In this paper, we discuss and address the significant educational disparity and academic challenges encountered by students diagnosed with Attention Deficit Hyperactivity Disorder (ADHD). Traditional learning environments often fail to accommodate the unique cognitive needs and attention deficits of these students, leading to difficulties in focusing, retaining information, and managing study schedules effectively. Consequently, lower academic performance, increased stress levels, and diminished self-esteem are common consequences.

The goal of this study is to provide a solution that caters to the diverse learning needs of students with Attention Deficit Hyperactivity Disorder. Our project introduces an innovative educational app specifically designed for this demographic. The app utilizes a personalized learning system that adapts to individual preferences, integrating Artificial Intelligence to provide intelligent responses. Key features include screen-time monitoring, daily schedule management, group study jams, and study reminders. Moreover, this solution emphasizes affordability and accessibility, particularly targeting students with limited resources. By addressing the key challenges faced by students with Attention Deficit Hyperactivity Disorder in traditional learning environments, our educational app aims to empower them with the tools necessary to thrive academically and mitigate the negative consequences associated with their condition. We propose a novel way to address Attention Deficit Hyperactivity Disorder by using a smart Artificial Intelligence-based application.

Rocha pear, a well-known Portuguese fruit, faces significant pre- and post-harvest challenges due to fungal infections. Stemphylium vesicarium is a phytopathogenic fungus that causes brown spot disease and has been responsible for significant economic losses. The available synthetic treatments are not fully effective and can negatively impact the environment, highlighting the need for sustainable alternatives. Several seaweeds are known for their antimicrobial properties, showing potential in this context. Pre-harvest trials investigated the effects of Fucus vesiculosus and Sargassum muticum extracts on pear trees. The seaweed extracts were applied both before and after inoculation with the pathogen S. vesicarium. The continuous application of S. muticum extract effectively prevented disease symptoms, possibly due to bioactive compounds including phytohormones, fatty acids, among others, suggesting the potential of seaweeds as natural priming agents to boost plant defenses.

Following the value-chain process of Rocha pear, post-harvest fungal infections, caused by pathogens such as Alternaria alternata, Botrytis cinerea, Fusarium oxysporum, and Penicillium expansum, also result in substantial losses, ranging from 20 to 25% of total fruit industry output. Seaweed extracts from Asparagopsis armata, Codium sp., F. vesiculosus, and S. muticum were evaluated for their antifungal properties. In vitro tests revealed that A. armata extracts strongly inhibited fungal growth, and promising in vivo results against B. cinerea were obtained using S. muticum.

These studies highlight the potential of seaweed-derived compounds in managing both pre- and post-harvest fungal diseases in Rocha pear, offering a more sustainable and ecofriendly approach to agricultural practices and fostering a bioeconomy that links the sea to the farm.

Water kefir is a fermented probiotic-rich beverage that has potential health benefits, which include improving digestive health and preventing chronic disorders like obesity, irritable bowel syndrome, hyperlipidaemia, and hypertension. It is also a very good alternative for someone who is lactose intolerance and cannot have milk-based fermented drinks. This study aims to formulate and examine the microbial and chemical properties of three samples (A, B and C) of fermented drinks made from water kefir grains. For the development of the water kefir-based fermented drinks, a concentration of 2-6 gm of water kefir grains (WKG) was inoculated into 100 ml of mineral water containing 10 gm of brown sugar in aerobic conditions. The samples' pH, titratable acidity, water activity, color, total soluble solids, total bacterial count (TPC), antioxidant activity, and total phenolic content were assessed using AOAC methods. The sensory evaluation of the water kefir samples was examined using a nine-point hedonic scale.

The chemical and microbiological examination revealed that sample C was more desirable in all aspects as compared to samples A and B, with a pH level of 3.86; a TA of 0.04 meq/mL; water activity=0.9273±0.04 AW Aw; TPC= 3.1 × 10⁷; DPPH= 78.75%; phenolic compounds= 40.755 mg/100 GAE; and an overall acceptability score of 7.29. The colour parameters of sample C were L* (lightness) = 20.29, a* (reddish/greenish) = -2.38, b* (yellowish/bluish) = 5.61, C**(saturation/vividness) = 6.01, and h° (hue angle) = 112.93. The overall results show that this concentration of water kefir fermented drink could be a great source of vegan fermented drink as well as a good alternative for preventing many diseases, including gut health issues.

