Browse Articles
Discover research articles across all indexed journals
Comparative Study of KEM, LWR and HOYW Denoising Methods
Background and Objective: In numerous occasions the recorded Neural signals are often contaminated by Noise from various intrinsic and extrinsic sources of the system. The noisy data can often give deceptive results when statistical analysis is performed on them. Hence, denoising the contaminated signal by filtering or otherwise is very important to get meaningful results. Several denoising techniques such as Kalman Filtering in conjunction with Expectation-Maximization (KEM algorithm), Levinson-Wiggins-Robinson (LWR) algorithm among others were developed in the recent past. This gave rise to a need for making “a comparative study on the performance of various noise removal methods” to assess their effectiveness.
Smart Intrusion Detection System for CAN Network Implemented using LSTM Strategy
In today's cars, communication between electronic control units is managed via the Controller Area Network (CAN) bus system. Nevertheless, the CAN bus system lacks means for authentication and authorisation, making it susceptible to attacks like denial-of-service, fuzzing, and spoofing. To identify and counteract CAN bus network intrusions, this study suggests an intrusion detection system based on a Long Short-Term Memory (LSTM) model. Extraction of attack-free data and attack injection produced the dataset used for testing and training. Findings show that the suggested LSTM model has a greater detection rate than the Survival Analysis approach and is efficient in defending current automobiles from assaults on the CAN bus network. The ability to identify these sorts of assaults is limited by the constraints of conventional intrusion detection systems (IDS) for CAN bus networks, such as statistical analysis, frequency-based analysis, and Hidden Markov Model (HMM). Using a Long Short-Term Memory (LSTM) based strategy, the objective of this article is to build a reliable IDS that can efficiently identify and counteract these assaults on the CAN bus network.
Design, Modelling and Optimization of an Electric Vehicle (EV) and Comparison of Performance for Different drive Cycles using MATLAB & SIMULINK
Electric cars (EVs) have established themselves as the most practical, ecologically acceptable substitute for conventional automobiles, and they are now widely accepted on the market. Recent improvements in the field of electric vehicles are mostly driven by different control realizations. From the standpoint of the controller designer, the model should be basic enough to permit easy implementation of model-based controllers while yet being able to contain the fundamental dynamics. The proposed model will be implemented in MATLAB/Simulink since all the components of the model are available in that software and all the tools related to our project were available for free. Also, leading car manufacturers such as Tesla use MATLAB / Simulink to optimise their designs and power trains adding reliability to this work.
SCFWM – Smart Container for Food Waste Management and Distribution using IoT and Cloud Computing
Indeed, there is a serious problem with food waste. Together with moral and economical difficulties, food waste poses major environmental risks. Food waste has a direct negative influence on hunger and malnutrition, as well as having significant negative effects on the ecology. Currently available technologies to decrease food waste focus mostly on repurposing large-scale leftovers, not domestic leftovers. As a result, we propose a digital application that would be used to provide extra food to those in need both on a big and local scale. Web apps serve as a platform that makes it easy to grow and allows us to reach a larger audience. Users may register as donors or receivers depending on their needs. Donors can join up as donors to offer food. This method, which focuses on kitchen leftovers and incorporates technology, aids in reducing food waste. Donations will be dispersed using the aforementioned strategy.
License Plate Recognition for Indian Vehicles based on Image Processing using OpenCV
Image processing technology is the foundation of the ANPR (Automatic Number Plate Recognition) system. It is one of the crucial methods created to recognise the plate of a vehicle. It is impossible to physically keep track of every car in the modern world due to the daily increase in the number of vehicles. It is now simple to maintain a record and utilise it as needed thanks to the creation of this system. Thus, creating an effective system for automatically identifying vehicles with their licence plates is the key goal. As a vehicle enters the security checking area, the system immediately starts to take pictures of the vehicle. The segmentation procedure is then used to extract the pictures that were collected. To recognise the characters, optical character recognition is utilised. The data collected is then compared to the data kept in their database. Real photos are used to assess the system's performance once it has been constructed and simulated in MATLAB. It is common practise to employ this kind of technology at parking lots, toll booths, and traffic control zones. This system is primarily intended for security system purposes.
