An Artificial Intelligence Approach Toward Food Spoilage Detection and Analysis

Aiming to increase the shelf life of food, researchers are moving toward new methodologies to maintain the quality of food as food grains are susceptible to spoilage due to precipitation, humidity, temperature, and a variety of other influences. As a result, efficient food spoilage tracking schemes are required to sustain food quality levels. We have designed a prototype to track food quality and to manage storage systems at home. Initially, we have employed a Convolutional Neural Network (CNN) model to detect the type of fruit and veggies. Then the proposed system monitors the gas emission level, humidity level, and temperature of fruits and veggies by using sensors and actuators to check the food spoilage level. This would additionally control the environment and avoid food spoilage wherever possible. Additionally, the food spoilage level is informed to the customer by an alert message sent to their registered mobile numbers based on the freshness and condition of the food. The model employed proved to have an accuracy rate of 95%. Finally, the experiment is successful in increasing the shelf life of some categories of food by 2 days.

Smart Home Automated System Using Raspberry-Pi and Google Cloud Services

This paper represents the development of an automated system based on IoT, which can mainly be used in the home and some features can also be implemented in offices, banks, or schools. The main purpose of this project is to save time and manpower along with security and convenience, using Raspberry pi. The salient features of this automated system are gas leakage detection for safety purposes, motion detection for security purposes, and controlling the home appliances as per the user’s need. The system takes command through voice as well as text as per the user’s requirements using google assistant, which further sends a response to Raspberry-Pi via Firebase for the required action. DHT22 sensor is used for the measurement of temperature and humidity, room temperature and Humidity will be displayed through Google assistant. This system consists of Python as the main programming language by default, provided by Raspberry Pi. The system will detect human presence with the help of a motion sensor i.e, whenever a person enters the room, the motion is detected and automatically an alert message will be sent to the user via Google assistant. Keywords: IoT, Raspberry-pi, Google assistant, Firebase, Python, Dialogflow, Voice Recognition.

Three Layered Architecture for Driver Behavior Analysis and Personalized Assistance with Alert Message Dissemination in 5G Envisioned Fog-IoCV

The Internet of connected vehicles (IoCV) has made people more comfortable and safer while driving vehicles. This technology has made it possible to reduce road casualties; however, increased traffic and uncertainties in environments seem to be limitations to improving the safety of environments. In this paper, driver behavior is analyzed to provide personalized assistance and to alert surrounding vehicles in case of emergencies. The processes involved in this research are as follows. (i) Initially, the vehicles in an environment are clustered to reduce the complexity in analyzing a large number of vehicles. Multi-criterion-based hierarchical correlation clustering (MCB-HCC) is performed to dynamically cluster vehicles. Vehicular motion is detected by edge-assisted road side units (E-RSUs) by using an attention-based residual neural network (AttResNet). (ii) Driver behavior is analyzed based on the physiological parameters of drivers, vehicle on-board parameters, and environmental parameters, and driver behavior is classified into different classes by implementing a refined asynchronous advantage actor critic (RA3C) algorithm for assistance generation. (iii) If the driver’s current state is found to be an emergency state, an alert message is disseminated to the surrounding vehicles in that area and to the neighboring areas based on traffic flow by using jelly fish search optimization (JSO). If a neighboring area does not have a fog node, a virtual fog node is deployed by executing a constraint-based quantum entropy function to disseminate alert messages at ultra-low latency. (iv) Personalized assistance is provided to the driver based on behavior analysis to assist the driver by using a multi-attribute utility model, thereby preventing road accidents. The proposed driver behavior analysis and personalized assistance model are experimented on with the Network Simulator 3.26 tool, and performance was evaluated in terms of prediction error, number of alerts, number of risk maneuvers, accuracy, latency, energy consumption, false alarm rate, safety score, and alert-message dissemination efficiency.

IoT Based Smart Cradle Using PI

In this modern era, parents are busy building their lifestyle, carrier etc. As we know it has now become hard because parents have to take care of their children simultaneously, which paves a lot of work pressure and family pressure especially for women. Health of the child is affected and better care has also reduced. So, in order to handle such situation, we use temperature, Humidity, ultra-sonic Sensor. The conditions of the external atmosphere help to detect increased body temperature, babies voice while crying and their movements while they are continuously moving and also indicates the time for the diaper to be changed. If there are any abnormal activities are observed in baby’s atmosphere. An alert message is sent to the parents. In this system a video camera is attached and operated under the microcontroller’s instruction and it records a video when the motion sensor detects any continuous movements. The recorded video is broadcasted in a display to the parents which helps them to monitor baby in live. And in addition, this system detects and displays the status of the infant and alert the respective guardian by collecting values from sensor like temperature sensor, ultrasonic sensor, and also the location value from raspberry pi.

