Raqamli texnologiyalar va iqtisodiyot: zamonaviy muammolari va istiqbollari mavzusida Respublika ilmiy-amaliy

-–SHO‘BA 6EUEQPMXI\RSPSKM]EPEVZEE\FSVSX \EZJWM^PMKMRMRKQYEQQSPEVMZE ]IGLMQPEVM

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil TABIIY TILNI QAYTA ISHLASHDA QO‘LLANILADIGAN NLP MODELLARI TAHLILI (NEQWLMH7YPXERSZ<YWRM]E%\QIHSZE “Muhammad alXorazmiy nomidagi TATU” O‘UYZMWLPEVMTVSVIOXSVM “Muhammad alXorazmiy nomidagi TATU” katta o‘qituvchisi LELQIHSZE$QEMPVY %RRSXEXWM]E So‘nggi yillarda Sun’iy intellekt (SI) texnologiyalari yuqori darajada VMZSNPERHMZEXYVPMWSLEPEVHENYQPEHERFEROPEVHEIPIOXVSRTSGLXEFSWLUEVYZMHEXMFFM]SXHE ZE boshqa ko‘plab sohalarda qo‘llanilmoqda. NLP (Natural Language Processing 8EFMM] Tilni Qayta Ishlash) so‘zida ko‘plab modellarni o‘z ichiga oladi. Bu modellar, matnni tahlil qilish, tarjima qilish, dialog tizimi, mazmuni tahlil qilish va boshqa ko‘plab ZE^MJEPEVRMFENEVMWL YGLYR MWLPEXMPEHM Bu modellar katta matnlar va ko‘p maqsadli vazifalarni bajarishda muvaffaqiyatli natijalarga erishish uchun yaratilgan. Har bir modellarning o‘z xususiyatlari ZE JS]HEPERMWL WSLEPEVM QEZNYH 9WLFY QEUSPEHE WLYRHE] QSHIPPEVRMRK FMV RIGLXEWMRMRK imkoniyatlari va o‘ziga xos xususiyatlari bo‘yicha ma’lumotlar keltirilgan. Kalit so‘zlar:XEFMM]XMPQEXR204622;SVHZIG+PS:I*EWX8I\X /MVMWL 8MPRMQSHIPPEWLXMVMWLRMRKZE^MJEPEVMHERFMVMSPHMRKMQEXRRMFMPMWLEWSWMHEkeyingi so‘zni bashorat qilishdir. Bu matn terish xatolarini tuzatish, avtoto‘ldirish, chatbotlar va boshqalar uchun zarurdir. Internetda tabiiy tilni qayta ishlash modellari haqida juda ko‘p tarqoq ma’lumotlarni topishingiz mumkin. 8MPRMQSHIPPEWLXMVMWLHa alohida so‘zlar va so‘zlar guruhlari vektorlarga, ya’ni semantik munosabatlarni saqlaydigan ma’lum sonli tasvirlarga ko‘rsatiladi. So‘zning siqilgan vektor ko‘rinishi embedding deb ataladi. Bunday model oldingi n ta so‘zning kirish vektor ko‘rinishini olEHM ZE NYQPERMRK WIQERXMOEWMRM XYWLYRMWLKE LEVEOEX UMPEHM 1SHIP XVIRMRKM uzluksiz so‘zlar algoritmiga asoslangan. Kontekstli (qo‘shni) so‘zlar markaziy so‘zni FEWLSVEXUMPEHMKERRI]VSRXEVQSURMRKOMVMWLMKEFIVMPEHM A bag of words (so‘zlar WYQOEWM bu matnni vektor (so‘zlar to‘plami) sifatida ifodalash uchun qo‘llaniladigan modellardan biridir. Bunda matndagi har bir so‘z uning paydo bo‘lish soni bilan bog‘liq holda ifodalanadi. 6IGYVVIRXRIYVEPRIX[SVO 622 Elementlar orasidagi yo‘naltirilKER EPSUEPEVKE IKE RI]VSR XEVQSUPEV 2I]VSRRMRK chiqishi kirishga qaytarilishi mumkin. Ushbu tuzilma sizga o‘ziga xos "xotira" ga ega bo‘lish va ma’lumotlar ketmaOIXPMKMRM QEWEPER XEFMM] XMPHEKM QEXRPEVRM UE]XE MWLPEWL MQOSRMRM FIVEHM?A - Hammamizga ma’lum Google ko‘pgina tillar uchun oldindan o‘qitilgan ochiq kodli modellardan foydalanadi. Model inglizcha Google News 200B korpusida o‘qitilgan va 128 o‘lchovli o‘rnatishni hosil qiluvchi, oldinga uzatiladigan neyron tarmog‘ining uchta yashirMR UEXPEQMHERJS]HEPEREHM&YRHE]]IGLMQUY]MHEKMEJ^EPPMOPEVKEIKE Oddiylik. Model tezda o‘rgatadi va o‘rnatishlarni yaratadi, bu ko‘pchilik oddiy ilovalar uchun ]IXEVPMLMWSFPEREHM 22