Smart Collar for Cattle Tracking and Health Monitoring Using IoT on ESP32
In Indonesia, there is still no real-time system for monitoring the health of cattle. Instead, a microchip RFID ear tag is used, which is implanted in the cow, but there is still no connection to the Internet of Things to help cattle producers with monitoring. The existing monitoring still relies on human labour, which is undoubtedly inefficient, particularly if you have to keep track on the health of many cows on a big farm. Cattle's movement, heart rate, and body temperature may all be read via a collar gadget. By gathering information from temperature sensors, heart rate sensors, and an inertial measurement unit installed on a dairy cow's neck, information is sent via the internet. To provide normal, less normal, and abnormal health categorization outputs, the gathered data is saved and categorised using machine learning. Also, depending on the axis sensor, generate a graphic output.
AGROPEDIA - One Stop for all Agricultural Needs
In India, more than half of the workforce is employed in agriculture and related sectors, which account for around 17 percent of the country's Gross Value Added (GVA). In India, 60–70% of the workforce is employed in agriculture directly or indirectly. Given the importance of food to human existence, it is always difficult to produce food profitably, efficiently, and with minimum land usage. The project's approach offers farmers a one-stop shop for all of their agricultural requirements. It uses a crop forecast system, a weather analysis model, information about government programmes, a system for renting equipment, and a system for analysing market prices. The system for renting out tools that has been developed here gives users the option of lending out their unused agricultural equipment in order to generate passive money from it. The farmer may make a claim for crop insurance or during crop losses with the aid of proper understanding of these programmes. The farmers are informed by our model, which is now in use, about potential future market price patterns.
Stanley Controller based Autonomous Path planning and Tracking in Self-Driving Cars
Autonomous systems have the ability to replace human-performed tasks like personal assistants in residential or commercial settings. Self-driving cars, which have shown potential, are one area of significant interest in AI. This may include anticipating the activities and goals of people, such as pedestrians, as well as those of other vehicles. The creation of high-resolution images and sophisticated obstacle-clearing manoeuvres at high speeds are other developments. Increased highway safety and better use of travel time are only two of the many advantages of autonomous cars. In order for automated steering to retain the best trajectory despite changes in the road's conditions, lateral steering control is a critical component of autonomous cars. This study aims to investigate the use of a dynamic bicycle model and Stanley controller as a route tracking method, as well as the use of sensors to identify objects and lanes on the way. Discussion will also include the outcomes of MATLAB and SIMULINK tests performed to evaluate these approaches.
A Security Protocol for V2V Communication using NS2 Network Simulator
The principles of MANETs, or mobile ad hoc networks, form the foundation of vehicular ad hoc networks (VANETs). Vanet was first introduced as "Car to Vehicle ad hoc mobile communication and networking" in 2001. In order to build a communication network and transfer data among vehicles, Vanet were invented. Vanet uses a variety of means to establish communication, including vehicle-to-vehicle communication. In this project, both roadside-to-roadside and vehicle-to-roadside communications are employed, and vehicle-to-roadside communication is taken into consideration. A different term for VANETs is Intelligent Transportation Networks. The "Internet of Vehicles" (Vanet) has expanded into a larger system and will ultimately become the internet. There will be a "Internet of autonomous vehicles" in the not too distant future. Wireless networking is used by Vanets for networking and communication; even LTE and 5G may be used by vanets. In this project, a protocol is being developed to provide security for the established connection in Vanet, i.e., to recognise and stop any network intrusions. The NS2 network simulator is used to implement this protocol for testing purposes.
