Category Archives: Uncategorized

Authors: Zachariah Munyoro Mwangi, Mwangi,Alice Nambiro

Abstract: Beach-litter management involves taking measures to minimize waste accumulation along the coastal environments towards healthy marine ecosystem. It involves various strategies including anthropogenic waste prevention, monitoring, mitigation and removal. Installation and positioning of trash bins, and interactive signage is one of the basic mechanism that plays key role in eradication of beach litter. Beach-litter management also entails environmental awareness, targeted campaigns and other behavioural interventions to reduce the gap between beach users’ actual behavioural characteristics and standard environmental values. However, evidence on specific paired behavioural relationships among Kenyan coastal beach users remains limited. This study examined four relationships between bin visibility versus bin use, disposal guidance versus litter-disposal behaviour, noticing litter versus concern about litter and frequency of beach visits versus litter-disposal behaviour. Cross-sectional questionnaire survey was conducted on selected beaches in Mombasa, Kilifi and Kwale involving 287 valid respondents. Responses were categorised, cross-tabulation and Pearson’s chi-square was determined. Simulated p-values were undertaken where necessary with Cramer’s V for association magnitude determined. There was statistical significance between the first three relationships, that is, bin visibility versus bin use, which had the largest observed association magnitude of 39.4%, disposal guidance versus litter-disposal behaviour and noticing litter versus concern about litter. The fourth relationship, frequency of beach visits versus litter-disposal behaviour was not statistically significant. This suggests that visiting beach many times does not necessarily influence change in beach user’s behaviour towards littering

DOI: https://doi.org/10.5281/zenodo.22207685

 

Published by: vikaspatanker

Authors: Abirami A, Miranda Lakshmi T, Martin A

Abstract: Conversational emotion recognition is inherently challenging because an utterance's emotional label does not depend on wording alone — it is shaped jointly by content, delivery, and the dialogue history surrounding it. This work introduces a multimodal deep-learning pipeline that fuses textual, acoustic, and contextual signals to classify emotion at the utterance level within conversations. Linguistic meaning is captured through pretrained BERT embeddings, broad acoustic patterns through Wav2Vec2 embeddings, and explicit vocal-affect cues through handcrafted prosodic descriptors (pitch statistics and short-time energy). Once concatenated at the utterance level, these heterogeneous features are passed into a Bidirectional Gated Recurrent Unit (BiGRU) that captures dependencies across dialogue turns, with a fully connected head performing the final classification. Because the benchmark dataset's seven-class emotion taxonomy is heavily skewed, a weighted cross-entropy loss built from inverse class-frequency statistics is applied to offset this imbalance during training. On the MELD (Multimodal EmotionLines Dataset) benchmark, the proposed pipeline reaches 77.56% overall accuracy and a weighted F1-score of 0.804, with per-class ROC-AUC spanning 0.89 to 0.96. Confusion-matrix and error analysis reveal that common emotions such as neutral and joy are classified reliably, whereas rarer emotions such as fear and disgust remain substantially harder to recognize even with class-weighted training — underlining how persistent the data-imbalance problem remains in this domain and pointing toward future work on stronger imbalance-handling and context-modelling techniques.

DOI: https://doi.org/10.5281/zenodo.22204728

Published by: vikaspatanker

Authors: T. Gopalakrishnan, Boopathi S, B. Niranjan, Mukesh P.M

Abstract: Global almond (Prunus dulcis) production leaves behind a shell fraction that exceeds the mass of the kernel it protects, and the great majority of this lignocellulosic by-product is presently burned, landfilled or sold at low value as biomass fuel. Because the shell is hard, largely cellulosic and available in very large and geographically concentrated volumes wherever almonds are processed, it is a natural candidate for the same role that walnut shell, groundnut shell, coconut shell and rice husk already occupy in the particulate-filled polymer composite literature: a low-cost, renewable, low-density filler for thermosetting resins. This review draws together what is presently known, and what is not yet known, about almond shell powder as a reinforcement for epoxy matrices. It begins with the scale and composition of the waste stream, since both bear directly on whether the material is a viable industrial filler rather than a laboratory curiosity. Processing considerations — drying, size reduction, sieving and surface treatment — are then examined, followed by the mechanical, physical, water-absorption, thermal and morphological behaviour reported for shell-powder-filled epoxy systems, read against the much larger body of work on chemically similar agro-waste fillers where almond-specific data are still sparse. The review closes by identifying the almond shell literature as considerably thinner than that for walnut or coconut shell despite comparable material properties, and names surface treatment optimisation, hybridisation with synthetic or other natural reinforcements, durability under moisture and weathering, and a proper life-cycle assessment against synthetic fillers as the most pressing gaps.