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil - Ko‘plab tillarda oldindan tayyorlangan versiyalar mavjud. - 7LYFMPERFMVKEFYRHE]]IGLMQUY]MHEKMOEQGLMPMOPEVKELEQIKE Uzoq muddatli bog‘lanishlarni hisobga olmaydi. 3HHM]PMOJS]HEPERMWLMQOSRM]EXPEVMRMGLIOPE]HM =ERKMIQFIHHMRKQSHIPPEVERGLEOYGLPMVSUMQOSRM]EXKEIKE ;SVHZIG ]MPHE +SSKPI OSQTERM]EWMHER 8SQEW 1MOSlov so‘zlarning vektor ko‘rinishini o‘rganish uchun yanada samarali modelni taklif qildi Word2vec. Usul ko‘pincha bir xil kontekstda uchraydigan so‘zlar o‘xshash ma’noga ega degan taxminga asoslangan edi. Bu 204 XMP QSHIPPEVMRM MWLPEF GLMUMWLHE OIWOMR FYVMPMWL ]EWEHM ;SVH:IG QSHIPM Y^PYOWM^ so‘zlarni to‘plash algoritmi o‘rniga SkipKVEQHER JS]HEPEREHM 9WLFY QSHIPRMRK QEUWEHM EZZEPKMQSHIPKEQYXPEUS^MHHMVmarkaziy so‘zlarga asoslanib, atrofdagi so‘zlarni bashorat UMPMWL 7OMTgram modeli, bir so‘zning boshqa so‘zlar bilan hamkorlik qilishi mumkinligini aniqlash uchun so‘zlar orasidagi aloqalar tahlilini bajaradi. Bu model uchun kiritish qatorining uchinchi jihati so‘zlar va ularning konteksti bo‘lishi mumkin bo‘lgan qatorlarning ko‘p ma’lumotlaridan foydalaniladi. Bu ma’lumotlar bilan model o‘rganadi va so‘zlarning xususiyatlari (embedding) ni yaratadi. Natijada, har bir so‘z uchun bir qator kontekst so‘zlar haqiqiy joyda joylashishi va ularning ma’nolari bo‘yicha o‘rganiladi[2]. SkipKVEQQSHIPMFY Wo‘zlarning vektor koordinatalarini olish orqali amaliyotlarda o‘zlashtirish imkonini beradi. Bu vektorlar, so‘zlarning aynan ularning kontekstida uchun ma’nolarga yaqinlik va uzoqliklarini ifodalaydi[1]. Ma’lumotlar tahlili, matematik va tarqalgan texnologM]EPEV yordamida bu vektorlar ustida amalga oshiriladi. Bu vektorlar, ko‘p yo‘nalishli ma’lumotlar tahlili, matematik va yadroli ustama ma’lumotlar tahlili (NLP) uchun muhimdir. - - %J^EPPMOPEV 3HHM]EV\MXIOXYVESPHMRKEY^EXMWLOMVMWL]EWLMVMRUEXPEQGLMUMWL Model tezda o‘rganadi va o‘rnatishlarni yaratadi (hatto o‘zingiz ham). O‘rnatishlar ma’noga ega, bahsli fikrlarni hal qilish mumkin. Metodologiya boshqa ko‘plab sohalarga kengaytirilishi mumkin (masalan, Lda2vec). /EQGLMPMOPEV So‘z darajasida o‘rganish: so‘z ishlatilgan jumla yoki kontekst haqida hech qanday ma’lumot yo‘q. Birgalikda yuzaga kelishi e’tiborga olinmaydi. Model so‘zning qo‘llanish kontekstiga qarab turli xil ma’nolarga ega bo‘lishi mumkinligini hisobga olmaydi. Bu GloVeRMSHEXHE ;SVH:IGdan afzal ko‘rishining asosiy sababidir. Noma’lum yoki kam uchraydigan so‘zlarni to‘liq qayta ishlamaydi. +PS:I +PSFEP:IGXSVW GloVe Word2Vec bilan chambarchas bog‘liq: algoritmlar bir vaqtning o‘zida paydo bo‘lgan va so‘z vektorlarining XEPUMR UMPMRMWLMKE XE]EREHM +PS:I QSHIPM LMX WXEXMWXMOEWMHER samarali foydalanish muammosini hal qilishga harakat qiladi. GloVe so‘z vektorlarining 23

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil QELWYPSXM ZE WXS\EWXMO KVEHMIRX XYWLMWLMHER JS]HEPERKER LSPHE YPEVRMRK FMVKEPMOHE TE]HS bo‘lish ehtimoli logarifmi o‘rtasidagi farqni minimallashtiradi. Olingan tasvirlar so‘zlarning vektor fazosining muhim chiziqli quyi tuzilmalarini aks ettiradi: bitta sayyoraning turli sun’iy yo‘ldoshlarini yoki shaharning pochta indeksini uning nomi bilan bog‘lash mumkin[5] ;SVH:IGda so‘zlarning birgalikda paydo bo‘lish chastotasi unchalik muhim emas, bu faqat qo‘shimcha o‘quv namunalarini yaratishga yordam beradi. GloVe faqat kontekstli statistik ma’lumotlarga tayanishdan ko‘ra, birgalikdagi hodisalarni hisobga oladi. So‘z vektorlari global o‘xshashlik asosida guruhlanadi. - - - %J^EPPMOPEV Neyron tarmog‘isiz oddiy arxitektura. Model tez va oddiy ilovalar uchun yetarli bo‘lishi mumkin. GloVe Word2Vec imkoniyatlarini to‘ldiradi. U so‘z chastotasini qo‘shadi va ko‘pgina QI^SRPEVHE;SVH:IGHERYWXYRXYVEHM /EQGLMPMOPEV Birgalikda sodir bo‘lish matritsasi global ma’lumotni taqdim etsada, GloVe so‘z darajasida o‘qitilgan bo‘lib qoladi va jumla va so‘z ishlatiladigan kontekst haqida kam ma’lumot FIVEHM Noma’lum va kam uchraydigan so‘zlarni sifatsiz qayta ishlash. *EWX8I\X *EGIFSSO XSQSRMHER ]EVEXMPKER JEWX8I\X OYXYF\SREWM XEFMM] XMP QSHIPPEVMRM MWLPEF chiqishda yana bir jiddiy qadam bo‘ldi. Uni ishlab chiqishda bizga Word2VecHER XERMWL bo‘lgan Tomas Mikolov ishtirok etdi. So‘zlarni vektorlashtirish uchun bir vaqtning o‘zida skip KVEQWEPFM]REQYRESPMWLZEY^PYOWM^WYQOEEPKSVMXQMHERJS]HEPERMPEHM?A %WSWM] ;SVH:IG QSHIPMKE VEQ^M] Rgramm modeli qo‘shildi. Har bir so‘z ma’lum Y^YRPMOHEKM FMV RIGLXE FIPKMPEV OIXQEOIXPMKMHER MFSVEX OSQTS^MXWM]E WMJEXMHE MJSHEPEREHM Klassifikator natijalari kam uchraydigan so‘zlar uchun juda mos keladi, chunki ular n grammga bo‘lingan. Word2Vec va Glovedan farqli o‘laroq, model noma’lum so‘zlar uchun qo‘shimchalar yaratish imkoniyatiga egE - %J^EPPMOPEV Nisbatan oddiy arxitektura: oldinga o‘tish, 1 kirish, 1 yashirin qatlam, bitta chiqish 2grammlar tufayli u kam uchraydigan va eskirgan so‘zlarda yaxshi ishlaydi. /EQGLMPMOPEV So‘z darajasida o‘rganish: so‘z ishlatilgan jumla yoki kontekst LEUMHELIGLUERHE] ma’lumot bo‘lmaydi. Birgalikda paydo bo‘lish e’tiborga olinmaydi, ya’ni model turli kontekstlarda so‘zning turli ma’nolarini hisobga olmaydi. <YPSWE >EQSREZM] XI\RSPSKM]EPEVRMRK NEHEP VMZSNPERMF FSVE]SXKERPMKMRM LMWSFKE SPWEO 204 sohasida yangiliklar doimiy ravishda paydo bo‘lishi mumkin. Mavjud modellar o‘zlarini yanada rivojlantirish uchun ko‘plab sohalarga qo‘llanilmoqda va yangi modellar ham paydo 24

