Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
Latar Belakang Gangguan kecemasan lebih banyak terjadi pada saat seseorang memasuki fase dewasa muda. Kecemasan merupakan salah satu faktor risiko dalam perilaku bunuh diri di dunia dan penyebab kematian kedua yang terjadi di kalangan mahasiswa atau dewasa muda. Saat ini, perkembangan AI dalam bentuk aplikasi berbasis machine learning telah banyak digunakan dalam berbagai bidang. Akan tetapi, penggunaan aplikasi berbasis machine learning di dunia medis, khususnya dalam mendeteksi dini gangguan kecemasan di Indonesia masih terbatas. Metode Studi ini menggunakan desain studi cross-sectional, dengan metode pengambilan sampel purposive sampling. Data terkait gejala kecemasan akan diambil dari hasil pengisian kuesioner STAI, sedangkan perseverasi akan dihitung melalui hasil transkrip perekaman suara pada aplikasi “StethoSoul”. Karakteristik studi akan ditampilkan dalam bentuk data deskriptif. Analisis statistik menggunakan uji alternatif Mann-Whitney, dengan hasil yang dianggap signifikan adalah p<0,05. Hasil Dalam penelitian ini terdapat total sebanyak data dari 121 mahasiswa yang memadai untuk dianalisis. Berdasarkan hasil analisis statistik, ditemukan adanya perbedaan yang signifikan pada komponen SAI (p=0.007), sedangkan pada komponen TAI, tidak ditunjukkan adanya perbedaan yang signifikan (p=0.480) antara perseverasi dengan kelompok gejala kecemasan. Kesimpulan Hipotesis nol penelitian ini ditolak karena pada kedua komponen ditemukan adanya perbedaan perseverasi antara kelompok dengan gejala kecemasan sedang dan gejala kecemasan berat. ......Introduction Anxiety disorders are becoming increasingly prevalent throughout the adolescent years. It is also a major risk factor for suicide behavior and the second leading cause of death among university students and adolescents. AI is now being used in a variety of fields as a machine learning-based application. However, its use in medicine, particularly for the early detection of anxiety disorders, is yet unknown in Indonesia. Method Purposive sampling was used in this cross-sectional study. Data regarding anxiety symptoms are obtained from STAI questionnaire, while perseveration was count from the recording transcript in the “StethoSoul” applicaiton. Study characteristics were shown as a descriptive data. Mann-Whitney test was applied in this study, with the findings considered significant if p<0,05. Results A total of 121 samples are eligible for analysis. Statistical analysis revealed a significant difference between perseveration and anxiety symptoms on the SAI component (p=0.007) but no significant difference on the TAI component (p=0.480). Conclusion The null hypothesis was rejected because there is difference between perseveration in moderate anxiety symptoms and high anxiety symptoms group.

Abstrak :
With Early Release ebooks, you get books in their earliest form--the author's raw and unedited content as he or she writes--so you can take advantage of these technologies long before the official release of these titles. You'll also receive updates when significant changes are made, new chapters are available, and the final ebook bundle is released. The Python programming language and its libraries, including pandas and scikit-learn, provide a production-grade environment to help you accomplish a broad range of machine-learning tasks. With this comprehensive cookbook, data scientists and software engineers familiar with Python will benefit from almost 200 practical recipes for building a comprehensive machine-learning pipeline--everything from data preprocessing and feature engineering to model evaluation and deep learning. Learn from author Chris Albon, a data scientist who has written more than 500 tutorials on Python, data science, and machine learning. Each recipe in this practical cookbook includes code solutions that you can put to work right away, along with a discussion of how and why they work--making it ideal as a learning tool and reference book

Abstrak :
Written by leading researchers, this complete introduction brings together all the theory and tools needed for building robust machine learning in adversarial environments. Discover how machine learning systems can adapt when an adversary actively poisons data to manipulate statistical inference, learn the latest practical techniques for investigating system security and performing robust data analysis, and gain insight into new approaches for designing effective countermeasures against the latest wave of cyber-attacks. Privacy-preserving mechanisms and the near-optimal evasion of classifiers are discussed in detail, and in-depth case studies on email spam and network security highlight successful attacks on traditional machine learning algorithms. Providing a thorough overview of the current state of the art in the field, and possible future directions, this groundbreaking work is essential reading for researchers, practitioners and students in computer security and machine learning, and those wanting to learn about the next stage of the cybersecurity arms race.

