Journal of Basic and Applied Research International

Artificial Intelligence Adoption in Smart Agriculture: A Review of Convolutional Neural Networks for Plant Disease Detection and Agribusiness Sustainability

2026-07-01T13:41:56+00:00

Plant diseases remain one of the most persistent and economically damaging threats to global food security, with yield losses across major staple crops running into the tens of billions of dollars each year. The rise of artificial intelligence, and convolutional neural networks (CNNs) in particular, has opened genuinely new possibilities for detecting plant disease early, accurately, and at scale. This review critically examines the state of CNN-based plant disease detection within the wider context of smart agriculture and agribusiness sustainability. Drawing on peer-reviewed literature published between January 2016 to February 2026, the paper traces the evolution of CNN architectures, training methods, and benchmark performance across a wide range of crops and disease categories. Particular attention is given to transfer learning, data augmentation, and lightweight architecture design as responses to the recurring problem of limited annotated training data. The paper also considers how CNNs are being combined with complementary technologies, including the Internet of Things, unmanned aerial vehicles, and edge computing, and what this means for deployment in real farming conditions. Economic and sustainability dimensions are explored throughout, with attention to whether the gains from AI adoption are likely to reach smallholder farmers or remain concentrated among larger, better-resourced agribusinesses. Despite genuinely impressive results under controlled benchmark conditions, several barriers to field deployment persist: dataset bias, poor generalisation in complex agricultural environments, computational constraints, and a continuing shortfall in model interpretability. The review closes by identifying priority research directions, including cross-domain transfer learning, explainable AI, the development of field-representative datasets, and participatory approaches to tool design. Taken together, the evidence suggests that CNN-based disease detection holds real promise for agribusiness sustainability, but realising that promise will depend on sustained interdisciplinary collaboration and deployment strategies that are sensitive to local context rather than assuming one-size-fits-all solutions.

Chemical Functionalization of Medical Textiles: Emerging Strategies for Smart Wound Healing, Therapeutic Delivery, and Regenerative Medicine

2026-07-01T13:48:14+00:00

Medical textiles have moved a long way from their original role as simple protective covers. Fibres, yarns, and fabrics can now be chemically engineered to sense, signal, and actively participate in tissue repair, rather than merely shielding a wound from the outside world. This critical review brings together recent work on the chemical functionalization of textile substrates across three connected areas: wound care, therapeutic delivery, and regenerative medicine. It begins with the chemistry that turns an inert fibre into a reactive platform — plasma and physical activation, wet-chemical grafting, click chemistry and bioconjugation, and nanoparticle or sol–gel coatings — before turning to antimicrobial functionalization using metal and metal-oxide nanoparticles, chitosan and related polycationic biopolymers, and antimicrobial peptides. The discussion then moves to therapeutic delivery through electrospun nanofibres, chemically modified gauzes, functionalized sutures, and haemostatic textiles, and from there to the growing convergence between textile science and electronics, in which fibres and fabrics are functionalized to track pH, temperature, exudate biomarkers, and infection status in real time, supporting closed-loop and theranostic wound management. A further section considers textile-derived scaffolds for regenerative medicine, including electrospun nanofibrous constructs, decellularized matrices, three-dimensional bioprinted skin substitutes, and peptide- or growth-factor-functionalized fibres designed to mimic the extracellular matrix. Throughout, laboratory promise is weighed against translational evidence, with attention to nanomaterial safety, comparative clinical efficacy, and the sustainability cost of chemically intensive finishing processes. Taken together, the literature suggests that individual functionalization chemistries are reaching real maturity, but combining antimicrobial, sensing, and regenerative function within one durable, scalable textile remains the harder, still largely unsolved problem. The review closes by identifying priorities for future work: standardised biocompatibility testing, clearer regulatory pathways, and design choices that reconcile chemical sophistication with the comfort, breathability, and biodegradability expected of next-generation medical textiles.

Phytochemical Profile and Therapeutic Potential of Acalypha indica: A Critical Review

2026-07-02T12:38:18+00:00

Acalypha indica L. (Euphorbiaceae), commonly known as Indian copperleaf or Indian nettle, is a pantropical herbaceous weed with a long-standing presence in Ayurvedic, Siddha and African ethnomedical systems. Despite its taxonomic obscurity and its frequent dismissal as nothing more than a roadside weed, the species has attracted sustained scientific attention because of an unusually diverse phytochemical repertoire that includes cyanogenic pyridone glucosides, flavonol glycosides, tannins, a pyranoquinolinone alkaloid, sterols and a range of volatile constituents. This critical review synthesises the phytochemical and pharmacological literature on A. indica published over roughly the past two decades, setting recent computational and nanotechnological studies against the longer arc of ethnopharmacological validation that the plant has undergone. The principal bioactive classes are catalogued, and the evidence underlying its antioxidant, antimicrobial, anti-inflammatory, antidiabetic, anticancer, wound-healing, antiasthmatic, neuroprotective and antiparasitic properties is weighed with explicit attention to methodological rigour, extract standardisation and the gap that still separates in vitro promise from in vivo, let alone clinical, confirmation. The toxicological literature, including clinical reports of glucose-6-phosphate dehydrogenase-related haemolysis and methaemoglobinaemia following ingestion, is examined to put the plant's dual identity — remedy and hazard at once — into proper context. Emerging applications in green nanoparticle synthesis and in silico drug discovery, including docking studies implicating compounds such as corilagin, are discussed as promising but still preliminary lines of work. The review concludes that A. indica possesses a biologically plausible and reproducibly demonstrated multi-target pharmacological profile, but that the field remains held back by inconsistent extract characterisation, an almost complete absence of controlled human trials, and insufficient attention, in much of the pharmacological literature, to the cyanogenic risk inherent in raw plant material. Priorities for future work — standardisation, pharmacokinetic characterisation and properly designed clinical evaluation — are set out in closing.