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil bo‘lmoqda. Masalan, GPT modellari ketmaOIXPMOHE VMZSNPERQSUHE ZE ]ERKM KIRIVEXMZ QSHIPPEV QEWEPER (%00E so‘z va tasvirlar kombinatsiyasini yaratishda muvaffaqiyat US^SRQSUHE&YRHE]QSHIPPEVXYVPMWSLEPEVYGLYR]ERKMMQOSRM]EXPEVIWLMKMRMSGLEHM Shuningdek, ko‘p kompaniyalar xizmatlarida NLP ni qo‘llashga qodir modellar ishlEF GLMUMWLKEUEVEXMPKER&YQSHIPPEVEZXSQEXPEWLXMVMPKERWEZSPPEVZENEZSFPEVQYPSUSXFSXPEVM va tizimlarini yaratishda ishlatiladi. Muloqot botlari, onlayn do‘konlarda xizmat ko‘rsatish, ma’lumotlarni topish va foydalanuvchilarga yordam berishda keng qo‘llanilmoqda. NLP WSLEWMHE RYJY^PM XEHUMUSXGLMPEV ZE OSQTERM]EPEV LEQ FYXYR NMLEXPEVMRM VMZSNPERXMVMWL ZE yangiliklarni ko‘rsatish bilan shug‘ullanmoqda. Ushbu soha, kiber xavfsizlik, tibbiyot, ta’lim, avtomatizatsiya va boshqa sohalar uchun e’tiboringizniNEPFIXYZGLM]YUSVMTSXIRWMEPKEIKE %HEFM]SXPEV S. A. Majali, “The impact of empowering people with special needs from information and communication technology,” Arab Journal of Disability and Talent 7GMIRGIWZSPRS 161SVVMW%>SP]Smi, C. Yao, S. Bahram, J. P. Bigham, and S. K. Kane, “With most of it being pictures now, I rarely use it: Understanding Twitter’s evolving accessibility to blind users,” in Proc. the 2016 CHI Conference on Human Factors in Computing Systems, 7ER.SWI'EPMJSVRME97% ' 1SVVMWSR ) 'YXVIPP % (LEVIWL[EV / (SLIVX] % 8LMIQI ERH % 7 8E]PSV “Imagining artificial intelligence applications with people with visual disabilities using tactile ideation,” in Proc. the 19th International ACM SIGACCESS 'SRJIVIRGISR'SQTYXIVWERH %GGIWWMFMPMX]&EPXMQSVI97% P. Shneha, P. Reddy, and V. M. Megala, “Artificial intelligence for vision impaired people,” International Journal of Latest Trends in Engineering and Technology, pp. 031– 0(IRK “Artificial intelligence in the rising wave of deep learning: the historical path and future outlook,” IEEE Signal Processing Magazine, vol. 35, no. 1, pp. 180– 25