Abstrak :
Machine learning focuses on predition-- using what you know to predict what you would like to know based on historical relationships between the two. At its core, it's a mathematical/algorithm-based technology that, until recently, required a deep understanding of math and statistical concepts, and fluency in R and other specialized languages. "Machine learning with Spark and Python" simplifies machine learning for a broader audience and wider application by focusing on two algorithm families that effectively predict outcomes, and by showing you how to apply them using the popular and accessible Python programming language. This edition shows how pyspark extends these two algorithms to extremely large data sets requiring multiple distributed processors. The same basic concepts apply. Author Michael Bowles draws from years of machine learning expertise to walk you through the design, construction, and implementation of your own machine learning solutions. The algorithms are explained in simple terms with no complex math, and sample code is provided to help you get started right away. You'll delve deep into the mechanisms behind the constructs, and learn how to select and apply the algorithm that will best solve the problem at hand, whether simple or complex. Detailed examples illustrate the machinery with specific, hackable code, and descriptive coverage of penalized linear regression and ensemble methods helps you understand the fundamental processes at work in machine learning. The methods are effective and well tested, and the results speak for themselves

Abstrak :
This book constitutes the thoroughly refereed post-conference proceedings of the 6th International Conference on Learning and Intelligent Optimization, LION 6, held in Paris, France, in January 2012. The 23 long and 30 short revised papers were carefully reviewed and selected from a total of 99 submissions. The papers focus on the intersections and uncharted territories between machine learning, artificial intelligence, mathematical programming and algorithms for hard optimization problems. In addition to the paper contributions the conference also included 3 invited speakers, who presented forefront research results and frontiers, and 3 tutorial talks, which were crucial in bringing together the different components of LION community.

Abstrak :
ABSTRAK
Anak anak merupakan generasi penerus bangsa. Perubahan pada citra tubuh misal pembengkakan pada leher yang disebabkan goiter dapat menyebabkan persepsi negatif terhadap diri sendiri. Kelainan pada kelenjar tiroid dapat mengakibatkan diantaranya penyakit kardiovaskuler, hipertensi, stunting, dan gangguan kesuburan pada wanita. Dampak lainnya adalah siswa yang terkena goiter memiliki nilai rata-rata lebih rendah rata-rata nilai pelajarannya daripada siswa normal. Kecamatan Bulakamba Kabupaten Brebes merupakan daerah dengan kategori parah untuk kejadian goiter. Tujuan dari penelitian ini adalah membuat sebuah aplikasi berbasis web yang bisa digunakan untuk melakukan skrining untuk kejadian Goiter pada anak-anak yang terpapar pestisida dengan parameter evaluasi yaitu Sensitivitas, Spesifitas, Positive Predictive Value, Negative Predictive Value. Penelitian ini menggunakan data sekunder, data didapatkan dari penelitian Rasipin tahun 2011. Jumlah data yang akan digunakan sebanyak 53 anak yang positif goiter dan 48 anak yang negatif goiter. Metode machine learning akan diimplementasikan dengan aplikasi WEKA. Hasil analisa dengan 10-fold Cross Validation didapatkan bahwa dengan sebelas variabel mampu mengenali siswa normal sebesar 92% dengan nilai Sensitivitas, Spesifitas, Positive Predictive Value, Negative Predictive Value berurutan sebesar 49%, 92%, 87% dan 62%. Prototipe sistem pintar untuk memprediksi kejadian goiter dapat dikembangkan, dan dapat digunakan untuk skrining kejadian goiter pada anak yang terpapar pestisida.

---

ABSTRACT
Children are the next generation of a nation. Changes in body image such as swelling of the neck caused by goiter can produce negative self perceptions. Abnormalities in the thyroid gland results in cardiovascular disease, hypertension, stunting and fertility disorders in women. Another impact is that students affected by goiter have lower average grades than normal students. Bulakamba Subdistrict(Brebes District) is a region with a severe category of goiter cases. The purpose of this study was to create a web based application which can be used to screen out the Goiter cases in children exposed to pesticides with evaluation parameters namely sensitivity, specificity, positive predictive value and negative predictive value. This study used secondary data which were obtained from Rasipin's research. Determination of goiter cases in the study was done using palpation method. The amount of data used was 53 positive-goiter children and 48 goiter-negative children. Machine learning techniques were then implemented using WEKA version 3.8.2 application. The analysis results with 10-fold Cross Validation showed that with 11 variabel, was able to recognize normal students by 92% with sensitivity, specificity, positive predictive value and negative predictive value of 49%, 92%, 87% and 62%, respectively. Smart sistem for predicting goiter cases can be developed and be used for screening goiter on children exxposed to pesticide.

Abstrak :
ABSTRACT
Big data or Data driven farming have been the latest improvement in agricultural sector. Data driven farming allows farmers to maximize the output of harvest by processing any significant data gathered regarding the crop. With the data of the crop available, it opens the possibility of evaluating the data to make a model for the crop. This model will allow predictions to be made which would improve the data driven farming to an extent. This project is based on improving Farmbot, a data driven farming tool, to allow the makings of a prediction based on sensor readings gathered by the tool. Several machine learning algorithms have been evaluated which takes account two sensor reading of the plant, and performances have been discussed. These parameters include soil moisture and light exposure level and the performance level gauged are predictability and interpretability. Based on the said parameters, Decision Tree Machine Learning Algorithm have been deemed the best method of prediction for a 2 class problem. This is based on its ability to make a prediction with relatively high confidence level with the addition of having high interpretability about how the algorithm come to the said conclusion. Decision Trees current state may be improved by implementing tree pruning method to omit unnecessary splits.

