Browse Articles
Discover research articles across all indexed journals
COUNTERFEIT PRODUCT DETECTION USING BLOCKCHAIN TECHNOLOGY
Fake Products is a serious issue, as in today’s world we can’t really distinguish between real and fake products. And some people make these fake products just to make some profit without thinking about their impact on users and also affecting the company’s name, profit, and sales. Blockchain technology can be used to detect whether the product is real or fake and assure users about the authenticity of the product. Blockchain is a trending technology and a lot of applications are using this technology. Blockchain technology is the technology where information is stored in the form of blocks in many databases which are connected with the chains and it doesn’t require any third-party users' permission. The benefit of blockchain is that it is immutable and secure. It is decentralized and distributed. We can use Quick Response (QR) code or an encrypted unique code which is a very efficient technique to detect fake products. When the QR code is scanned or the unique code is entered, it will redirect us to the blockchain containing the information of the product and provides us with the details of the manufacturer and information of the owner to make the decision easy for the buyer if they are looking to buy the product.
MEDICAL BOT USING ARTIFICIAL INTELLIGENCE
Nowadays people hardly try to consult a doctor for diagnosing disease, they instead search in internet sources, where the information is scattered and sometimes, required medical advice is not available. So, it is impractical to find the required information. People sometimes ignore the symptoms and later regret their decision. Healthcare is very important to lead a good life. However, it is very difficult to obtain the consultation with the doctor for every health problem. The idea is to create a medical chatbot using Artificial Intelligence that can diagnose the disease and provide basic details about the disease before consulting a doctor. This will help to reduce healthcare costs and improve accessibility to medical knowledge through medical chatbot. Chatbots are computer programs that use natural language to interact with users. The chatbot stores the data in the database to identify the sentence keywords and to make a query decision and answer the question. Named Entity recognition and cosine similarity is performed to make a reliable reply to the user.
ALZHEIMER'S DISEASE PREDICTION USING ENHANCED U-NET ARCHITECTURE
Alzheimer's disease (AD) is the most prevalent kind of dementia for which there is now no cure. Correctly classifying AD may facilitate diagnosis and therapy selection. Multiple studies over the last decade have shown that DL algorithms effectively diagnose AD. Based on 3D T1-weighted magnetic resonance imaging, this work presents an E-U-net model for identifying AD (MRI). It has been shown that the Model's performance is boosted when coupled with stringent supervision. Attempts have been attempted to quantify the presence of amyloid-beta in body fluids for clinical diagnosis of Alzheimer's disease. However, these approaches have not been completely successful in predicting cognitive decline in patients. They are not aimed at elucidating the molecular pathogenesis induced by Tau and amyloid-beta proteins in hippocampus neurons of AD patients. This paper proposed Enhanced U-Net architecture for MRI Image segmentation. This study recommends evaluating the segmentation of True and predicted masks by detecting the fluorescence signal inside, which might give valuable insight into the nature of the disease. The experimental results are shown in the input MRI image with corresponding true and predicted masks and training and testing details.
MANHOLE DETECTION AND MONITORING SYSTEM
A smart city is the future goal to have cleaner and better amenities for the society. Smart underground infrastructure is an important feature to be considered while implementing a smart city. Drainage system monitoring plays a vital role in keeping the city clean and healthy. Since manual monitoring is incompetent, this leads to slow handling of problems in drainage and consumes more time to solve. To mitigate all these issues, the system using a wireless sensor network, consisting of sensor nodes is designed. The proposed system is low cost, low maintenance, IoT based real time which alerts the managing station through message when any manhole crosses its threshold values. This system reduces the death risk of manual scavengers who clean the underground drainage and also benefits the public.