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil O‘ZBEK TILIDAGI MATNLARNI TAHLIL QILISH VA ELEMENTAR BIRLIKL%6+%%.6%8-7, %0+36-81- &E\XM]SV%OQYVEHSZ “University of Management and Future Technologies” universiteti kafedra mudiri FYEOQYVEHSZ$KQEMPGSQ %RRSXEXWM]E%\FSVSX OSQQYRMOEXWM]E XI\RSPSKM]EPEVMRMRK VMZSNPERMWLM FMPER FMV qatorda ma’lumotlarni elektron matn ko‘rinishida saqlash, ishlov berish va uzatishni amalga oshiruvchi vositalarga bo‘lgan talab ham ortib bormoqda. Ushbu maqolada o‘zbek tilidagi IPIOXVSRQEXRPEVRMWXVYOXYVENMLEtidan tahlil qilish va guruhlash masalalari ko‘rib chiqilgan. )PIOXVSRQEXRRMXEVOMFM]FMVPMOPEVKEENVEXMWLEPKSVMXQMMWLPEFGLMUMPKERZEXEZWMJPERKER Kalit so‘zlar:elektron matn, o‘zbek tili, algoritm, abzats, gap, elementar birlik. /MVMWL /SQT]YXIV PMRKZMWXMOEWM '0 'SQTYXIV 0MRKYMWXMGW ]SOM /SQT ]YXIVPM 8MPWLYRSWPMO QEXRZEXMPRMRKEZXSQEXPEWLXMVMPKERXELPMPXYWLYRMWLXEVNMQEZEFSWLUEZE^MJEPEVRMFENEVMWLKE EWSWPERKERXEVQSU HEWXYVPEWL ZE XI\RSPSKM]EPEVHERMFSVEX QYPXMHMWMTPMREV WSLE &YWSLE QEXRZEXMPRMQE PYQSXPEVRMUE]XEMWLPEWLXELPMPUMPMWLZEEZXSQEXPEWLXMVMWLYGLYRQEXIQEXMO MRJSVQEXMOE ZE XMPWLYRSWPMORM FMVPEWLXMVEHM /SQT]YXIV PMRKYMWXMOEWM QE PYQSXPEV XELPMPM matematika va tilshunoslikning birlashtirilgan multidisiplinar sohasidir va ko‘p turdagi ZE^MJEPEVRM FENEVMWLHE MWLPEXMPEHM 7LYRMRKHIO ^EQSREZM] 204 2EXYVEP 0ERKYEKI 4VSGIWWMRK XEFMM] XMPRM UE]XE MWLPEWL XI\RSPSKM]EPEVM LEQ OSQT]YXIV PMRKZMWXMOEWMRMRK ko‘plab modellarni o‘z ichiga oladi. Bu modellar, matnni tahlil qilish, tarjima qilish, dialog tizimi, mazmuni tahlil qilish va boshqa ko‘plab vazifalarni bajarish uchun ishlatiladi. O‘zbek adabiy til me’yorlariga to‘liq mos keluvchi lMRKZMWXMO ]IGLMQPEVRM MWLPEF chiqishda matnga dastlabki ishlov berish jarayonini to‘g‘ri tashkil etish eng muhim ZE^MJEPEVHER FMVM LMWSFPEREHM 7LYRMRK YGLYR QEXRKE HEWXPEFOM MWLPSZ FIVMWLRM EQEPKE oshiruvchi dasturiy ta’minot elektron matn strukturasini vE WIQERXMO XEWLOMP IXYZGLMPEVMRM xususiyatlariga ko‘ra tahlil qilish va guruhlashni amalga oshiradi. %WSWM]UMWQ /MVYZGLMQEXRRMXELPMPUMPMWLHEWXPEFYRMRKPSXMREPMJFSWMHE]S^MPKERPMKMRMXIOWLMVMWLHER boshlanadi. Tizim faqat lotin alifbosida yozilgan o‘zbek tilidagi matnlar uchun mo‘ljallanganligi sababli, lotin alifbosi elementlari kuzatilmagan matnlar uchun jaraySR EQEPKESWLMVMPQE]HM.EVE]SRRMERMUZEWMJEXPMXEWLOMPIXMWLYGLYRQEXRXEVOMFMZEWXVYOXYVEWM o‘rganiladi, ya’ni tarkibida sarlavhalar, xatboshilar soni, gaplar va elementar birliklar soni ERMUPEREHM?A -WLPEFGLMUMPKERQEXRRMXELPMPUMPMWLZEFMVPMOPEVKEENVEXMWLHEWXYVM]SVHEQMHEQEXRRM xatboshilar bo‘yicha tahrirlash amalga oshiriladi. Ushbu dasturning blok sxema ko‘rinishidagi ifodasi 1VEWQHEOIPXMVMPKER 26

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil Boshlanishi Param: S – sahifalar soni, N=0; i=1; j=1; ... S>0 Yoʻq Sahifa mavjud emas Yoʻq Matn mavjud emas Ha B(j)> 0 Ha X(i)> 0 Yoʻq Xatboshi mavjud emas Ha pointer=P(j) B(j) tahrirlash Ha pointer=Enter Yoʻq j++ n(i)=j; N=N+n(i); i++; Tugashi VEWQ)PIOXVSRQEXRRMXELPMPUMPMWLZEFMVPMOPEVRMENVEXMWLEPKSVMXQM FY ]IVHE < M – \EXFSWLMPEV R M – \EXFSWLMHE QEZNYH FMVPMOPEV WSRM 2NEQMFMVPMOPEVWSRM4 N –TVSFIPPEV& N –FMVPMOPEVRMMJSHEPE]HM /IPXMVMPKER VEWQHEKM FPSOsxemadan ko‘rish mumkinki, matnga dastlabki ishlov berish NEVE]SRM JE]PRMRK FMVMRGLM WELMJEWMHER FSWLPEREHM .EVE]SR FENEVMPMWL OIXQEOIXPMKMRM UY]MHEKMGLEXEZWMJPEWLQYQOMR - dastlab, matnni tahrirlash uchun zarur bo‘lgan parametrlar belgilanadi va e’lon UMPMREHM - OI]MRKMUEHEQHEJE]PXEVOMFMHEWELMJEPEVQEZNYHPMKMXIOWLMVMPEHM - REZFEXHEKMFSWUMGLHENSVM]WELMJEHEQEXRIPIQIRXPEVMQEZNYHPMKMXIOWLMVMPEHM - REZFEXHEKMFSWUMGLHENSVM]WELMJEHE\EXFSWLMQEZNYHPMKMXIOWLMVMPEHM - ko‘rsatkich (pointer) o‘zidan keyin turgERIRKFMVMRGLMFMVPMORMENVEXEHM Yuqorida aytib o‘tilganidek, “birlik” atamasi shartli ravishda belgilab olingan va u MWXEPKERQEXRIPIQIRXM]SOMIPIQIRXPEVOIXQEketligi bo‘lishi mumkin[2]. 1EXR FMVPMOPEVM XY^MPQEZM] SVEPMUPEV LMWSFPERKER \EXFSWLM FIPKMWM TVSFIP ZE IRXIV belgilari shuningdek, qo‘shimcha belgilar chiziqcha (tire), paralellik, proportsionallik va boshqalarning istalgan ikkitasining oralig‘ida joylashgan matn elementlari qatori deyish mumkin. O‘z navbatida bunday qo‘shimcha belgilar mustaUMP XEV^HE FMVPMO WEREPEHM?A Shunda ushbu bosqichda pointer joriy nuqtadan boshlab o‘zidan keyin turgan birinchi belgi yoki oraliqqacha bo‘lgan belgilar qatorini ajratib ko‘rsatadi va uni birlik sifatida keyingi FSWUMGLKEY^EXEHM 27