DOI: https://doi.org/10.5281/zenodo.22203936

Published by: vikaspatanker

Authors: Zachariah Munyoro, Alice Nambiro

Abstract: Different researchers have carried out Beach-litter prediction, with basis of their studies being detection and counting of existing litter. Forecasting requires integration of temporal litter patterns, with contextual conditions that influence accumulation. Continuous monitoring of beach litter is necessary within this area of study. Conventional process of monitoring provides observation to a given extent, which limits rapid or automated assessment. AI-based detection allows automatic identification and quantification, allowing monitoring to continue from detection towards prediction. Existing methods address detection, forecasting or contextual integration separately. Various predictive studies use historical litter records, contextual variables, camera observations and Machine Learning. Limited architectural integration connects AI-derived litter measurements directly with temporal and contextual information for multi-predictor variables within multi-duration dimensions. This study developed an AI-based predictive model architecture. The model connected automated litter measurement temporal construction, contextual integration, predictive modelling and forecasting generation. Images were captured through IoT-enabled cameras, subjected under RT-DETRv2, which detected, classified and counted the objects. The output of this process is category-specific quantitative litter observations. The image-level counts are aggregated into beach-week observations, forming temporal litter representation. The temporal information provides the predictive baseline. The predictive model generated category-specific forecasts at multiple future durations. These were weekly, bi-weekly and monthly forecasts. The architecture linked AI-based measurement (RT-DETRv2), data integration, prediction and monitoring output in one end-to-end flow. The model provides a framework for anticipatory beach-litter monitoring instead of detection alone. The output of the predictive model architecture provide diverse options necessary for specific management decision making as well as a feedback loop to the predictive process.

Published by: vikaspatanker

Authors: Deepa Shree R

Abstract: The rapid rise of antimicrobial resistance necessitates robust diagnostic tools that can integrate heterogeneous clinical data across decentralized healthcare institutions while ensuring patient data confidentiality. To address these requirements, this framework leverages federated learning to enable collaborative model training across institutions without necessitating data centralization (Zwiers et al., 2024), while simultaneously incorporating Bayesian inference to quantify predictive uncertainty and enhance clinical interpretability (Kumari et al., 2026). Furthermore, by synthesizing multimodal electronic health records, the proposed architecture overcomes the limitations of centralized data silos and addresses the inherent challenges of data bias and clinical validation in AMR research (Hardan et al., 2024; Narra et al., 2024). Antimicrobial resistance makes infections harder to treat, so we need faster and more reliable ways to detect resistant pathogens. Artificial intelligence can help predict resistance using genomic and other biological data (Lastra et al., 2024). However, many current methods depend on centralized datasets (Zwiers et al., 2024), offer little insight into how certain their predictions are, and are difficult to interpret in high-stakes settings (Kumari et al., 2026). In addition, healthcare and biological data are often spread across institutions and cannot be freely shared because of privacy, governance, and regulatory requirements. This paper presents FedBioGuard, a privacy-preserving framework for predicting antimicrobial resistance. It combines federated learning, multimodal data, uncertainty estimates, explainable AI, and evidence-based large language model support. The main goal is to examine whether this approach can make reliable AMR predictions across institutions with different types of data, without sharing raw patient records. Each participating institution keeps its data locally and helps train a shared model by sending model updates. The model can use genomic data, microbiome or metagenomic data when available, and structured clinical information. An uncertainty module shows how reliable each prediction may be, while explainability methods highlight the biological and clinical features that influence the results. A retrieval-augmented language model is used only after prediction to turn the results into clear summaries supported by scientific evidence. By decentralizing the training process, FedBioGuard mitigates the risks associated with data privacy while addressing the limitations of traditional cultivation-based diagnostics that are often too slow to guide immediate treatment decisions (Dayan et al., 2021; Inda-Díaz et al., 2026). By addressing technical hurdles such as data heterogeneity and the "black box" nature of deep learning, this framework fosters the development of transparent, robust clinical decision support systems (Cavallaro et al., 2023). The evaluation will compare centralized, local-only, single-modality, and federated models using simulated data from multiple institutions. The models will be assessed for predictive performance, calibration, uncertainty quality, performance under distribution shifts, and consistency of their explanations. The study aims to provide a reproducible way to examine how privacy-preserving collaboration, multimodal learning, and uncertainty estimation can work together for AMR prediction. FedBioGuard is not intended to replace laboratory susceptibility testing; instead, it is a research framework for studying trustworthy AI-assisted AMR analysis.

