Practical design and implementation of recognition assisted dynamic surveillance system

Java 2 Micro Edition (J2ME) technology has been designed to bring a common framework of development for mobile devices. This can bring the Java development approach of develop once run everywhere to the Mobile application emerging market. Combined with the widespread of the support for this platform among the park of mobile devices, all of this makes J2ME a suitable option for mobile application development. However, J2ME has been designed to run in small devices, that's why the APIs (Application Programming Interface) implemented are very limited and kept to the strictly necessary. This decision has let out all the structured data persistence management, like object serialization, and the relational database access; neither to store data inside the mobile device nor to access a remote host. This paper presents J2MEMicroDB, an Open Source development that implements Object Serialization, local relational database engine and a remote database access protocol that allows the access to any JDBC database. In the design and implementation of J2MEMicroDB specific requirements and limitation of Mobile devices have been considered. Even some performance improvements have been developed, like BTree indexing structures which improves significantly the efficiency, as the cross-platform presented benchmarking proves.

To develop a network management system (NMS) more easily, the authors developed an application programming interface (API) for configuring network devices. Because this API is used in a Java development environment, an NMS can be developed by utilizing the API and other commonly available Java libraries. It is thus possible to easily develop an NMS that is highly compatible with other IT systems. And operations that are generated from the API and that are exchanged between the NMS and network devices are based on NETCONF, which is standardized by the Internet Engineering Task Force (IETF) as a next-generation network-configuration protocol. Adopting a standardized technology ensures that the NMS developed by using the API can manage network devices provided from multi-vendors in a unified manner. Furthermore, the configuration items exchanged over NETCONF are specified in an object-oriented design. They are therefore easier to manage than such items in the Management Information Base (MIB), which is defined as data to be managed by the Simple Network Management Protocol (SNMP). We actually developed several NMSs by using the API. Evaluation of these NMSs showed that, in terms of configuration time and development time, the NMS developed by using the API performed as well as NMSs developed by using a command line interface (CLI) and SNMP. The NMS developed by using the API showed feasibility to achieve “autonomic network management” and “high interoperability with IT systems.”

Delivering first aid before transferring patients to hospital is among keys to survival. Moreover, calling the emergency center as soon as possible and providing brief information about the patient are helpful for the emergency center to dispatch specialized medical team and equipments proportionate to the conditions of the patient. Mobile phone is a device which many people use and always carry with them. One more thing is that SMS (Short Message Service) stands as a favorite service in mobile network, used to exchange short messages and featuring low cost, non-stop lines of dispatch, possibilities for offline work and so forth. This paper puts forward procedures of calling an emergency center through SMS in which whenever a patient feels sick, it is enough just to press a button on mobile phone for seconds to activate a special program which automatically sends a message for the emergency center, the family doctor and a next of kin, carrying residence address (by using GPS system), personal information (age, name, etc.) and a brief medical record (current illnesses, individual second habits like smoking, etc.). As a follow-up, the emergency team will examine the records and subsequently send a medic and a specialized doctor for possible diseases (for example a cardiac medic for potential heart attack). Family doctor and relatives on the other hand will be briefed on the patient's conditions. The project is written by the Java 2 Micro Edition (J2ME) programming language and tested on a Nokia N71 mobile phone.

From the supply chain management (SCM) perspective, the low level of information accessibility to rice commodities availability has been one of the major postharvest distribution-related problems. This issue potentially cause delay in delivery, product scarcity and eventually financial loss for stakeholders. Previous studies concerned more with web and mobile applications for distribution of production means applicable for pre-harvest stage. This study focuses on the development of modest web and mobile SCM applications for distribution of post-harvest rice commodities. The characteristics of these applications are capable of addressing problems faced by those involved in such product delivery system. Web application was designed using Simple Object Access Protocol (SOAP) through Hypertext Transfer Protocol (HTTP) towards a service at Uniform Resource Locator (URL). Mobile application was designed using Java 2 Micro Edition (J2ME) to build a smart client loaded onto handphone. Comparison of system simulation on sofware requirement specification (SRS), use case diagram was presented in tabular form enabling users for need adjustment. Output of this research included user interface model and application prototype introduced to client and user to obtain feedback. The tabular SRS measure using use case showed on average a degree of appropriateness of 92%. User satisfaction level averaged 4.345 (out of 5) suggesting a good performance of the designed applications. Utilizing internet and handphone technology, the application models have fulfilled theoretical requirements and have adequately responded problems relating to the poor information accessibility in an SCM-based, postharvest rice distribution system, hence are worthy of being called as a modest web and mobile SCM. Keywords: information accessibility, application analysis and development, distribution of post-harvest rice commodities, web-SCM, mobile-SCM

