Saifullah Khalid
Saifullah Khalid has a total of 74 co-authors. Here are the top co-authors by number of shared publications:
- Dinesh Kumar Nishad
Department of Electrical Engineering, Dr. Shakuntala Misra National Rehabilitation University, Lucknow, India
10 shared publications D. K. Nishad
Department of Electrical Engineering, Dr. Shakuntala Misra National Rehabilitation University, Lucknow, India
4 shared publicationsDinesh Kumar Nishad
Department of Electrical Engineering, Dr. Shakuntala Misra National Rehabilitation University, Lucknow, UP, India
4 shared publicationsSarika Shrivastava
Ashoka Institute of Technology & Management, Varanasi, India
4 shared publications- Anurag Sinha
Research Scholar, Department of Information Technology Guru Ghasidas Vishwavidyalaya Bilaspur Chhattisgarh India
3 shared publications Radhey Lal
Dr. APJ Abdul, Kalam Technical University Lucknow, Lucknow, India
3 shared publications
Latest Publications
- Open Access
- 16 November 2026
- Published by Springer Nature in Scientific Reports
Reproducible laboratory evaluation of speaker independent speech command recognition with an artificial neural network for humanoid robot control
- 16 November 2026
- Published by Springer Nature in Scientific Reports
Open AccessReproducible laboratory evaluation of speaker independent speech command recognition with an artificial neural network for humanoid robot control
- Open Access
- 24 February 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
Enhanced Breast Cancer Prediction Using Self-Adaptive Sea Lion Optimization-Based Recurrent Neural Network
- 24 February 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
Open AccessEnhanced Breast Cancer Prediction Using Self-Adaptive Sea Lion Optimization-Based Recurrent Neural Network
- Top Cited PapersOpen Access
- 29 January 2026
- Published by Springer Nature in Journal of Cloud Computing
- Vol. 15 (1)
A lightweight blockchain-enabled federated intrusion prevention framework for resource-constrained industrial IoT devices to detect and mitigate emerging cyberattacks
The rapid growth of Industrial Internet of Things (IIoT) networks has created new cybersecurity risks that traditional centralized intrusion detection systems can’t handle because they can’t scale up, protect privacy, or work in environments with limited resources. This study introduces a lightweight, blockchain-enabled federated intrusion prevention platform. Our research integrates three fundamental concepts: (i) a Proof-of-Trust (PoT) agreement mechanism specifically designed for IIoT devices with limited resources, replacing traditional consensus algorithms that use a lot of processing power; (ii) Byzantine fault-tolerant trust management that can keep the system’s integrity even with up to 33% malicious participants; and (iii) an integrated communication optimization strategy that combines model quantization and gradient sparsification. The system helps find strange behavior at the edge, keeps trust via blockchain, and trains models with federated learning while keeping privacy. Extensive experiments on four benchmark datasets (ToN-IoT, UNSW-NB15, CIC-IDS-2017, and a custom IIoT dataset with 1.25 million records) show that this approach works better than others: it has a 97.8% detection accuracy, a 1.2% false positive rate, an average response time of 85 ms, and an 80% reduction in communication overhead. This work presents the inaugural architecture for the integration of blockchain-based trust management and federated learning, specifically tailored for resource-constrained IIoT contexts, hence introducing a novel paradigm for integrated cybersecurity while preserving data sovereignty.
- 29 January 2026
- Published by Springer Nature in Journal of Cloud Computing
- Vol. 15 (1)
Top Cited PapersOpen AccessA lightweight blockchain-enabled federated intrusion prevention framework for resource-constrained industrial IoT devices to detect and mitigate emerging cyberattacks
The rapid growth of Industrial Internet of Things (IIoT) networks has created new cybersecurity risks that traditional centralized intrusion detection systems can’t handle because they can’t scale up, protect privacy, or work in environments with limited resources. This study introduces a lightweight, blockchain-enabled federated intrusion prevention platform. Our research integrates three fundamental concepts: (i) a Proof-of-Trust (PoT) agreement mechanism specifically designed for IIoT devices with limited resources, replacing traditional consensus algorithms that use a lot of processing power; (ii) Byzantine fault-tolerant trust management that can keep the system’s integrity even with up to 33% malicious participants; and (iii) an integrated communication optimization strategy that combines model quantization and gradient sparsification. The system helps find strange behavior at the edge, keeps trust via blockchain, and trains models with federated learning while keeping privacy. Extensive experiments on four benchmark datasets (ToN-IoT, UNSW-NB15, CIC-IDS-2017, and a custom IIoT dataset with 1.25 million records) show that this approach works better than others: it has a 97.8% detection accuracy, a 1.2% false positive rate, an average response time of 85 ms, and an 80% reduction in communication overhead. This work presents the inaugural architecture for the integration of blockchain-based trust management and federated learning, specifically tailored for resource-constrained IIoT contexts, hence introducing a novel paradigm for integrated cybersecurity while preserving data sovereignty.