Published by: vikaspatanker

Authors: Sachin Gihar

Abstract: Background: Lead poisoning is a severe public health crisis globally. In India, despite the phase-out of leaded gasoline in 2000, pediatric lead exposure remains a critical issue up to 2021. According to a 2020 UNICEF and Pure Earth report, an estimated 275 million Indian children have blood lead levels (BLLs) ≥ 5 µg/dL. The informal recycling of used lead-acid batteries (ULAB), adulterated spices, traditional cosmetics (kohl, sindoor), and Ayurvedic medicines are major contributors to this environmental toxicity. Methods: This paper synthesizes epidemiological data, systematic reviews, and toxicological reports on lead poisoning cases in India up to 2021. Data on BLL prevalence, neurological and hematological impacts, and socioeconomic burdens were analyzed. Results: Studies indicate that the pooled mean BLL in Indian children ranges from 8.8 µg/dL to 10.4 µg/dL, significantly above the CDC's updated reference value. Children residing proximal to informal ULAB recycling sites (e.g., in Patna, Bihar) exhibit alarmingly high BLLs, averaging up to 14.9 µg/dL. Lead toxicity poses a massive economic burden, with diminished IQs estimated to cost India 12.5% of its GDP annually. Conclusion: Lead poisoning in India represents a silent epidemic. Strict enforcement of battery waste management rules, remediation of contaminated sites, and nationwide BLL screening are urgently required.

DOI: https://doi.org/10.5281/zenodo.22124874

Published by: vikaspatanker

Authors: Scott Strozier

Abstract: It is arguably the most popular trope of the science fiction genre, yet over the past couple of decades it has found its way into mainstream science. The concept of time travel, specifically the ability to escape the linear path of time and return to a moment which has already occurred or to preemptively journey to a point in time that has yet to come to pass. The justification of the practical means of this theory come from Eistein’s theories and his well-known statement” Time is relative.” However, a closer examination of Einstein’s theories and the notion of time in relation to the multitude of natural forces acting upon the physical world highlight a misinterpretation of behavior of the property known as time. This paper seeks to mathematically and logically showcase these misconceptions and present an alternative understanding of the functions of time and the impossibility of time travel.

Published by: vikaspatanker

Authors: Hanamantray R. Horaginamani, Prakash R. Khedad, Shreyas Suresh Rathod, Varun S. Naik, Prof. Gopinath Rathod

