Data Mining - Concepts and Techniques.

Understanding the data and reaching accurate conclusions are of paramount importance in the present era of big data. Machine learning and probability theory methods have been widely used for this purpose in various fields. One critically important yet less explored aspect is capturing and analyzing uncertainties in the data and model. Proper quantification of uncertainty helps to provide valuable information to obtain accurate diagnosis. This paper reviewed related studies conducted in the last 30 years (from 1991 to 2020) in handling uncertainties in medical data using probability theory and machine learning techniques. Medical data is more prone to uncertainty due to the presence of noise in the data. So, it is very important to have clean medical data without any noise to get accurate diagnosis. The sources of noise in the medical data need to be known to address this issue. Based on the medical data obtained by the physician, diagnosis of disease, and treatment plan are prescribed. Hence, the uncertainty is growing in healthcare and there is limited knowledge to address these problems. Our findings indicate that there are few challenges to be addressed in handling the uncertainty in medical raw data and new models. In this work, we have summarized various methods employed to overcome this problem. Nowadays, various novel deep learning techniques have been proposed to deal with such uncertainties and improve the performance in decision making.

/pdf/handling-of-uncertainty-in-medical-data-using-machine-rpi8bge796.pdf

Handling of uncertainty in medical data using machine learning and probability theory techniques: a review of 30 years (1991–2020)

Understanding data and reaching valid conclusions are of paramount importance in the present era of big data. Machine learning and probability theory methods have widespread application for this purpose in different fields. One critically important yet less explored aspect is how data and model uncertainties are captured and analyzed. Proper quantification of uncertainty provides valuable information for optimal decision making. This paper reviewed related studies conducted in the last 30 years (from 1991 to 2020) in handling uncertainties in medical data using probability theory and machine learning techniques. Medical data is more prone to uncertainty due to the presence of noise in the data. So, it is very important to have clean medical data without any noise to get accurate diagnosis. The sources of noise in the medical data need to be known to address this issue. Based on the medical data obtained by the physician, diagnosis of disease, and treatment plan are prescribed. Hence, the uncertainty is growing in healthcare and there is limited knowledge to address these problems. We have little knowledge about the optimal treatment methods as there are many sources of uncertainty in medical science. Our findings indicate that there are few challenges to be addressed in handling the uncertainty in medical raw data and new models. In this work, we have summarized various methods employed to overcome this problem. Nowadays, application of novel deep learning techniques to deal such uncertainties have significantly increased.

Handling of uncertainty in medical data using machine learning and probability theory techniques: A review of 30 years (1991-2020)

The WHO announced that more than 52 million people tested positive for Covid-19, and 1.2 million died in the second week of November 2020. Meanwhile, Indonesia recorded 463 thousand individuals with 15,148 deaths that were confirmed positive. Strategy against pandemics by incorporating socialization. However, learning that was initially bold as a technique became controversial due to the briefness of the adaptation process. a wide continuum of social reactions has resulted in the sudden transition from face-to-face learning to bold learning on a large scale. This research focuses on public opinion on online learning during the Indonesian COVID-19 pandemic in early November 2020. The analysis was carried out on Twitter by mining document-based text that was interpreted using the Naive Bayes algorithm. The results show that online learning has a positive sentiment of 30 percent, a negative sentiment of 69 percent, and a neutral 1 percent over the period. Due to community dissatisfaction about online learning, a significant amount of negative sentiment is created. Some tweets indicate disappointment with the words' stress 'and' lazy 'in the conversation being high-frequency words.

/pdf/analisis-sentimen-pembelajaran-daring-pada-twitter-di-masa-4gid7ejeht.pdf

Analisis Sentimen Pembelajaran Daring Pada Twitter Di Masa Pandemi COVID-19 Menggunakan Metode Naïve Bayes

The library at SMP N 5 Bandarlampung is a junior high school library that has library management staff and the number of book collections according to library standards, and has adequate library facilities and infrastructure. Students and students are required to become members of the school library to support the learning process. However, the process of borrowing and returning books currently carried out is still conventional, that is, all library administration data collection in borrowing and returning books is still written in the book, and when looking for the required data, you must open the book page. Application of library administration information systems using this user experience design, users can better understand and easily use applications that are made to maximize the performance of library staff, school principals, and students in managing library administration. The design of the library administration information system using the user experience design at SMP Negeri 5 Bandarlampung using the user centered design method has 5 stages, namely Empethized, Define Problem Statements, Indentation, and Prototype in accordance with the needs of users in the library administration information system based on the user experience design undertaken. The results of testing the criteria for the DeLone and McLean Model criteria for the success of the information system were 84.31% with the criteria being Very