Communication Network Architectures for Driver Assistance Systems

Autonomous Driver Assistance Systems (ADAS) are of increasing importance to warn vehicle drivers of potential dangerous situations. In this paper, we propose one system to warn drivers of the presence of pedestrians crossing the road. The considered ADAS adopts a CNN-based pedestrian detector (PD) using the images captured from a local camera and to generate alarms. Warning messages are then forwarded to vehicle drivers approaching the crossroad by means of a communication infrastructure using public radio networks and/or local area wireless technologies. Three possible communication architectures for ADAS are presented and analyzed in this paper. One format for the alert message is also presented. Performance of the PDs are analyzed in terms of accuracy, precision, and recall. Results show that the accuracy of the PD varies from 70% to 100% depending on the resolution of the videos. The effectiveness of each of the considered communication solutions for ADAS is evaluated in terms of the time required to forward the alert message to drivers. The overall latency including the PD processing and the alert communication time is then used to define the vehicle braking curve, which is required to avoid collision with the pedestrian at the crossroad.

Smart Security System Using IoT, Face Recognition and Processor to Processor Communication

In the present world the security of the home, banks, shops, etc., are the prime concerns. The traditional security such as Closed-Circuit Television (CCTV) cameras are very easy to break and lead to theft. And moreover, the installation cost of the security systems is costlier. To overcome these problems, we are presenting Internet of Things (IoT) based solution where we can setup a smart security system. In this paper, we are proposing the system with the help of face detection and face recognition algorithms to secure our home which gives us the facility of entire surveillance of our buildings remotely and take appropriate action if anything goes wrong. The Camera Serial Interface (CSI) is attached to the Raspberry PI which detects presence of person using Face detection and recognition algorithms. The multiple Raspberry PIs attached in different areas of our buildings are connected to the main Raspberry PI which acts as hub module. If the person is identified as unknown, the information is sent to Hub module which in turn sends the alert message and live video streaming to the user using an app which we developed.

KS IOT Based Automation System to Prevent Crop Vandalization by Rain Water in Agricultural Regions

India’s keystone is Agriculture. Around 70 percent of India’s revenue comes from Agriculture. Conversely the population of India amplifies each and every day which requires efficient and well planned decision making techniques for the production of crops. In this research paper we find the intensification of the structures which prevent destruction of crops due to uneven and heavy rainfall. The goal is achieved by the concept of Embedded System design using IOT technology. This is done automatically without any human interference. Here we first identifies the water level in the agriculture field during rainfall by using water level sensors , if the water level exceeds there limit that will cause spoilage of crop then the device are automatically cover the agriculture field. It also identifies the temperature of the crops by using temperature sensor during the sunny days, if the heat causes spoilage of crops due to intensive sun rays then the device will automatically covers the agriculture field. After covering the agriculture field it will send the alert message using GSM module to the farmer and simultaneously the water of rain is collected through piles that will be reuse later for irrigation. To achieve this we use microcontroller , Solar panels, GSM module, DC motor, sensors, Switched-mode power supply (SMPS), Rechargeable battery

Smart Aid for Blind People

Eyesight is one of the most useful living organisms, but visually impaired people do not realize that sense. They are unable to see the beauty of nature. Not all the problems of the visually impaired can be solved but with the help of modern technology life could be made easier for them. In this era, where everybody tends to be independent in order to survive, people with lack of visuality find it almost not possible. Blindness is a very common disability across the world. Our project is designed in order to give blind people a helping end in overcoming their daily life challenges. The “Smart Aid for Blind People” project consists of Ultrasonic sensors for detection of obstacles like a car, staircase and alert the person with the help of in-built buzzer and a voice module. It also detects the motion of the object by Sensors. We have also used vibrating motor and voice module for sending alert message to the blind person. The overall aim of the project is to provide a safety and convenience to blind people. Keywords: Blind People, Ultrasonics sensors, Voice Module, Arduino Microcontroller, Wearable Device, Ear Phone, Buzzer, Obstacle.

Personal Identity Identification and Authentication Statistics Based on Countermeasures against Spoofing

To make the online banking system secure, a three-step authentication method using the face, iris, and fingerprint is used. To improve security, spoofing detection has also been included. A spoofing attack happens when someone attempts to impersonate someone else and gets unauthorized access. The face and iris are captured by the camera, while the fingerprint is captured by the fingerprint module. Gray Level Co-occurrence Matrix is used to extract a picture of a person's face, iris, and fingerprint (GLCM). A reference module is constructed using the extracted picture so that the input may be compared to it, and if the input matches the module, a one-time password (OTP) is delivered to the user's mobile phone. Only the online transaction may take place if the OTP is entered correctly. Otherwise, the account holder will get an alert message. This method allows for a very secure online transaction.

Disaster Management Using VANET

Disaster management is management of tasks involving responses to emergencies and methods of devising recovery strategies from havocs caused by nature. It assumes paramount importance now as the human surrounding has enormously become unpredictable owing to natural or man-made disasters. Consequence of disaster can be reduced by broadcasting of disaster alert to a defined radius that could be affected by the disaster. The objective of disaster management is to ensure energy economical and reliable communication that is resilient to network topology changes within the area. Vehicular ad hoc network (VANET) is efficiently utilized to transfer the disaster alert information. Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication is used for disseminating the disaster alert message. This study proposes an effective data acquisition from the disaster location, data dissemination to the neighbouring zones and disaster management using VANET technology.