iosr-JCE   Volume-20 ~ Issue-1 ~ Jan-Feb 2018

Abstract: The Internet of Things (IOT) is a system of related computing devices, animals or people that are given a distinct identifiers and the capability of transferring data across a network without human interaction. IOT has been highly equipped in transport system. In today's fast growing world people tend to wait for a long time in bus stops for buses to arrive due to increased traffic, accidents and bad roadways. To overcome such disadvantages, this paper deals with major challenges in the public transport system and discusses various approaches to intelligently manage it. Basically, the current position of the bus is located using GPRS and GPS but they would not able to handle high demand on the backend which will exist in the near future. The primary attribute of this paper is that we have used MQTT (Message Query Telemetry Transport) for the backend handling. MQTT will be light weight, data efficient and scalable. This system is implemented at the backend and the front end required for the tracking system and has exhibited the improvements. As large numbers of buses are tracked, the data generated will be huge, that will be stored in a Cloud server..

Keywords: GPRS, GPS, IOT, MQTT, Tracking System, Transport.

[1]. Ala Al-Fuqaha, Senior Member, IEEE, Mohsen Guizani, Fellow, IEEE, Mehdi Mohammadi, Student Member, IEEE, Mohammed Aledhari, Student Member, IEEE, and MoussaAyyash, Senior Member, IEEE "Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications" IEEE COMMUNICATION SURVEYS & TUTORIALS, VOL. 17, NO. 4, FOURTH QUARTER 2015
[2]. AdarshJha Department of Computer Engineering AmitTiwari Vishal Paarcha Department of Computer Engineering PadmabhushanVasantdada and PatilPratishthan"Real Time Bus Position and Time Monitoring System" INTERNATIONAL JOURNAL OF SCIENCE TECHNOLOGY & ENGINEERING | VOLUME 1 | ISSUE 10 | APRIL 2015
[3]. Madhu Manikya Kumar, Rajesekhar, Pavani, "Design of punctually enhanced bus transportation system using GSM and Zigbee," INTERNATIONAL JOURNAL OF RESEARCH IN COMPUTER AND COMMUNICATION TECHNOLOGY, VOL. 2, ISSUE 12, DECEMBER 2013.
[4]. S. Eken, Sayar, "A Smart bus tracking system based on location aware services and QR codes," IEEE INTERNATIONAL SYMPOSIUM ON INNOVATIONS IN INTELLIGENT AND APPLICATIONS PROCEEDINGS, PP: 299-309, 2014.
[5]. Swati Chandurkar, SnehaMugade, SanjanaSinha, PoojaBorkar, "Implementation of real time bus monitoring and passenger information system," INTERNATIONAL JOURNAL OF SCIENTIFIC AND RESEARCH PUBLICATIONS, VOL. 3, ISSUE 5, MAY 2013

Abstract: Vision is a beautiful gift to the human being by the god. The proportion of visually impaired and blind people in the world has been increased very largely. In this paper, we are introducing a smart stick system for assisting the blind people. The smart stick comes as a solution to enable visually impaired people to find difficulties in detecting obstacles and dangers in front of the blind people during walking and to identify the world around. The system consists of various sensors along with the Arduino Uno microcontroller and the GPS-GSM. Microcontroller receives the sensor signals and process them to short pulses to the Arduino pins where buzzers and vibrator are connected, which get starts if the obstacle finds in the way. GPS and GSM technology helps for tracking the device. The aim of this research is to provide a good understanding to make a suitable system in the future. It can be made available to all segments of the society and families who need them..

Keywords: Smart stick, Ardunino Uno, GSM, and GPS

[1]. M Akshay Salil Arora(Author), Vishakha Gaikwad (Author) " Blind Aid Stick: Hurdle Recognition, Simulated Perception, Android Integrated Voice Based Cooperation via GPS Along With Panic Alert System."
[2]. Ayat Nada(Author), Mahmoud Fakhr(Author), Ahmed Seddik(Author) "Assistive Infrared Sensor based smart stick for blind people."