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil - REZFEXHEKMFSWUMGLHEUEFYPUMPMRKER& M FMVPMOXELVMVPEREHM REZFEXHEKMFSWUMGLHETSMRXIVRMRK)RXIVFIPKMWMKEXIRKPMKMXIOWLMVMPEHM - so‘nggi bosqichda statistik ma’lumotlar saqlanadi va keying xatboshiga o‘tish amalga oshiriladi; Matnni xatboshilarga bo‘lib tahrirlovchi algoritmning ushbu so‘nggi FSWUMGLMHEJEUEXFMXXE\EXFSWLMKEMWLPSZFIVMPEHM%PKSVMXQRMWMOPMOXEV^HEXEOVSVPEWLSVUEPM JE]PHEQEZNYHFEVGLE\EXFSWLMPEVKEMWLPSZFIVMWLQYQOMR?A &MXXEWEXVFMVRIGLXEFMVPMOPEVOIXQEOIXPMKMHERXEWLOMPXSTEHM7LYRHEFMXXEEF^EXWHEKM NEQMFMVPMOPEV & WSRMRMUY]MHEKMifoda orqali aniqlash mumkin bo‘ladi: 𝑃𝑃𝑙𝑙 = ∑𝑛𝑛𝑖𝑖=1 𝐵𝐵𝑙𝑙𝑙𝑙 FYRHE4P–PEF^EXWHEQEZNYHFMVPMOPEVWSRMRWEXVPEVWSRM 7LYRHER JS]HEPERMF UY]MHE OIPXMVMPKER JSVQYPE EWSWMHE QEXR XEVOMFMHEKM NEQM birliklar sonini aniqlash mumkin bo‘ladi. 𝑃𝑃𝑗𝑗𝑗𝑗𝑗𝑗𝑗𝑗 = ∑𝑚𝑚 𝑖𝑖=1 𝑃𝑃𝑙𝑙 FYRHE4NEQM–QEXRXEVOMFMHEQEZNYHNEQMFMVPMOPEVWSRMQEF^EXWPEVWSRM <YHHM WLYRHE] USMHE EWSWMHE JE]P XEVOMFMHEKM FEVGLE FMVPMOPEV WSRMRM ERMUPEWL MQOSRM]EXMQEZNYH <YPSWE Katta hajmga ega bo‘lgan elektron matnli fayl tarkbidagi sahifalarning va ularda mavjud birliklarning ko‘pligi hisobga olinsa, bunday matnlarni tahrirlash algoritmlarining ishlash jarayonini kichik tarkibiy qismlar bo‘yicha amalga oshirisL QEUWEHKE QYZSJMU bo‘ladi. Bunday yondashuvga ko‘ra, ya’ni matnning bir bo‘lagini tahrirlab bo‘lgach keying bo‘lagiga o‘tish orqali ko‘rib chiqilgan qismini keyingi ishlov berish bosqichiga o‘tkazish MQOSRM]EXM ]EVEXMPEHM )PIOXVSR QEXR FMPER MWLPSZGLM ^EQSREZM] VIEP ZEUX XM^MQPEVMHE FY \YWYWM]EXE]RMUWEQYLMQELEQM]EXKEIKELMWSFPEREHM %HEFM]SXPEV %OQYVEHSZ&/LEQHEQSZ9)PSZ(N7YPXERSZ(N2EV^YPPE]IZ-3VKERM^EXMSR SJMRMXMEPXI\XTVSGIWWMRKMRXLI9^FIOPERKYEKIW]RXLIWM^IV-RXIVREXMSREP'SRJIVIRGISR -RJSVQEXMSR 7GMIRGI ERH 'SQQYRMGEXMSRW 8IGLRSPSKMIW -'-7'8 2SZIQFIV 8EWLOIRX–T &VEYRWGL[IMPIV 2 &YGLLSP^ 7 %YXSQEXMG WIRXIRGI WIPIGXMSR JVSQ WTIIGL GSVTSVE MRGPYHMRK HMZIVWI WTIIGL JSV MQTVSZIH ,11887 W]RXLIWMW UYEPMX] -28)674))',%YKYWX*PSVIRGI-XEP]4 Боярский К. К., Введение в компьютерную лингвистику // Учебное пособие, СПб: НИУ ИТМО, 2013. –72 с Цитульский А. М., Иванников А. В., Рогол И.С. Интеллектульный анализ текста // StudNet2020. №6. С. 476 28

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil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

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil *MKYVI7]WXIQ%VGLMXIGXYVISJ9^%WWMWXERX 8LIW]WXIQ[EWXVEMRIHYWMRKXLI9^FIO&ERO7TIIGL'SVTYWEGSQTVILIRWMZI HEXEWIXGSRXEMRMRKXLSYWERHWSJLSYVWSJGYWXSQIVWIVZMGIGEPPWMR9^FIO(EXE TVITVSGIWWMRKMRZSPZIHRSMWIVIHYGXMSRRSVQEPM^EXMSRERHXLII\XVEGXMSRSJ1IP *VIUYIRG]'ITWXVEP'SIJJMGMIRXW 1*''W XSWIVZIEWMRTYXJIEXYVIWJSVXLIRIYVEPRIX[SVO 8LI622FEWIHQSHIPW[IVIXVEMRIHSRXLITVITVSGIWWIHHEXEWIX[MXL L]TIVTEVEQIXIVXYRMRKGSRHYGXIHXSSTXMQM^ITIVJSVQERGI:EPMHEXMSR[EWTIVJSVQIH YWMRKEWITEVEXIWIXSJHEXEXSIRWYVIXLIQSHIP WKIRIVEPM^EFMPMX]?A 6IWYPXW 9^%WWMWXERX EGLMIZIH E WTIIGL VIGSKRMXMSR EGGYVEG] SJ WYVTEWWMRK FIRGLQEVOWWIXF]I\MWXMRKW]WXIQWMRSXLIVPERKYEKIW8LMWLMKLEGGYVEG]VEXIMWTMZSXEP JSVYRHIVWXERHMRKGYWXSQIVUYIVMIWEGGYVEXIP]ERHTVSZMHMRKVIPIZERXVIWTSRWIW 30

