Indeks Saham Syariah Indonesia (ISSI) merupakan indikator pergerakan harga dari keseluruhan saham syariah yang tercatat di BEI. Dalam Tugas Akhir ini ISSI diprediksi menggunakan Model Hidden Markov dengan data yang dipakai adalah periode bulan Januari 2016 sampai Maret 2017. Data selisih indeks saham dibagi menjadi beberapa state yaitu 3, 4, 5, 6, 7, dan 8 state. Berdasarkan hasil analisis pada pembagian 4 dan 5 state nilai prediksi memiliki kecocokan 100%, sedangkan pada pembagian 3 dan 6 state nilai prediksi memiliki kecocokan sebesar 80%. Prediksi ISSI hanya dapat dilakukan sampai 6 state karena pada 7 dan 8 state tidak memenuhi karakteristik Model Hidden Markov. Kata Kunci-Indeks Saham Syariah Indonesia (ISSI), Model Hidden Markov, Prediksi.
The library is a learning infrastructure that must be available in every school. Libraries provide information and knowledge needed by students. The development of technology and information is expected to have an impact, namely the effi ciency and eff ectiveness of the implementation of work. One way is to change the manual system into a computer-assisted system supported by internet technology. In this community service activity, a web-based library application has been designed and built at SMAN 1 Jombang. Application development uses the Waterfall model which consists of 4 stages, namely system requirements analysis, system design, implementation, and maintenance. The library application is built using the Code Ignaiter framework with the Hypertext Pre-Processor (PHP) programming language while the database uses MySQL.The benefi t of this application is to address the needs of students for book searches and book ordering, while for school library offi cers it manages the circulation of book borrowing and reporting. The result of community service that has been implemented is a Web-based library application at SMA Negeri 1 Jombang to improve the quality of library management.
Cancer is a disease characterized by the ability of abnormal cells to grow uncontrollably. In the medical field, detection of breast cancer is done using a mammogram. Examination of the mammogram image is still done manually by the doctor / radiologist, so it is necessary to use technology as supporting information. In this research, mammogram image classification based on gray-level co-occurrence (GLCM) matrix and gray-tone difference matrix (GTDM) has been done with backpropagation method. The stages of the mammogram image classification process include the process of image acquisition, pre-processing, feature extraction with GLCM and GTDM and classification using backpropagation. The preprocessing process carried out is gray-scalling, contrast enhancement, image segmentation with Otsu thresholding, edge detection process, and image thickening process with widening morphology method. The highest performance results for accuracy are 85% and precision is 85.7%. This result was obtained when using the GLCM and GTDM feature extraction methods.
Prediksi data time series dapat digunakan sebagai bahan pertimbangan dalam pengambilan keputusan yang akan datang. Jaringan syaraf tiruan merupakan metoda yang baik untuk memprediksi data time series, akan tetapi sulit dihindari adanya epoch (iterasi) yang banyak selama pelatihan. Sedangkan wavelet dapat dipakai untuk mendekomposisi dan merekontruksi data sehingga dapat mengurangi banyaknya epoch. Pada makalah ini, dibahas bagaimana Wavelet-Jaringan Syaraf Tiruan, yang selanjutnya disebut WANN (Wavelet-Artificial Neural Network) digunakan untuk memprediksi data time series. Ada tiga tahapan untuk mendapatkan hasil prediksi data times series dengan metoda WANN, yaitu pre-processing, prediction, dan post-processing. Pre-processing digunakan untuk mendekomposisi data masukan, prediction merupakan proses training, dan post processing dipakai untuk merekontruksi data setelah dilakukan training. Selanjutnya dilakukan simulasi dengan menggunakan MATLAB. Dari simulasi ini diperoleh data short term prediction dan long term prediction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.