16 research outputs found
The question of the system of protection of human rights
No full textThe Russian state is subject to the human rights activities through the system of state bodies, including the judiciary, as reflected in the Constitution of the Russian Federation. The authors consider the human rights function of the state, judicial protection as one of the ways of state protection of the rights and freedoms of man and citizen, study the elements of General system of protection of human rights in the Russian Federation and its Central element — the right to judicial protection. In this article, the authors carried out a comparative analysis of the effectiveness of judicial protection of subjective rights in comparison with other forms of human rights functions of the state, analyzes judicial practice and the writings of legal scholars. The article discusses the system of judicial protection of the rights and freedoms of the individual in the broad and narrow sense, the author formulates the definition of the system of judicial protection of the rights and freedoms of man and in the broad and narrow sense, justifies the view on the right to judicial protection as a Central element of the system of judicial protection of the rights and freedoms of man and citizen, since in the absence of such law it is impossible to protect other constitutional rights and freedoms
Analisis Nilai Tambah dan Karakteristik Pemasaran Bakso Goreng Ikan Pada JurBas Kota Cimahi, Jawa Barat
No full textIndustri pengolahan hasil ikan merupakan sektor yang memiliki prospek strategis dan potensi besar untuk pengembangan yang berkelanjutan. JurBas (Juragan Basreng) merupakan UMKM yang bergerak di bidang produksi dan penjualan basreng (bakso goreng), kerupuk seblak, dan keripik lainnya. Penelitian ini bertujuan untuk mengetahui manajemen produk makanan ringan dari JurBas serta nilai tambah dari produk hasil JurBas. Pendekatan yang digunakan adalah pendekatan kualitatif dengan jenis penelitian deskriptif. Data primer diperoleh dari hasil wawancara semi terstruktur dengan pemilik usaha basreng, sedangkan data sekunder diperoleh dari data tertulis mengenai hasil penjualan, biaya produksi, pendapatan, dan omzet. Hasil penelitian menunjukkan bahwa produk JurBas menggunakan bahan baku berkualitas yang lebih unggul dari produk lainnya. Konsumen produk JurBas tersebar di berbagai daerah terutama Pulau Jawa, Kalimantan dan Sumatera dengan strategi pemasaran yang melibatkan influencer dan afiliasi atau mitra. Hal ini berdampak signifikan terhadap peningkatan permintaan. Produk JurBas memiliki pesaing yang cukup banyak dikarenakan banyaknya perusahaan sejenis yang mengikuti ide salah satu produknya, oleh karena itu perlu dilakukan promosi secara offline dan online dengan penetapan harga yang berbeda. Penentuan harga ditentukan oleh modal dan biaya tambahan (admin, afiliasi, dan jasa).
DAFTAR PUSTAKA
Dewan Pertimbangan Presiden. 2017. Potensi Perikanan Indonesia. Watimpres.
Fatahillah, L.A., E. Sunarya, dan D. Jhoansyah. 2023. Pengaruh Strategi Diferensiasi Dan Iniovasi Produk Terhadap Keunggulan Bersaing Pada IKM Konveksi Di Kecamatan Caringin Kabupaten Sukabumi. Management Studies and Entrepreneurship Journal, 4(1) : 61-66.
Herminawaty. 2023. Manajemen Strategi Kinerja Perusahaan. Penerbit Telektual. Makassar. 336 hlm.
Hidayat, A.N.F., A.D. Dinanti dan K.D. Fathiyyah. 2024. Preferensi Mahasiswa Terhadap Makanan Tradisional dengan Makanan Cepat Saji dari segi Pemahaman Bahan Kimia. Konstanta : Jurnal Matematika dan Ilmu Pengelatuan Alam, 2(1) : 226-238.
Istiqomah, N.H., S. Magfiroh, dan Z.N. Habibana. 2024. Memahami Perilaku Konsumen: Tinjauan Aspek Psikologis dalam Keputusan Pembelian dan Strategi Pemasaran. Jurnal HEI EMA,3(3) : 71-82.
