Attention based automated radiology report generation using CNN and LSTM

The automated generation of radiology reports provides X-rays and has tremendous potential to enhance the clinical diagnosis of diseases in patients. A new research direction is gaining increasing attention that involves the use of hybrid approaches based on natural language processing and computer vision techniques to create auto medical report generation systems. The auto report generator, producing radiology reports, will significantly reduce the burden on doctors and assist them in writing manual reports. Because the sensitivity of chest X-ray (CXR) findings provided by existing techniques not adequately accurate, producing comprehensive explanations for medical photographs remains a difficult task. A novel approach to address this issue was proposed, based on the continuous integration of convolutional neural networks and long short-term memory for detecting diseases, followed by the attention mechanism for sequence generation based on these diseases. Experimental results obtained by using the Indiana University CXR and MIMIC-CXR datasets showed that the proposed model attained the current state-of-the-art efficiency as opposed to other solutions of the baseline. BLEU-1, BLEU-2, BLEU-3, and BLEU-4 were used as the evaluation metrics.

Optimization of Management Mode of Small- and Medium-Sized Enterprises Based on Decision Tree Model

Decision tree algorithm is a common classification algorithm in data mining technology, and its results are usually expressed in the form of if-then rules. The C4.5 algorithm is one of the decision tree algorithms, which has the advantages of easy to understand and high accuracy, and the concept of information gain rate is added compared with its predecessor ID3 algorithm. After theoretical analysis, C4.5 algorithm is chosen to analyze the performance appraisal results, and the decision tree for performance appraisal is generated by collecting data, data preprocessing, calculating information gain rate, determining splitting attributes, and postpruning. The system is developed in B/S architecture, and an R&D project management system and platform that can realize performance assessment analysis are built by means of visualization tools, decision tree algorithm, and dynamic web pages. The system includes information storage, task management, report generation, role authority control, information visualization, and other management information system functional modules. They can realize the project management functions such as project establishment and management, task flow, employee information filling and management, performance assessment system establishment, report generation of various dimensions, management cockpit construction. With decision tree algorithm as the core technology, the system obtains scientific and reliable project management information with high accuracy and realizes data visualization, which can assist enterprises to establish a good management system in the era of big data.

Rancangan Aplikasi Kasir Berbasis Dekstop Pada Toko Citra MJ Cikarang

Abstrak: Citra MJ merupakan perusahaan yang mempunyai suatu usaha penjualan berupa pakaian. Dimana Citra MJ dalam proses usahanya masih terkendala dalam hal pengelolaan data. Selain itu sistem pembayaran transaksi yang dilakukan oleh kasir masih bersifat manual sehingga menyebabkan banyak waktu yang terbuang. Sistem yang masih manual dalam pengelolaan data menyebabkan kasir kesulitan dan membutuhkan waktu yang lama dalam mencari data produk, data pelanggan maupun data transaksi. Karena itu untuk mempermudah hal tersebut toko Citra MJ membuat pengolahan data dan pembuatan laporan administrasi sistem kasir, Toko Citra MJ memanfaatkan penggunaan teknologi salah satunya penggunaan teknologi komputer dengan membuat perancangan aplikasi program kasir untuk toko Citra MJ. Tujuan dari perancangan program ini adalah membantu kegiatan kasir dalam hal pengolahan data seperti pengolahan data produk, data pegawai, data transaksi, data pelanggan serta pembuatan laporan di toko MJ. Aplikasi program ini sementara ini di peruntukkan untuk kasir saja ke depannya tidak menutup kemungkinan mengembangkan menjadi aplikasi yang berbasis web. Sistem kasir ini menggunakan metode waterfall, yang mana metode ini dilakukan secara berurut mulai dari analisa, rancangan, pengkodean, pengujian sampai implementasi. Dalam perancangan program kasir di toko MJ bahasa pemrograman yang digunakan adalah java, database xampp dengan software pendukung adalah NetBeans IDE 8.1. Dengan melihat dari hasil pengujian yang menggunakan metode kuisioner diperoleh tngkat kepuasaan pengguna aplikasi program kasir sebesar 82,12 %, hal ini berarti bahwa pengguna sangat puas dengan aplikasi program kasir. Kata kunci: program kasir, rancangan program Abstract: Citra MJ is a company that has a sales business in the form of clothing. Where Citra Mj in its business process is still constrained in terms of data management. In addition, the payment system for transactions carried out by the cashier is still manual, causing a lot of wasted time. The system that is still manual in data management causes cashiers to have difficulty and takes a long time in finding product data, customer data and transaction data. Therefore, to make this easier, the Citra Mj store makes data processing and makes administrative reports for the cashier system, the Citra Mj store utilizes One of the uses of technology is the use of computer technology by designing a cashier program application for the Citra MJ store. The purpose of this program design is to assist cashier activities in terms of data processing such as product data processing, employee data, transaction data, customer data and report generation. This program application is currently intended for cashiers only, in the future it is possible to develop it into a web-based application. This cashier system uses the waterfall method, where this method is carried out sequentially starting from analysis, design, coding, testing to implementation. In designing the cashier program at the Mj store the programming language used is java, the xampp database with supporting software is NetBeans IDE 8.1. By looking at the test results using the questionnaire method, the level of user satisfaction of the cashier program application is 82.12%, this means that the user is very satisfied with the cashier program application. Keywords: cashier program, program design

Encoder-decoder models for chest X-ray report generation perform no better than unconditioned baselines

