Earticle

본 논문에서는 지능적 계산법인 개미-군집 이론을 응용한 분산적 피어 선택을 통해 통신 대역폭, 데이터 처리 능력 및 저장 용량이 상이한 피어들로 구성된 P2P 오버레이 멀티케스트 네트워크를 효율적으로 구성할 수 있는 방안을 제안한다. 제안 기법은 피어의 용량뿐만 아니라 피어가 서비스하고 있는 자식 노드의 수 및 멀티케스트 소스와 피어 사이의 거리를 고려하여 부모 피어를 선택한다. 따라서 제안기법은 멀티케스트 소스와 피어 사이의 거리를 작게 유지한다는 측면에서 효율적인 네트워크 구성을 가능하게 한다. 또한 제안기법은 특정 서버가 참여 노드의 상태 정보를 이용하는 기존의 중앙집중적 방식에 비해 각 피어들의 로컬 정보를 이용하는 분산적 방식이므로, 참여 노드의 수에 따른 확장성이 우수하다. 모의실험을 통해 제안 기법은 소수의 대용량 피어가 다수의 소용량 피어를 지원함으로써 수천개의 피어가 오버레이 네트워크에 참여하더라도 오버레이 네트워크의 크기를 작게 유지할 수 있다는 것을 보였다.

In this paper, we propose a method that can construct efficiently a P2P overlay multicast network composed of many heterogeneous peers in communication bandwidth, processing power and a storage size by selecting a peer in a distributed fashion using an ant-colony theory that is one of the computational intelligence methods. The proposed method considers not only the capacity of a peer but also the number of children peers supported by the peer and the hop distance between a multicast source and the peer when selecting a parent peer of a newly joining node. Thus, an P2P multicast overlay network is constructed efficiently in that the distances between a multicast source and peers are maintained small. In addition, the proposed method works in a distributed fashion in that peers use their local information to find a parent node. Thus, compared to a centralized method where a centralized server maintains and controls the overlay construction process, the proposed method scales well. Through simulations, we show that, by making a few high capacity peers support a lot of low capacity peers, the proposed method can maintain the size of overlay network small even there are a few thousands of peers in the network.

All the imputation techniques proposed so far in literature for data imputation are offline techniques as they require a number of iterations to learn the characteristics of data during training and they also consume a lot of computational time. Hence, these techniques are not suitable for applications that require the imputation to be performed on demand and near real-time. The paper proposes a computational intelligence based architecture for online data imputation and extended versions of an existing offline data imputation method as well. The proposed online imputation technique has 2 stages. In stage 1, Evolving Clustering Method (ECM) is used to replace the missing values with cluster centers, as part of the local learning strategy. Stage 2 refines the resultant approximate values using a General Regression Neural Network (GRNN) as part of the global approximation strategy. We also propose extended versions of an existing offline imputation technique. The offline imputation techniques employ K-Means or K-Medoids and Multi Layer Perceptron (MLP)or GRNN in Stage-1and Stage-2respectively. Several experiments were conducted on 8benchmark datasets and 4 bank related datasets to assess the effectiveness of the proposed online and offline imputation techniques. In terms of Mean Absolute Percentage Error (MAPE), the results indicate that the difference between the proposed best offline imputation method viz., K-Medoids+GRNN and the proposed online imputation method viz., ECM+GRNN is statistically insignificant at a 1% level of significance. Consequently, the proposed online technique, being less expensive and faster, can be employed for imputation instead of the existing and proposed offline imputation techniques. This is the significant outcome of the study. Furthermore, GRNN in stage-2 uniformly reduced MAPE values in both offline and online imputation methods on all datasets.

인공지능 모델은 성능을 높이기 위해 층수와 채널 수를 계속 확장해 왔지만, 그 결과 계산량과 메모리 요구량이 폭증해 모바일 등의 엣 지 기기나 핸드폰과 같은 개인 장비에서 실시간 서비스가 어려워지고 있다. 이 문제를 해결하는 방법들에 대해 본 논문에서는 두 가지 핵심 전략으로 구분하여 소개하고자 한다. 첫째, 모델 구조 설계 중심 접근 방법은 깊이별-그룹 합성곱, 복합 스케일링 등등의 구조 탐 색을 통해 처음부터 연산 부담을 줄이는 방법을 소개한다. 둘째, 파라미터 변환 기반 접근 방법은 이미 학습된 모델을 대상으로 지식 증 류, 정수 양자화, 가지치기 등등을 적용해 파라미터와 연산을 크게 줄이는 방법을 소개한다. 현장실무에서는 경량 백본을 만든 뒤 양자 화와 증류로 정확도를 복구하는 파이프라인이 흔히 사용된다. 앞으로는 대형 멀티모달 모델과 친환경 인공지능시대에 대응하기 위해 아키텍처 탐색과 하드웨어, 소프트웨어의 통합 최적화가 필수 과제로 떠오를 전망이다.