Junianto. 2015. Peran Strategis, Peluang dan Tantangan Industri Pengolahan Hasil Perikanan dalam Pembangunan Nasional Indonesia. Orasi Ilmiah. Universitas Padjadjaran
Junianto. 2016. Buku Ajar, Manajemen Industri Hasil Perikanan. Unpad Press, Bandung. 210 hlm.
Junianto dan A. Syauqibik. 2025. Artikel Review, Keunggulan Protein Ikan Dibandingkan Protein Non Ikan Lainnya. Jurnal Perikanan, 15(3): 281-1289.
Legi, D. Y. N., S. Murni, dan A.L.J. Tampenawas. 2023. Analisis Strategi Pemasaran Dalam Meningkatkan Penjualan Produk Di Rumah Makan Varel Pineleng. Jurnal EMBA, 11(4): 893-903.
Manahutu, D.N., N.A. Saimima, dan A. Wagola. 2024. Teknologi Pengolahan Perikanan – Inovasi dan Aplikasi Modern. PT Media Penerbit Indonesia. Medan. 211 hlm.
Muslimin, Z. Zainuddin, dan M.K. Saputra. 2022. Strategi Pemasaran Untuk Meningkatkan Penjualan Pada Usaha UMKM Sederhana. Soutra Journal of Economic and Business, 3(2) : 132-149.
Nikawanti, G dan R. Aca. 2021. Ecoliteracy: Membangun Ketahanan Pangan Dari Kekayaan Maritim Indonesia. Jurnal Kemaritiman: Indonesian Journal of Maritime, 2 (2) : 113-122.
Nurhikmah., I. Rosada, dan I. Hasan. 2019. Analisis Produksi Dan Pendapatan Usahatani Cabai Rawit Di Kelurahan Malakke, Kecamatan Belawa, Kabupaten Wajo. Jurnal Wiratani, 2(2) : 82-91.
Sandi, F., dan M.C. Sari. 2022. Pengaruh Biaya Produksi, Omset Penjualan, dan Biaya Promosi Terhadap Laba Foresthree Coffee Tulungagung. EKOMA: Jurnal Ekonomi, Manajemen, Akuntansi, 2 (1) : 1-11.
Skjøndal B. E. 2015. A case study of obstacles and enablers for green innovation within the fish processing equipment industry. Journal of Cleaner Production , 90(1) : 234–243.
Syamsuri. 2010. Analisis Penerapan Srategi Pemasaran Pada Rumah Makan Ayam Bakar Wong Solo Cabang Malang. Skripsi. Universitas Islam Negeri Maulana Malik Ibrahim Malang
Syamtoro, B., R.N. Wahidah, dan N.P. Kencana. 2024. Pengaruh Strategi Promosi Dan Pelayanan Terhadap Keputusan Pemilihan Jasa Pada PT. Bina Edu Pratama. Jurnal Ilman: Jurnal Ilmu Manajemen, 12(1) : 7-10.
Pratama, A., E. Nurlaela, R.S. Mardiah, U.S.S.Huriyah, B. Hadiwinata, A.P. Yusrizal, I.C.M.Siahaan, Y. Prasetyo, Handoko, R.H. Wirayudha, dan N.Mulyandari. 2025. Rantai Pasok Produk Perikanan. Penerbit Yayasan Kita Menulis. Medan. 206 hlm.
Tingga, P. C., dan P.A.Z. Geno. 2021. Segmentasi Dan Target Pasar Produk Umkm Sektor Perikanan Melalui Strategi Bauran Pemasaran Di Kota Kupang. Jurnal Bahari Papadak, 2(2) : 72-75.
Widiati, A. 2019. Peranan Kemasan (Packaging) dalam Meningkatkan Pemasaran Produk Usaha Mikro Kecil Menengah (UMKM) di “Mas Pack” Terminal Kemasan Pontianak. Jurnal Audit dan Akuntansi Fakultas Ekonomi dan Bisnis Universitas Tanjungpura, 8(2), 67-76.