Skin cancer is one of the most strongly growing types of cancer due to pollution and many other factors. The early diagnosing of skin cancer and its types can contribute to stop this rapid growth of skin cancer disease and for this purpose AI can be utilized. Skin cancer is one of the most researched topics, with various methods used to diagnose it; however, there is always room for improvement and new technologies to perform this task more effectively. This study aimed to utilize a data set containing skin cancer types, known as PAD-UFES-20, to classify different types of skin cancers using advanced data pre-processing and a combination of deep learning and machine learning techniques and finally these features were analyzed to determine what impacted most for disease to be classified as skin cancer. The proposed methodology includes detailed pre-processing of the data set, a custom Convolutional Neural Network model for feature extraction, training Boosting models on pre-processed data, and finally finding features that impact the model the most to identify disease to be a skin cancer type. The CatBoost Classifier, XGBoost Classifier, and LGBM Classifier were trained on the PAD-UFES-20 data set to diagnose skin cancer and its six different types. With better pre-processing techniques, we obtained more accurate results compared to previous studies. The XGBoost Classifier produced the highest accuracy compared to CatBoost and LGBM Classifiers. In addition, this study also includes research on the features of the data set that most effect the prediction of the model. In summary, the proposed method focused more on the best pre-processing and feature extraction techniques to obtain the most possible predictions from Boosting models.

As AI and transformers make progress, Vision-Language Models (VLMs) are set to have a big impact on medical diagnostics when it comes to understanding picture-based data.
X-rays play a key role in radio diagnoses, helping doctors spot many different illnesses.
This research aims to train a Vision-Language Model Visual BERT, to diagnose diseases by using both written patient info and X-ray images.
In the past few years, researchers around the world have tried out various AI models to identify different health problems; however, since Vision-Language Models are pretty new, people use them for general tools like chatbots.
But these models could be useful for automating the process of diagnosing diseases from X-rays.
The proposed methodology involves merging three separate datasets to build a full dataset that covers many diseases that X-ray images can spot. By bringing together different datasets, the model can figure out how to spot a wide range of conditions, which makes it better at diagnosing and more useful.
This method shows how VLMs can change medical diagnostics for the better, giving doctors a smart way to spot diseases faster and more frequently.
Visual BERT is trained on the dataset to diagnose diseases using visual as well as textual data.
For the evaluation matrix, an accuracy score is used and after fine tuning the model on the combined dataset, we obtained a 60% accuracy score.
To test the model, a front-end app with Streamlit was made to make it easier to use for end users.

Laparoscopic surgeries are minimally invasive, requiring only small incisions which result in faster patient recovery and a lower risk of complications. Despite these advantages, surgeons face some challenges, such as limited visibility and control over instruments, potentially compromising precision and coordination during procedures. To address these limitations, advanced technological systems enhance the visibility, control, and overall effectiveness of laparoscopic surgeries.

This research introduces an instrument segmentation method using a modified U-Net model. The model integrates residual blocks in the encoder to optimize learning and prevent gradient degradation, enabling the capture of complex patterns. The decoder is designed with two branches: one focused on instrument segmentation and the other on background segmentation. By combining both outputs, the system improves the accuracy and efficiency of segmenting surgical instruments in real-time.

The system's performance was evaluated through metrics such as the Jaccard index, precision, recall, F1 score, and accuracy. Tests under geometric and signal processing distortions were also conducted to replicate varying surgical conditions, revealing the system's high robustness and adaptability. The results show a high efficiency with an accuracy of 0.94 and a Jaccard index of 0.93. Additionally, this approach demonstrates significant improvements in identifying instruments accurately and reducing potential patient injury.

This development enhances surgical precision and increases patient safety during laparoscopic procedures. Furthermore, it provides a valuable tool for training and evaluating surgeons' psychomotor skills. This innovation represents a step toward the future of minimally invasive surgery, minimizing direct surgeon intervention and improving overall patient outcomes.

Introduction: All are interested in the estimation of the sale price of crop yield beforehand. Crop yield is dependent on the growth rate of the plant. Plant growth rate depends on factors like soil, water, sunlight, and season. Due to this multi-factor dependency, it is not easy to estimate the sale price of the crop yield or predict the timeline beforehand. Objective: By advancing AI technology, we can leverage and eliminate the challenges and predict crop yield, timeline, and sale price. We use computer vision, Deep Learning, and regression to predict the estimation of the sales price of the crop yield. Materials/Methods: By using computer vision YOLO algorithms, we detect plants in the field and categorize the plants using the CNN classification algorithm. We use IOT devices to monitor the growth of the plant from time to time and collect the data. The collected data are used to predict time, crop yield, and sale price beforehand. The prediction is derived based on historical data of sales prices in different sessions and a plant growth data set using regression algorithms. Result: The experimental results demonstrate the effectiveness of the proposed approach, where we detect the plant using computer vision; categorize the plant using CNN; and accurately predict yield, timeline, and sale price using regression. To evaluate the proposed framework, we conducted experiments using sample data. Through hypothesis testing using the "T Test" and "chi-square" test, we failed to reject the null hypothesis, and the evaluation metrics show that the accuracy of plant detection is 92.5; the categorization of plants using CNN is 96.31; and the accuracy score obtained using regression to predict yield, timeline, and sale price is 91.57. The Precision, Recall, and F1 scores also look good.