- Open Access
- 27 January 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
Multi-modal AI-Enabled UAV Network for Fog Dispersal and Runway-Visibility Enhancement at an International Airport
Fog-related flight disruption is costing big international airports more than Rs 2.5 crores for each such event, while the traditional countermeasures, chemical seeding and thermal heating, are expensive, slow and environmentally damaging. This paper proposes the first field-validated airport fog dispersal autonomous UAV system that combines deep reinforcement learning with targeted UV-C photolysis technology. Conventional ways of fog dispersal take 30–45 min for runway clearance, cost Rs 15,000 per operation and produce 500 kg of CO2 emissions. These strategies evaporate fog droplets without tackling the condensation nuclei that are causing them and so the fog can quickly reform. We use a 4-UAV swarm with UV-C LED arrays (254 nm wavelength) for the degradation of hygroscopic aerosols which act as cloud condensation nuclei (CCN). Unlike thermal approaches that only evaporate droplets, our photolysis-based approach can reduce the efficiency of CCN by 35–45% so that the fog does not re-form. A deep Q-Network (DQN), based on 625-256-256-8 architecture, autonomously coordinates swarm positioning based on real-time sensor fusion from LiDAR (25 × 25 m resolution), thermal imaging (640 × 480 at 30fps) and meteorological arrays. 96% accuracy of fog detection. Our operational flights took place at Sri Guru Ram Dass Jee International Airport Amritsar, India, with 120 flights starting from November 2024 till March 2025. Results show: 83.1% reduction in time of fog clearance (from 30 to 5.06 min), 80% improvement of runway visibility range (from 450 to 810 m), 95% reduction in cost (from Rs 800 to Rs 15000 per sortie), 96% reduction in CO2 emission (from 20 to 500 kg per operation).Randomized complete block design using Friedman analysis (kh2 = 128.45, p < 0.001, Cohen’s d effect sizes of 4.85–7.92 show very large practical significance for all of the metrics. Zero incidents during 120 flights with ground exposure from UV-C (0.008 mJ/cm 2 ) 375x below ICNIRP occupational limits. Real-time DQN inference latency (183+-27ms) is the aviation safety-critical requirement (< 250ms). This research sets up a scalable paradigm for fog management at fog-prone airports anywhere in the world economically and environmentally and the potential savings is Rs. 2.5 Crores every year at major international airports.
- 27 January 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
Open AccessMulti-modal AI-Enabled UAV Network for Fog Dispersal and Runway-Visibility Enhancement at an International Airport
Fog-related flight disruption is costing big international airports more than Rs 2.5 crores for each such event, while the traditional countermeasures, chemical seeding and thermal heating, are expensive, slow and environmentally damaging. This paper proposes the first field-validated airport fog dispersal autonomous UAV system that combines deep reinforcement learning with targeted UV-C photolysis technology. Conventional ways of fog dispersal take 30–45 min for runway clearance, cost Rs 15,000 per operation and produce 500 kg of CO2 emissions. These strategies evaporate fog droplets without tackling the condensation nuclei that are causing them and so the fog can quickly reform. We use a 4-UAV swarm with UV-C LED arrays (254 nm wavelength) for the degradation of hygroscopic aerosols which act as cloud condensation nuclei (CCN). Unlike thermal approaches that only evaporate droplets, our photolysis-based approach can reduce the efficiency of CCN by 35–45% so that the fog does not re-form. A deep Q-Network (DQN), based on 625-256-256-8 architecture, autonomously coordinates swarm positioning based on real-time sensor fusion from LiDAR (25 × 25 m resolution), thermal imaging (640 × 480 at 30fps) and meteorological arrays. 96% accuracy of fog detection. Our operational flights took place at Sri Guru Ram Dass Jee International Airport Amritsar, India, with 120 flights starting from November 2024 till March 2025. Results show: 83.1% reduction in time of fog clearance (from 30 to 5.06 min), 80% improvement of runway visibility range (from 450 to 810 m), 95% reduction in cost (from Rs 800 to Rs 15000 per sortie), 96% reduction in CO2 emission (from 20 to 500 kg per operation).Randomized complete block design using Friedman analysis (kh2 = 128.45, p < 0.001, Cohen’s d effect sizes of 4.85–7.92 show very large practical significance for all of the metrics. Zero incidents during 120 flights with ground exposure from UV-C (0.008 mJ/cm 2 ) 375x below ICNIRP occupational limits. Real-time DQN inference latency (183+-27ms) is the aviation safety-critical requirement (< 250ms). This research sets up a scalable paradigm for fog management at fog-prone airports anywhere in the world economically and environmentally and the potential savings is Rs. 2.5 Crores every year at major international airports.