Yang, Z., Li, S., Chen, B., Kang, H., and Huang, M. 2016. China’s aquatic product processing industry: Policy evolution and economic performance. Trends in Food Science & Technology, 58(1) : 149–154
Short-term Econometric Forecasting of Latvian GDP
No full textANOTĀCIJA
Promocijas darba mērėis ir īstenot Latvijas reālā IKP īstermiĦa ekonometriskās
prognozēšanas procesu, noteikt ar to saistītas problēmas un to atrisināšanas iespējas,
kā arī izstrādāt rekomendācijas īstermiĦa ekonometriskās prognozēšanas procesa
uzlabošanai.
Apkopojot promocijas darba rezultātus, autors secina, ka promocijas darbā
izvirzītā hipotēze ir pierādīta: ekonometrisko modeĜu, paredzētu Latvijas reālā IKP
īstermiĦa prognozēšanai, izmantojot uzĦēmumu un patērētāju apsekojumu rādītājus
vai monetāros rādītājus, kā arī ekonometrisko modeĜu, balstītu uz ražošanas funkciju
vai biznesa ciklu, izmantošana nodrošina precīzākas prognozes nekā ARIMA saimes
modeĜi.
Balstoties uz īstenoto Latvijas reālā IKP īstermiĦa ekonometriskās
prognozēšanas procesu, autors apkopo darba izstrādes gaitā noteiktās ar īstermiĦa
ekonometrisko prognozēšanu saistītas problēmas un to atrisināšanas iespējas, kā arī
izstrādā rekomendācijas īstermiĦa ekonometriskās prognozēšanas procesa
uzlabošanai.ANNOTATION
The objective of the Doctoral Thesis is to implement the procedure of the shortterm
econometric forecasting of Latvian real GDP, to determine related problems and
solution thereto, as well as to elaborate proposals for improving short-term
econometric forecasting procedure in Latvia.
Based on the results of the short-term econometric forecasting procedure the
author concludes that the hypothesis formulated in the Thesis is proved: using the
econometric models developed for Latvian real GDP short-term forecasting applying
business and consumer survey indicators or monetary indicators, as well as
econometric models based on the production function or business cycle ensures more
accurate forecasts in comparison to the family of ARIMA models.
Based on the implemented Latvian real GDP short-term econometric forecasting
procedure in the last Section of the Thesis the author summarizes the problems related
to short-term econometric forecasting and the solutions thereof, as well as presents the
proposals for the improvement of the short-term econometric forecasting
The analysis of financial limited liability company "Norcon"
No full textDiplomdarba nosaukums ir ”SIA “Norcon” finanšu darbības analīze”.
Uzņēmuma finansiālā stāvokļa novērtēšana ir pamats pareizai uzņēmuma vadīšanai un tā nākotnes perspektīvu nodrošināšanai, tādēļ autors nolēma izpētīt uzņēmuma finanšu situāciju un izstrādāt priekšlikumus tās uzlabošanai.
Darba gaitā teorētiskajā daļā apskatīti finanšu analīzes teorētiskie aspekti, kuri sastāv no finanšu pārskatu horizontālās un vertikālās analīzes, finanšu koeficientu analīze, kā arī no apgrozāmo līdzekļu analīzes.
Praktiskajā daļā autors veica uzņēmuma gada pārskatu analīzi par 2008., 2009. un 2010. gadu, novērtējot uzņēmuma finanšu stāvokļa izmaiņas analizējamo periodu laikā, un mēģinot noteikt to izmaiņu cēloņus, kā arī veica finanšu analīzi ar mērķi uzlabot un pilnveidot uzņēmuma finanšu darbību.
Turpinājumā autors veica bilances un peļņas vai zaudējumu aprēķina horizontālo un vertikālo analīzi un veic uzņēmuma finanšu analīzi aprēķinot likviditātes, maksātspējas, aktivitātes un rentabilitātes rādītājus. Šajā nodaļā autors izteica piedāvājumu finanšu situācijas uzlabošanai, kuru varētu izmantot analizētā uzņēmuma vadība turpmāko finanšu lēmumu pieņemšanā.