Abstract: Face recognition is being used in a variety of fields because of its advantages such as a non-contact process, fast and accurate results, reliable matching, and diverse applications. Machine recognition of faces can be classified into two types: still image recognition and video image recognition of a person from video image face databases. Nowadays, face recognition or verification systems have a wide range of commercial and law enforcement applications. To achieve good recognition results, this paper proposes a coupled the Hidden Markov Model (HMM) with an Artificial Neural Network (ANN) to recognize the face image. The proposed system detects the facial region and recognizes the faces using the existing video face databases and finally, the system is experimentally analyzed. The proposed method is ascertained that it has small observation vector set, reduced number of transitions among states, low computing time, and most promising recognition accuracy..

Keywords: accuracy, Artificial Neural Network, face recognition, Hidden Markov Model

[1]. W. ZhaoSarnoff Corporation, Princeton, NJR. Chellappa,‖ Face recognition: A literature survey‖, ACM computing surveys (CSUR) ,2003,Volume 35 ,pp.399-458.
[2]. ElhamBagherian, RahmitaWirza O.K. Rahmit,‖ Facial feature extraction for face recognition: a review ―, IEEE, 2008, pp: 1-9.
[3]. Yang, M.H., Kriegman, D.J., Ahuja, N, ―Detecting Faces in Images: A Survey‖,IEEE TransPAMI, 2002, Volume 24 , Issue 1, pp.34–58 .
[4]. Rowley, Baluja, Kanade, ― Neural Network-Based Face Detection‖, IEEE Transaction on Pattern Analysis and Machine Intelligence, 1998 , Volume 20 , Issue 1, pp.23–38 .
[5]. Pankaj D.S., Wilscy M., ―Face Recognition Using Fuzzy Neural Network Classifier‖, Parallel Distributed Computing. Communications in Computer and Information Science, Springer, 2011, Volume 203. pp. 53-62.

Abstract: This study aimed to estimate the prevalence of internet addiction, determine its associated factors and its relationship with their demographic data among secondary school students ,and to identify potential intervention strategies that may help to minimize harm of IA.Material and Methods: A cross sectional survey, using a self-administered questionnaire, was conducted between May and June 2016, among governmental secondary school students (boys and girls) in Elthawra city, sudan, their ages between 13and 19-years-old ,a simple random sampling were collected from students in class two and three, students under study collected from 5 schools, the sample size was 303 from total 500 students from total governmental school which are 8 schools. Results: 303 students answered..........

Keywords: Internet Addiction. Secondary school students .Sudan

[1] Schneider, G. P., Evans, J., & Pinard, K. T. (2006). The Internet Fourth EditionIllustrated Introductoty (4th ed.). United States of America: Thomson Course Technology
[2] Internet World Stats. (2010b). Internet Usage Statistics: The Internet big picture: World Internet users and population stats, from http://www.internetworldstats.com/stats.htm.
[3] Mashhor Al-hantoushi et al. Internet Addiction among Secondary School Students. International Journal of Medical Science and Public Health | 2014 | Vol 3 | Issue 1
[4] Buchholz, L. (2009, 4 December 2009). Teen Internet addicts more likely to self harm. Retrieved from http://abcnews.go.com/US/wireStory?id=9245921.
[5] Jonson-Reid, M., Williams, J. H., & Webster, D. (2001). Severe emotional disturbance and violent offending among increased adolescents. Social Work Researh, 25, 213-222 .

Abstract: There are many challenges currently faced by the humanoid robot' models to achieve the objective or target planned for them. One of these challenges is the trade-off between the ability to accurately mimic the human body and uptime. While some of these models like ASIMO has very accurate degree to mimic the bipedal walking gait used by human due to high actuations, it consumes high power. Through our proposed model we introduce a model-free deep Q-learning algorithm (DQN) that doesn't simulate the bipedal walking gait used by human based on predetermined sequence or modelling via supervised learning. On counter, our proposed model learns from interactions/interfacing with the surrounding environment by applying actions on the robot and observing the reward from that action to make an under-actuated robot able to balance and walk forward, backwards, sideways, and rotate in place............

