Articles
<![CDATA[PENERAPAN JARINGAN SARAF TIRUAN BACKPROPAGATION UNTUK MEMPREDIKSI INDEKS HARGA SAHAM LQ45 ]]>
<![CDATA[Febia Zein Aziza]]>;
<![CDATA[Abduh Riski]]>;
<![CDATA[Ahmad Kamsyakawuni]]>
<![CDATA[ UNEJ e-Proceeding 2022: E-Prosiding Seminar Nasional Matematika, Geometri, Statistika, dan Komputasi (SeNa-MaGeStiK) ]]>
Publisher : <![CDATA[UPT Penerbitan Universitas Jember ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Stock price movements are very volatile from time to time. The stock price movement is influenced by many factors, including company performance, dividend risk, the country’s economic conditions, and inflation rate. The existence of these complex factors makes stock price movements challenging to predict. Investors need stock price predictions to see the company’s stock investment prospects in the next period. The method that can predict stock prices is Backpropagation. The Backpropagation method is an algorithm that adopts a human mindset systematically to minimize the error rate by adjusting the weights based on differences in output and the desired target. This study uses historical stock index data for LQ45 from February 26, 2019 – February 26, 2021, namely the closing price as an input and the opening price as the target. The best network model from the Backpropagation method uses a binary sigmoid activation function with nine neurons in the hidden layer. The testing accuracy value is 95.2481% (MAPE), and the error value is 0.000266 (MSE). The error value shows that the prediction model results are excellent. Keywords: Backpropagation, index, prediction, stock.]]>
<![CDATA[Peramalan Curah Hujan Harian Kabupaten Jember Dengan Jaringan Saraf Tiruan Dan General Circulation Model ]]>
<![CDATA[Abduh riski]]>;
<![CDATA[Ahmad Kamsyakawuni]]>;
<![CDATA[Cahya Ramadhani Azhar]]>
<![CDATA[ J STATISTIKA: Jurnal Imiah Teori dan Aplikasi Statistika Vol 16 No 1 (2023): Jurnal Ilmiah Teori dan Aplikasi Statistika ]]>
Publisher : <![CDATA[Faculty of Science and Technology, Univ. PGRI Adi Buana Surabaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.36456/jstat.vol16.no1.a7862
<![CDATA[Curah hujan memiliki peran penting di beberapa bidang seperti pertanian dan pengairan. Oleh sebab itu diperlukan model peramalan untuk mengetahui curah hujan di masa yang akan datang. Model peramalan dapat dibentuk menggunakan jaringan saraf tiruan (JST) backpropagation. Hasil akurasi peramalan JST diukur dengan MAE, korelasi dan RMSE. Data lokal sebagai data target model merupakan data rataan curah hujan harian dari 73 stasiun di wilayah kabupaten Jember mulai dari Oktober 2019 hingga Desember 2020. Data global sebagai data input model menggunakan data Global Circulation Model (GCM) model CSIRO-MK3-6-0 dengan eksperimen RCP 2.6. Data GCM direduksi menggunakan principal component analysis (PCA) guna menghindari multikolinieritas pada data. Penelitian ini mengkombinasikan jumlah neuron sebesar 10 hingga 100 neuron dan dua fungsi aktivasi pada model JST. Berdasarkan hasil penelitian, model terbaik yang digunakan untuk peramalan adalah model JST dengan 100 neuron dan fungsi aktivasi biner dengan MAE sebesar 6,1205, korelasi sebesar -0,0125, dan RMSE sebesar 9,0251. hasil peramalan curah hujan harian kabupaten Jember untuk bulan Januari 2021 adalah terjadi curah hujan tertinggi pada hari ke-19 sebesar 10,0471 mm/hari dan curah hujan terendah terdapat pada hari ke-2 sebesar 1,3106 mm/hari.]]>
<![CDATA[PENGEMBANGAN KUALITAS GURU-GURU SMA DAN MA BERBASIS PONDOK PESANTREN KOTA JEMBER MELALUI PELATIHAN PEMBUATAN VIDEO TUTORIAL PEMBELAJARAN ]]>
<![CDATA[M. Ziaul Arif]]>;
<![CDATA[Abduh Riski]]>;
<![CDATA[Dian Anggraeni]]>
<![CDATA[ Jurnal Abdimas Vol 22, No 1 (2018): June 2018 ]]>
Publisher : <![CDATA[Universitas Negeri Semarang ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.15294/abdimas.v22i1.12612