- Top Cited PapersOpen Access
- 7 January 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Explainable AI-enabled adaptive fuzzy MPPT and energy management for bifacial PV and battery-powered electric vehicle charging system
The widespread adoption of electric vehicles (EVs) requires efficient, sustainable charging infrastructure. The use of bifacial photovoltaic (PV) panels with battery energy storage systems (BESS) will provide uninterrupted, sustainable power to EV charging stations. This research is a combination of both an Explainable Artificial Intelligence (XAI)-enabled adaptive fuzzy Maximum Power Point Tracking (MPPT) controller and hierarchical rule-based Energy Management System (EMS) of a 10-kW bifacial solar-driven EV charging system in Madan Mohan Malaviya University of Technology (MMMUT), Gorakhpur, India (26.7 N 83.4 E). The suggested design incorporates a 400 V, 50 Ah (20 kWh) Lithium Iron Phosphate (LiFePO4) battery pack and a 10 kVA two-way inverter, which creates a robust hybrid design. RETScreen Expert software was used to retrieve real-time solar irradiance and atmospheric data. XAI-Fuzzy controller achieves a tracking efficiency of 80.9% under partial shading, which is 4.5% points better than the mainstream Perturb and Observe (P&O) algorithm. The EMS will successfully regulate the flow of power among five operational modes, with the grid power quality having a Total Harmonic Distortion (THD) of 2.40%, quite under the IEEE 519 standard limit of 5%. Explainability metrics reported fidelity of 0.96 and consistency of 0.91, with a sparsity index of 0.38, validating correct and interpretable controller behaviour. Simulation results in MATLAB/Simulink show that the proposed model enhances the overall system efficiency and provides reliable grid support for EV charging under different environmental conditions.
- 7 January 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Top Cited PapersOpen AccessExplainable AI-enabled adaptive fuzzy MPPT and energy management for bifacial PV and battery-powered electric vehicle charging system
The widespread adoption of electric vehicles (EVs) requires efficient, sustainable charging infrastructure. The use of bifacial photovoltaic (PV) panels with battery energy storage systems (BESS) will provide uninterrupted, sustainable power to EV charging stations. This research is a combination of both an Explainable Artificial Intelligence (XAI)-enabled adaptive fuzzy Maximum Power Point Tracking (MPPT) controller and hierarchical rule-based Energy Management System (EMS) of a 10-kW bifacial solar-driven EV charging system in Madan Mohan Malaviya University of Technology (MMMUT), Gorakhpur, India (26.7 N 83.4 E). The suggested design incorporates a 400 V, 50 Ah (20 kWh) Lithium Iron Phosphate (LiFePO4) battery pack and a 10 kVA two-way inverter, which creates a robust hybrid design. RETScreen Expert software was used to retrieve real-time solar irradiance and atmospheric data. XAI-Fuzzy controller achieves a tracking efficiency of 80.9% under partial shading, which is 4.5% points better than the mainstream Perturb and Observe (P&O) algorithm. The EMS will successfully regulate the flow of power among five operational modes, with the grid power quality having a Total Harmonic Distortion (THD) of 2.40%, quite under the IEEE 519 standard limit of 5%. Explainability metrics reported fidelity of 0.96 and consistency of 0.91, with a sparsity index of 0.38, validating correct and interpretable controller behaviour. Simulation results in MATLAB/Simulink show that the proposed model enhances the overall system efficiency and provides reliable grid support for EV charging under different environmental conditions.
