1,721,020 research outputs found
Ekspansi Kueri pada Sistem Temu Kembali Informasi Berbahasa Indonesia Menggunakan Analisis Konteks Lokal
No full textUsers express their needs in a query to get information using a information retrieval system. However, many are not able to compose appropriate queries as the average length of their queries were too short. Another problem is word mismatch, which refers to the phenomenon that the users of information retrieval systems often use words to describe the concept in their queries which are different from words that authors use to describe the same concept in their documents. Local context analysis is an automatic query expansion which is a combination of global and local techniques. Like global techniques, local context analysis select expansion features based on their co-occurrences with the query terms. Like local techniques, it selects expansion features from the top retrieved documents for a query. Local context analysis ranks the concept by their co-occurrences with the query term in the top ranked documents and uses the highest ranked concepts for query expansion. Basically, a document consists of topics, so in this research, the top ranked documents are divided into passages which represent topics in the relevant document. The highest ranked concepts are then taken from top ranked passages. The purpose of this research is to implement query expansion with local context analysis. The performance of information retrieval system with local context analysis gave good result with around 60% average precision. The results showed that the retrieval performance using local context analysis was significantly higher based on statistical analysis using t-test. The average precision increased by 6.07% compared to retrieval without local context analysis, indicating relevant documents occur higher in the retrieval result. The results also showed that the number of top-ranked documents and passages did not significantly affect the average precision. The more influential factor was the number of query expansions added. Local context analysis is quite suitable for collection of relatively similar documents
Penentuan Rute Optimum dalam Supply Chain Network dengan Algoritma Ant Colony Untuk Kota dan Kabupaten Bogor
No full textPersaingan antarperusahaan semakin marak terjadi seiring berkembangnya teknologi dan permintaan pasar. Agar produk suatu perusahaan dapat bertahan dipasaran, diperlukan suatu manajemen yang dapat mengatur informasi dari produsen ke konsumen dengan efektif dan efisien. Pada penelitian ini, menitikberatkan cara pendistribusian produk melalui jalur dengan jarak terpendek, yaitu memanfaatkan Algoritma Ant Colony untuk memperoleh rute pendistribusian dengan jarak terpendek. Algortima ini bekerja pada sebuah graf berbobot jarak dan berarah sesuai lajur lalu lintas. Data yang digunakan pada penelitian ini adalah data sistem jalan Kota dan Kabupaten Bogor wilayah Barat. Sistem ini menggunakan Google Maps untuk merepresentasikan rute hasil dari Algoritma Ant Colony. Penelitian ini berhasil mengimplementasikan Algoritma Ant Colony pada sebuah sistem untuk mencari rute optimum pendistribusian. Hasil dari sistem ini berupa rute optimum dengan akurasi sebesar 92%
Aplikasi Bagan Warna Daun untuk Optimasi Pemupukan Tanaman Padi Menggunakan k-Nearest Neighbor
No full textThe leaf color of rice is closely associated with the adequacy of nitrogen (N) level of the ground. N deficiency symptoms that are most obvious and commonly seen is the reduction of green color of the leaf. This research developed a mobile application to identify the color of rice leaf and to determine the appropriate fertilizer. The application was built by using the histogram feature of several color components namely Red, Green, Blue in the RGB color space, Hue, Saturation Value in the HSV color space, and grayscale. K-Nearest Neighbor was choosen as the classification method. This research showed the highest average accuracy of 90.63% on the G (green), V (Value) and grayscale color component. The k-NN classification method produced the highest average accuracy of 72.62% when the value of k is equal to 3
Cross Language Question Answering System Menggunakan Pembobotan Heuristic dan Multidokumen
No full textPeople tend to ask when they need to get some information. This often raises a difficulty whenever available information is not in same the language with the person understands or speaks. Cross Language Question Answering System (CL-QAS) is an information retrieval system that is able to handle this kind of situation. It accepts a question query as the input and outputs the answer in the translated language. In this study, CL-QAS is developed that takes query in Indonesian language and answers in English. The system output is calculated by weighting heuristic and multi-documents. The average time to produce answer is quite fast, i.e. 3.03 seconds. The system accuracy is good considering for the following queries: SIAPA (100%), KAPAN (100%), DIMANA (100%), and BERAPA (90%)
Uji Usability dengan Metode Cognitive Walkthrough pada Aplikasi Herbal Medicine Systems.