Abstract: Agricultural pesticide spraying is an essential crop-protection operation, but conventional hand-operated, engine-driven and battery-dependent sprayers can impose operator effort, fuel dependence, inconsistent application and chemical loss. The 21 studies reviewed in this paper collectively cover photovoltaic sprayers, multi-nozzle systems, remote and robotic platforms, autonomous aerial spraying, air-assisted atomization, spray-drift management, variable-rate application and machine-vision control. The literature indicates a progression from replacing manual or fossil-fuel power with photovoltaic electric pumping toward systems that also adapt spray delivery to crop geometry and target conditions. Solar-powered trolley and knapsack systems demonstrate the feasibility of photovoltaic operation and reductions in operator burden; remote and robotic systems provide greater separation between the operator and spray plume; and precision systems demonstrate substantial reductions in applied chemical when spray rate is matched to the target. At the same time, solar intermittency, battery capacity, machine mass, nozzle calibration, pressure control, spray uniformity, drift and sensing cost remain important limitations. This review synthesizes the 21 studies through a transparent corpus-based review methodology and identifies design principles relevant to a practical solar-powered multifaceted sprayer. Based on the synthesis, a modular machine architecture is proposed in which solar PV, battery storage, an efficient DC pump, pressure regulation, a filtered multi-nozzle boom and a stable wheeled chassis form the basic platform, while remote control, flow/pressure sensing and machine vision can be added progressively. The review concludes that the most practical development pathway is a layered system that combines renewable energy, mechanical simplicity, adjustable spraying and provision for future precision automation.

DOI: http://doi.org/10.5281/zenodo.22055698

Published by: vikaspatanker

Authors: S S Davanageri, M MGanganallimath, Shreedhar B Biradar, Ajaykumar G Honnalli, Sanjay S Balulad, Shridhar S Palled

Abstract: Agricultural cultivators are important soil-tillage implements used for breaking soil clods, loosening soil and preparing suitable soil conditions for sowing. The performance and reliability of cultivator components are influenced by soil condition, operating parameters, tool geometry, material properties and the loads acting during field operation. This review paper examines published research related to the design, structural behaviour and optimization of agricultural cultivators and their working components, withemphasis on computer-aided design and finite element analysis.The reviewed studies demonstrate the application of numerical methods for evaluating stress, deformation, structural strength and soil–tool interaction. Research on tine cultivators has investigated different shovel geometries and soil conditions, while other studies have examined cultivator shares under different static loading conditions using the finite element methods. Recent work on a combined cultivator working tool has further demonstrated the influence of tine geometry and angle of attack on stress distribution and structural performance. Based on the reviewed literature, computer-aided modelling and finite element analysis provide useful approaches for identifying critical regions and comparing alternative cultivator designs before physical fabrication. It provides a technical foundation for the proposed future work on design optimization and structural analysis of an agricultural cultivator using SolidWorks.

DOI: http://doi.org/10.5281/zenodo.22055188

Published by: vikaspatanker

Authors: Abdulazeez Danjuma, M. S. Aliyu, Zaharradeen S. Iro, Usman Abdullahi Musa, Abdulrrazaq A Umar, Abdullahi Ahmed Talba

Abstract: Pneumonia is a prominent preventable cause of death in children, leading to 14% of all fatalities under five and over 700,000 paediatric deaths annually. Chest radiography is the principal diagnostic tool, but interpretation depends on radiologist availability and inter-observer variability, causing severe bottlenecks in low- and middle-income countries.A hybrid CNN–Transformer architecture with convolutional local feature extraction and multi-head self-attention for binary pneumonia classification on chest radiographs was designed, implemented, and evaluated. Studies used a publicly available chest radiograph dataset of 5,856 pictures (4,273 pneumonia, 1,583 normal). Five convolutional blocks (32→64→64→128→256 filters) with batch normalisation and dropout (0.3–0.5) generate a 6,400-dimensional feature vector, which is reshaped into a token sequence using positional encoding and passed through two Transformer encoder layers (8 attention heads, feed-forward dimension 512 The hybrid model had 92.0% accuracy, 96.1% precision, 92.8% recall, 94.4% F1-score, and 0.998 AUC. Confusion-matrix analysis on the held-out test partition (n = 879; 641 pneumonia, 238 normal) gave 595 true positives, 214 true negatives, 24 false positives, and 46 false negatives Self-attention and convolutional feature extraction increase discriminative performance over CNN-only baselines, with precision outperforming accuracy. External multi-institutional validation, multi-class subtyping, and attention-based interpretability are needed before clinical application.

DOI: https://doi.org/10.5281/zenodo.22053763

Published by: vikaspatanker