LIP TO SPEECH AND TEXT SYNTHESIS
Humans involuntarily tend to infer parts of the conversation from lip movements when the speech is absent or corrupted by external noise.In this work, we explore the task of lip to speech synthesis, i.e., learning to generate natural speech given only the lip movements of a speaker. Acknowledging the importance of contextual and speaker specific cues for accurate lip-reading, we take a different path from existing works.We focus on learning accurate lip sequences to speech mappings for individual speakers in unconstrained, large vocabulary settings. We collect and release a large-scale benchmark dataset, the first of its kind, specifically to train and evaluate the single speaker lip to speech task in natural settings.We propose a novel approach with key design choices to achieve accurate, natural lip to speech synthesis in such unconstrained scenarios for the first time. Extensive evaluation using quantitative, qualitative metrics and human evaluation shows that our method is four times more intelligible than previous works in this space.
RABBITMQ MICROSERVICE WITH ASP.NET CORE WEB API FOR ASYNC OPERATIONS
Nowadays, developers prefer to create apps using a microservice design rather than a monolithic system. The entire functionality is typically included in a single system in monolithic architecture, which is frequently huge, complicated, and closely connected. In other hand, microservice architecture works with independent and decoupled services. A message broker plays pivotal role in microservice architecture. One of the most widely used message-broker services is RabbitMQ. Most important is RabbitMQ is Open-Source message broker. RabbitMQ helps microservices to exchange data while staying independent. This article focuses on implementation of RabbitMQ with ASP.Net core and its advantages for asynchronous operations.
B-SHAPED MICROSTRIP PATCH ANTENNA FOR FREQUENCY RANGE OF 5-6.5 GHZ
Slotted B shaped Rectangular microstrip patch antenna has been proposed. With the help of CST software, the design parameters and results for a B-slotted rectangular microstrip patch antenna is explained and the results obtained from the simulations are demonstrated. The proposed antenna has been designed using FR4 as substrate having dielectric constant of 4.4 sandwiched in between the patch and ground plane made up of copper. The power from coaxial connector is fed to the B-shaped antenna via microstrip feed line and impedance of the antenna is matched. It has observed that antenna slotted antenna is resonate at frequency 6.4 GHz. Proposed antenna has return loss -39.7 dB at resonant frequency of 6.4GHz. The gain of the proposed antenna is 10dB. For the proposed antenna the VSWR is 1.03. The microstrip patch design is achieved by using microstrip line feed technique. This patch is studied because they offer high bandwidth and gain. The gain enhancement has been achieved by suitable cutting slots in the rectangular patch using suitable feeding technique. The electromagnetic simulation of the proposed antenna has been carried out using CST software. The analysis of performance will be based on changing the geometry of the patch and the obtained results are gain, VSWR, antenna efficiency and radiation pattern.
EXPERIMENTAL ANALYSIS OF SOLAR OPERATED AUTOMATIC MAWA MAKING MACHINE
The hasty development of India and a upward population has directed to natural resources and available energy for everyday use becoming sparse. Many areas in rural India use wood as their main source of fuel for cooking. This demand has led to deforestation of the land, as well as increased health issues due to smoke inhalation during wood-fueled cooking. So, efforts should be made to solve these problems. An enormous amount of energy is expended regularly on cooking. So the demand can be fulfilled by solar reflector. The main purpose of system is to reduce human effort by implementing the stirring mechanism and to prevent the fuel consumption by use of solar energy In this research project mawa made in both Ways, direct heating and storing thermal energy in oil. So it’s available for day night. From 5 liter of milk, made 1kg of mawa in 3.5 Hours, by direct method. By storing thermal energy in oil its takes more time, but by providing insulation made mawa also in night time. Total mawa made capacity of system is 2.5kg per day.
RESILIENCE OF NETWORK PROTOCOLS TO DEEPFAKE DETECTION TRAFFIC
This research analyzes the robustness of current multimedia protocols in managing traffic produced by real-time, high-volume deepfake detection. The widespread occurrence of deepfakes on online platforms necessitates swift and precise detection algorithms for multimedia data, highlighting the demand for optimized network protocols. This paper assesses the existing functionalities of multimedia protocols, including RTP and RTSP, in facilitating deepfake detection and proposes improvements to enhance robustness, speed, and accuracy. The results underscore the necessary protocol modifications to accommodate real-time deepfake traffic requirements and reduce network stress.