Diplomdarba apjoms ir 65 lappuses, tas sastāv no 3 daļām un 6 pielikumiem. Darbā ir izmantotas 8 tabulas, 19 attēli un 24 formulas.The title of the diploma work is “The analysis of financial limited liability company “Norcon””.
The assessment of financial situation of the enterprise is the basis of its right man-agement and provision of future perspectives, therefore the author decided to research the fi-nancial situation of the enterprise and to work out suggestions for improvement.
The theoretical aspects of financial analysis are surveyed in the theoretical part and it consists of horizontal and vertical analysis of financial statements, analysis of financial co-efficients, as well as the analysis of cash flow.
In practical part the author carries out the analysis of annual reports of the years 2008. 2009., and 2010., evaluating the changes of financial position during the period of anal-ysis and trying to determine the reasons of changes, as well as fulfils the financial analysis aimed to improve and upgrade the financial activities of the enterprise.
In continuation the author performs the financial analysis of the enterprise, calculat-ing the indices of liquidity, paying capacity, activity and profitability, and carries out the hori-zontal and vertical analysis of calculation of balance and profit or losses. In this part the au-thor gives his suggestions of improvement of financial situation, what could be used by the head of the analyzed enterprise in order to make the further financial decisions.
The amount of the diploma work is 65 pages, consisting of 3 parts and 6 supple-ments. 8 tables, 19 pictures and 24 formulas are used in this work
Analysis of real estate of Riga
No full textMaģistra darba “Rīgas nekustamā īpašuma tirgus analīze” mērķis ir uz nekustamā īpašuma tirgus attīstības un to ietekmējošo faktoru pētījuma pamata veikt vispusīgu Rīgas dzīvokļu tirgus attīstības analīzi.
Maģistra darbā ir 81 lapas, 3 tabulas, 36 attēli, 2 formulas.
Maģistra darbs sastāv no 4 nodaļām, kas veidotas, lai nodrošinātu loģiski secīgu informācijas izklāstu, noteiktā mērķa sasniegšanai.
Balstoties uz pētījumiem par dzīvokļu tirgus attīstību autore ir izdarījusi savus secinājumus un devusi priekšlikumus veiksmīgai Rīgas nekustamā īpašuma tirgus attīstībai.
Atslēgvārdi: nekustamais īpašums, Rīgas dzīvokļu tirgus, hipotekārais kredīts, privatizācijas process, Rīgas dzīvokļu cenas.The aim of the present master paper “Analyse of real estate of Riga” is to conduct comprehensive analysis of the real estate market on the basis of research of development of the flat market and factors that impact its development.
The master paper consists of 81 pages, 2 tables, 36 figures and 2 formulas.
The master paper comprises 4 chapters that are elaborated to ensure logical sequence in the outline of information to achieve the set aim of the paper.
On the basis of the research made in the field of development of the flat market, the author of the present paper has provided his conclusions about the factors that impact the Riga’s real estate market, as well as the author has given suggestions how to enhance its development.
Key words: real estate, Riga’s flat market, bank system, privatisation process, costs of Riga’s flats
Analysis of crediting products in Latvia
No full textMaģistra darba nosaukums ir “Kreditēšanas pakalpojumu analīze Latvijā”. Darbs uzrakstīts latviešu valodā. Darbs ir izstrādāts 87 lappušu apjomā, tai skaitā 14 attēli, 14 tabulas, formulas un grafiki. Darba izstrādāšanai izmantoti izdevumi un publicētie materiāli.
Darba mērķis ir analizēt Latvijas lielāko komercbanku kreditēšanas produktus un pakalpojumus privātpersonām un uzņēmumiem, veikt to salīdzinošo analīzi un atklāt pozitīvas un negatīvas tendences un riskus, kas saistās ar kreditēšanas procesu un izstrādāt priekšlikumus, lai novērstu vai samazinātu negatīvo efektu, kurš rodas nepareizas kreditēšanas procesā.
