Kehadiran mal memungkinkan masyarakat untuk memenuhi kebutuhannya hanya pada satu lokasi saja. Layanan parkiran merupakan salah satu layanan yang terpenting pada mal. Kendala yang sering ditemukan pada layanan parkir mal adalah pengunjung kesulitan mencari lokasi lot parkir yang kosong. Pengunjung ketika ingin mengunjungi sebuah outlet tertentu cenderung memilih pintu yang terdekat agar tidak membutuhkan waktu yang lama untuk berjalan. Dalam memperoleh lokasi parkir, pengunjung terkadang harus berputar terlebih dahulu untuk mendapatkan tempat parkir yang diinginkan. Berdasarkan permasalahan tersebut, sebuah sistem dirancang untuk dapat memberikan rekomendasi lokasi lot parkir terdekat dari lokasi kunjungan. Setiap lot dan outlet akan diberikan titik koordinat yang digunakan untuk menghitung jarak terdekat dengan menggunakan Euclidean Distance. Arduino Uno digunakan untuk mengendalikan sensor Light Dependent Resistor (LDR), buzzer, dan Radio Frequency Identification (RFID) reader. Pengujian sistem yang dirancang dilakukan terhadap 10 skenario. Hasil pengujian menunjukkan persentase ketersediaan lot parkir terdekat dengan outlet yang akan dikunjungi adalah sebesar 100%. Hal ini disebabkan karena sistem dirancang dengan mempertimbangkan jarak antara lot dengan outlet tujuan dan status ketersediaan lot terdekat. Apabila lot terdekat telah ditempati maka sistem secara otomatis akan memberikan rekomendasi lot terdekat berikutnya kepada pengguna
The TSP problem can resolved using Genetic Algorithms. In other previous research,crossover is one process that can be eliminated from the genetic algorithm to get betterÂ optimization. This research tried to solve TSP by using genetic algorithms without using theÂ crossover. To improve optimization by applying the method of mutation with 2 phases. MutationÂ operator used the inversion mutation, exchange mutation, and insertion mutation . The resultsÂ using these methods is the average error percentage of optimum distance 10%.Keywords: Travelling Salesmen Problem, Genetic Algorthim, Two Step Mutattion
Security is a supporting factor in creating order and stability in the social environment. The issue of environmental security is related to efforts made to avoid and overcome criminal acts in society and now thanks to the advancement of information and communication technology, the function of safeguarding and controlling the environment can be supported by the help of technology to facilitate human work. The security system developed is supported by digital image processing software to process snapshot and recorded images from system cameras with the aim of improving the quality of visual images for the sake of analysis and digital forensic evidence that can be used in law enforcement related to criminal acts. The end result is a product innovation security system that can be utilized by the community in various needs related to security and supervision activities.
One disadvantage in the genetic algorithm is the number of iterations in the search for the optimum solution. This caused long computation time. This study aimed to obtain the best method to determine the individual parent crossover operator and mutation Genetic Algorithm in the case of the Traveling Salesman Problem (TSP). the results obtained in this research with a set of individuals in the process of crossover and mutation can reduce the number of iterations. So as computing time can be even faster.Â Keywords: Travelling Salesmen Problem, Genetic Algorthim, Crossover, Mutattion.
This research is focus on how to optimize the usage of bandwidth at the University of Atma Jaya Makassar to provide fluency either online or offline while accessing the service of UAJM.In this research user management to be made using the Hotspot management and for Management bandwidth will be created using the queue tree and per connection queuing (PCQ). Queue tree used to allocate bandwidth to each user category and is used to divide the bandwidth PCQ fairly and evenly.Keywords: hotspot, queue tree, per connection queuing (PCQ)
Today, Collection of image data on the Internet is growing rapidly in terms of quantity. In parallel with this a method of content -based image retrieval (Content -based image retrieval) is needed in the process of identifying and accessing visual information. Content -based image retrieval basically simulates the human perception of an image so that an error occurred in the text -based retrieval methods can be overcome. In this research, the image retrieval system is implemented with the extraction of low level features of the image. Low-level information used in this study is the color information contained in the image. Composition of color pixels in an image can be represented in a color histogram. The degree of similarity between the image color is determined based on the distance between the histogram using Laplace distance and Euclidean distance. The smaller the distance between the histogram, the higher the percentage of similarity of an image. Results of image retrieval through the database will be displayed according to the query by example method performed by a user, based on the sequence of images that have a higher percentage of similarity.
This research aimed at improving the reliability of the system by developing a machine learning framework as aÂ relevance feedback mechanism that aims to harness human perception in the training system to learn to map between the vector feature extraction results to the specifications given query. In the developed relevance feedback mechanism, users are involved in providing feedback to the system via the query by example (QBE) interface model. Basically, this module works with the user to decide how to involve the relevant results or irrelevant that emerged as a result of the system output user-defined queries. Then the machine-learning mechanisms will reformulate return query results based on user ratings and displays the new results. This process can take place iteratively until the user is satisfied on the relevance of the results obtained. Outcomes of this study will produce an image search system that can be integrated with information systems of third party services through the modules developed
Traffic accident are the third killer in the world after HIV / AIDS and tuberculosis. Factors that cause accidents classified by elements of the transportation system itself are the road user, vehicle, road and environment. In this research apply fuzzy logic to control the vehicle speed limits by using Mamdani inference method. This research was carried out to control the driver so that not to accelerate the vehicle exceeds a predetermined speed limit based on surrounding circumstances. Circumstances which are used as variables: class, weather and distance between vehicles. The results of this research have been successfully made speed control vehicle simulation with fuzzy logic in matlab r2012a
This research focuses on the manufacture of home automation systems to optimize the use of electricity. Home automation system has four features, namely automatic control, manual control, control based on the habits and customs control based on fuzzy logic and method Tsukamoto. Fuzzy logic Tsukamoto will calculate the temperature that should be spent by the AC, using input from sensors LM35 that are indoors and outdoors, so that the temperature of the issued AC was not too hot and too cold home automation system features 3 sensors which PIR sensor, sensor LM35 and LDR sensor that will be used as input data on the system. Home automation system will control electrical equipment, namely air conditioning and lighting optimally.Keywords: Arduino Uno R3, Controlling, Home Automation, Fuzzy LogicÂ Â
This research aimed to develop the image search system using content-based retrievalÂ approach by applying algorithm to extract low-level feature from images. Low-level informationÂ that is used to extract image features in the image retrieval system is color information containedÂ in the image. Composition of color pixels in an image can be represented in a color histogram.Â The degree of similarity between the image colors is determined based on the distance betweenÂ the histogram using Laplace distance and Euclidean distance. The smaller the distance betweenÂ the histogram, the higher the percentage of similarity of an image. Results of image retrievalÂ through the database will be displayed according to the query by example method performed byÂ a user, based on the sequence of images that have a higher percentage of similarity. The testÂ results for images with a maximum size of 150 x 150 pixels get fairly accurate results withÂ percentages of similarity is above 60 percent.Keywords: Content Based Image Retrieval, Histogram, color space