<![CDATA[Teknologi mulai berpengaruh pada sistem pendidikan. Seiring dengan perkembangnya ilmu pengetahuan dan teknologi komputerisasi dan internet, lebih khusus pada perangkat lunak atau aplikasi, maka baik langsung maupun tidak langsung dunia pendidikan juga merasakan dampaknya. Guru yang mempunyai peran penting dalam dunia pendidikan harus selalu tanggap dan peka terhadap berbagai perkembangan yang terjadi di sekelilingnya. Proses pembelajaran merupakan proses komunikasi dan berlangsung dalam suatu sistem, maka media dan perangkat pembelajaran menempati posisi yang cukup penting sebagai salah satu komponen sistem pembelajaran. Tanpa media, komunikasi tidak akan terjadi dan proses pembelajaran sebagai proses komunikasi juga tidak akan bisa berlangsung secara optimal. Pengoptimalan pembelajaran dapat dilakukan dengan menggunakan media pembelajaran yang uptodate. Oleh karena itu, disini diperkenalkan metode pembelajaran berbasis video tutorial langkah demi langkah dalam menyelesaikan suatu soal pelajaran SMA baik secara online maupun offline melalui IbM SMA dan MA berbasis pondok pesantren di kota Jember dengan cara melaksanakan workshop dan bimbingan intensif pembuatan video tutorial pembelajran kepada guru-guru SMA dan MA Unggulan NURIS Jember dan SMA Unggulan dan MA Daruh Sholah Jember. Dari hasil kegiatan didapatkan bahwa guru-guru sudah mampu membuat video tutorial pembelajaran secara baik dan mandiri..]]>
<![CDATA[Penerapan Adaptive Neuro Fuzzy Infrence System (ANFIS) dalam Prediksi Produksi Tembakau di Jember ]]>
<![CDATA[Azimatul Matsniya]]>;
<![CDATA[Abduh Riski]]>;
<![CDATA[Ahmad Kamsyakawuni]]>
<![CDATA[ InComTech : Jurnal Telekomunikasi dan Komputer Vol 13, No 1 (2023) ]]>
Publisher : <![CDATA[Department of Electrical Engineering ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.22441/incomtech.v13i1.15655
<![CDATA[Tembakau merupakan salah satu komoditas perkebunan di Indonesia. Kabupaten Jember merupakan penghasil tembakau kualitas dunia terbesar di Jawa Timur. Produksi tembakau di Kabupaten Jember mengalami fluktuasi setiap tahunnya sehingga perlu dilakukan prediksi produksi tembakau dengan menggunakan ANFIS (Adaptive Neuro Fuzzy Inference System). Penelitian ini bertujuan untuk memprediksi produksi tembakau di Kabupaten Jember. Data yang digunakan dalam penelitian ini adalah curah hujan, luas lahan panen tembakau, produktivitas tembakau, dan produksi tembakau di Kabupaten Jember. Jaringan ANFIS yang dibuat terdiri dari tiga variabel input dan satu variabel output. Fungsi keanggotaan yang digunakan adalah generalized bell dan gaussian dengan total fungsi keanggotaan sebesar tiga buah. Jenis output dibagi menjadi dua, yaitu linier dan konstan. Hasil penelitian menunjukkan bahwa model terbaik adalah menggunakan fungsi keanggotaan generalized bell tipe output konstan dengan nilai MAPE pada proses pelatihan dan pengujian berturut-turut adalah 0,00015% dan 0,091%. Hasil prediksi produksi tembakau pada tahun 2021 adalah 199.603,71 kuintal. Variabel yang paling berpengaruh untuk produksi tembakau adalah curah hujan dan produktivitas tembakau.]]>
<![CDATA[PENYEMBUNYIAN CIPHERTEXT ALGORITMA GOST PADA CITRA KE DALAM AUDIO DENGAN METODE LEAST SIGNIFICANT BIT ]]>
<![CDATA[Abduh Riski]]>;
<![CDATA[Heri Purwantoro]]>;
<![CDATA[Ahmad Kamsyakawuni]]>
<![CDATA[ Jurnal Ilmiah Matematika dan Pendidikan Matematika (JMP) Vol 10 No 2 (2018): Jurnal Ilmiah Matematika dan Pendidikan Matematika (JMP) ]]>
Publisher : <![CDATA[Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.20884/1.jmp.2018.10.2.2844
<![CDATA[Government Standard (GOST) is a 64-bit block cipher algorithm with 32 round, use a 256-bit key. The weakness of this algorithm is the keys so simple, than make cryptanalyst easy to break this algorithm. Least Significant Bit (LSB) use to insert message into another form without changing the form of the cover after insertion. This research does by hiding encrypted ciphertext to image and hiding image into audio. This research use grayscale and RBG image with BMP and PNG format. Audio using music with wav format. Security analysis using differential analysis NPCR and UACI. Security analysis aims to calculate percentage from cover after hiding the message. The smaller the NPCR and UACI values, the higher the level of security the message is hidden. The results of the analysis of concealment in the image obtained by the average values of NPCR and UACI were 99.98% and 3.46% respectively. While the results of the analysis of hiding in audio obtained the average value of NPCR and UACI were 83.78% and 12.66% respectively.]]>