Autore izanalizēja kreditēšanas pakalpojumus, kurus piedāvā SEB Unibanka, Hansabanka un Parex banka, veica to salīdzinošo analīzi, atklāja trūkumus, kas rodas kreditēšanas procesā un izstrādāja priekšlikumus to novēršanai.The title of Master’s thesis is “Analysis of crediting products in Latvia”. The work is written in Latvian language. The thesis has been developed on 88 pages, including 14 charts and 14 tables. For analysis author used book issues and published materials.
The main purpose of thesis is to make analysis of crediting products and services for private customers and enterprises provided by biggest Latvian commercial banks, to make comparative analysis of these services, discover positive and negative trends and risks related to the crediting process and develop suggestions for further development and elimination of existing imperfections.
The author has analysed crediting product provided by SEB Unibanka, Hansabanka and Parex banka, made its comparative analysis, discovered lacks in crediting process and proposed ways for problem’s solution
Thesis is Creation and Analyse of Investment Portfolio
No full textBakalaura darba tēma ir “Vērtspapīru portfelis. Tā veidošana un vadīšana”. Bakalaura darba mērķis ir sastādīt vērtspapīru portfeli ar 10% ienesīgumu gadā uzņēmējam, kurš nevēlas sava uzņēmuma peļņu pilnībā ieguldīt atpakaļ uzņēmumā, bet diversificēt, jeb dažādot savus ieguldījumus izvēloties akciju portfeļa izveidi.
Darbā ir aplūkoti dažādi vērtspapīru veidi, tiek aplūkots un izanalizēts Latvijas vērtspapīru tirgus un nolemts, ka portfelī tiks izmantotas akcijas un portfelis tiks veidots ar ASV akcijām. Tiek aplūkotas un pielietotas tehniskā un fundamentālā analīze, pēc Markoviča teorēmas tiek sastādīts portfelis kas atbilst dotajiem uzstādījumiem.
Darbā izmantoti investīciju zinātnes teorētiķu darbi, LR likumi, Rīgas fondu biržas un ASV fondu biržu dati par akcijām, ekonomikas laikraksti, Latvijas Republikas, Eiropas Savienības, Amerikas Savienoto valstu statistika, informācija no interneta.
Darbs izstrādāts latviešu valodā un sevī ietver 8 tabulas, 15 attēlus, 20 formulas un 4 pielikumus.
Atslēgvārdi:
1)Investīcijas
2)Vērtspapīri
3)Tehniskā analīze
4)Fundamentālā analīze
5)Vērtspapīru portfelis
6)Markoviča modelisThe Bachelor’s Thesis is “Securities portfolio. It’s creation and management”. The goal is to make investment portfolio vith 10% expected return for entrepreneur, who doesn’t want to invest all profit from enterprise back in it , but wants to diversify and not to risk with all money invested in one entreprise.
At the Thesis author looks at the various types of securities, discusses and analyzes Latvian security market and decides that better in making securities portfolio is to use USA stocks. To make a profitable portfolio author uses financial – tehnical and fundamental analysis and in portfolio making uses Markowitz portfolio theorem.
In thesis are used many kinds of informational sources – investment theorists books, the laws of Latvia, the Baltic stock exchange and USA stock exchange data for the shares, EU and Republic of Latvia and USA statistics, economical newspapers and information from the internet.
The Thesis ir prepared in Latvian and includes 8 tables, 15 pictures, 20 formulas and 4 attachments.