/pdf/penerapan-sistem-informasi-administrasi-perpustakaan-159v4vtl6m.pdf

Penerapan Sistem Informasi Administrasi Perpustakaan Menggunakan Model Desain User Experience

Abstrak—Semakin berkembangnya teknologi maka semakin banyaknya kebutuhan yang diperlukan ini bisa menjadi peluang yang mampu dimanfaatkan untuk mendukung suatu pengembangan teknologi. Pada penelitian ini menerapkan salah satu model dalam perancangan aplikasi dengan mengimplementasikan Scrum framework dan Algoritma Greedy pada aktivitas product backlog Wedding Application Planner (Wepplan). Dimana hal tersebut membentuk 271 jam waktu kerja pada 23 aktivitas product backlog yang terbagi menjadi 4 sprint dengan memberikan solusi optimal pada permasalahan penjadwalan pembagian waktu kerja masing-masing developer. Hasil yang didapat yaitu developer 1 mendapatkan 70 jam waktu kerja, developer 2: 68 jam waktu kerja, developer 3: 69 jam waktu kerja, dan developer 4: 64 jam waktu kerja dalam pengerjaannya. Pada pengujian terhadap nilai response time aplikasi, hasil tercepat pada daftar uji Test Daftar: 27.386 (s), Test Login: 15.378 (s), Test Wedding: 24.433 (s), dan Test Engagement 25.841 (s) didapat menggunakan katalon, pada daftar uji Test Venue: 26.104 (s), Test Catering: 29.244 (s), Test Top Up: 26.617 (s), dan Test Edit Profile: 27.239 (s) menggunakan Testproject. Disimpulkan penelitian ini dapat memberikan manfaat terutama kepada para developer untuk mengefisiensi penjadwalan waktu kerja terhadap rancangan aktivitas dalam membangun sebuah produk aplikasi.Kata Kunci—Wepplan, Android, Scrum Framework, Algoritma Greedy. Abstract—Development of a technology, the more needs that are needed this can be an opportunity that can be used to support a technology development. In this study, one of the models in application design is implemented by Scrum framework and Greedy Algorithm in the Wedding Application Planner (Wepplan) product backlog activity. Where this forms 271 hours of work time on 23 product backlog activities which are divided into 4 sprints by providing optimal solutions to the scheduling problem of each developer's work time division. The results obtained are developer 1 gets 70 hours of work time, developer 2: 68 hours of work time, developer 3: 69 hours of work time, and developer 4: 64 hours of work time in the process. In testing the application response time value, the fastest results on the Test List Signup Test: 27,386 (s), Login Test: 15,378 (s), Wedding Test: 24,433 (s), and Engagement Test 25,842 (s) were obtained using Katalon, while in Venue Test: 26,104 (s), Catering Test: 29,244 (s), Top Up Test: 26,617 (s), and Profile Update Test: 27,239 (s) using Testproject. It is concluded that this research can provide benefits, especially for developers to make work time scheduling efficient for the design of activities in building an application product.

Scrum Framework and Greedy Algorithm in Product Backlog Wedding Application Planner (Wepplan) Activities

Tujuan dari penelitian ini adalah menjadi solusi membantu tim helpdesk dalam mengelola proses dari membuat tiket hingga penyelesaiannya. Penelitian ini menggunakan algoritma kombinasi Forward Chaining untuk mengelola SLA (Service Level Agreement) pengerjaan tiket dan Simple Additive Weighting (SAW) untuk prioritas pengerjaan tiket. Pengujian telah dilakukan sebanyak 600 data, metode forward chaining mencatat SLA pengerjaan tiket seperti urutan 1 sampai 20 berdurasi 7.9 jam indikator warna hijau, 21 sampai 40 durasi 6 jam berindikator kuning, 41 sampai 70 berdurasi 3 jam indikator hijau, 71 sampai 172 berdurasi 7 hari 19 jam indikator merah, 173 sampai 174 durasi 4 hari, 175 sampai 230 durasi 2 hari 21 jam, 231 sampai 260 berdurasi 8 jam berwarna kuning, 261 sampai 305 4 jam berwarna hijau, 306 sampai 325 berdurasi 7 hari 19 jam indikator merah, 326 sampai 345 berdurasi 12.6 jam berwarna kuning, 346 sampai 356 berdurasi 6.5 jam warna hijau, 357 sampai 469 berdurasi 7 hari 19 jam indikator merah, 470 sampai 475 berdurasi 4 hari, 476 sampai  556 berdurasi 2 hari 19 jam indikator merah, 557 sampai 576 berdurasi 23.9 jam berwarna kuning dan 577 sampai 600 berdurasi 7 jam serta berwarna hijau. Metode SAW mengurutkan prioritas pengerjaan berdasarkan bobot dan nilai awal yang telah ditentukan. Urutan 1 sampai 70 bernilai 100 diperingkat kesatu, 71 sampai 305 bernilai 55 diperingkat kedua, 306 sampai 356 dengan nilai 25 diperingkat ketiga, dan 357 sampai 600 bernilai 10 serta diperingkat keempat.