CNN-BASED CONTINUOUS AUTHENTICATION OF SMARTPHONES USING MOBILE SENSORS
With the advancement of technology, the smartphone has become a reliable source to store private details, personal photos, credentials, and confidential information. However, smartphones are easily stolen and it has become a suitable target for attackers. Usually, smartphones require only initial explicit authentication, once the initial login is passed all the information can be accessed easily. Hence, this paper proposes an efficient implicit, continuous authentication of the smartphone based on the user’s behavioral characteristics. We propose architecture to differentiate legitimate smartphone owners from intruders. Our model relies on the smartphone’s built-in sensors like an accelerometer, gyroscope, and GPS. The sensors respond according to the user’s behavior which is recorded by the smartphone. We have used the rest filter model to separate motion data from rest since the rest data does not contain much information about the user’s behavior. We have used Xgboost and Convolutional Neural Network as our rest filter and legitimate-intruder classifier respectively. Our system can predict legitimate and intruders in a few seconds. Our proposed CNN model has an achieved average accuracy of 95.79% in our custom dataset, which has further improved after integrating GPS data.
ANTI-CANCER PROPERTIES OF HERBS : A REVIEW
There are tremendous reserves of organic compounds found in many plants on Earth that only a very small amount of which as an anti-cancer compounds tested and used. Worldwide endeavors are underway to discover new anti-cancer drugs. Nowadays, there is a proclivity to use of traditional and herbal medicines in cancer treatment. The omission of this paper aimed to investigate the medicinal plants which are endemic in many parts of the world and were used for the treatment of various cancers. The evaluated plants and consequently appropriated ones that are used in cancer treatment as well as metabolites that are extracted from which would be useful to scholars around the world.
A SURVEY ON DANGEROUS SIDE EFFECTS OF OTC MEDICATION ON HUMAN HEALTH
OTC drugs are those drugs which are safe and effective for use by the general public without a doctor’s prescription. It is also called prescription de controlled drugs.These drugs are the non prescription or over-the-counter drugs. These have little significant pharmacological activity and therefore the physician need not to be very much concerned about their use by the patients themselves. It is used primarily for symptomatic relief and not as substitutes for prescription drugs. Associated harms included direct physiological or psychological harm (e.g. opiate addiction), harm from another ingredient (e.g. ibuprofen-related gastric bleeding) and associated social and economic problems.
MEDICINAL PLANTS USED FOR THE TREATMENT OF DIABETES IN INDIA: A REVIEW
upload soon
COMPARATIVE STUDY OF GARLIC AND CURCUMIN FOR ITS CARDIOPROTECTIVE PROPERTY
The combination of garlic and curcumin showed a significant increase in total protein value as compared to cadmium control, thus showing decrease in oxidation of total protein. Garlic and curcumin combination also showed significant reduction in serum enzymes i.e SGOT, SGPT, as compared to other antioxidants and combination. Current study has shown that exposure to cadmium had significant effects on rats blood parameters. In our present study treatment of garlic and curcumin in combination decreased the toxic effects of Cadmium on the hematological values and had a protective role in anaemia induced by cadmium as compared to other antioxidants. The combination of garlic and curcumin was found to be most significantly effective in the treatment of cadmium induced oxidative stress. In current study garlic and curcumin in combination decreased the activity of SOD and Catalase significantly as compared to other treatment groups.
LICENSE PLATE DETECTION METHODS BASED ON OPENCV
With the popularization of automobile and the progress of computer vision detection technology, intelligent license plate detection technology has gradually become an important part of intelligent traffic management. License plate detection is used to segment vehicle image and obtain license plate area for follow-up recognition system to screen. It is widely used in intelligent traffic management, vehicle video monitoring and other fields. In this paper, two license plate detection methods are studied, one is based on Sobel edge detection and the other is based on morphological gradient detection. Basing on OpenCV and visual studio 2012 under Windows system, two methods of license plate detection are implemented, and the two algorithms are compared in detail from the aspects of license plate detection accuracy. These methods have high efficiency and good interactivity, which provide a reference for later license platere cognition.