There are many websites specially designed for mobile phones. Some hackers write automated programs to abuse these website services and waste the website resources. Therefore, it is necessary to distinguish between human users and computer programs. Methods known for achieving this are known as CAPTCHA (Completely Automated Public Turing test to tell Computers and Human Apart). CAPTCHA methods are mainly based on the weaknesses of OCR (Optical Character Recognition) systems and ask the user to type a word. So using them is difficult in tools such as PDAs (Personal Digital Assistant) or mobile phones that lack a complete keyboard. In this paper, a new CAPTCHA system is proposed for touch-screen devices such as PDAs and mobile phones. In this system, a word is drawn in a random place on the screen and a number of arcs are drawn on the screen. Then the user is asked to highlight the word by the stylus. Due to the limitations of the PDA and mobile phone, OCR programs on these devices cannot recognize the shown word, while a human user can easily highlight the word. The proposed method is implemented by the JavaME (Java Platform Micro Edition) language and tested on a Sony Ericsson P990i mobile phone.

A fundamental dilemma in location-aware mobile applications is how to determine their physical location. Because pervasive computing is still immature, and its ubiquitous infrastructure is not set to serve location-aware applications, much research has been conducted in the last few years to use available technologies to determine physical location. This paper describes the definition and implementation of a generic location identification framework which is reusable by most location-aware mobile applications. A review of technologies for location determination leads to the design of a Location Abstract Framework (LAF) to implement different location sensing techniques under a common Application Programming Interface (API). A Java Micro-Edition (J2ME) implementation of LAF using Radio Frequency Identification (RFID) based location sensing methods is described

The human traffic in each bus station is estimated in real-time by means of an embedded ARM(Acorn RISC Machine) platform and the API(Application Programming Interface) in OpenCV(Open Source Computer Vision). For high-density human traffic situations, this paper proposed a method in which the Hough Circle Transform, centroid coordinates and color are used as the features for detecting, tracking and counting the moving targets. Experimental results show that the proposed method can solve the problem of counting the moving targets from the video sequences in the case of high-density human traffic.

This paper discusses how a Java 2 Micro Edition (J2ME) application may be developed to visualise a wide variety of differing fractal types on a mobile phone. A limited number of J2ME applications are available that are capable of generating the Mandelbrot Set. At present there are no J2ME applications capable of generating a multitude of fractal image types.

An intelligent security system that provides a high level of home security using visual surveillance is developed and explored in this paper. This will be very much useful in home and company automation. The main processing unit is a cortex ARM processor with Linux operating system and the board we are using is Beagle Bone Black (BBB). Surveillance system is achieved using OpenCV(open source computer vision) and the communication system is designed by using GSM(Global System for Mobile Communication) Module. Total number of people in a room is counted by using the OpenCV. The user while leaving the premises can give voice command to make the system active. The system continues automatic surveillance when the user left the house or office. It can be modified to turn on automatic surveillance at a specific time of the day. If the user left the premises and the system detects the presence of a human being in there then an SMS will be sent to the Cell phone of the user and the alarm will be turned on. After turning on the alarm the system will start recording video on the SD card so the user can inspect later. The system can also count the number of people in the room by using image processing algorithm and will automatically turns off all the load in the room when no one is present. This will also help to reduce the unnecessary wastage of power.

In this paper, the authors propose a smart home-care system built on an Android smartphone. The database and application programming interface (API) are set up on the server side. The database collects information from various sensors and stores it, and the API acts as a bridge between the mobile phone and the database. The API prevents the leakage of private data. In the associated Android smartphone app, two functions are provided: instant monitoring based on in-home sensor data and fall detection using the three-axis accelerometer, gyroscope, and orientation sensor inbuilt into the smartphone. When the sensor data are abnormal, the remote controller is notified immediately. Moreover, the remote controller can view real-time images by using an IP camera to guarantee home safety. As for fall detection, given that falls cause severe injuries in elder people and children, the proposed app can detect a fall event, send a help message, and indicate the user’s location by using the global positioning system and Google Maps API. According to the simulation results obtained in this study, the proposed system exhibited a fall-detection sensitivity of 92.5% and specificity of 97.6%, thus proving that the system can be effectively used for home care.