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil (YVMRK XLI I\TIVMQIRXW XLI (IIT 7TIIGL QSHIP HIQSRWXVEXIH WYTIVMSV TIVJSVQERGIMRXIVQWSJ;SVH)VVSV6EXI ;)6 ERH'LEVEGXIV)VVSV6EXI ')6 3REXIWX WIXGSQTVMWMRKWEQTPIWXLI(IIT7TIIGLQSHIPEGLMIZIHE;)6SJ ERHE ')6SJ MRHMGEXMRKMXWIJJIGXMZIRIWWMREGGYVEXIP]TVSGIWWMRKERHXVERWGVMFMRKWTIIGL 8EFPI'SQTEVMWSRSJ7TIIGL6IGSKRMXMSR%GGYVEG] 1SHIP )) &0781 (22'8' )) 'SRJSVQIV (IIT 7TIIGL 01 %2 74 7% :EPMH 8IWX ')6 ;)6 ')6 ;)6 ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ 8LI887GSQTSRIRX[EWVEXIHLMKLP]JSVREXYVEPRIWWERHMRXIPPMKMFMPMX]MREWYVZI] GSRHYGXIH [MXL REXMZI 9^FIO WTIEOIVW MRHMGEXMRK 9^%WWMWXERX W GETEFMPMX] XS KIRIVEXI VIWTSRWIWXLEXEVIFSXLGPIEVERHIRKEKMRK (MWGYWWMSR 8LI MRXIKVEXMSR SJ 9^%WWMWXERX MR GEPP GIRXIVW MW ERXMGMTEXIH XS RSX SRP] MQTVSZI GYWXSQIV WEXMWJEGXMSR XLVSYKL IJJMGMIRX ERH EGGYVEXI UYIV] LERHPMRK FYX EPWS VIHYGI STIVEXMSREPGSWXWF]EYXSQEXMRKVSYXMRIMRXIVEGXMSRW*YXYVI[SVO[MPPJSGYWSRI\TERHMRK 31

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil UzAssistant’s domain of knowledge and exploring its application in other industries. 'SRGPYWMSR 9^%WWMWXERXVITVIWIRXWEWMKRMJMGERXEHZERGIQIRXMRXLIJMIPHSJ%-HVMZIRGYWXSQIV WIVZMGIWTIGMJMGEPP]EHHVIWWMRKXLIRIIHWSJXLI9^FIOWTIEOMRKTSTYPEXMSR-XWWYGGIWWJYP HITPS]QIRX GSYPH WIVZI EW E QSHIP JSV HIZIPSTMRK WMQMPEV XIGLRSPSKMIW JSV SXLIV YRHIVVITVIWIRXIHPERKYEKIWTVSQSXMRKMRGPYWMZMX]ERHEGGIWWMFMPMX]MRHMKMXEPWIVZMGIW 6IJIVIRGIW +Y^QER%0 :SMGIWMRERHSJXLIQEGLMRI7SYVGISVMIRXEXMSRXS[EVH QSFMPIZMVXYEPEWWMWXERXW'SQTYXIVWMR,YQER&ILEZMSV–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

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil )7SRK*/7SSRKERH,G. Kang, “Effective Spectral and Excitation Modeling 8IGLRMUYIW JSV 0781622&EWIH 7TIIGL 7ynthesis Systems,” IEEE/ACM Trans. Audio, 7TIIGLERH0ERK4VSGIWWZSPRSTT– 33

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil )2,%2')((-%+237-73*'%880)(-7)%7)797-2+*9>>=03+-'%0+36-8,17 (MPQYVSH8YVMQSZ (ITEVXQIRXSJ-8'SRZIVKIRGI)RKMRIIVMRK+EGLSR9RMZIVWMX]7YNISRK+Y7ISRKREQ7M +]ISRKKM(S6ITYFPMGSJ/SVIE HMPQYVSH$KEGLSREGOV %FWXVEGX 'EXXPI MPPRIWWIW GER KVIEXP] EJJIGX FSXL ERMQEP LIEPXL ERH XLI IGSRSQMG WXEFMPMX]SJJEVQIVW4VSQTXERHTVIGMWIHMEKRSWMWMWGVYGMEPJSVIJJIGXMZIQEREKIQIRXERH XVIEXQIRXSJXLIWIHMWIEWIW8LMWWXYH]I\TPSVIWXLIHIZIPSTQIRXSJHMEKRSWXMGQSHIPWERH algorithms for cattle diseases using Sugeno’s fuzzy inference system. It includes an EREP]XMGEP VIZMI[ SJ QEXLIQEXMGEP QIXLSHW JSV ERMQEP HMWIEWI HMEKRSWMW ERH WSJX GSQTYXMRK ETTVSEGLIW JSV XEGOPMRK GPEWWMJMGEXMSR GLEPPIRKIW 8LI WXYH] TVSTSWIW ER EPKSVMXLQ XS GVIEXI E ORS[PIHKIFEWI JVSQ XLIGPMRMGEP WMKRW SJ HMWIEWIW IRLERGMRK XLI VIPMEFMPMX] SJ MRJSVQEXMZI JIEXYVIW 9XMPM^MRK XLMW EPKSVMXLQ E WSJX[EVI TVSKVEQ [EW HIZIPSTIHXSHMEKRSWIGEXXPIHMWIEWIW%GSQTYXEXMSREPI\TIVMQIRX[EWGSRHYGXIHERHMXW VIWYPXW RS[ WIVZI EW EHHMXMSREP HIGMWMSRQEOMRK XSSPW JSV HMEKRSWMRK HMWIEWIW MR GEXXPI 9WMRKXLITVSKVEQE7YKIRSJY^^]PSKMGQSHIP[EWGSRWXVYGXIHERHMXWVIWYPXW EHIUYEG] EREP]^IH 8LI WXYH] EPWS IZEPYEXIW XLI TIVJSVQERGI SJ XLMW QSHIP F] GSQTEVMRK MX [MXL I\MWXMRK EPKSVMXLQW ERH EHHVIWWIW ZEVMSYW GPEWWMJMGEXMSR ERH IZEPYEXMSR GLEPPIRKIW 8LI SYXGSQIWJEGMPMXEXIUYMGOHMEKRSWMWERHXMQIP]MRXIVZIRXMSRVIHYGMRKHEXEEREP]WMWXMQIERH improving the diagnostic process’s efficiency. The scientific innovation of this research lies MRXLIHIZIPSTQIRXSJEORS[PIHKIFEWIGSRWXVYGXMSREPKSVMXLQERHIRLERGIQIRXWXSXLI 7YKIRS JY^^] PSKMG QSHIP JSV GEXXPI HMWIEWI HMEKRSWMW 8LI JMRHMRKW LEZI WMKRMJMGERX MQTPMGEXMSRW JSV ZIXIVMREV] QIHMGMRI TEVXMGYPEVP] MR XLI HMEKRSWMW SJ GEXXPI HMWIEWIW ERH WYTTSVXMRKHIGMWMSRQEOMRKMRMRXIPPMKIRXW]WXIQW /I][SVHWSWXISH]WXVSTL] WIGSRHEV] WXISH]WXVSTL] L]TSQMGVSWIPIQIRXSWMWHIGMWMSRQEOMRKI\TIVXW]WXIQWJY^^]WIXW OIXSWMW -RXVSHYGXMSR (MEKRSWMRKGEXXPIHMWIEWIWTVIWIRXWEWMKRMJMGERXGLEPPIRKIHYIXSXLISZIVPETTMRK W]QTXSQWEQSRKZEVMSYWGSRHMXMSRW'YVVIRXP]XLIMRXIKVEXMSRSJEVXMJMGMEPMRXIPPMKIRGI %- [MXL QEXLIQEXMGEP ETTVSEGLIW YXMPM^MRK JY^^] WIXW MW TVSZMRK GVMXMGEP JSV XLI EGGYVEXI HMEKRSWMWERHTVIHMGXMSRSJERMQEPHMWIEWIW6IWIEVGLLEWWLS[RTVSQMWMRKVIWYPXWMRXLI HIZIPSTQIRXSJGSQTYXIVFEWIHHMEKRSWXMGERHTVSKRSWXMGW]WXIQWIRLERGMRKXLIUYEPMX] SJXVIEXQIRXWXLVSYKLIEVP]HIXIGXMSRSJHMWIEWIX]TIWERHGEYWIWERHIREFPMRKXEVKIXIH MRXIVZIRXMSRW ,S[IZIV GSRXMRYEP MQTVSZIQIRXW XS XLIWI W]WXIQW EVI RIGIWWEV] XS JEGMPMXEXIXLIIEVP]HMEKRSWMWSJERMQEPHMWIEWIWIJJIGXMZIP] 3RIWYGLHMWIEWISWXISH]WXVSTL]MRGEXXPIIRGSQTEWWIWEVERKISJQIXEFSPMGFSRI HMWIEWIW QEVOIH F] EFRSVQEP FSRI KVS[XL ERH QMRIVEPM^EXMSR 8LMW GSRHMXMSR GER WXIQ JVSQ WIZIVEP JEGXSVW MRGPYHMRK QMRIVEP MQFEPERGIW LSVQSREP HMWSVHIVW ERH KIRIXMG TVIHMWTSWMXMSRW 'SQQSR W]QTXSQW SFWIVZIH MR EJJIGXIH GEXXPI MRGPYHI PEQIRIWW WXMJJRIWWERHEVIHYGXMSRMRQMPOTVSHYGXMSR %RSXLIV TVIZEPIRX QIXEFSPMG HMWSVHIV MW OIXSWMW SV OIXSXMG L]TSKP]GIQME [LMGL EVMWIW[LIRGEXXPIQIXEFSPM^IJEXWMRWXIEHSJGEVFSL]HVEXIWEWXLITVMQEV]IRIVK]WSYVGI 34