SPEECH EMOTION RECOGNITION USING DEEP LEARNING
Speech Emotion Recognition is a present topic of the research since it has wide range of application. SER is a vital part of effective human interaction in the speech processing. Speech Emotion recognition is a domain that is growing rapidly in the recent years. Unlike humans, machines deficit the potential to perceive and express emotions. But the improvisation of human-computer interaction can be done by automated SER thereby turn down the need of human mediation in recent time. The primary goal of SER is to improve man-machine interface. This paper covers Deep Learning to train the model, Librosa to classify the audio data. In deep learning CNN is used to classify the model based on frequency parameter. This paper also contains the study of various speech emotion recognition methods like, happy, sad, angry, disgust, surprise and fear.
FAKE NEWS DETECTION USING MACHINE LEARNING
Fake news has been increasingly prevalent in recent years due to the quick growth of online social networks, which are used for a variety of political and commercial goals. Users of online social networks can easily become infected by these online fake news with deceptive language, and this has already had a significant impact on offline culture. Finding bogus news quickly is a crucial step in enhancing the reliability of information in online social networks. In order to identify false news pieces, creators, and subjects from online social networks and assess the performance of these methods and algorithms, this research looks at them. The report also discusses the difficulties posed by the varied linkages across news sources and the unknowable characteristics of fake news.
PEER TO PEER MEDIA STREAMING USING CLUSTERS
Audio and video Streaming is one of the most interesting technologies that give the user detailed multimedia resources such as important video updates, real time sports surfing and entertainment movies. Constructive management of the information is the important factor to gain rapid and fast success in this field of service. As it is a very habitual for many users wanting have the same type of entertainment resource at the same time, the conventional Client server model may provide service bottle neck, bandwidth loss, improper management of the cache and increased delay. Broadcasting or multiple screening is not a solution because there will be different users who will be connecting to the server and request to provide access to similar kind of video at different interval of time. Apart from this, once we start playing a video, the following part must be obtained and should be provided to the user at the right time to keep away the video from getting interrupted. Predictive stashing is very important to prevail over the instability of wireless connection. In this paper, we put forth the idea and deliver a new two-level cooperative architecture service and a wide range of technology for streaming.
POLYCYSTIC OVARY SYNDROME USING MACHINE LEARNING
One of the most common hormonal conditions in women of reproductive age is polycystic ovarian syndrome (PCOS). Since pcos is frequently linked to obesity, type 2 diabetes mellitus, and high cholesterol levels, early detection and treatment are crucial. By counting the number of follicles in an ovarian ultrasound image and adding clinical, biochemical, and imaging characteristics, pcos can be automatically detected and patients divided into normal and pcos-affected groups. The body mass index (BMI), hormone levels, and other factors are all taken into consideration by the Support Vector Machine method, which is utilized for categorization.
MEGACOSM – DETECTION AND CLASSIFICATION OF ASTRONOMICAL OBJECTS
The concept of existence started with the bigbang theory, which was a phenomenon where multiple objects collided to create multiple other things. This creation is said to be increasing at the rate of the cosmic acceleration due to which multiple new objects came into existence called as the astronomical objects. Space object (SO) detection, classification, and characterization are significant challenges in many research fields. In recent years, deep learning and other forms of artificial intelligence (AI) have drawn the attention of many astronomers and academics. Megacosm is project that is used for the classification and the identification of those newly created celestial objects. It works on the process of manually training the model with the data annotation techniques and the dataset is enhanced using the data augmentation technique. It uses YOLO as the core algorithm and also deep learning concepts like CNN (Convolution Neural Network) to predict results. It gives the output as a bounding box around the detected object along with the accuracy of that prediction.