RTD3 – Real Time Driver Drowsiness Detection System Using CNN on Inception V3 Model
This paper suggests a behaviourally based driver sleepiness detection system. Faces provide data that may be used to gauge sleepiness levels. The level of tiredness may be determined by extrapolating a variety of facial functions from the face. They include head movements, yawning, and eye blinks. Yet, since it needs accurate and reliable algorithms, creating a sleepiness detection system that produces accurate and trustworthy results is a difficult issue. In the past, a wide range of methods have been explored to detect driver sleepiness. The most recent growth in deep learning requires that those algorithms be reviewed to evaluate their efficacy in detecting sleepiness. In this study, the eyes the body feature that matters the most—are used to identify driver sleepiness. The algorithm has been taught to examine the face, isolate the ROI (Region of Interest), or the eyes, and determine whether they are open or closed. When the eyelids are closed continuously for a certain amount of time, the alarm begins to beep to warn the driver. CNN serves as our classifier (Convolution Neural Networks). After a comprehensive review of the literature, we conclude that, in order to get the best outcomes, CNN is the best method to use when compared to vector system approaches, Markov models, etc. The InceptionV3 model, which is a trained image recognition model, is the one employed in this instance. Also, we go through the installation, training, and testing accuracy methodologies.
Face Recognition Technique using YOLO V5 Algorithm
In today’s date real world application like human-machine interaction, security surveillance face recognition has made its great importance. For face recognition the steps to be followed are data collection, preprocessing, Feature Extraction, Training Evaluation and finally testing. One of the best Algorithms used for face recognition is Viola-Jones Algorithm. Viola Jones Algorithm is highly accepted because of its fast processing time and high detection rate. The other detection Algorithms which can be used are HOG Algorithm (Histogram Oriented Gradient), Deep Learning CNN (Convolution Neural Network) Algorithm, Haar cascade Algorithm and MTCNN Algorithm. In this Paper we will discuss about all this Algorithms and compare the detection rate of facial points among various methods for the datasets. YOLO V5 algorithm is another algorithm which can be used for face recognition technique. Face recognition can be achieved by combining the YOLO V5 algorithm with additional technique such as deep face recognition models like face net, which can recognize and compare facial features to identify individuals.YOLOV5 can identify facial features such as eyes, mouth, and nose, making it useful for a variety of face recognition applications.
Risk Mitigation Analysis in the Procurement Process of Construction Goods and Services In SIGI District
In every procurement activity, there will be an opportunity for a risk to arise, including activities in the process of procuring goods and services at the Department of Public Works (PU) for Highways and the Regional Secretary (Sekda) of Sigi Regency. To prevent risks, the HOR (House of Risk) method is used which can identify dominant risk sources and prioritize appropriate mitigation strategies to anticipate existing risks. The purpose of this research is to know the risks and analyze the risks that can cause obstacles, as well as to find out the necessary risk mitigation measures for risk events that occur in the process of procuring construction goods and services in Sigi Regency. The results showed that of the 22 identified risk causes for the procurement of construction goods/services, 14 priority risk causes were obtained with the largest Aggregate Risk Priority (ARP) value, namely, the documents required for the completeness of the tender process were incomplete and sudden and the existing personnel did not comply with the requirements. Of the 14 priority risk causes with the largest ARP value, obtained through the Pareto Diagram 6 handling strategies recommended to the Regional Secretary in the field of procurement of construction goods and services. And from the calculation results of the House of Risk 2 method, 2 risk management strategies with the highest Effectiveness to Difficulty (ETD) values are obtained, which will be used in handling 14 priority risk agents.
Study on the Calculation method of the Coal and Gas Outburst Threshold
The four undetermined parameters of the temperature-pressure-adsorption equation (TPAE) were obtained by regression of the series isothermal adsorption data of the measured middle-rank deformed coal and normal coal. The unit isosteric adsorption enthalpy (UIAE) was obtained. According to the negative value of the UIAE, adsorption is an exothermic process, desorption is an endothermic process. The coal and gas outburst threshold (OT) is defined as the product of the firmness coefficient and the unit isosteric desorption enthalpy (UIDE) to show the combined effect of adsorption thermodynamics and tectonic stress. The UIDE difference between the two coals was from 1.91 times expanded to OT difference of 5.74 times.