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil 8LMWWLMJXGERVIWYPXJVSQLMKLJEXHMIXWWXVIWWSVLIMKLXIRIHIRIVK]HIQERHW7]QTXSQW X]TMGEPP]MRGPYHIEHIGVIEWIMRETTIXMXI[IMKLXPSWWERHVIHYGIHQMPOTVSHYGXMSR 1MGVSIPIQIRXSWMWEPWSORS[REWXVEGIQMRIVEPHIJMGMIRG]SGGYVW[LIRGEXXPIHMIXW PEGO IWWIRXMEP XVEGI IPIQIRXW PMOI GSTTIV ^MRG WIPIRMYQ ERH MSHMRI 8LMW HIJMGMIRG] GER XVMKKIVEZEVMIX]SJLIEPXLMWWYIWMRGPYHMRKMQQYRIH]WJYRGXMSRVITVSHYGXMZIJEMPYVIWERH TSSV KVS[XL %JJIGXIH GEXXPI SJXIR I\LMFMX W]QTXSQW WYGL EW ERIQME HIXIVMSVEXIH GSEX UYEPMX]ERHHIGVIEWIHQMPOSYXTYX 1IXLSHW 8LI QIXLSHSPSK] MRZSPZIH HIZIPSTMRK E JY^^] PSKMGbased system using Sugeno’s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

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil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

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil 2)<8–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

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil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ls, evaluating its performance with the “EdgeIIoTset” dataset [A STXMQM^MRK MX JSV VIWSYVGI IJJMGMIRG] ERH FIRGLQEVOMRK MX EKEMRWX I\MWXMRK WSPYXMSRW ;I IZEPYEXIXLIensemble model’s efficacy in enhancing detection accuracy, its performance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