ZWT: A new cross-platform graphical interface framework for Java applications

This paper presents the Peer2Me framework that enables developers to create mobile peer-to-peer applications. The framework provides an API that is easy to adopt, yet capable of creating advanced peer-to-peer applications. The framework was built to provide applications providing pure peer-to-peer network where all nodes have the same responsibility and services. Further, the framework provides services to transparently manage the detection of new and lost peers. The message component of the framework makes it possible to exchange any kind of data between peers including Java objects. The Peer2Me has been implemented in Java 2 Micro Edition (J2ME) and runs on standard mobile phones. The framework supports management and communication of mobile ad hoc networks (MANETs) like Bluetooth. The paper describes the architecture, the API and some of the applications developed using the Peer2Me framework. Further, we share and discuss experiences from developing mobile peer-to-peer applications.

Image Processing and Computer Vision solutions have become commodities for software developers, thanks to the growing availability of Application Programming Interfaces (APIs) that encapsulate rich functionality, powered by advanced algorithms. Tech giants like Apple, Google, IBM, and Microsoft have made APIs and micro-services available in the cloud for the agile integration of machine learning and intelligent features onto everyday applications. As privacy and cyber welfare become prime concerns, special efforts have been devoted in the field of face processing and recognition. In this context, this paper provides a friendly, intuitive and fun to use mobile app that leverages the state-of-the-art APIs for face, age, gender and emotion recognition. The Face- It-Up app was implemented for the iOS platform and uses the Microsoft Cognitive Services APIs as a tool for human vision and face processing research. Experimental work on image compression, upside-down orientation, the Thatcher effect, negative inversion, high frequency, facial artifacts, caricatures and image degradation were performed to test the application. For this purpose, we used the Radboud and 10k US Adult Faces Databases. The app benefits from accessing high-resolution imagery and touch input from the smart-devices, allowing for a wide range of new experiments from the user perspective. Furthermore, our approach serves as a potential framework for new initiatives in image-based biometrics, the Internet of Things, and citizen science.

Multicore processors have been adopted for consumer electronics like portable electronics, mobile phones, car navigation systems, digital TVs and games to obtain high performance with low power consumption. The OSCAR automatic parallelizing compiler has been developed to utilize these multicores easily. Also, a new consumer electronics multicore application program interface (API) to use the OSCAR compiler with native sequential compilers for various kinds of multicores from different vendors has been developed in NEDO (New Energy and Industrial Technology Development Organization) "Multicore Technology for Realtime Consumer Electronics" project with Japanese 6 IT companies. This paper evaluates the parallel processing performance of multimedia applications using this API by the OSCAR compiler on the FR1000 4 VLIW cores multicore processor developed by Fujitsu Ltd, and the RP1 4 SH-4A cores multicore processor jointly-developed by Renesas Technology Corp., Hitachi Ltd. and Waseda University. As the results, the parallel codes generated by the OSCAR compiler using the API give us 3.27 times speedup on average using 4 cores against 1 core on the FR1000 multicore, and 3.31 times speedup on average using 4 cores against 1 core on the RP1 multicore.

Objectives/Aim: The present paper deals with building a smart assistant with the aim of assisting the visually impaired people in mobility with confidence by realizing the nearby obstacles and also implement image processing techniques to recognize people. Methods: We use Raspberry Pi 4 which has increased computing performance and is interfaced to the picamera, GPS and GSM modules. Arduino pro mini with buzzer, ultrasonic sensors and vibration motors are used for obstacle detection. Certain libraries important for image processing are used such as OpenCV, Dlib, face detection (Haar cascades, HOG + Linear SVM, or CNNs), espeak for converting text to speech. Programming was implemented through Python and Arduino compiler. Findings: Analysis was carried out using the proposed system for the blind and visually impaired people who could move around comfortably with confidence and were also able to detect objects and recognize people. Hence the proposed system removes the use for the cumbersome white cane in exchange for small and handy modules which can be used in the form of wearables mounted on shoulders, hands and legs to detect the obstacles from multiple directions and provide for a comfortable wear. It was determined that the Raspberry pi 4 was incapable of running CNN detection for which ideally computer GPU was required, so HOG detection method was used instead. Application/Improvements: This project can be implemented mainly in the commercial field of helping visually impaired people with poor eyesight or being completely blind. Industrial applications can be devised and enhanced like robots and machineries along with Security, Identifying and Tracking. Keywords: Face Recognition; Obstacle Detection; Open Source Computer Vision (OpenCV); Deep Learning; Histogram of Oriented Gradients (HOG); Support Vector Machine (SVM); Convolutional Neural Network (CNN)