- Open Access
- 2 January 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
A hybrid framework of hesitant fuzzy soft sets and rough sets for uncertainty modelling
The process of decision making involves uncertainty due to lack of agreement among experts, inaccuracy in measurements and incomplete information. Current frameworks are inadequate in dealing with cases in which hesitation, indiscernibility, and parameterization may all take place simultaneously. The article proposes a new Hesitant Fuzzy Soft Rough Set (HFSRS) model that combines hesitant fuzzy soft sets and rough sets with dynamic $$\:\varvec{\beta\:}$$ covers that changes approximation boundaries in relation to hesitant membership levels. The suggested framework deals with severe constraints such as the impossibility to model parameter-dependent hesitation, duality violation of the classical fuzzy rough sets, and fixed thresholding processes that cannot be used in a noisy environment. The three fundamental properties provided by mathematical formalization: (a) duality preservation to provide logical consistency important for safety-critical applications, (b) monotonicity to provide predictable behavior important to explainable AI systems, and (c) topological consistency to provide hierarchical uncertainty modeling. HFSRS is empirically validated using synthetically generated datasets (500 photovoltaic modules with three fault indicators adjusted to IEC 61215-2:2021 standards) to achieve 92 per cent accuracy versus 85 per cent on classical rough sets, 86 per cent on fuzzy rough sets, 88 per cent on intuitionistic fuzzy rough sets, with 35 per cent reduction in boundary region and AUC of 0.97 versus 0.92 on competing methods running 30 times The best 0.65 -threshold of the beta value balances accuracy and coverage. The HFSRS-TOPSIS algorithm provides practitioners with strong decision support, computational tractability of $$\:\left(O\right(n\:\times\:\:m\:\times\:\:k\left)\right)$$ on a dataset of up to $$\:{10}^{4}$$ objects.- 2 January 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessA hybrid framework of hesitant fuzzy soft sets and rough sets for uncertainty modelling
The process of decision making involves uncertainty due to lack of agreement among experts, inaccuracy in measurements and incomplete information. Current frameworks are inadequate in dealing with cases in which hesitation, indiscernibility, and parameterization may all take place simultaneously. The article proposes a new Hesitant Fuzzy Soft Rough Set (HFSRS) model that combines hesitant fuzzy soft sets and rough sets with dynamic $$\:\varvec{\beta\:}$$ covers that changes approximation boundaries in relation to hesitant membership levels. The suggested framework deals with severe constraints such as the impossibility to model parameter-dependent hesitation, duality violation of the classical fuzzy rough sets, and fixed thresholding processes that cannot be used in a noisy environment. The three fundamental properties provided by mathematical formalization: (a) duality preservation to provide logical consistency important for safety-critical applications, (b) monotonicity to provide predictable behavior important to explainable AI systems, and (c) topological consistency to provide hierarchical uncertainty modeling. HFSRS is empirically validated using synthetically generated datasets (500 photovoltaic modules with three fault indicators adjusted to IEC 61215-2:2021 standards) to achieve 92 per cent accuracy versus 85 per cent on classical rough sets, 86 per cent on fuzzy rough sets, 88 per cent on intuitionistic fuzzy rough sets, with 35 per cent reduction in boundary region and AUC of 0.97 versus 0.92 on competing methods running 30 times The best 0.65 -threshold of the beta value balances accuracy and coverage. The HFSRS-TOPSIS algorithm provides practitioners with strong decision support, computational tractability of $$\:\left(O\right(n\:\times\:\:m\:\times\:\:k\left)\right)$$ on a dataset of up to $$\:{10}^{4}$$ objects. - Open Access
- 25 August 2025
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 18 (1) , 1-46
A Hybrid DL with Battle Royal Optimisation Algorithm for Accurate Tree Counting Using Satellite Images
- 25 August 2025
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 18 (1) , 1-46
Open AccessA Hybrid DL with Battle Royal Optimisation Algorithm for Accurate Tree Counting Using Satellite Images
- Open Access
- 20 August 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-36
Advanced algorithms for UAV tracking of targets exhibiting start-stop and irregular motion
