Search

This paper presents an intelligent system that can identify and recognize faces with applications, including a person's tracking, home surveillance, and private security. An automatic face recognition intrinsically handles security issues with flexibility — in the case of an unrecognized or unknown person, the real-time video stream is processed, motion is detected, and dual-axis pan-tilt servos track that person with a camera. Furthermore, such peculiar activities are video recorded with synchronization from cloud storage, and mobile alerts are generated. In the absence of the internet, a database file is developed with an audio notification to the security room if the anonymous face detected is not present in the database. Speech recognition and relay are also added for voice transmission and activation of surrounding lights. This project intends to substitute costly security systems using Raspberry pi 3B+ as the microcomputer.

The proposed project involves the development of a safety gadget with innovative and life saving features. The development of an intelligent helmet ensures the safety of a rider or an employee in an utmost sense. The intelligent pre-safety accident prevention measures are embedded through smart techniques with immediate notification in case of an emergency. The prototype comprises of several features that are programmed and managed through Raspberry Pi microcomputers. The solution is tested and integrated with custom mobile application for controlling parameters. The display connected to the helmet provides indication of controlling parameters. The system design is efficient and cost-effective involving manual and auto-charging solutions. The unique approaches used makes it efficient and productive according to different applications.

This paper is aimed towards students and roboticists with an objective to provide the concise theoretical and applied knowledge necessary for the control design of mobile manipulator. For this purpose, topics such as kinematics, motion planning and control theory are explored. Moreover, this knowledge is integrated from the perspective of Mecanum wheeled 5-R mobile manipulator for the pick-and-place task of cube. Finally, the paper shows the successful application of the accumulated knowledge in simulated V-REP environment.

In recent years, reinforcement learning (RL) has emerged as a strong candidate to solve many decision-making problems. It fundamentally combines the benefits of both deep neural networks and control engineering practices to accomplish human-level or even superior competency in decision-concise systems. This work extends this very idea and proves the applicability of RL algorithms to combinatorial puzzles such as river-crossing puzzle and seating arrangement problems. In that regard, this work applied quality-networks (QN), deep-quality-networks (DQN), and double-deep-quality-networks (DDQN) to environments mentioned above, and afterward, evaluated their performance through analyzing reward and performance plots. The study concludes that all these methods effectively completed the puzzle tasks with unnoticeable performance differences for the given environments.

Recently, there has been a rise in car theft, lifting, and snatching in various towns of Pakistan. Plus, some harassment cases in Uber/Careem ride booking services are also reported. Therefore, this paper presents an innovative solution, named as I-safe Technology, which introduces black-box in cars. I-safe functionalities include live streaming with audio/video recording, cloud integration, real-time location tracking, personalized user app, and centralized database for the managerial process. The device is water-proof, fire-proof, and compact; it ensures the safety of data for future inspection and helps in the determination of the root cause of incidents.This idea is novel in several ways. Firstly, the problems addressed are uniquely local, and there is no such prior work in technical literature. Secondly, this solution 2x times cost-effective than comparable products available in the market. Thirdly, this solution is highly customizable with a smartphone application that provides ease to users by automating all functionalities of a car.

To manage and handle the issues of physical security in the modern world, there is a dire need for a multilevel security system to ensure the safety of precious belongings that could be money, military equipment or medical life-saving drugs. Security locker solution is proposed which is a multiple layer security system consisting of various levels of authentication. In most cases, only relevant persons should have access to their precious belongings. The unlocking of the box is only possible when all of the security levels are successfully cleared. The five levels of security include entering of password on interactive GUI, thumbprint, facial recognition, speech pattern recognition, and vein pattern recognition. This project is unique and effective in a sense that it incorporates five levels of security in a single prototype with the use of cost-effective equipment. Assessing our security system, it is seen that security is increased many a fold as it is near to impossible to breach all these five levels of security. The Raspberry Pi microcomputers, handling all the traits efficiently and smartly makes it easy for performing all the verification tasks. The traits used involves checking, training and verifying processes with application of machine learning operations.

Motion simulators are gaining popularity for training, quality-assurance and gaming purposes. Washout-filter is considered to be the core component of such motion platforms. This work presents the theoretical background of washout filter for Stewart-Gough flight Simulator followed by its design implementation on MATLAB/Simulink. All six degree of freedom flight simulation results are comprehensively discussed and evaluated separately as well as in co-ordination cases on mechanical structure of hexapod in SimMechanics environment of MATLAB/Simulink.

The increased modernization has made the world more dependent on technology, thus increasing the demand for more power and energy. Therefore, a need to generate energy by minimal consumption has become a dire need for researchers. Thus, this research paper puts forth an optimal solution of such problems by harvesting energy through mechanical vibrations by means of low power consumption setup. This paper presents a project that generates electricity through piezoelectric setup in the floor tiles. As piezoelectricity is the generation of electricity by means of mechanical vibrations, we use an electromechanical converter that is a piezoelectric transducer, which converts applied mechanical pressure into electrical energy. These piezoelectric transducers were placed in tiles or areas where the highest pressure is observed so that maximum stress through walking is applied, and possibly be converted into optimum amount of electricity. To harvest maximum amount of electricity generated, a small bridge rectifier circuit is designed which is used as an AC-DC converter. This bridge rectifier circuit converts alternating current AC into direct current DC and the converted DC energy is used to charge the battery which can be utilized for further usage in low-power electronic equipment.