<![CDATA[PENGAMANAN CITRA DENGAN ALGORITMA DIFFIE-HELLMAN DAN ALGORITMA SIMPLIFIED DATA ENCRYPTION STANDARD (S-DES) ]]>
<![CDATA[ahmad Kamsyakawuni]]>;
<![CDATA[Ahmad Husnan Fanani]]>;
<![CDATA[abduh Riski]]>
<![CDATA[ Jurnal Ilmiah Matematika dan Pendidikan Matematika (JMP) Vol 10 No 2 (2018): Jurnal Ilmiah Matematika dan Pendidikan Matematika (JMP) ]]>
Publisher : <![CDATA[Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.20884/1.jmp.2018.10.2.2846
<![CDATA[Simplified Data Encryption Standard (S-DES) is a cryptographic algorithm whose data-disguise process is simple and fast enough compared to other algorithms. Because of its simplicity, the S-DES algorithm is vulnerable to statistical attacks when applied to imagery, so this study tries to minimize S-DES weaknesses in image data by modifying S-DES keys with Diffie-Hellman. Diffie-Hellman is one of the key generating algorithms and key exchange. This research uses image data that is RGB image and grayscale image. A modified S-DES key with Diffie-Hellman is then used to encrypt the image. This study also analyzed the security level of S-DES algorithm that the key has been modified with Diffie-Hellman.]]>
<![CDATA[Prediksi Harga Saham PT Bank Rakyat Indonesia Tbk Menggunakan AUTOML H2O ]]>
<![CDATA[I Made Tirta]]>;
<![CDATA[Abduh Riski]]>;
<![CDATA[Sholikhah, Nining]]>
<![CDATA[ Jurnal Ilmiah Komputasi Vol. 23 No. 3 (2024): Jurnal Ilmiah Komputasi : Vol. 23 No 3, September 2024 ]]>
Publisher : <![CDATA[Lembaga Penelitian dan Pengabdian Kepada Masyarakat ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.32409/jikstik.23.3.3624
<![CDATA[Bank BRI is a government-owned company with share prices recorded in the Initial Public Offering (IPO) which has the status of a public company. BRI Bank's share price experienced fluctuations caused by some factors. Predicting BRI Bank share prices is important to make it easier for investors to enter make investment decisions. Auto Machine Learning (AutoML) refers to the concept of machine learning and training automatic parameter setting. H2OAutoML can be used to predict stock prices with deliver program code and accelerate the development of accurate algorithms. H2OAutoML provides various algorithms, but the one used in this research is the Generalized Linear Model (GLM), Distributed Random Forest (DRF), Gradient Boosting Machine (GBM), and stacked ensemble. The aim of this research is to find out the optimal algorithm and prediction results produced by H2OAutoML on close stock prices. Algorithm The best basis according to H2OAutoML is GBM with the smallest MAPE value and the largest R Square. However, when this basic algorithm combined with stacking techniques produces better predictions. The basic algorithm used to build stacked ensembles are DRF, XRT, GLM, and GBM. This stacked ensemble is constructed sequentially automatically by H2OAutoML with the GLM metalearning algorithm. Thus, stacked ensembles are capable predicts with fairly good accuracy and can explain data variability.]]>
<![CDATA[Determining The Ripeness Level Of Crystal Guava Fruit Using Backpropagation Neural Network ]]>
<![CDATA[Shofia Nabila Azzahra]]>;
<![CDATA[Ahmad Kamsyakawuni]]>;
<![CDATA[Abduh Riski]]>
<![CDATA[ Lontar Komputer : Jurnal Ilmiah Teknologi Informasi Vol 15 No 03 (2024): Vol.15, No. 3 December 2024 ]]>
Publisher : <![CDATA[Institute for Research and Community Services, Udayana University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.24843/LKJITI.2024.v15.i03.p04
