Browse Articles
Discover research articles across all indexed journals
BMTC BUS DISTRIBUTION AND MANAGEMENT
The quality of any public transport system is crucially dependent on its reliability. BMTC bus distribution is not well planned in the Bengaluru Metro City resulting in massive crowds in Buses and Bus stands. Hence this is a real-life problem that needs an immediate solution. Using ‘YOLO’ (You Only Look Once) Machine Learning algorithm, we try to solve the existing crowd problem in BMTC buses. By making use of the camera present inside the bus upfront, we can count the onboarded passengers and store it in cloud (Real Time). These numbers can be seen by passengers who are waiting for the bus. If the upcoming buses are crowded, then passengers can choose another alternative means of transport like a cab or an auto rikshaw. The same count will be shown on an LED board in the BMTC base stations (depots) so that distribution is taken care manually. Like this we can achieve bus distribution and hence providing reliable and safe transportation for the public. As far as the BMTC management part is concerned, temperature and gas sensor are installed so that any smoke casualties can be prevented.
AN EXPLAINABLE AI MODEL FOR DIABETIC RETINOPATHY DETECTION
Diabetes is the most common long-term condition that affects people of all ages due to inadequate insulin production. The appearance of black spots for millennia, interpreting eye pictures, and detecting diabetic retinopathy in its early stages has been a big challenge. The Explainable AI method is to explain the deep learning model that is understandable by humans and trusts the result. This is especially important in safety critical domains like healthcare or security, which replaces manual processes and understanding of the models function by non-technical domain skilled person. Explainable AI is used to describe an AI model, its expected impact and potential biases. It helps characterize model accuracy, fairness, transparency and outcomes in AI-powered decision making. Explainable AI is crucial for an organization in building trust and confidence when putting AI models into production. AI explains ability also helps an organization adopt a responsible approach to AI development. Specifically, the back propagation step is responsible for updating the weights based on its error function. SHAP or SHAPley Additive explanations are a visualization tool that can be used for making a machine learning model more explainable by visualizing its output. It can be used for explaining the prediction of any model by computing the contribution of each feature to the prediction.
ASSET MANAGEMENT SYSTEM IN HIGHER EDUCATION INSTITUTION USING TDWI BIG DATA MATURITY MODEL
Asset management is the process of recording, collecting data, reporting and documenting assets at a specific time based on existing provisions, proper asset management can support operational activities especially in the maintenance, repair, and procurement of assets for the organization. This study aims to addition to acquiring additional assets data and calculating devaluation of assets, including tracking their location, collating data regarding their operation and maintenance status, with the aim of improving the overall utilization of the assets The methodology used in this research is TDWI Big Data Maturity, which can accommodate changes during the system design process, by taking samples based on the business process of asset management in one of the private institution. This study produced a web-based asset management information system that can assist in managing and tracking asset data and logistic items.
DESIGN PROTOTYPE OF KANTONG MIMPI APPLICATION AS A PLACE FOR GOODS DONATION USING USER-CENTERED DESIGN METHOD
Many social activities are carried out by the community as a form of their concern for others, such as raising donations for local communities in need. By utilizing technology and the internet, these social activities will be carried out in a fresher and more structured manner. Kantong Mimpi is an application that can cover problems regarding raising donations for people in need. Donation raising that can be done in this application only focuses on raising donations in the form of goods. In designing the prototype of this application, later it will connect fundraiser and donors. This research will focus on user needs, so to achieve this goal, the design of this study uses the User-Centered Design method. The result of this research is the design of the prototype of the Kantong Mimpi Application. In the process of testing the prototype, the System Usability Scale (SUS) questionnaire was distributed to 40 respondents as a benchmark for evaluation and the result is acceptable.
HOW AI USED TO PREVENT CYBER THREATS
The merging of AI and CS has opened new possibilities for both disciplines [AI]. When used to the creation of intelligent models for malware categorization, intrusion detection, and threat intelligence sensing, deep learning is only one example of the many types of AI that have found a home in cyber security. The integrity of data used in AI models is vulnerable to corruption, which increases the risk of a cyberattack. Specialized cyber security defence and protection solutions are necessary to safeguard AI models from dangers such as adversarial machine learning [ML], keeping ML privacy, preserving federated learning, etc. These two tenets form the basis of our investigation into the effects of AI on network safety. In the first part of this essay, we take a high-level look at the present state of research into the use of AI in the prevention and mitigation of cyber-attacks, including both the use of more conventional machine learning techniques and existent deep learning solutions. We then examine possible AI countermeasures and divide them into distinct defence classes according to their characteristics. To wrap up, we expand on previous studies on the topic of building a safe AI system, paying special attention to the creation of encrypted neural networks and the actualization of secure federated deep learning.