This study presents breakthrough mathematical formulations for UAV tracking that achieve 56.1% HOTA accuracy for targets with start-stop and irregular motion—a 65% improvement over traditional Kalman Filter approaches. Unmanned aerial vehicles face significant challenges when tracking targets exhibiting abrupt velocity changes, intermittent stops, and nonlinear trajectories due to motion discontinuities, occlusions, and environmental noise. Conventional tracking algorithms, typically based on the assumption of constant velocity, are poorly suited for such dynamic scenarios. Our key innovation is an adaptive hybrid framework that automatically switches between motion models using innovation-based confidence metrics, maintaining tracking continuity during motion discontinuities. The framework introduces three novel technical contributions: (1) innovation-based model switching achieving 89.3% accuracy in motion transition detection, (2) enhanced α-β-γ-δ filtering with jerk compensation providing 15–25% performance improvement for irregular motion, and (3) SMART-TRACK’s 3D-to-2D uncertainty propagation enabling 2.3-second recovery time compared to 5.8-second average for traditional methods. A comprehensive evaluation on benchmark datasets (VisDrone2019, UAVDT, MOT17, DanceTrack) demonstrates that hybrid approaches combining adaptive filtering with deep learning-based detection achieve superior tracking accuracy and reliability. Flow-guided margin loss specifically addresses the motion long-tailed problem, improving large motion tracking by 18.7%. Environmental robustness testing shows that advanced algorithms maintain an average accuracy of 52.3% under corruptions, compared to 34.1% for traditional methods. These findings offer practical guidance for deploying robust UAV tracking systems that can handle unpredictable target behaviors in real-world applications.
- 20 August 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-36
Open AccessAdvanced algorithms for UAV tracking of targets exhibiting start-stop and irregular motion
This study presents breakthrough mathematical formulations for UAV tracking that achieve 56.1% HOTA accuracy for targets with start-stop and irregular motion—a 65% improvement over traditional Kalman Filter approaches. Unmanned aerial vehicles face significant challenges when tracking targets exhibiting abrupt velocity changes, intermittent stops, and nonlinear trajectories due to motion discontinuities, occlusions, and environmental noise. Conventional tracking algorithms, typically based on the assumption of constant velocity, are poorly suited for such dynamic scenarios. Our key innovation is an adaptive hybrid framework that automatically switches between motion models using innovation-based confidence metrics, maintaining tracking continuity during motion discontinuities. The framework introduces three novel technical contributions: (1) innovation-based model switching achieving 89.3% accuracy in motion transition detection, (2) enhanced α-β-γ-δ filtering with jerk compensation providing 15–25% performance improvement for irregular motion, and (3) SMART-TRACK’s 3D-to-2D uncertainty propagation enabling 2.3-second recovery time compared to 5.8-second average for traditional methods. A comprehensive evaluation on benchmark datasets (VisDrone2019, UAVDT, MOT17, DanceTrack) demonstrates that hybrid approaches combining adaptive filtering with deep learning-based detection achieve superior tracking accuracy and reliability. Flow-guided margin loss specifically addresses the motion long-tailed problem, improving large motion tracking by 18.7%. Environmental robustness testing shows that advanced algorithms maintain an average accuracy of 52.3% under corruptions, compared to 34.1% for traditional methods. These findings offer practical guidance for deploying robust UAV tracking systems that can handle unpredictable target behaviors in real-world applications.
- Open Access
- 1 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-14
Improving EEG based brain computer interface emotion detection with EKO ALSTM model
Decoding signals from the CNS brain activity is done by a computer-based communication device called a BCI. In contrast, the system is considered compelling communication equipment enabling command, communication, and action without using neuromuscular or muscle channels. Various techniques for automatic emotion identification based on body language, speech, or facial expressions are nowadays in use. However, the monitoring of exterior emotions, which are easily manipulated, limits the applicability of these procedures. EEG-based emotion detection research might yield significant benefits for enhancing BCI application performance and user experience. To overcome these issues, this study proposed a novel EKO-ALSTM for emotion detection in EEG-based brain–computer interfaces. The proposed study comprises EEG-based signals that record the electrical activity of the brain connected to various emotional states, which are gathered as real-time acquired EEG signals for emotion detection. The data was pre-processed using a bandpass filter to remove unwanted frequency noise for the obtained data. Then, feature extraction is performed using DWT from pre-processed data. Specifically, the proposed approach is implemented using Python software. The proposed system and existing algorithms are compared using a variety of evaluation criteria, including specificity, F1 score, accuracy, recall or sensitivity, and positive predictive values or precision. The results demonstrated that the proposed method achieved better performance in EEG-based BCI emotion detection with an accuracy of 97.93%, a positive predictive value of 96.24%, a sensitivity of 97.81%, and a specificity of 97.75%. This study emphasizes that innovative approaches have significantly increased the accuracy of emotion identification when applied to EEG-based emotion recognition systems. Additionally, the findings suggest that integrating advanced machine learning techniques can further enhance the effectiveness and reliability of these systems in real-world applications, paving the way for more responsive and intuitive BCI technologies.