Making meanings out of the huge amounts of data that are generated almost every second across the globe is becoming an important data science concern. Discovering a unique feature(s) that can aid in the classification, prediction, and general analysis of a particular system under consideration could be considered a major task of data science. Data science tools are desperately needed to draw insights from the vast amounts of data that are generated for critical decision-making and planning for the government, businesses, military, politics, and academia, amongst several other critical organizations. In this paper, our motivation is to investigate whether Benford’s law can serve as a data science tool. For this, experiments were performed on Point of Sale (POS) datasets. POS key features such as TranTime (Transaction time in seconds), BreakTime (Break time including idle time in seconds), ArtNum (Number of items, i.e., basket size), and Amount (Transaction value) served as inputs into Benford’s law. Results obtained showed that the Amount feature of the POS system perfectly conforms to Benford’s law based on its plots and chi-square divergence. The results showed that normal Amount transactions on POS systems followed Benford’s law, whereas fraudulent/tampered POS Amount transactions deviated from this law. We found that Benford’s law can actually serve as a data science tool by giving us insights into POS operations.

Conventional packaging, often reliant on synthetic preservatives and non-biodegradable materials, is incompatible with the EU’s Green Deal and Farm to Fork Strategy, which promote a reduced dependence on chemically based components for single-use plastics. As a result, there is a growing need for eco-friendly packaging alternatives that preserve fresh produce while minimizing their environmental impact. Sustainable packaging, particularly bio-based and biodegradable materials, presents a promising solution by reducing waste and enhancing food preservation. In line with zero-waste principles, food industry by-products, such as dried apple by-products, can be repurposed into innovative packaging materials. Combined with natural polymers like pectin, these by-products can create functional absorbent pads that reduce moisture and prevent spoilage in strawberries. The present study aimed to develop a biodegradable packaging film based on apple by-products to be applied as a controller of strawberry degradation. Apple by-products (30% w/v) were incorporated into a pectin matrix (5% w/v) with sorbitol, forming the primary components of the films. The films were evaluated for microbiological stability, water solubility, water absorption, colour properties, and biodegradability in soil. A response surface methodology was employed to optimize the production conditions of the films, varying the pectin concentrations (0.5% to 5%), by-product content (5% to 30%), and solid-to-area ratios (0.33 to 0.132 g/cm²). The results demonstrated that the pectin concentration and by-product content significantly influenced the films' water absorption capacity and microbiological stability. Over a 38-day period, the films exhibited biodegradation rates ranging from 62.3% to 98.51%. More than 50% of the material disintegrated during the assay period, highlighting the rapid and environmentally safe degradation potential of these pads. The use of agrifood by-products aligns with zero-waste policies and promotes sustainable consumption, providing an eco-friendly solution for extending the shelf-life of fresh fruits.

Introduction: The growing demand for different dietary interventions including synbiotics that promote gut health benefits. We characterized the novel formulation of a synbiotic drink (SD) combination of Kefir (probiotic) and basil seed mucilage (prebiotic). Kefir, a milk-based fermented beverage, contains beneficial microorganisms and basil seed, a natural polysaccharide, and acts as prebiotic and fat-replacer agent.

Methodology: Kefir grains (3% w/v) and basil seed mucilage extract (BSME, 0.3% w/v) were inoculated with cow-milk and further allowed to ferment at 25°C for 24 hours. Stability and zeta-potential of SD was analysed using Zetasizer. Formulation of SD was estimated using Fourier-Transform Infrared Spectroscopy (FTIR). Micronutrient analyses were performed using AOAC methods. Amino acid profiling and fatty acid content was estimated using LC-MS and GC-FID, respectively. Antioxidant potential was evaluated through DPPH radical-scavenging activity, total phenolic compounds (TPC), total flavonoid content (TFC), and Ferric reducing antioxidant power (FRAP) assay.

Results: Zetasizer showed that the Zeta potential of 15 mV indicated towards substantial stability of synthesized SD. FTIR analysis confirms that the physicochemical properties of the milk changed during the fermentation process, due to addition of BSME. Micronutrient profiling revealed iron 3.5mg, calcium 29.3mg, potassium 120.6mg, and sodium 59.3mg per 100mL. Amino acid and fatty acid analysis revealed notable concentrations of essential amino acids and unsaturated fatty acids. Antioxidant assays indicated DPPH inhibition at 82%, TPC at 24 mgGAE/100mL, TFC at 61mg QE/100ml, and FRAP at 31mgTE/100mL

Conclusion: Novel SD formulation showed noble stability and micronutrient content and significant antioxidant potential. These findings suggest that this novel SD could serve as a beneficial dietary intervention for gut health.