No full textHerbal Medicine Systems merupakan aplikasi mobile berplatform Android yang dikembangkan sebagai ensiklopedia Jamu dan Kampo. Keterlibatan pengguna dalam mengevaluasi aplikasi melalui pengujian usability menjadi sangat penting guna melihat kemudahan pengguna dalam menggunakan aplikasi. Penelitian ini dilakukan untuk menganalisis antarmuka aplikasi mobile Herbal Medicine Systems menggunakan metode Cognitive Walkthrough.. Pengujian usability pada aplikasi Herbal Medicine Systems dilakukan terhadap lima responden. Responden dipilih dengan teknik Purposive Sampling dari mahasiswa Departemen Ilmu Komputer FMIPA IPB dan masyarakat peminum jamu. Hasil evaluasi menunjukkan waktu tercepat yang diperlukan responden untuk menyelesaikan 10 skenario tugas adalah 344 detik. Peresentase skenario tugas yang dapat diselesaikan responden bernilai 98%, sehingga dapat dikatakan bahwa aplikasi mobile sudah baik digunkan untuk mencari informasi jamu dan kampo. Walaupun demikian perlu perbaikan seperti penambahan pilihan bahasa dan perlu adanya fitur registrasi sebelum pengguna aplikasi melakukan penambahan data di menu Databases
Question Answering System Menggunakan N-Gram Term Weight Model
No full textCurrently, search engine has been widely developed having question query feature known as the query answering system. The information provided by the system must fit a specific user requirement. This research will apply the passage selection method using n-gram term weighting model. The evaluation of the method is measured based on the set of questions and documents, and the accuracy for each answer. One thousand documents and 40 queries are used in this research. The result of the research indicates the accuracy for WHO questions is 90%, for WHEN questions is 80%, for WHERE questions is 80%, and for HOW MUCH/MANY questions is 40%
Integrasi Data SemiterstruktuI' Berbasis XML Menggunakan Metode Translasi Skema Basisdata Relasional
No full textThe recent emergence of eXtensible Markup Language (XML) as a new standard for data representation on the world wide web has drawn attention. Beside that, the similarity between semistructured data models and XML made it used to represent semi structured data models. The goals of this study are to analyze and design integration semistructured database on XML using schema translation relational database method. This study uses schematic approach to integrate the semistructured data. The integration can occur in two steps, which are schema translation and schema integration. In the first step, semistructured data schemas are translated to XML's schema. In the second step, each individual schema document as the source schema is mapped into the global conceptual schema or target schema thereby achieving data integration for XML documents. The result of this research shows that integration between relational database could be done with generated global conceptual schema semistructured data based on XML
Penerapan Metode Search Engine Optimization pada situs Web untuk Meningkatkan Trafik Pengunjung (Studi Kasus: www.infobeasiswa.org)
No full textIn this research project an empirical study was done on the application of Search Engine Optimization (SEO) techniques to a website (infobeasiswa.org), in an attempt to increase its visibility to the Google.co.id search engine so that increasing web traffic. The methodology involved the measurement of visibility and re-engineering of the website according to the elements indicated by the research paper. The results indicated that the website now occupied the first position on the Google.co.id for a number of selected keywords. It can be concluded that the implementation of SEO methodologies, careful placing of text, the use of key phrases, and backlinks can dramatically increase the website visibility and search engine rankin
Klasifikasi Khasiat Jamu dan Identifikasi Metabolit yang Potensial
No full textJamu adalah obat tradisional dari Indonesia yang bersifat herbal dan berasal dari
tanaman-tanaman obat yang berkhasiat. Analisis tentang formula jamu dapat
diperluas ke tingkat molekuler dengan menambahkan informasi senyawa yang
terdapat pada tanaman obat sebagai komposisi formula jamu dan menggunakan
model ini untuk memprediksi khasiat jamu berdasarkan senyawa aktifnya.
Penelitian ini bertujuan menerapkan metode Random Forest untuk memprediksi
khasiat jamu dan mengidentifikasi metabolit yang potensial. Data yang digunakan
dalam penelitian ini diperoleh dari penelitian Wijaya et al. (2017) dan basis data
KNApSAcK. Single Filtering dan Regularized Random Forest digunakan sebagai
pra-proses data untuk reduksi data dan fitur. Akurasi tertinggi dalam memprediksi
khasiat jamu dengan Random Forest diperoleh saat menggunakan data hasil praproses
yaitu sebesar 95.59%. Jumlah metabolit yang berhasil diidentifikasi
sebanyak 180 dari 11 kelas khasiat
Perbandingan Efisiensi Model Ruang Vektor pada Sistem Temu Kembali Informasi
No full textInformation retrieval system is a system to represent, store, organize, and process informations. Discovered documents were ranked by vector space model . Normalization of the vector space models similarity consist of cosine, Jaccard, and Dice. This research aims to compare efficiency of three vector space models based on recall and average precision (AVP), computation time, and algorithm complexcity. A thousand document were used in this research. The result showed that each coefficient of vector space model yield equal value for recall and AVP. The measure of similarity in cosine coefficient vector space model better than Jaccard coefficient and Dice coefficient, in terms of algorithms complexity and 3.1% faster than Jaccard coefficient and 9.4% than Dice coefficient, in terms of computation time
- …
