to demonstrate nuanced differentiations in metaphorical force. This quantitative manner complements traditional qualitative analyses and provides a replicable, scalable tool for literary criticism. We also report inter-rater reliability (Cohen’s κ = 0.82) and include updated figures (actual plots, not placeholders) for membership functions and α-cuts. Potential applications in educational and digital humanities are discussed, alongside future avenues such as automated NLP assignments and cross-linguistic validation. Including the AMI and sensitivity analysis strengthens methodological rigor and sets clear benchmarks for subsequent work.
- 13 June 2025
- Published by Bilingual Publishing Group in Forum for Linguistic Studies
- Vol. 7 (6) , 895–909
Open AccessQuantifying Metaphorical Language in Literature Using Fuzzy Semantics
Using fuzzy semantics—a framework derived within cognitive linguistics that defines the way in which entities relate to objects—we introduce empirical justification for our parameter weights (0.3, 0.4, 0.3) based on a pilot study of 50 metaphor instances. We present a new approach for quantifying metaphorical language in centuries of literary writings. We deal with the inherent gradience of metaphoric expression by computing Fuzzy Membership Values (FMVs) from three core parameters: literalness, vividness, and abstraction. The analysis was complemented with the Metaphor Identification Procedure (MIP), and expert evaluations reveal insights into metaphoric use for a small-scale case study of selected verses by Sylvia Plath, Emily Dickinson, and an Indian English poet. Extended metaphors, novel sensory mappings, and conventional metaphors each produce different FMV ranges, offering an objective metric to demonstrate nuanced differentiations in metaphorical force. This quantitative manner complements traditional qualitative analyses and provides a replicable, scalable tool for literary criticism. We also report inter-rater reliability (Cohen’s κ = 0.82) and include updated figures (actual plots, not placeholders) for membership functions and α-cuts. Potential applications in educational and digital humanities are discussed, alongside future avenues such as automated NLP assignments and cross-linguistic validation. Including the AMI and sensitivity analysis strengthens methodological rigor and sets clear benchmarks for subsequent work.