Keywords: Deep Q-learning, Humanoid robots, Multilayer Perceptron Deep Neural Networks

[1] L. Bottou , " Large-Scale Machine Learning with Stochastic Gradient Descent '' , NEC Labs America, Princeton NJ 08542, USA
[2] N. Srivastava, G. Hinton , A. Krizhevsky and I. Sutskever , " Dropout: A Simple Way to Prevent Neural Networks from Overfitting" , Journal of Machine Learning Research 15, Canada , June 2014 .
[3] MathWorks, (2017). Vision Toolbox: User's Guide (R2017a). Retrieved June 15, 2017 from https://www.mathworks.com/help/vision/examples/object-detection-using-deep-learning.html
[4] Marc G Bellemare, Yavar Naddaf, Joel Veness, and Michael Bowling. The arcade learning environment: An evaluation platform for general agents. Journal of Artificial Intelligence Research, 47:253–279, 2013.
[5] Marc G. Bellemare, Joel Veness, and Michael Bowling. Bayesian learning of recursively factored environments. In Proceedings of the Thirtieth International Conference on Machine Learning (ICML 2013), pages 1211–1219, 2013"

Abstract: Software inspection is a means of detecting faults in software artifacts, such as documents and code. The objective of an inspection is to detect and identify faults in the software product by a visual examination. Finding faults early in the development life cycle is important since the cost of correction increases the later the fault is found in the development cycle. Faults can be found early with inspections, since inspections can be performed as soon as an artifact has been created.Unified Modeling Language (UML) diagrams have been widely used for modeling different aspects of software systems during its life cycle. In this study an experiment is conducted in an educational institution to verify the effect of including Use Case and Activity diagram in the software requirements specification..........

Keywords: Software Requirements, Software engineering.

[1] Albayrak, O. 2009. An experiment to observe the impact of UML diagrams on the effectiveness of software requirements inspections. 3rd International Symposium, pp. 506-510.
[2] Aurum, A. H. Petersson, and C. Wohlin, 2002.State of- the-art: Software Inspections After 25 Years. Software Testing, Verification and Reliability, 12: 133-154.
[3] Berling, T., and Thelin, T. 2004.A case study of reading techniques in a software company.In Empirical Software Engineering, ISESE'04.Proceedings. 2004 International Symposium on, pp. 229-238.

[4] Biffl, S. 2000. Analysis of the impact of reading technique and inspector capability on individual inspection performance.In Software Engineering Conference.Proceedings. Seventh Asia-Pacific, pp. 136-145.
[5] Mendonça, M. G., Maldonado, J. C., de Oliveira, M. C., Carver, J., Fabbri, C. P. F., Shull, F., and Basili, V. R. 2008.A framework for software engineering experimental replications.In Engineering of Complex Computer Systems, 13th IEEE International Conference on, pp. 203-212."

Abstract: "Real world" applications tend to contain complex performance specifications riddled with contradictory performance elements. This state arises because policymaking naturally involves multifaceted problems that are riddled with competing performance objectives and contain incompatible design requirements which are very problematic – if not impossible – to capture at the time that the requisite decision models are constructed. There are invariably unmodelled components, not readily apparent during model formulation, which could greatly impact the suitability of the model's solutions. Consequently, it proves preferable to generate a number of dissimilar alternatives that provide multiple, distinct perspectives to the problem. These different options should all possess close-to-optimal measures with respect to the specified objective(s), but be maximally different from each other in the decision space............