- 1 July 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-14
Open AccessImproving EEG based brain computer interface emotion detection with EKO ALSTM model
Decoding signals from the CNS brain activity is done by a computer-based communication device called a BCI. In contrast, the system is considered compelling communication equipment enabling command, communication, and action without using neuromuscular or muscle channels. Various techniques for automatic emotion identification based on body language, speech, or facial expressions are nowadays in use. However, the monitoring of exterior emotions, which are easily manipulated, limits the applicability of these procedures. EEG-based emotion detection research might yield significant benefits for enhancing BCI application performance and user experience. To overcome these issues, this study proposed a novel EKO-ALSTM for emotion detection in EEG-based brain–computer interfaces. The proposed study comprises EEG-based signals that record the electrical activity of the brain connected to various emotional states, which are gathered as real-time acquired EEG signals for emotion detection. The data was pre-processed using a bandpass filter to remove unwanted frequency noise for the obtained data. Then, feature extraction is performed using DWT from pre-processed data. Specifically, the proposed approach is implemented using Python software. The proposed system and existing algorithms are compared using a variety of evaluation criteria, including specificity, F1 score, accuracy, recall or sensitivity, and positive predictive values or precision. The results demonstrated that the proposed method achieved better performance in EEG-based BCI emotion detection with an accuracy of 97.93%, a positive predictive value of 96.24%, a sensitivity of 97.81%, and a specificity of 97.75%. This study emphasizes that innovative approaches have significantly increased the accuracy of emotion identification when applied to EEG-based emotion recognition systems. Additionally, the findings suggest that integrating advanced machine learning techniques can further enhance the effectiveness and reliability of these systems in real-world applications, paving the way for more responsive and intuitive BCI technologies.
- Top Cited PapersOpen Access
- 1 July 2025
- Published by Springer Nature in Discover Sustainability
- Vol. 6 (1) , 1-20
Leveraging artificial intelligence in agribusiness: a structured review of strategic management practices and future prospects
This paper presents a structured review of the applications of Artificial Intelligence (AI) in agribusiness, emphasizing its transformative impact on farming practices. By integrating AI technologies such as machine learning, robotics, and data analytics, AI enhances productivity, sustainability, and profitability in agriculture. The paper explores key AI-driven advancements in precision agriculture, resource management, and supply chain optimization, which allow for real-time monitoring and informed decision-making. Additionally, the research discusses the ethical challenges and barriers to AI adoption, particularly in smallholder farming and developing economies. It also identifies emerging trends, such as the integration of AI with blockchain and biotechnology, to further optimize agricultural processes. The paper concludes with recommendations for advancing AI adoption, addressing data privacy concerns, and fostering inclusive, sustainable farming practices to ensure long-term resilience and food security in the agricultural sector.
- 1 July 2025
- Published by Springer Nature in Discover Sustainability
- Vol. 6 (1) , 1-20
Top Cited PapersOpen AccessLeveraging artificial intelligence in agribusiness: a structured review of strategic management practices and future prospects
This paper presents a structured review of the applications of Artificial Intelligence (AI) in agribusiness, emphasizing its transformative impact on farming practices. By integrating AI technologies such as machine learning, robotics, and data analytics, AI enhances productivity, sustainability, and profitability in agriculture. The paper explores key AI-driven advancements in precision agriculture, resource management, and supply chain optimization, which allow for real-time monitoring and informed decision-making. Additionally, the research discusses the ethical challenges and barriers to AI adoption, particularly in smallholder farming and developing economies. It also identifies emerging trends, such as the integration of AI with blockchain and biotechnology, to further optimize agricultural processes. The paper concludes with recommendations for advancing AI adoption, addressing data privacy concerns, and fostering inclusive, sustainable farming practices to ensure long-term resilience and food security in the agricultural sector.