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil YWIWGSRZSPYXMSREPJMPXIVWXLEXWPMHIEGVSWWXLIMRTYXHEXEXSMHIRXMJ]GVYGMEPJIEXYVIWWYGLEW WTIGMJMGTEGOIXWM^IWSVYRYWYEPTVSXSGSPFILEZMSVXLEXGSYPHWMKRMJ]ERMRXVYWMSREXXIQTX *SPPS[MRKXLIWTEXMEPEREP]WMWXLIXIQTSVEPGLEVEGXIVMWXMGWSJXLIHEXEEVIHIGMTLIVIH F] XLI 0781 ERH +69 PE]IVW 0781W EVI EHITX EX VIGSKRM^MRK PSRKXIVQ HITIRHIRGMIW TVIWIVZMRKORS[PIHKISJIZIRXWXLEXSGGYVVIHQER]WXITWFEGOMRXLIWIUYIRGI[LMGLMW IWWIRXMEP[LIREXXEGOWGSQTVMWIEWIVMIWSJHMWGVIIXFYXVIPEXIHEGXMSRW+69WGSQTPIQIRX XLMWF]JSGYWMRKSRQSVIVIGIRXMRJSVQEXMSREPPS[MRKXLIQSHIPXSEHETXVETMHP]XSXLIQSWX GYVVIRXHEXEMRTYXWERHIRLERGMRKMXWEFMPMX]XSHIXIGXERSQEPMIWMRVIEPXMQIXVEJJMGJPS[ 8LITVSTSWIHQSHIPFIKMRW[MXLERMRTYXPE]IVHIWMKRIHXSVIGIMZIEZIGXSVM^IHJSVQ SJ RIX[SVO XVEJJMG HEXE 8LI MRTYX WLETI MW XEMPSVIH XS XLI HMQIRWMSRW SJ XLI JIEXYVI WIX I\XVEGXIHJVSQXLIRIX[SVOTEGOIXW8LIHEXEYRHIVKSEWIVMIWSJXVERWJSVQEXMSRWXLVSYKL X[S'SRZ(PE]IVWIEGLJSPPS[IHF]E1E\4SSPMRK(PE]IVXSVIHYGIHMQIRWMSREPMX]ERH IQTLEWM^IXLIQSWXWEPMIRXJIEXYVIW 8LI WIUYIRXMEP EWTIGX SJ XLI HEXE MW XLIR TVSGIWWIH XLVSYKL E L]FVMH 0781+69 EVVERKIQIRXEWMRKPI0781PE]IV[MXLVIXYVRWIUYIRGIWWIXXSXVYIJIIHWMRXSE+69PE]IV GVIEXMRKEHIITWIUYIRXMEPQSHIPGETEFPISJLERHPMRKGSQTPI\XMQIHITIRHIRXTEXXIVRW 8LMWGSQFMREXMSRGETXYVIWEGSQTVILIRWMZIXIQTSVEPTVSJMPISJXVEJJMGHEXEIRGSQTEWWMRK FSXLWLSVXXIVQJPYGXYEXMSRWERHPSRKXIVQXVIRHWMRHMGEXMZISJMRXVYWMZIFILEZMSV 8SJMREPM^IXLIGPEWWMJMGEXMSRXLIQSHIPMWJPEXXIRIHERHTEWWIHXLVSYKLEHIRWIPE]IV [MXL 6I09 EGXMZEXMSR MRXVSHYGMRK RSRPMRIEVMX] ERH EMHMRK MR PIEVRMRK GSQTPI\ TEXXIVRW % HVSTSYXPE]IVMWMRGPYHIHXSQMXMKEXISZIVJMXXMRKJSPPS[IHF]EWSJXQE\EGXMZEXMSRPE]IVXLEX GPEWWMJMIWXLIXVEJJMGHEXEMRXSTVIHIJMRIHGEXIKSVMIWVERKMRKJVSQRSVQEPXSZEVMSYWX]TIW SJEXXEGOZIGXSVW 8LIQSHIPMWGSQTMPIH[MXLXLI%HEQSTXMQM^IV[LMGLMWORS[RJSVMXWIJJMGMIRG]MR LERHPMRK PEVKI HEXEWIXW ERH MXW EHETXMZI PIEVRMRK VEXI GETEFMPMXMIW 8LI PSWW JYRGXMSR IQTPS]IHMWWTEVWIGEXIKSVMGEPGVSWWIRXVST][LMGLMWTEVXMGYPEVP]WYMXIHJSVGPEWWMJMGEXMSR TVSFPIQWMR[LMGLXLIGPEWWIWEVIQYXYEPP]I\GPYWMZI 8LMWMRRSZEXMZI2-(7JVEQI[SVOMWHIWMKRIHXSFIEGSVRIVWXSRIMRHIJIRWIEKEMRWX G]FIVXLVIEXWMR-S8FEWIH):'79WMRKE(0ETTVSEGLXLEXMRXIKVEXIW'22PE]IVWJSVJIEXYVI I\XVEGXMSR[MXL0781ERH+69PE]IVWJSVXIQTSVEPHEXEEREP]WMWXLITVSTSWIHQSHIPRSX SRP]MHIRXMJMIWI\MWXMRKXLVIEXTEXXIVRWFYXEPWSEHETXWXSIQIVKMRKERSQEPMIW-XWXERHWEW E XIWXEQIRX XS XLI TSXIRXMEP SJ %- MR JSVXMJ]MRK XLI G]FIVWIGYVMX] QIEWYVIW SJ GVMXMGEP MRJVEWXVYGXYVI[MXLMRXLIWQEVXGMX]IGSW]WXIQ )\TIVMQIRXEP6IWYPXWERH(MWGYWWMSR 8LIIWWIRGISJIQTMVMGEPZEPMHEXMSRPMIWMRXLIVMKSVSJI\TIVMQIRXEPEREP]WMW[LIVIMR XLISVIXMGEP QSHIPW GSRJVSRX XLI XIWX SJ TVEGXMGEP TIVJSVQERGI 8LMW WIGXMSR TVIWIRXW E HIXEMPIHI\TSWMXMSRSJXLII\TIVMQIRXEPVIWYPXWHIVMZIHJVSQXLIIZEPYEXMSRSJXLIIRWIQFPI QSHIP XEMPSVIH JSV MRXVYWMSR HIXIGXMSR [MXLMR XLI MRXVMGEXI JVEQI[SVO SJ -S8FEWIH ):'7 9WMRKEQIXLSHSPSKMGEPETTVSEGLXLIQSHIP[EWWYFNIGXIHXSZEVMSYWXIWXWVERKMRKJVSQ FMREV]XSQYPXMJEGIXIHQYPXMGPEWWGPEWWMJMGEXMSRW)EGLXIWX[EWQIXMGYPSYWP]HIWMKRIHXS probe the model’s predictive prowess across a spectrum of scenarios that mirror the LIXIVSKIRIMX]SJTSXIRXMEPWIGYVMX]FVIEGLIWMR-S8IRZMVSRQIRXW 39

Respublika ilmiy-amaliy konferensiyasi 24-25-aprel, 2024-yil &MREV] GPEWWMJMGEXMSR XVMEPW [IVI EMQIH EX HMWGIVRMRK XLI TVIWIRGI SV EFWIRGI SJ intrusion attempts, thus laying the groundwork for the model’s capability to distinguish FIX[IIRRSVQEPSTIVEXMSRWERHERSQEPMIW4VSKVIWWMRKXSQSVIKVERYPEVPIZIPWWM\GPEWW ERH JMJXIIRclass classification tests were orchestrated to evaluate the model’s ability to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