Volume 12 | Issue 2 |

 Abstract

The agricultural industry has been facing challenges in traditional and manual visual grading of fruits due to its laborious nature and inconsistent inspection and classification process. To accurately estimate yield and automate harvesting, it is crucial to classify the fruits based on their ripening stages. However, it can be difficult to differentiate between the ripening stages of the same fruit variety due to high similarity in their images during the ripening cycle. To address these challenges, we plan to develop an accurate, fast, and reliable fruit detection system using deep learning techniques. The modernization of crops offers opportunities for better quality harvests and significant cost savings. Our approach involves adapting the state-of-the art object detector faster R-CNN, using transfer learning, to detect fruits from images obtained through model colour (RGB). Spectroscopy analysis to predict the quality of fruit and categorization by using AS7265x Spectrophotometer. Our system's robustness will enable us to differentiate between fruit varieties and determine the ripening stage of a particular fruit with effectiveness and accuracy. The system will also efficiently segment multiple instances of fruits from an image and accurately grade individual objects

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

RGB,Spectrophotometer,Spectroscopy,Transfer Learning,R-CNN.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project introduces an Internet of Things (IoT) based pressure monitoring system utilizing the BMP085 sensor. The primary objective is to measure and monitor atmospheric pressure, offering real-time data visualization through the Blynk IoT platform. The Adafruit BMP085 sensor is employed for measuring temperature, pressure, and altitude, with an Arduino microcontroller and an ESP8266 Wi-Fi module facilitating wireless connectivity.The system leverages the Blynk library to establish a connection between the Arduino and the Blynk platform. Through the Blynk app, users gain remote access to pressure readings and receive alerts based on predefined thresholds. Additionally, the system controls an output pin, enabling the activation of a buzzer or external device in response to detected pressure levels.The implementation involves initializing the BMP085 sensor, configuring Wi-Fi credentials, and establishing a seamless connection with the Blynk platform. Sensor readings are then acquired and transmitted to the Blynk app, where they are visually displayed on a virtual terminal. Continuous monitoring of pressure levels provides visual feedback on both the Blynk app and the serial monitor.The proposed IoT-based pressure monitoring system boasts various advantages. It offers real-time data visualization, allowing users to remotely monitor atmospheric conditions. Integration with the Blynk platform enables the customization of alerts and notifications based on user-defined pressure thresholds. Moreover, the system exhibits flexibility for expansion, accommodating additional sensors or actuators to cater to more complex applications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Blood Pressure Monitoring System,Internet of Things(IoT),Blynk Platform,Data Visualization,Pressure Thresholds.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project is an effective technique to categorize data on specific requirements and conditions for the majority of marine species. To determine which species are all threatened or endangered, depending on the situation. Not only is the bulk of the data being classified here, but also the causes of and fixes for the classification of the data. The actual process of decision-making and branching based on the qualities of the data is carried out using a set of algorithms and tools. It facilitates the creation of efficient machine learning models that are capable of making precise predictions. Logistic regression is used to estimate discrete values (typically binary values like 0/1) from a collection of independent variables. The logic function is changed to match the data,It helps in estimating how likely an event is to occur. These algorithms function on this application well. Since there are just two outcomes in this project, logistic regression is employed as a binary classifier. It will also explain the causes and a fix for that here.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine Learning Models,Logistic Regression,Logic Function,Binary Classifier,Precise Prediction

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Adult and pediatric populations have distinct medication pharmacokinetics and pharmacodynamics with the latter being more variable. While these variations in pharmacokinetics and pharmacodynamics support particular research, they also bring up a variety of moral and practical concerns. The invasiveness of the procedures and the barriers to patient recruitment are the main practical challenges to overcome while conducting clinical research in children. The Classical pharmacokinetic studies cannot often be performed on children due to the invasiveness associated with pain/anxiety and blood loss, especially in neonates and infants. Pharmacokinetic , pharmacodynamic modeling-based population techniques are especially attractive for pediatric populations due to their ability to handle sparse data. It has previously been highlighted how important population techniques are for examining dose-concentration-effect correlations and for qualitatively and quantitatively evaluating variables that could account for interindividual variability.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Screening methods , Drug studies, In vivo-vitro studies, Animal cell culture Technique

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The Image Generation and Captioning Application project represents a groundbreaking fusion of artificial intelligence and creative expression, revolutionizing content creation. This innovative application leverages AI and computer vision to deliver a user-friendly platform for generating high-quality images with contextually relevant captions. Key objectives include developing resilient models, creating an intuitive interface, ensuring scalability, and maintaining ethical content generation. With applications spanning marketing, advertising, social media, and education, the project aims to redefine content creation by efficiently pairing compelling visuals with informative captions. The accompanying comprehensive review explores state-of-the-art techniques, emphasizing multimodal approaches, ethical considerations, and diverse applications. Addressing technical challenges and ethical guidelines, this project stands at the forefront of reshaping how we interact with visual information in the digital age.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Image Generation, Captioning Application, User-Friendly Interface, Deep Learning, Generative Adversarial Networks (GANs)