COMPARATIVE STUDY OF OSPF AND BGP FOR HYBRID CLOUD CONNECTIVITY
The current paper will perform a detailed analysis of Open Shortest Path First and Border Gateway Protocol in the context of a hybrid cloud, based on a set of relevant key performance indicators such as latency, load balancing, convergence speed, and resiliency in network designs which bridge an on-premise infrastructure with the cloud. It contrasts, through simulations and case studies, the suitability of OSPF versus BGP in hybrid cloud architectures, investigating means to optimize connectivity, efficiency, and fault tolerance. Contributions include added perspective into unique benefits and limitations when OSPF and BGP are used in multidomain, hybrid cloud architectures as part of ongoing discussions on cloud networking.
A SURVEY ON HAND GESTURE CONTROLLED ROVER
The Gesture Controlled Rover is a robot that responds to simple human motions. Robots these days are playing quite a significant role in day-to-day life. This work aims to propose a new technique to operate a robot by utilizing gestures, as well as to develop a remote-control robot that can be controlled using only gestures from a distance. A gesture gadget is to be worn by a user that has a sensor attached to it. As instructed by this user, the sensor records the movement made and thus the robot will move in the same instructed direction. This concept can be used to create a robot whose navigation can be automated. Gesture commands that the user can freely train can be utilized to control external devices using a handheld wireless sensor unit. The accelerometer is controlled by hand movements. The signals received by the accelerometer are then processed by the Arduino microcontroller. The robot is moved in the instructed direction by the microcontroller. The sensors have control over vehicle since they act as the remote control that controls the vehicle. The user will be able to control the bot's forward, backward, left, and right movements using the same accelerometer sensor that controls the bot's throttle. The differential mechanism controls the robot's movement.
AUTOMATED COIN RECOGNITION SYSTEM USING ANN
Coins are integral part of our day to day life. We use coins everywhere like grocery store, banks, buses, trains etc. So it becomes a basic need that coins can be sorted and counted automatically. For this it is necessary that coins can be recognized automatically. In this paper we have developed an ANN (Artificial Neural Network) based Automated Coin Recognition System for the recognition of Indian Coins of denomination `1, `2, `5 and `10 with rotation invariance. We have taken images from both sides of coin. So this system is capable of recognizing coins from both sides. Features are extracted from images using techniques of Hough Transformation, Pattern Averaging etc. Then, the extracted features are passed as input to a trained Neural Network. 97.74% recognition rate has been achieved during the experiments i.e. only 2.26% miss recognition, which is quite encouraging.
SMART ATTENDENCE MANAGEMENT SYSTEM USING FACE DETECTION
This project involves building an attendance system which utilizes facial recognition to mark the presence, time-in, and time-out of Students. It covers areas such as facial detection, alignment, and recognition, along with the development of a web application to cater to various use cases of the system such as registration of new Students, addition of photos to the training dataset, viewing attendance reports, etc. This project intends to serve as an efficient substitute for traditional manual attendance systems. It can be used in corporate offices, schools, and organizations where security is essential. Facial recognition is becoming more prominent in our society. It has made major progress in the field of security. It is a very effective tool that can help low enforcers to recognize criminals and software companies are leveraging the technology to help users access the technology. This technology can be further developed to be used in other avenues such as ATMs, accessing confidential files, or other sensitive materials. Using this system any corporate offices, school and organization can replace their traditional way of maintaining attendance of the Students and can also generate their availability (presence) report throughout the Month.
EDUVISTA 2.0 “THE FUTURE WAY OF LEARNING”
A direct or indirect real-world representation of an environment whose components are augmented by computer produced information, ideally across many sensory modalities, is what virtual and augmented reality (AR) is all about. Augmented reality is a type of reality that is augmented digitally by the presence of virtual items in our range of vision. The basic goal of augmented reality is to incorporate elements of the digital world into a person's imagination of the actual world. This is accomplished by the integration of immersive sensations that are viewed as natural features of an environment, rather than simply displaying data. The application will mostly benefit pupils who are learning. Students can learn through interacting with virtual objects and learning materials, and by assisting students in actively interacting in the lab while completing various experiments in order to boost their understanding and learning rather than reading. Augmented Reality is a breakthrough technology that could considerably ease execution of complex operations. Augmented Reality mixes virtual and actual reality, making available to the user new tools to ensure efficiency in the transfer of knowledge for several processes and in several environments. Various solutions based on Augmented Reality have been proposed by the research community: particularly in maintenance operations Augmented Reality tools have offered new perspectives and have promised dramatic improvements. On the other side Augmented Reality is an extremely demanding technology and, at the present day, it is still affected by serious flaws that undermine its implementations in the industrial context.