Keywords:
1) Investments
2) Securities
3) Technical Analysis
4) Fundamental Analysis
5) Investment portfolio
6) Markowitz mode
Assessment of real versus nominal convergence with respect to EMU accession
No full textMaģistrā darbā, lietojot absolūtās vai bez nosacījuma beta konverģences metodi, tiek analizēta Latvijas nominālās, reālās un finanšu konverģences pakāpe, kā arī Latvijas ekonomisko ciklu sinhronizācija ar vecajām ES dalībvalstīm. Izmantojot VAR modeli, autors arī izpēta Latvijas ekonomikas izturību pret ārējiem šokiem un mēģina atrast tādu mehānismu, lai sabalansētu vai uzsūktu šo šoku ietekmi. Lai iegūtu salīdzināmus rezultātus, autors izveido paneļmodeli, iekļaujot modelī Baltijas valstis un Slovēniju.Kopumā var secināt, ka, neskatoties uz Baltijas valstu progresu nominālajā un reālajā konverģencē, tās joprojām atšķiras no vecajām ES dalībvalstīm. Tādēļ ciešāka biznesa ciklu sinhronizācijas, kā arī integrācijas pakāpe ir nepieciešama.The main topic of this paper is to analyze the degree of nominal, real and financial convergence and synchronization of the economic cycle of Latvia with that of the European Union using unconditional beta convergence approach. This paper also explores the resistance to different external shocks using VAR model as well as the mechanisms for balancing and absorption of these shocks. To give a better comparative picture author compose the panel including other Baltic countries and Slovenia.Overall it could be concluded that notwithstanding their progress in nominal and real convergence Baltic States still significantly differ from the EU economies and deeper synchronization as well as integration is needed
The Altman model and its application in Latvia
No full textMūsdienās, kad ir ļoti jūtama ārējās vides ietekme uz uzņēmuma saimniecisko darbību, ir svarīgi novērtēt uzņēmuma finanšu stāvokļa izmaiņas un operatīvi reaģēt uz ārējās vides izmaiņām. Lai precīzi novērtētu uzņēmuma finansiālo stāvokli, ir nepietiekami analizēt atsevišķus finansiālos koeficientus, papildus ir vēlams veikt arī bankrota prognozēšanas analīzi.
Darba mērķis ir novērtēt bankrota prognozēšanas modeļa precizitāti Latvijā, izmantojot Altmana oriģinālo modeli, un izstrādāt jaunu modeli, kas būtu piemērots Latvijas uzņēmumu vērtēšanā.
Veicot uzņēmumu finansiālā stāvokļa vērtējumu, autore secināja, ka ne vienmēr finanšu rādītāji var norādīt uz finanšu neveiksmi. Altmana bankrota prognozēšanas modeļa precizitāte Latvijas uzņēmumiem ir tikai 68%, tāpēc tika veikta modeļa pārvērtēšana. No jauna izveidoto modifikāciju precizitāte sastādīja vidēji 90%.Nowadays, when external environment affects the company’s business activities very much, it is important to evaluate the company’s financial state and it changes as well as react to external environment changes immediately. For the evaluation of financial state it is not enough to analyze individual accounting ratios. In addition, it is desirable to perform bankruptcy prediction analysis.
The purpose of the work is to evaluate the accuracy of bankruptcy prediction model in Latvia, applying the most well-known Altman model, as well as to develop new model, which will be more corresponding for evaluation of Latvia’s companies.
Performing the financial evaluation of the company, the author came to the conclusion that financial ratios not always can indicate financial difficulties. Predictive accuracy of the Altman Z-model for Latvia’s companies is only 68%, therefore re-estimation of the model was performed. Accuracy of re-estimated modifications composed 90% on average
Pengembangan Aplikasi Diagnosis Dini Penyakit Paru-Paru Berbasis Website pada Citra X-Ray Menggunakan Pendekatan Deep Learning
No full textParu-paru adalah salah satu organ vital manusia yang berfungsi sebagai alat pernafasan. Apabila paru-paru tidak berfungsi dengan baik maka akan menyebabkan kematian. Penyakit paru-paru dapat terjadi pada siapa saja dan dapat disebabkan oleh banyak faktor, seperti polusi udara, rokok, dan infeksi. Diagnosis penyakit paru-paru saat ini umumnya menggunakan citra medis, seperti citra X-ray yang dikaji oleh dokter spesialis atau tenaga medis seperti radiolog. Namun, diagnosis dini oleh dokter spesialis atau tenaga medis membutuhkan waktu dan proses yang cukup panjang. Salah satu penelitian menunjukkan bahwa faktor human error masih terjadi dalam diagnosis penyakit paru-paru. Oleh karena itu, pada penelitian ini penulis akan mengembangkan