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Schizophrenia is a psychiatric disorder affecting 1% of the population, characterized by a split mind disorder affecting emotions, thoughts, reasoning, and behaviour. It is a genetically influenced neurodevelopmental illness, with symptoms appearing after a 1-3% latency period. The disorder is characterized by delusions, hallucinations, illogical conclusions, and withdrawal from social interactions. The term "schizophrenia" was coined in 1908 by Swedish psychiatrist Eugen Bleuler, and its symptoms were first documented in Haslam and Pinel's 1809 publication. Mindfulness is a meta-cognitive exercise that involves focusing on the present moment while reducing emotional and cognitive reactivity. It originated from Buddhist vipassana meditation and has been applied to various health issues, particularly those with psychopathological profiles and somatic disorders. Mindfulness-based interventions (MBIs) have been shown to be effective in treating various mental health disorders. MBIs have shown moderate to strong effect sizes on depression and anxiety, and have been found to be beneficial during pregnancy. However, the benefits of mindfulness practices as stand-alone interventions are unclear. MBIs have also been found to improve insomnia and sleep quality, with effects lasting 3 months postintervention. They have also been found to have a positive effect on eating disorders, addiction, psychosis, post-traumatic stress disorder, and autism spectrum disorders. MBIs have also been shown to improve physical health outcomes for cancer patients, particularly in reducing cancer-related fatigue (CRF) scores. Furthermore, contemplative movement has been suggested to improve lung function and physical activity in COPD patients.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Schizophrenia, Mindfulness-based interventions, addiction, psychosis, post-traumatic stress disorder, and autism spectrum disorders

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The fast-spreading infection of the retina is affecting persons of every age. There is photosensitive optic nerve material within a person's retina. The objective of the proposed approach is to gather a dataset of retinal illnesses so that the model can be trained on a range of images utilizing an open resume to enhance our standing. To identify the thing by analyzing the images and videos. From the smallest set of images if the retina, a machine learning technique based Deep Convolutional Neural Network (Deep CNN) will be used to determine the major retinal issues. The architecture consists of five layers, of which the second hidden layer and the third convolution layer are utilized to enhance and sharpen the images. The high as well as medium range characteristics are improved when the low-level characteristics are retrieved. Based on an experimental assessment, the suggested framework outperforms the others utilizing the multi-class Based on each stage's ability to recall, efficiency, and duration consumption, a complete assessment is being created. ss Kaggle dataset in terms of validity. On the Kaggle dataset, the recommended technique yielded a 97% accuracy rate.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine Learning, Deep CNN, Convolutional Neural Network, CAT Boost Algorithm

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The aim of this investigation was to develop fast dissolving tablets containing Cyproheptadine Hydrochloride, with the goal of achieving a high onset of action. Fast dissolving tablet of Cyproheptadine hydrochloride was prepared by using direct compression method, there were nine batches were prepared of fast dissolving tablets, by using super disintegrant as crosspovidone ,croscarmellose and SSG. The fast dissolving tablets are evaluated for various parameters, the FDT of Cyproheptadine HCL containing crosspovidone showed faster disintegration time at concentrations 5% as compare to other. Hence from all nine formulation batch B3 showed better result like drug content, disintegrating time, drug release hence this is our optimized batch.Aalso, B3 was found stable during the stability study for 2 months. Hence prepared Fast dissolving tablet was stable in all conditions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Fast Dissolving Tablets, Cyproheptadine, Direct compression

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Neuroleptics, also known as antipsychotic medications, are used to treat and manage symptoms of many psychiatric disorders. They fall into two classes: first-generation or "typical" antipsychotics and second-generation or "atypical" antipsychotics. Both first and second-generation antipsychotics are used in various neuropsychiatric conditions. These include attention-deficit hyperactivity disorder (ADHD), behavioral disturbances in dementia, geriatric agitation, depression, eating disorders, personality disorders, insomnia, generalized anxiety disorder, obsessive-compulsive disorder, post-traumatic stress disorder (PTSD), and substance use and dependence disorders. For many of these conditions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Neuroleptics, classification, Types, Advantages, Disadvantages, Advers effects Neuroleptic Malignant Syndrome, Treatment

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Tuberculosis (TB), one of today's most deadly diseases, is caused by Mycobacterium tuberculosis and primarily affects the lungs, often exploiting weakened immune systems. TB poses a significant threat, with mortality rates escalating if left undetected. To address this challenge, various computer-assisted diagnostic methods have emerged, leveraging machine learning, particularly deep learning, in image processing. By analyzing chest X-rays, these techniques aim to provide more accurate, timely, and reliable diagnoses. Recent studies suggest that machine learning-based approaches can outperform manual diagnosis, offering superior accuracy. Notably, Digital image processing (DIP) is gaining prominence in biomedical research. Leveraging image processing, Support Vector Machine (SVM) models can effectively classify lung abnormalities indicative of TB. The primary focus of this study is to detect tuberculosis through the implementation of machine learning models trained on chest X-ray images.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Mycobacterium Tuberculosis, Digital Image Processing (DIP), Machine Learning, Deep Learning, Support Vector Machine (SVM)

  License

Creative Commons Attribution 4.0 and The Open Definition