UTILIZATION OF UGV IN MINING SECTORS
Many existing UGV applications in defense and mining areas have specific constraints, for example, unfit to accomplish wide range control and incapable to work in dark place, etc. Presently days the reason for Unmanned Ground Vehicle in different fields become important to stay away from the human loses. Particularly in defense and mining area to lessen the human interaction in dispatching bombs numerous recommendations are made. Here we propose a model/framework which sense the environment conditions utilizing gas sensor and temperature sensor In this structure we began designing an UGV application in a more effective with covering wide range Wi-Fi empowered controlling gadgets with night mode camera operability. This guarantees the fast detection of objects even in higher range and emphasis on mobile application where UGV is controlled from remotely. These outcomes in programmed dispatching of bombs where the human dangers is decreased.
CACHE UTILIZATION USING A ROUTER BUFFER
Network on chip (NOC) is used to connect Multiple Cores in a tiled multicore Processor. Here each core is connected to L1 cache where LLC (L2) is shared by the entire core. The data in the Last Level Cache slices can be accessed by multiple cores simultaneously and results in congestion at the LLC and increases the access time .So in order to find a solution to this problem, Propose a congestion management Technique in the LLC that contains NOC Router with small storage (Router Buffer Cache) to keep a copy of heavily shared cache blocks. The simulation of the Multicore system can be done by Gem5 tool and evaluate its effectiveness by running a set of parallel benchmarks , Thereby Reducing the LLC access Time “
MACHINE LEARNING TECHNIQUES TO PERCEIVE INTRUSIVE SOFTWARE
Machine learning based malware detection algorithms are usually integrated into antivirus software and therefore they are black-box systems to malware authors. It is hard for malware authors to know which classifier a malware detection system uses and the parameters of the classifier. However, it is possible to figure out what features a malware detection algorithm uses by feeding some carefully designed test cases to the black-box algorithm. Malware authors can modify a benign program’s DLL or API names to malware’s DLL or API names, and vice versa. If the detection results change after most of the modifications, they can judge that the malware detection algorithm uses DLL or API features. Therefore, in this paper we assume that malware authors can know what features a malware detection algorithm uses but know nothing about the machine learning model. The proposed model in this paper uses GANs, which generates adversarial examples to attack black-box malware detection algorithms. A substitute detector is trained to fit the black-box malware detection algorithm, and a generative network is used to transform malware samples into adversarial examples. Experimental results show that almost all the adversarial examples generated by GANs successfully bypass the detection algorithms.
AUTOMATED ADAPTIVE LIGHT CONTROL FOR AUTOMOBILES
The purpose of this paper is to discuss the design and operation of self-adaptive lights systems in automobiles. The primary goal of this approach is to present an inexpensive methodology for illuminating blind spots and to make the objects visible in dark while driving and during periods of significant diminished visibility in dark locations, thereby avoiding accidents. The reasons for most road accidents without the control of a driver would be due to high beam lights approaching from the vehicles in the opposite direction and the fog causing invisibility of road depending on weather condition and since the beams are focused in a particular direction, it would be difficult in curves to handle the worst situations in driving. To address this problem, motorized headlights that turn according to the steering wheel of a car with adjustable brightness, and depending on atmospheric moisture, fog light is controlled and automatic dim and dip option is used on the basis of opposite vehicle's beam are being proposed as a solution.
LIDAR BASED ACTIVE SUSPENSION
A car's suspension system is the device that physically separates the vehicle's body from its wheels. Traditional suspension systems have a limited ability to protect the car's chassis from the outside elements. Recent developments in this area go by the label of "active suspensions". As vehicle capabilities have risen, the suspension system's performance has significantly improved. Active suspensions are effective but by no means flawless. There are several things that can be done to make them better. Herein is the significance of this research paper. Using sensors like global navigation satellite systems (GNSSs), light detection and ranging (LiDAR), and inertial measurement units, autonomous cars are able to localize accurately and perceive real-time route information (IMUs). Using route information, cars may automatically go to a certain location without causing any traffic incidents. The majority of research on autonomous cars, although being an important reference for vehicles travelling on uneven terrain, has given little attention to information on road profiles. The precision and stability of data collected by LiDAR and IMUs are decreased by the strong vibrations that the majority of vehicles encounter when travelling over uneven terrain. On the other side, active suspension systems enable vehicles to retain stability on inclines, further ensuring sensor accuracy. In this article, we present a brand-new approach to estimating road profiles that makes use of active suspension systems on automobiles and LiDAR. In the former, an elevation map was supplemented with real-time cloud data points that were collected using 3D laser scanners, IMU, and GPS. In the latter, a Kalman filter method was used to further analyze the elevation map and fuse several cloud data points at a single map cell. The active suspension system is intended to be controlled using the model predictive control (MPC) approach in order to maintain vehicle stability and further lessen drifts of LiDAR and IMU data. The trial findings showed that the proposed approach was accurate and efficient when used in outdoor settings.