Artificial Intelligence and Machine Learning in Pest and Disease Surveillance: From Detection to Decision Support

2026-07-11T11:26:18+00:00

Plant pests and diseases remain among the most persistent threats to global food security, reducing potential crop yields substantially every year and imposing heavy economic losses on producers across both smallholder and industrial farming systems. Conventional surveillance relies on manual scouting and visual diagnosis, approaches that are slow, subjective, and poorly suited to the scale and speed at which modern outbreaks develop. Over the past decade, artificial intelligence and machine learning have reshaped the surveillance landscape, offering tools that span image-based detection, sensor-driven monitoring, predictive modelling, and decision support. This review synthesises developments across this continuum, tracing the progression from convolutional neural networks and vision transformers used for leaf-level disease classification, through object detection frameworks and Internet of Things-enabled smart traps used for insect pest monitoring, to remote sensing and species distribution models used for landscape-scale forecasting, and finally to decision support systems that translate model outputs into actionable field guidance. Particular attention is given to persistent technical constraints, including the scarcity and imbalance of labelled field data, poor generalisation of models trained on curated datasets when deployed under variable field conditions, and the limited interpretability of deep architectures, alongside emerging responses such as transfer learning, generative data augmentation, and explainable artificial intelligence. The review further considers infrastructural and adoption barriers relevant to resource-constrained farming systems, including connectivity, computational cost, and the integration of artificial intelligence outputs into existing extension and decision-making structures. Drawing on this synthesis, priority directions for future research are identified, including federated and privacy-preserving learning across distributed agricultural datasets, multimodal sensor fusion, and closer coupling between predictive analytics and site-specific intervention. The findings indicate that while detection accuracy has advanced considerably, the translation of artificial intelligence outputs into reliable, trusted, and economically viable decision support remains the central unresolved challenge for the field.

Microsponge-based Drug Delivery Systems: Recent Developments and Therapeutic Applications

2026-07-11T11:32:04+00:00

Microsponge delivery systems occupy a distinctive niche among particulate drug carriers, combining a porous, highly cross-linked polymeric architecture with the capacity to entrap, protect and gradually liberate a wide range of therapeutic agents. Unlike liposomes or polymeric nanoparticles, microsponges are mechanically robust, chemically inert across a broad pH range and amenable to incorporation into conventional dosage forms such as gels, creams, capsules and tablets. Over the past decade, the field has moved well beyond its original dermatological remit, extending into gastroretentive and colon-targeted oral delivery, ocular therapeutics, and, through the closely related cyclodextrin-based nanosponge platform, oncology and antimicrobial applications. This review synthesises the contemporary literature on microsponge design, preparation and evaluation, with particular attention to the physicochemical determinants of drug loading and release, the comparative merits of quasi-emulsion solvent diffusion and related fabrication techniques, and the clinical evidence supporting microencapsulated benzoyl peroxide and tretinoin formulations in acne management. The regulatory pathway for microsponge-based products, the expanding role of nanosponge variants in cancer drug delivery, and emerging computational approaches to formulation optimisation are also examined. The review concludes that microsponge technology has matured from a niche cosmetic tool into a versatile platform with demonstrable clinical benefit, while identifying scale-up reproducibility, standardised characterisation and long-term biocompatibility data as the principal barriers to broader translation.

Types, Access Levels, and Determinants of Farm Input Access among Arable Crop Farmers in South-South, Nigeria

2026-07-08T10:51:41+00:00

Aims: This study examined the types of farm inputs used by arable crop farmers, assessed their level of access to key farm inputs, and analysed the determinants of input access.

Study Design: A cross-sectional survey design was adopted.

Place and Duration of Study: The study was conducted among arable crop farmers in Rivers, Delta, and Edo States, Nigeria, from February to April 2026.

Methodology: A multi-stage sampling procedure was used to select 600 arable crop farmers. Primary data were collected using a structured questionnaire and analysed using descriptive statistics and logistic regression analysis.

Results: Most respondents were female (64%) and married (66%), with a mean age of 43 years, an average household size of six persons, and mean farming experience of 15 years. About 61% had at least secondary education, while 59% belonged to cooperative societies and 52% had access to extension services. The major inputs used were hired labour (87%), fertiliser (82%), family labour (78%), herbicides (76%), and improved seeds (73%). Access was high for improved seeds (mean = 2.93) and fertiliser (mean = 3.02), but low for mechanised services (mean = 2.19), credit (mean = 2.32), and irrigation facilities (mean = 2.07). The logistic regression model was statistically significant (LR Chi-square = 148.61, p < 0.01; pseudo R² = 0.410). Education (coefficient = 0.421), farm size (coefficient = 0.563), and cooperative membership (coefficient = 0.719) positively influenced access to farm inputs, whereas distance to market had a negative effect (coefficient = -0.487).

Conclusion: Arable crop farmers in Rivers, Delta, and Edo States had relatively better access to improved seeds and fertiliser than to mechanisation, agricultural credit, and irrigation facilities. Strengthening farmer cooperatives, improving rural road and market infrastructure, expanding farmer education, and increasing access to credit, mechanisation, and irrigation services are essential for improving farm input access and agricultural productivity.