High quality radiology reporting of chest X-ray images is of core importance for high-quality patient diagnosis and care. Automatically generated reports can assist radiologists by reducing their workload and even may prevent errors. Machine Learning (ML) models for this task take an X-ray image as input and output a sequence of words. In this work, we show that ML models for this task based on the popular encoder-decoder approach, like ‘Show, Attend and Tell’ (SA&T) have similar or worse performance than models that do not use the input image, called unconditioned baseline. An unconditioned model achieved diagnostic accuracy of 0.91 on the IU chest X-ray dataset, and significantly outperformed SA&T (0.877) and other popular ML models (p-value < 0.001). This unconditioned model also outperformed SA&T and similar ML methods on the BLEU-4 and METEOR metrics. Also, an unconditioned version of SA&T obtained by permuting the reports generated from images of the test set, achieved diagnostic accuracy of 0.862, comparable to that of SA&T (p-value ≥ 0.05).

Management Information System for Compensation under Multihoming Network Architecture

The management information system for compensation under multihoming network architecture has been developed in order to improve the time efficiency, accuracy, and level of informatization of compensation management in university and deal with the rising data and difficulty in exchanging information between various management information systems resulting from the changing compensation policies. This system is designed based on multihost data network architecture, including function modules of all kinds of compensation promotion, personnel historical data management, time warning, statistics, and report generation. This system integrates my five years’ experience in the front-line of compensation management work. The purpose is to fully solve the practical problems of compensation management in universities, truly help the work of compensation administrators, unify the fragmented compensation management works, and comprehensively improve the level of compensation management. It has a strong popularization and signification for reference for the compensation management work of similar universities.

PELATIHAN PHOTOSHOP UNTUK PEMBUATAN LAPORAN PADA WORD DAN POWER POINT DI SMA TARSISIUS II JAKARTA

This PKM activity is implemented in the form of extracurricular teaching at Tarsisius II High School Jakarta. The training targets are high school students and are targeted to be able to use Photoshop applications to support report generation using Microsoft Word, PDF files and Power Point. Use Photoshop to edit images needed in reports or for presentation needs. The contents of the training materials are related to images for copying, pasting, cropping, separating images, providing additional information on images, changing text on images, editing photos, making banners or activity posters, as well as applications using the snipping tool. This training is given for one semester in school extracurricular activities, with a schedule every Monday at 12.00 – 14.00 during the period from September to November 2021. The activity has been running since September 6, 2021. This activity is a community service program that is carried out routinely and financed by research institute and service to the community of Tarumanagara University. This activity is offered through the principal of SMA Tarsisius II Jakarta who forwards this information to the principal, Pak Adi, who is part of the school curriculum. The head of the implementing team has communicated with the principal, and extracurricular activities will be carried out for one year. This activity was carried out online due to the PPKM level 3 emergency situation due to the Covid-19 pandemic, but it was planned to be carried out offline. Materials will be made and prepared for each meeting and are scheduled for 10 meetings this semester. Photoshop training lecturers are lecturers and students of Electrical Engineering at Tarumanagara University. Outcomes produced by designing posters or banners for high school student participants and seminars for lecturers who support this activity.Kegiatan PKM ini diterapkan dalam bentuk pengajaran ektrakurikuler di SMA Tarsisius II Jakarta. Sasaran pelatihan para siswa SMA dan ditargetkan mampu menggunakan aplikasi photoshop untuk menunjang pembuatan laporan menggunakan microsoft word, file pdf dan power point. Penggunaan photoshop untuk meng-edit gambar yang dibutuhkan di dalam laporan atau untuk kebutuhan presentasi. Isi materi pelatihan berkaitan dengan gambar untuk pengerjaan copy, paste, crop, memisahkan gambar, memberikan keterangan tambahan pada gambar, mengganti tulisan pada gambar, meng-edit foto, membuat spanduk atau poster kegiatan, serta aplikasi penggunaan snipping tool. Pelatihan ini diberikan selama satu semester dalam kegiatan ektrakurikuler sekolah, dengan jadwal setiap hari senin pukul 12.00 – 14.00 selama periode bulan September sampai November 2021. Kegiatan sudah berjalan mulai tanggal 06 September 2021. Kegiatan ini merupakan program pengabdian kepada masyarakat yang dilaksanakan rutin dan dibiayai oleh lembaga penelitian dan pengadian kepada masyarakat Universitas Tarumanagara. Kegiatan ini ditawarkan melalui kepala sekolah SMA Tarsisius II Jakarta yang meneruskan informasi ini kepada kepala pak Adi yang merupakan bagian kurikulum sekolah. Ketua tim pelaksana sudah berkomunikasi dengan kepala sekolah, dan kegiatan ektrakurikuler akan dilaksanakan selama satu tahun. Kegiatan ini dilakukan secara daring karena situasi darurat PPKM level 3 dikarenakan masih dalam kondisi pandemi Covid-19, tetapi akan direncanakan untuk dilakukan secara luring. Materi akan dibuatkan dan dipersiapkan untuk setiap kali pertemuan dan dijadwalkan untuk 10 kali pertemuan pada semester ini. Tenaga pengajar pelatihan photoshop adalah dosen dan mahasiswa Teknik Elektro Universitas Tarumanagara. Luaran yang dihasilkan dengan desain poster atau spanduk bagi peserta siswa SMA dan seminar bagi dosen pengampu kegiatan ini.