SMART WRIST PULSE OXIMETER
In the present day we live in, a catastrophic virus COVID-19 has drastically changed the day to day living of a human being. The virus causes hypoxemia (shortness of breath), sometimes even severe cases. Hypoxemia is caused due to low oxygen saturation (SpO2) levels and in order to monitor SpO2 levels we utilize the method of Pulse Oximetry. It has played a major role in monitoring oxygen levels in a continuous and accurate manner. Patients who are diagnosed during the early stages with the virus are able to monitor their SpO2 levels at home and take the prescribed medicines. This reduced the need for hospital beds and chaos during the pandemic as patients were able to self-isolate and monitor themselves. The principle that Oximetry is contingent on is light reflectance. The fingertip model is the most common technique used to display the blood oxygenation level. However, the finger model is not as comfortable and does not promote continuous monitoring of SpO2 levels. Factors such as nail polish can play a role in the accuracy of the reading. The proposed design is a non-invasive medical device that can measure the oxygen saturation level in a person’s blood. Wrist wearing is preferrable to finger models as it is a comfortable site for measuring than that of the latter, therefore enabling continuous monitoring of oxygen saturation level. Most devices in application today are inaccurate and used for non-clinical use. Therefore, it is aimed to achieve better accuracy by avoiding readings that are influenced by factors such as motion artifacts by utilizing sensors that are appropriate through an accelerometer and gyroscope. The sensors have been utilized to its maximum potential as the model also detects heart rate levels. Providing device connectivity to the proposed wrist pulse oximeter through a Wi-Fi module has advanced its functionality by transmitting notifications that alert an individual with the levels of oxygen saturation, fall detection and heart rate levels.
FORMULATION, DEVELOPMENT AND OPTIMIZATION OF SUSTAINED RELEASE DELIVERY SYSTEM OF ANTI-PLATELET DRUGS
Antiplatelet medications currently on the market interfere with one or more phases in the platelet release and aggregation process, leading to a meaningful decrease in thrombosis risk that cannot be separated from an elevated risk of bleeding. Understanding that under physiological conditions, 1011 platelets are created daily-a quantity that can rise up to 10-fold during times of greater need—is crucial when thinking about antiplatelet medications.
PHARMACOGNOSTICAL AND PHYTOCHEMICAL EVALUATION OF BARK EXTRACT OF ZMA AND ZME ZIZIPHUS MAURITIANA AND ZIZIPHUS NUMMULARIA (RHAMNACEAE)
Medicinal plants are used in traditional system of medicine to treat various diseases and many of these plants have been evaluated for their different pharmacological activities. Ziziphus mauritiana (ZM) (Rhamnaceae) is found wild and cultivated in many parts of India, Burma and Srilanka. Seeds of Ziziphus mauritiana have been reported to have sedative-hypnotic, hypotensive, antihypoxic, antihyperlipidemic and hypothermic activities. It is reported to contain minerals, alkaloids, flavonoids, sterols, tannins and saponins. Traditional medicine using herbal drugs exists in every part of the world. The major areas are Chinese, Indian and European traditions. The philosophies of these traditional medicines have some resemblance to each other but differ widely from modern western medicine. In view of the progress of western medicine not only new synthetic drugs but also herbal drugs have to fulfill the international requirements on quality, safety and efficacy. Herbal drugs have the advantage of being available for patients in the geographical area of the special traditional medicine. The development procedure of herbal drugs for world-wide use has to be different from that of synthetic drugs.
EVALUATION OF ANTIDIABETIC ACTIVITY OF ETHANOLIC EXTRACT OF CITRULLUS COLOCYNTHIS
The plant which is selected for studies is Citrullus colocynthis. These plants are available in large quantities in desert area of Rajasthan and different region of the world. The pharmacological studies on diabetes mellitus, hyperlipidemia, fever, bacteria, wound healing activities and antioxidant activities of the plants have been tested and evaluated for various disease treatments like diabetes, fever, obesity and other many various disorders. The main focus is given against streptozocin induced diabetes treatment in albino rats and comparison is done with standard drug glibenclamide.
VIRTUAL LABORATORY OF THIN LENSES USING ANDROID SMARTPHONE WITH PYTHON PROGRAMMING
A computer program has been created to simulate a ray diagram on a thin lens using the Python programming language. The program is a ray diagram simulation on a convex lens and a concave lens. The program is built using the canvas, create line, button and motion functions in the object-oriented programming language Python. The object being simulated is a convex and concave lens with a focal length of 10 cm and an object's height of 4 cm. The simulation results are in the form of an interface with the user using computer graphic media and interaction via a touch screen. The program can run on Android mobile phones. The results of ray diagrams on computers and Android cellular phones show that they are in accordance with theory, so that the program can be used as a virtual laboratory material.