<![CDATA[The ripeness of crystal guava fruit is currently sorted conventionally by analyzing the colour of the rind visually with the human eye. However, this method has several weaknesses that result in low accuracy and inconsistency. Therefore, automatic determination of ripeness level is necessary to increase accuracy and obtain precise information. This research uses the HSI colour space as an interpretation of fruit image characteristics and uses the Backpropagation algorithm to perform classification. This study utilizes image data of crystal guava fruit, categorizing them into four stages of ripeness: unripe, half-ripe, ripe, and very ripe. There are 140 fruit image data with 35 data for each ripeness category. Each image will be processed with median filter, cropping and segmentation. The HSI value will be taken from the image and processed at the classification stage using the Backpropagation algorithm. In classification using Backpropagation Neural Network, the best network model in this study was achieved in the 3 10 4 network architecture with a binary sigmoid activation function, learning rate = 0.3, and batch size = 64. This model produces a loss value of 0.5364 with an accuracy of 0.9 in testing process.]]>
<![CDATA[OPTIMASI KEUNTUNGAN PRODUKSI MAKANAN DENGAN METODE SIMPLEKS BERBASIS POM-QM FOR WINDOWS (Studi Kasus: UMKM Bakmi & Nasi Goreng Jowo Mas Narto) ]]>
<![CDATA[Abduh Riski]]>;
<![CDATA[Agustina Pradjaningsih]]>;
<![CDATA[Durratul Sayyidah Adilah Munawaroh]]>
<![CDATA[ MathVisioN Vol 7 No 1 (2025): Maret 2025 ]]>
Publisher : <![CDATA[Prodi Matematika FMIPA Unirow Tuban ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.55719/mv.v7i1.1339
<![CDATA[Micro, Small, and Medium Enterprises/UMKM are some of the businesses that have an important role in developing the economy in Indonesia. Bakmi and Nasi Goreng Jowo Mas Narto is one of the UMKM engaged in culinary in the Jember area. Based on the results of interviews conducted with owners, sales fluctuate in food production, thus making the profit of food sales not always predictable. Thus, this study aims to provide a solution for optimizing the benefits of food production with the simplex method using POM-QM for Windows. The results of this research show that these MSMEs will get optimal profits if they produce food, namely 50 portions of fried rice, 43 portions of fried noodles, 8 portions of fried vermicelli, and 8 portions of letek noodles with a profit of Rp 438,095 in a day.]]>
<![CDATA[Sistem Biometrik Pengenalan Wajah dengan Metode Grey Level Co-Occurrence Matrix dan Support Vector Machine ]]>
<![CDATA[Adhitiyah Redaya Kusuma Bhakti]]>;
<![CDATA[Abduh Riski]]>;
<![CDATA[Ahmad Kamsyakawuni]]>
<![CDATA[ IJAI (Indonesian Journal of Applied Informatics) Vol 7, No 2 (2023) ]]>
Publisher : <![CDATA[Universitas Sebelas Maret ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.20961/ijai.v7i2.69069
<![CDATA[Abstrak Teknologi biometrik wajah dikembangkan untuk mengenali seseorang secara unik. Pada penelitian ini biometrik diaplikasikan pada aplikasi pengenalan wajah dengan citra wajah manusia sebagai objeknya menggunakan metode Grey Level Co-Occurrence Matrix dan Support Vector Machine. Metode GLCM merupakan metode yang digunakan untuk proses ekstraksi fitur citra. Sedangkan SVM digunakan untuk proses pengenalan/identifikasi. Tujuan dari penelitian ini adalah mendapat hasil akurasi yang baik untuk pengenalan wajah melalui kedua metode yang digunakan. Hasil yang diperoleh dari penelitian ini adalah akurasi pada data pelatihan sebesar 93% dengan total 200 citra wajah. Sedangkan pada data pengujian diperoleh akurasi sebesar 90% untuk 50 citra wajah.===================================================AbstractFacial biometric technology was developed to uniquely recognize a person. In this research, biometrics was applied to face recognition applications with human face images as objects using the Gray Level Co-Occurrence Matrix and Support Vector Machine methods. The GLCM is a method used for the image feature extraction process. While SVM is used for the identification process. The purpose of this research is to get good accuracy results for face recognition through the two methods used. The results obtained from this research are the accuracy of the training data by 93% with a total of 200 face images. While the test data obtained an accuracy of 90% for 50 face images.]]>