Breast Cancer Exposure and Categorization Using Unsystematic on Machine Learning
The idea behind this initiative is to eliminate the laborious process of finding breast cancer. This method is mechanised using CAD and the mammographic picture of the breast is used as the input in order to go around many of the superstations in society. For processing the user-provided database using a computer device in our system, we suggested a machine learning technique. With the help of this programme, women may avoid breast cancer instances while remaining in the comfort of their own homes. This would increase the diagnostic results' openness, removing any room for patient scepticism. The technology will allow users and computers to communicate directly. The screening picture of the mammography must be verified by an expert, but occasionally patients are unable to see them in person, causing the appointment to be delayed. The usual method of diagnosis would need at least a week to complete. As a consequence, the diagnosis will take longer, which might lead to lengthy therapy or perhaps even death. To solve these issues, we turn to CAD so that early diagnosis would make it simpler and less laborious for both patients and medical professionals to treat the condition.
Face Mask Detection Using Tensor Flow, KERAS, and OPEN CV
For face mask identification; this journal examines the use of Python programming with Deep Learning, TensorFlow, Keras, and Open CV. The classifier uses the MobileNetV2 architecture as a foundation to do real-time mask detection. This system can be used in real-time applications which require face-mask detection for safety purpose due to the outbreak of coronavirus pandemic. The system’s method is set up in such a way that it uses a video camera to capture people’s images and apply detecting algorithms. After the successful implementation of face mask detection with a video camera that helps in the detection of people wearing and not wearing a face mask. Using the visualization algorithms, it is possible to show the detection percentage of calculation in various ways.
LC2BS – Low Cost Secondary Braking System Implemented using Arduino and Motor Speed Control Mechanism
In the industrialised world, roads constitute a huge problem. According to recent research, excessive or unsuitable speed as well as changes in the highway are linked to one-third of fatal or severe accidents. Accidents brought on by brake failure are a problem as well. The major cause of brake failure, pressure loss, is failure in the brake lining. A backup braking system has been created in case of unexpected brake failure or partial brake failure in order to prevent accidents. The project involves creating a hardware braking system using an Arduino, motors, and speed control that is displayed on an LCD screen. This system continuously monitors the condition of the brake wire, notifies the driver in the event of a primary brake failure, and automatically engages the secondary braking system.
OAOF - Obstacle Avoidance using Optical Flow Algorithm for Unmanned Aerial Vehicles
A camera sensor may be a useful tool for a number of robotic and autonomous systems when used with MATLAB Simulink for obstacle avoidance. Using a camera sensor and MATLAB Simulink's optical flow algorithm, the obstacle avoidance system is shown in this work. For the purpose of identifying and following the motion of objects in the picture, the system analyses visual data from the camera. The motion vectors of the objects are computed using the optical flow technique, and the robot and obstacles' relative motion is calculated using those motion vectors. In order to provide safe and easy navigation, the system can recognise and avoid obstacles in real-time. The system is easily adjustable and adaptable to diverse applications thanks to the usage of MATLAB Simulink, which enables the integration of several sensor and control systems. The suggested system's findings demonstrate that using a camera sensor with the optical flow algorithm may be a useful tool for obstacle avoidance in a range of robotic and autonomous systems.
FORMULATION, DEVELOPMENT AND EVALUATION OF COLON TARGETED BEADS FOR ANTI-INFLAMMATORY DRUG
Mesalamine is an anti-inflammatory drug used in treatment of Crohn’sdisease and ulcerative-colitis. Since Mesalamine islargely absorbed from the upper intestine, selective delivery of drugs into the colon may be regarded as a better method of drug delivery with fewer side effects and a higher efficacy.An objective of the present investigation is to prepare and evaluate Mesalamine microbeads for colon targeting. These microbeads were prepared by Ionotropic gelation method using physical mixtures of gellan gum locust bean gum and sodium alginate in ratio 1:3:2, 1:1:2 and 3:1:2. Eudragitcoated Mesalamine microspheres were evaluated for surface morphology, particle size analysis, percentage drug entrapment, percentage yield and in vitro drug, in-vivo drug release and stability studies. Drug release studies carried out in SGF (pH 1.2) for 2hrs, SIF (pH 6.5) for 5 hrs, SCF (pH 7.4) for 24hrs. The cumulative percent drug release after 24 hrs was found to 96.73%; 89.76%; 86.12% and 82.12%, 74.79%, 68.24% for F-1, F-2, F-3 of uncoated and CF1, CF2, CF3 of coated formulation respectively. By comparing the in vitro release pattern of all coated and uncoated formulations, it was found that the drug release from coated formulations was prolonged than uncoated beads. The drug release may be mainly controlled by drug diffusion through the natural gums matrix. The in vivo release performance of the developed colon specific formulation was carried out by gamma scintigraphy.The scintigraphy of the optimized formulation CF3 (92 ± 0.8% Radio labeling efficiency) was performed using rabbits (animal model) in order to establish its colon targeting potential. Scintigram shows the residence of beads in colon more than 12 hrs. These results showed that Eudragit S-100 coated beads formulation may be useful for targeting mesalamine to the colon. Stability studies indicated that the optimized formulation does not show any significant change with respect to shape, color, surface and in vitro drug release.It is concluded from the present investigation that Mesalamine microspheres are promising controlled release carriers for colon-targeted drug delivery.
