Volume 11 | Issue 5 |

 Abstract

Abstract: -- The Main Objective of this research paper is to find out the early stage of lung cancer and explore the accuracy levels of various machine learning algorithms. After a systematic literature study, we found out that some classifiers have low accuracy and some are higher accuracy but difficult to reached nearer of 100%. Low accuracy and high implementation cost due to improper dealing with DICOM images. For medical image processing many different types of images are used but Computer Tomography (CT) scans are generally preferred because of less noise. Deep learning is proven to be the best method for medical image processing, lung nodule detection and classification, feature extraction and lung cancer stage prediction. In the first stage of this system used image processing techniques to extract lung regions. The segmentation is done using K Means. The features are extracted from the segmented images and the classification are done using various machine learning algorithm. The performances of the proposed approaches are evaluated based on their accuracy, sensitivity, specificity and classification time.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Structural Co-occurrence Matrix (SCM), Classifier, Data Set, ROC curve, Malignant nodule, Benign nodule.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Malware detection is a very important factor in security of internet oriented machines. The combination of different features is used for dynamic malware analysis. The different combinations are generated from APIs, Summary Information, DLL and Registry Keys Changed. Cuckoo sandbox is used for dynamic malware analysis, which is customizable, and provides good accuracy. More than 2300 features are extracted from dynamic analysis of malware and 92 features are extracted statically from binary malware using PEFILE. We used machine learning to discover different types of windows malwares. The dataset used to train the model has static and dynamic analysis of different programs. According to the data every one program was labeled as humanely or malware. There are 6 types of malwares in total: Backdoor, Trojan, Trojan Downloader, Trojan Dropper, Virus, and Worm. Static features are extracting from 39000 hateful binaries and 10000 benign files. Dynamically 800 humanely files and 2200 malware files are analyzed in Cuckoo Sandbox and 2300 features are extracted. The precision of dynamic malware analysis is 94.64% while static analysis precision is 99.36%. The dynamic malware analysis is not effective due to tricky and intelligent behaviors of malwares. The dynamic analysis has some restrictions due to controlled network behavior and it cannot be analyzed completely due to limited access of network.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

API, DLL, Registry Key, Static and Dynamic analysis

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

ABSTRACT: The primary objective of this project is to design and implement a device to aid visually impaired individuals in navigating their surroundings with enhanced confidence and ease. The proposed device aims to alleviate some of the common challenges that visually impaired individuals face while walking. The project intends to mitigate the significant travel-related difficulties faced by visually impaired individuals, which arise due to their restricted ability to gather and interpret visual information. This lack of awareness about their surroundings makes it challenging to navigate both indoor and outdoor environments and increases their risk of accidents and injuries. "There are approximately 37 million people across the globe who are blind according the (WHO) World Health Organization [1]." And if talking about numbers of blind people in India, then "one out of every three blind people in world is Indian i.e., estimated 15 million blind people love in India [2]." Thus, the project aims to develop an All-In-One device that would provide as a guidance to the blind people. The paper focusses on constructing a device for visually impaired (or blind) people that would support them to travel independently. The Technology introduced in the paper serves as a solution for visual impaired people that alerts them over obstacles coming between their ways, alerting for any fluid or moisture in the path and even tracking and sending the location of user and also other functionalities that make it fully smart.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Keywords-- Visually impaired, Smart shoes, Sensors, Guidance device, Obstacle detection, Fluid or water detection, Location tracking, Smart device, Assistive technology, Arduino, Blind Navigation system, wireless.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Objectives: To find effectiveness of proprioceptive training exercises in upper extremity on reaction time in batsmen by using ruler drop test after 3 weeks Methods:An experimental study was performed from Oct22 to April 23 A convenient sampling technique was applied to select 38 samples Results: Paired t test was done The result obtained for upper extremity proprioceptive training exercises on reaction time in batsmen by Rular drop test suggests significnce as P value obtained was (<0.0001) Conclusion: According to results it can be concluded that proprioceptive exercise training for upper extremity shows significantly beneficial in improving reaction time in batsmen.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Batsmen, Reaction time, proprioceptive exercises, ruler drop test

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Tridosha theory is the foundation of Ayurvedic science. One of the three doshas, called Pitta, is very important for digestion and metabolism. There are five different varieties of pitta dosha: Pachaka, Ranjaka, Alochaka, Bhrajaka, and Sadhaka. Food digestion, Sara and Kitta's Vibhajan, and feeding the Agneya component of Pitta, which is distributed throughout the body, are all tasks carried out by the Pachaka Pitta. It also goes by the name Jatharagni. After aiding in food digestion, this Agni form Pitta divides the Sara and Kitta Bhaga. Due to its position, it nourishes and gives Pitta power to relax. It is amply demonstrated in our book that Pachaka Pitta is accountable for Aahar Pachan. On the other hand, modern science has established via numerous research that several digestive fluids are responsible for food digestion. All digestive enzymes, such as amylolytic, proteolytic, and lipolytic enzymes, can be compared to pachaka pitta, as suggested by the functions of this substance. The goals of digestive enzymes, gastrointestinal hormones, and local hormones can be linked to the actions of Pachaka Pitta.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Pachaka, Pitta, Shareera, Kriya, Digestive Enzymes.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Water bodies have a huge aquatic ecosystem within them. Any high concentration of suspended solids can cause numerous issues for aquatic life by blocking light from reaching submerged vegetation. Hence, there is a need for a solution to remove this trash from the water bodies. The Water cleaning boat Project is an endeavour to clean water bodies with an ambitious mission: to achieve cleaner water-bodies that are free from suspended solids; to reduce human intervention and human labour. This project gives a solution of automated river cleaning with the help of a tread mill arrangement. The RF transmitter and receiver are used to control the cleaning machine. The battery energizes the conveyer belt to clean suspended solids in the river, then is stored in the boat itself to aside. A camera affixed to the boat helps in monitoring the movement of the boat in the necessary directions. The Water-boat Project not only concentrates on technology but also believes that using Science, Technology and Community it is possible to build a sustainable environment.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