Forward Chaining Algorithm and Simple Additive Weighting (SAW) in Smart HelpDesk Ticketing Information System

The current population census is still Carried out by visiting each house. With a process like this, it will take a lot of time so that it will have an impact on the number of costs incurred by the government. For this reason, an online application is needed to Facilitate officers in conducting population censuses. Also, through this population census, the Researchers conducted a grouping of education levels intending to find out the population based on their level of education. The method used is the k-means clustering algorithm. There are three groupings items, namely C1 = population at a high level, C2 = population at a moderate level and C3 = population at a moderate level. The final centroid value used at C1 = (4.8000000,959.20000), C2 = (4.00000,854.000000) and C3 = (9.00000,668.00000). So that the results Obtained grouping C1 = RW2, RW7 and RW8,

/pdf/application-to-classify-the-population-census-the-total-1c89bt0o9a.pdf

Application To Classify The Population Census The Total Population By Level Of Education Using K-Means Clustering Algorithm: Application To Classify The Population Census The Total Population By Level Of Education Using K-Means Clustering Algorithm

In education in school, the teacher is an importent figure in determining the hight and low qualityof educatin outcomes, so teacher is required to cotinue to improve the performancein teaching, and ensure teacher performance the need for assessment, at ach school, teacher assesment is still i the form of manual of the principal as the party who assesses teacher performance, while not everytime the principal monitors how the teacher’s performance in teaching, it is necessary to add other more intensive assesors to meet with the teacher, namely students with several conditions that make students eligible to be correspondents, and a teacher assessment application to support students assessing their teacher more easily, making the application using the Rating Scale method for taking initial grade data and Profile Matching for calculating the average final grade.  The results of the testing of this program is that 100% accuracy is tested from 6 teachers and 20 students

/pdf/application-assessment-method-using-teacher-rating-scale-and-n5yf7p1i4v.pdf

Application Assessment Method Using Teacher Rating Scale And Profile Matching: Application Assessment Method Using Teacher Rating Scale And Profile Matching

Information technology plays a big role in various aspects. With technology, which can make it easier for humans to make decisions quickly and effectively. An expert system is an information system that contains knowledge from an expert in order to help with decision making. This system was designed with the theory of Dr. William Moulton Marston to find out his personality and work references. To find out a person, a personality test is carried out. The Personality Test uses a manual version through distributing questionnaires to find out people's dispositions. The evaluation is made a manual version through an answer sheet. Each person takes a lot of duration, this system is made using forward chaining. forward chaining begins the way inference begins with facts to verify the principle of an assumption. The way data is retrieved begins with assumptions until it is completed. The goal is to determine a person's disposition and propose a field of work for their personality. The app also uses Agile development, because the process of upgrading software requires a duration that tends to be fast and does not consume large resources, so modifications according to customer needs can be processed more agilely, and can use input to the development team to prepare methods. The existence of this application can help psychologists and users in the personality test process so that users do not have to come to see a psychologist and more efficiently carry out the personality test process carried out.

/pdf/aplikasi-mobile-tes-kepribadian-dengan-metode-disc-dan-2klclle9.pdf

Ira Diana Sholihati

Papers

Scrum Framework and Greedy Algorithm in Product Backlog Wedding Application Planner (Wepplan) Activities

Forward Chaining Algorithm and Simple Additive Weighting (SAW) in Smart HelpDesk Ticketing Information System

Application To Classify The Population Census The Total Population By Level Of Education Using K-Means Clustering Algorithm: Application To Classify The Population Census The Total Population By Level Of Education Using K-Means Clustering Algorithm

Application Assessment Method Using Teacher Rating Scale And Profile Matching: Application Assessment Method Using Teacher Rating Scale And Profile Matching

Aplikasi Mobile Tes Kepribadian dengan Metode DISC dan Forward Chaining