---

ABSTRACT
Big-Data Farming atau pertanian berbasis data merupakan perkembangan mutakhir pada sektor agrikultur. Dengan berbasis data mengenai asupan cahaya dan tingkat kelembaban, petani dapat memaksimalkan hasil panen dari suatu tanaman dengan memproses data mengenai tanaman tersebut. Dengan menyediakan data mengenai tanaman, hal ini memungkinkan pengolahan data dan membuat model yang menggambarkan pengaruh data ndash; data yang diperoleh dengan hasil panen suatu tanaman. Proyek ini dilaksanakan atas dasar mengembangkan sistem Farmbot, sebuah alat tanam automatis berbasis data, untuk menyediakan prediksi tentang bagaimana hasil panen tanaman tersebut berdasarkan data yang diperoleh dari sensor yang terdapat pada alat tersebut. Kemampuan Farmbot untuk melakukan perdiksi tersebut bisa dilakukan dengan mengimplementasikan algoritma Machine Learning, Dengan adanya berbagai macam algoritma Machine Learning, pemilihan algoritma yang paling tepat untuk implementasi Farmbot juga merupakan salah satu bahan pembahasan. Berhubung 2 parameter yang telah disebutkan merupakan kunci dari pembuatan model prediksi, algoritma Decision Tree dianggap sebagai algoritma yang paling optimal untuk diimplementasikan. Keputusan ini berdasarkan kemampuan Decision Tree dalam membuat prediksi dengan tingkat keyakinan yang tinggi dan juga berkemampuan untuk menggambarkan langkah langkah yang ditempuh untuk mencapai suatu prediksi. Algoritma Decision Tree yang telah diimplementasikan pada Farmbot dapat ditingkatkan dengan mengimplementasikan metode Tree Pruning untuk menghilangkan perpisahan yang tidak dibutuhkan.

Abstrak :
Pemeriksaan hemoglobin umum dilakukan secara invasif menggunakan berbagai metode, seperti automated hematology analyzer dan hemoglobinometer. Akan tetapi metode tersebut memakan waktu, biaya, dan menyakitkan bagi pasien. Pemeriksaan hemoglonin secara invasif juga tidak memungkinkan untuk dilakukan secara real-time dalam situasi mendesak. Akurasi dan ketepatan pembacaan menjadi tantangan dalam pengembangan sistem pengukur konsentrasi hemoglobin non-invasif. Pada penelitian ini dilakukan pengembangan dua desain sistem pengukur hemoglobin non-invasif (desain prototipe A dan desain prototipe B) menggunakan prinsip photoplethysmography (PPG) menggunakan sensor MAX30102 dan Arduino Uno sebagai mikrokontroler. Pengembangan prototipe dibuat berbasis machine learning dengan menggunakan model Dense Neural Network (DNN) dan menunjukkan akurasi paling maksimal menggunakan MSE loss function sebesar 92,31% untuk desain prototipe A dan 94,70% untuk desain prototipe B. Didapatkan juga hasil pengukuran reliabilitas alat ukur untuk desain prototipe A dan B masing-masing sebesar 84,9% dan 97,3%. Meski sudah memiliki tingkat akurasi yang cukup baik, penelitian ini masih perlu dikembangkan dari segi pemilihan alat referensi pemeriksaan Hb invasif, pengambilan dan pengolahan data yang lebih bervariasi mencakup usia, warna kulit, dan penyakit yang sedang dialami. ...... Hemoglobin examination is commonly conducted invasively using various methods such as automated hematology analyzers and hemoglobinometers. However, these methods are time-consuming, costly, and painful for patients. Invasive hemoglobin examinations also do not allow real-time measurements in urgent situations. Accuracy and precision of readings pose challenges in the development of non-invasive hemoglobin concentration measurement systems. In this study, the development of two designs of non-invasive hemoglobin measurement systems (prototype design A and prototype design B) using photoplethysmography (PPG) principle with MAX30102 sensor and Arduino Uno as the microcontroller was conducted. Prototype development was based on machine learning using a Dense Neural Network (DNN) model and achieved maximum accuracy using MSE loss function of 92,31% for prototype design A and 94,7% for prototype design B. The measurement reliability of the measurement device was also obtained, with 84,9% for prototype design A and 97,3% for prototype design B, respectively. Although the study already achieved a relatively good level of accuracy, further development is still needed in terms of selecting invasive Hb examination reference devices, obtaining and processing more diverse data including age, skin color, and existing diseases.