river water cleaning boat, pollution free water bodies, dust collecting boat-

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project is a song recommendation system, which maps facial expressions to detect the current mood of the user and recommends the songs based on the analysis. This project uses various modules like Mediapipe and Keras for emotional analysis, OpenCV and Streamlit for making the web app and the Streamlit-WebRTC to access user's web camera for mapping facial expressions in real time. The system provides a personalized music experience which in result enhances the user's music listening experience. By analyzing the user's facial expressions, the application can identify the user's current emotional state and recommend songs that match their mood. The web app provides a simple yet user-friendly interface which allows users to easily interact with the system and listen to songs.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Open CV, Keras, Mediapipe, Streamlit, Streamlit-WebRTC

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Existing techniques in user-individualized recommendation scenarios have faced significant challenges due to the vast amount of music data and the wide variety of listening habits. Many prior music recommendation algorithms only considered temporal links between records of sequential listening, ignoring the use of other data like the artist and album. A person's mood can be controlled, and profound emotional experiences can be evoked through music. The study of music recommendation services has advanced significantly since the introduction of online streaming services. The importance of information retrieved from lyrics and acoustic content has been disregarded by contemporary methods that leverage users' listening histories to inform session-based song suggestions. We approach song prediction using a variety of modalities, such as tags, lyrics, and acoustic content. We suggest a novel approach to ensemble learning for acoustic characteristics in this study. By combining poetic and acoustic data, our model outperforms current state-of-the-art models in terms of performance. Additionally, we conduct research to determine how users' psychological well-being affects the effectiveness of our models. Particularly, a piece of music frequently originates from and is part of an album by a particular musician. Singer and album information, which is regarded as music metadata, can be used as crucial supplementary information between various music pieces and may greatly affect the user's musical preferences. In this paper, we concentrate on the sequential recommendation task for music while considering additional information, and we propose a novel Graph based Attentive Sequential model with Metadata (GASM) that uses metadata to enhance music representations and efficiently mine user listening behaviour patterns. To be more specific, we first model the relationships between various types of nodes (user, music, singer, album) using a directed listening graph, and then we utilise graph neural networks to learn their latent representation vectors. The user's musical preference is then divided into long- term, short-term, and dynamic components using customised attention networks. Finally, GASM combines three different sorts of preferences to anticipate the upcoming (new) song in line with the user's musical interests. Three real-world datasets have been the subject of extensive testing, and the findings indicate that the suggested method, GASM, performs better than baselines. From a long list of available songs, choosing one that matches a user's preferences can be challenging. The primary problem with music software recommendations is that they correspond to song recommendations. Although this might not seem to be a problem at first, any typical music recommendation engine will undoubtedly notice a pattern and provide a monotonous selection of music, disappointing the user and making them lose interest. To keep the recommendations exciting and appealing to the user's tastes, our programme overcomes this problem by mixing in fresh music from different genres that matches the user's interests. Using machine learning and KNN, we present a customised music recommendation system in this work. We suggest a collaborative filtering and content filtering recommendation algorithm for the personalised music recommendation system that combines the output of the network with the log files to recommend music to the user. User data from the log file is used by the suggested technique to generate song recommendations for each recommendation. While collaborative approaches forecast potential preferences using a matrix with scores on various songs, content-based approaches make recommendations based on the similarities between the contents or attributes of two songs.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Keywords:- KNN, Machine learning, Collaborative filtering, GASM

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Information and communication technology have a significant role in building the new global economy and causing fast societal changes. New ICT technologies have significantly transformed people's lives during the last decade. The current era is the age of technology, and technology plays an important part in our everyday life. The present study tries to investigate the effect of technological use in the teaching-learning process on the pupil-teachers' of B. Ed institutions. The investigation carried out to find the signifcance difference among urban and rural B.Ed pupil-teachers; male and female B.Ed pupil-teachers' and science education and social sciences B.Ed pupil-teachers'.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Effect, Technology, Use, B.Ed pupil-teachers'

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Our Aims to provide effective and active rehabilitation for patients suffering from upper limb paresis, using gaming based a therapy technique. By disguising the tasks into further amusing, patients are motivated to train for longer and more constantly. The advantage of this system can be a tone- managed, at- home remedy system; reducing fatigue for physical therapists, and the time needed for therapist- case sessions. The system incorporates a virtual reality (VR) terrain displaying both the games and a mortal model as feedback of the patients' conduct whilst playing the games. The game was developed, each targeting enhancement of muscle strength, control, delicacy, and speed. The difficulty of the games can be varied to suit several impairments and patient progress is covered. The games are played using a band. The successful advancements with lower costs associated with this system, are pronounced advancements for patients suffering from such an enervating condition.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Paralysis, Rehabilitation, Stroke, Upper extremity, Video games, Virtual reality.

  License

Creative Commons Attribution 4.0 and The Open Definition