Keywords: Firefly Algorithm, Modelling-to-generate-alternatives, Nature-inspired Metaheuristic Algorithms

[1] M. Brugnach, A. Tagg, F. Keil, and W.J. De Lange, Uncertainty matters: computer models at the science-policy interface, Water Resources Management, 21, 2007, 1075-1090.X
[2] J.A.E.B. Janssen, M.S. Krol, R.M.J. Schielen, and A.Y. Hoekstra, The effect of modelling quantified expert knowledge and uncertainty information on model-based decision making, Environmental Science and Policy, 13(3) , 2010, 229-238.
[3] M. Matthies, C. Giupponi, and B. Ostendorf, Environmental decision support systems: Current issues, methods and tools, Environmental Modelling and Software, 22(2), 2007, 123-127.
[4] H.T. Mowrer, Uncertainty in natural resource decision support systems: Sources, interpretation, and importance, Computers and Electronics in Agriculture, 27(1-3), 2000, 139-154.
[5] W.E. Walker, P. Harremoes, J. Rotmans, J.P. Van der Sluis, M.B.A. P. Van Asselt, Janssen, and M.P. Krayer von Krauss, Defining uncertainty – a conceptual basis for uncertainty management in model-based decision support, Integrated Assessment, 4(1), 2003, 5-17.

Abstract: The Medical Image Can Be Understood By Its Visual Features Also Known As Image Signatures. These Features When Modified Or Enhanced Under Certain Geometrical Functions, It Improves The Resultant Retrieval By The Increase Of 94% In The Performance With The Comparison Of 85% In The Case Of The Nearest Neighbor And In The Case Of Normal Image Retrieval It Comes Out To Be 75 %. This Research Includes The Approach Of Calculating Edge Density Is Applicable For The Five Human Body Parts- Hands, Pelvis, Breast, Brain And Chest And Is Cam Parable To The System In The Previous Work In Literatures. The Result Acquired For The Proposed System Comprises Of Edge Density Concepts............

Keywords: Medical Images, Edge Density, Geometric Feature Vector, Content Based Image Retrieval

[1]. Akbarpour Sh., "A Review On Content Based Image Retrieval In Medical Diagnosis", International Journal On Technical And Physical Problems Of Engineering 2013, June Vol 5, Pp .148-153.
[2]. Andaloussi Jai Said, Eladoulh Abdelijail, Chaffai Abdelmajid, Madrane Nabil And Sekkai Adderralim," Medical Content Based Image Retrieval By Using The HADOOP Framework", 20th International Conference On Telecommunication, P No.1-6, 2013.
[3]. Bhandari Vibha And Patil B.Sandeep, "CBIR Using DCT For Feature Vector Generation", International Journal Application Or Innovations In Engineering & Management, Vol I,Issue 2, P No. 196-200, 2012
[4]. Chavan H.S, Shete S. Deepak, "Content Based Image Retrieval : Review", International Journal Of Emerging Technology And Advanced Engineering, Vol 2, Issue 9, September 2012.
[5]. Chen Yixin, Wang James Z., Krovetz Robert,"Content Based Image Retrieval By Clustering", MIR'03, Berkley, California, U.S.A, 2003..

Abstract: Several classification algorithms have been developed as there is potential growth in image data. Each classifier has its own strengths and shortcomings. Hybridization of classifiers with one another has the potential to combine the strengths and to overcome the shortcomings. This paper presents a study of various Hybrid Classification algorithms as KNN and SVM with Genetics Programming, Decision trees with Artificial Neural Network, Naïve Bayes with Decision Trees and Decision tree with K-means.

Keywords: Supervised classification, Soft classification, hard classification, genetics programming, NB trees.

[1]. J. Holland, Adaption in Natural and Artificial Systems. University of Michigan Press, Ann Arbor, MI, 1975.
[2]. D.E. Goldberg, Genetic Algorithms-in Search, Optimization and Machine Learning. London: Addison-Wesley Publishing Company Inc, 1989
[3]. Ishwar K.Sethi, "Entropy Nets: from Decision tree to Neural Network", 1990, IEEE.

[4]. James D. Kelly, Jr, Lawrence Davis, "A Hybrid Genetic Algorithm for Classification", IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2, 1991.
[5]. N.S. Altman, "An introduction to kernel and nearest-neighbor nonparametric regression," The American Statistician, vol. 46, no. 3, pp. 175-185, 1992...