ESTIMATION OF TOTAL ALKALOID, POLYPHENOL, FLAVONOID CONTENTS, AND ANTIOXIDANT ACTIVITY OF SAGA - SAGA SEEDS
The research work aims to estimate the Total Alkaloid content, Total flavonoid content, and Total polyphenol content of the methanol crude extract (CMME) of the Abrus precatorius seeds and to determine the Antioxidant power of the methanol crude extract CMME and its isolated compounds CMME I, CMME II, and CMME III. The methanol crude extract was prepared from the dried powdered Abrus precatorius seeds by the maceration method for 7 days. The compounds from the crude extract CMME were isolated by column chromatography using silica gel 60-120 mesh as the adsorbent. The isolated compounds are further purified by Thin Layer Chromatography. The total alkaloid content of CMME was found to be 88 mg Atropine equivalent per gram of dried crude extract. The total flavonoid content of the crude extract CMME was found to be 415 mg Quercetin equivalent per gram of dried crude extract. The total phenol content of the crude extract CMME was found to be 239 mg Gallic acid equivalent per gram of dried crude extract. The antioxidant activity was determined by FRAP assay and ABTS assay. The isolated compound CMME II has more Ferric reducing antioxidant power compared to the CMME, CMME I, CMME III, and the standard Ascorbic acid. The isolated compound CMME II and CMME III have more ABTS radical scavenging activity compared to the CMME and CMME I. The isolated compounds CMME II and CMME III have IC50 values of 15mcg/ml and 11mcg/ml correspondingly.
IN-VITRO ANTI TUMOUR AND BRINE SHRIMP LETHALITY ASSAY OF ABRUS PRECATORIUS SEEDS
Abrus precatorius seeds are generally called Crab's eye seeds. The research work aims to determine the In-vitro Anticancer and the Brine shrimp lethality assay for the methanolic crude extract CMME and its isolated compounds CMME I, CMME II, and CMME III. The methanolic crude extract was prepared by the maceration method for 7 days. The compounds from the crude extract were isolated by column chromatography using silica gel 60-120 mesh as the adsorbent. The isolated compounds are further purified by Thin Layer Chromatography. The In-vitro anticancer activity of CMME and its isolated compounds are determined against the skin cancer B16F10 cell line by the MTT assay method using 5fluoro uracil as the standard drug. The isolated compound CMME I shows more % inhibition against the skin cancer B16F10 cell line compared to CMME, CMME II, CMME III, and the standard. It has an IC50 value of 40µg/ml. The In- Vitro Antitumor activity was determined for the crude extract CMME and its isolated compounds against the Lung cancer cell line A549 by MTT assay method using 5fluoro uracil as the standard. The crude extract CMME and the isolated compound CMME III showed more % of inhibition against the Lung cancer A549 cell line compared to CMME I, CMME II, and the standard 5fluoro uracil. The crude extract CMME and the isolated compound CMME III have the IC50 value of 17µg/ml and 23µg/ml respectively. A brine shrimp lethality assay was done for the crude extracts and their isolated compounds. The crude extract CMME has more cytotoxicity against the Brine shrimp compared to CMME I, CMME II, and CMME III. The crude extract CMME has an IC50 value of 106µg/ml.