suatu sistem deep learning berbasis website dengan tujuan untuk membantu tenaga medis dalam meningkatkan akurasi dan efisiensi diagnosis dini penyakit paru-paru. Penelitian ini akan berfokus pada diagnosis dini dari 6 jenis penyakit paru-paru, yaitu, Pneumonia, Mass, Nodule, Edema, Consolidation dan COVID-19. Penelitian ini menggunakan arsitektur DenseNet-121 dan arsitektur VGG16 sebagai pembanding. Dataset yang digunakan adalah dataset chest X-Ray yang tersedia secara publik, yaitu dari National Institutes of Health (NIH) dan COVID-19 Radiography. Pada implementasi sistem penulis menggunakan bantuan library Streamlit dalam pembuatan website. Dokter akan mengunggah gambar chest X-Ray ke dalam website yang kemudian akan diklasifikasikan oleh model berupa teks score prediksi. Penulis menggunakan 4 versi model, model versi 1 memiliki F-1 Score sebesar 66,45%, model versi 2 memiliki F-1 Score sebesar 76,79%, model versi 3 memiliki F-1 Score sebesar 58,21% dan model versi 4 memiliki F-1 Score sebesar 76,48%. Model versi 2 dan 4 dengan penambahan dataset Guangzhou Women and Children's Medical Center menunjukkan akurasi yang sangat baik pada label pneumonia dan label normal. Hasil tersebut didapatkan setelah melakukan pengujian model dengan data validation dan test. Model versi 2 menggunakan Densenet-121 memiliki performa lebih baik dalam mengklasifikasikan gambar dengan akurasi dan tingkat prediksi yang lebih tinggi dibandingkan dengan VGG16. Salah satu penelitian menunjukkan adanya masalah misslabeling pada dataset NIH Chest X-Ray yang dapat mempengaruhi performa algoritma CNN dalam mendiagnosis kondisi medis. Misslabeling pada dataset NIH Chest X-Ray secara signifikan mempengaruhi akurasi model setelah dilatih dan diuji. Jika dataset NIH Chest X-Ray memiliki label yang benar, model memiliki potensi untuk memberikan prediksi dengan tingkat akurasi yang tinggi.
===============================================================================================================================
lungs are one of the vital human organs that function as a means of respiration. If the lungs do not function properly, it will cause death. Lung disease can happen to anyone and can be caused by many factors, such as air pollution, smoking, and infection. Current diagnosis of lung diseases generally uses medical images, such as X-ray images, which are reviewed by specialists or medical personnel such as radiologists. However, early diagnosis by specialists or medical personnel requires a long time and process. One study shows that human error still occurs in the diagnosis of lung disease. Therefore, in this research, the author will develop a website-based deep learning system with the aim of assisting medical personnel in improving the accuracy and efficiency of early diagnosis of lung diseases. This research will focus on the early diagnosis of 6 types of lung diseases, namely, Pneumonia, Mass, Nodule, Edema, Consolidation and COVID-19. This research uses the DenseNet-121 architecture and the VGG16 architecture as a comparison. The datasets used are publicly available chest X-Ray datasets, from the National Institutes of Health (NIH) and COVID-19 Radiography. In the implementation of the system, the author uses the help of the Streamlit library in making the website. Doctors will upload chest X-Ray images to the website which will then be classified by the model in the form of prediction score text. The author uses 4 versions of the model, model version 1 has an F-1 Score of 66.45%, model version 2 has an F-1 Score of 76.79%, model version 3 has an F-1 Score of 58.21% and model version 4 has an F-1 Score of 76.48%. Model versions 2 and 4 with the addition of the Guangzhou Women and Children's Medical Center dataset show excellent accuracy on pneumonia labels and normal labels. These results were obtained after testing the model with validation and test data. Version 2 of the model using Densenet-121 performed better in classifying images with higher accuracy and prediction rate compared to VGG16. One study showed a misslabeling problem in the NIH Chest X-Ray dataset that can affect the CNN algorithm's performance in diagnosing medical conditions. Misslabeling in the NIH Chest X-Ray dataset significantly affects the accuracy of the model after training and testing. If the NIH Chest X-Ray dataset is correctly labeled, the model has the potential to provide predictions with a high degree of accuracy