Deep‑learning models have continually increased their layer depth and channel width to boost performance, but this expansion has caused an explosive growth in computation and memory demand, making real‑time service on edge devices such as smartphones and other personal hardware increasingly difficult. To tackle this problem, the present paper distinguishes and introduces two core strategies. The first strategy, an architecture‑centric design approach, reduces the computational burden from the outset by exploring structures such as depthwise‑group convolutions and compound scaling. The second strategy, a parameter‑transformation approach, targets already‑trained networks and sharply cuts parameters and operations by applying knowledge distillation, integer quantization, pruning, and similar techniques. In the field, a common pipeline first builds a lightweight backbone and then recovers accuracy through a combination of quantization and distillation. Looking forward, architecture search and full hardware–software co‑optimization are expected to become essential tasks in order to cope with large multimodal models and to meet the demands of an eco‑friendly era of artificial intelligence.

4차 산업혁명 시대에 세계와 우리나라는 미래 인재 양성을 위해 컴퓨팅 사고력(Computational Thinking)의 사고 과정을 제시하고, 교수학습에 반영하여 소프트웨어 교육을 수행하고 있다. 초등학교 컴퓨터 교육에서 인공 지능 교육의 필요성이 증가하면서 인공지능 교육을 통한 컴퓨팅 사고력 증진을 기르고자 하고 있다. 본 논문에 서는 인공지능 교육이 컴퓨팅 사고력 증진과 관계가 있음을 살펴본 후, 한 학기 동안 인공지능 교육을 수업 받 은 예비교원의 컴퓨팅 사고력 이해도를 분석하였다. 또한, 예비교원의 소프트웨어 교육 방법에 따라 컴퓨팅 사고 력 이해도에 영향을 미치는지 비교 분석하였다. 분석 결과 미래 핵심역량인 컴퓨팅 사고력을 인공지능 교육을 통해 향상시킬 수 있음을 알 수 있었다.

In the era of the 4th industrial revolution, the world and Korea are presenting the thinking process of computational thinking in order to cultivate future talents, and reflecting them in teaching and learning to conduct software education. As the necessity of artificial intelligence education increases in elementary school computer education, we are trying to cultivate the improvement of computational thinking through artificial intelligence education. In this paper, after examining the relationship between artificial intelligence education and the improvement of computational thinking, we analyzed the understanding of computational thinking of prospective teachers who took artificial intelligence education for one semester. In addition, it was compared and analyzed whether the software education method of prospective teachers affects the understanding of computing thinking ability. As a result of the analysis, it was found that computational thinking, a core competency in the future, can be improved through artificial intelligence education.

본 연구에서는 Computational Thinking기반의 인공지능교육을 위한 프레임워크와 인지적 학습환경 구성의 절 차를 구현하고자 하였으며, 추후 인공지능교육을 위한 교육과정 설계의 이론적 근거를 제시하고자 하였다. 연구 의 결과를 토대로 데이터수집 및 발견의 단계에서 추상화 과정을 통해 알고리즘과 문제해결의 모형을 선택하는 학습모형을 제시하였고 이를 자동화하여 평가하는 단계를 기반으로 문제해결 및 예측하는 과정을 수행함으로써 인공지능을 활용한 문제해결력을 기를 수 있는 Computational Thinking 기반 AI의 교수학습모형을 제시하였다. 인공지능교육에 대한 인지적 학습환경과 관련된 연구를 분석하여 Computational Thinking의 핵심 사고과정 중 하나인 추상화의 단계를 중심으로 절차를 구성하였으며, Agency(학습보조)에서 Modeling(인지적 구조화)으로의 전이를 토대로 학습구성의 단계를 제시하였다. 본 연구에서 제시한 인공지능교육의 프레임워크와 인지적 학습환 경 구성의 절차는 Computational Thinking을 기반으로 제시되었다는 점에서 특징을 갖고 있으며 추후 인공지능 기반 교수학습연구의 근간이 될 것으로 기대한다.

The purpose of this study is to design an instructional framework and cognitive learning environment for AI education based on computational thinking in order to ground the theoretical rationale for AI education. Based on the literature review, the learning model is proposed to select the algorithms and problem-solving models through the abstraction process at the stage of data collection and discovery. Meanwhile, the instructional model of AI education through computational thinking is suggested to enhance the problem-solving ability using the AI by performing the processes of problem-solving and prediction based on the stages of automating and evaluating the selected algorithms. By analyzing the research related to the cognitive learning environment for AI education, the instructional framework was composed mainly of abstraction which is the core thinking process of computational thinking through the transition from the stage of the agency to modeling. The instructional framework of AI education and the process of constructing the cognitive learning environment presented in this study are characterized in that they are based on computational thinking, and those are expected to be the basis of further research for the instructional design of AI education.

본 연구에서는 Computational Thinking 기반의 인공지능(AI)교육에 대한 학습자의 내재적 사고의 변화를 살펴보 기 위한 평가도구 개발의 기준과 프레임워크를 구성하여 제시하고자 하였다. 이를 위해 데이터수집을 위한 인지적 학습보조(Agency)의 단계, 수집된 데이터의 특징을 분해하여 데이터의 패턴을 인식하고 카테고리화 과정을 수행하 는 추상화(Abstracting)의 단계, 추상화과정을 수행한 정제된 데이터를 토대로 알고리즘을 구성하는 모델링 (Modeling)단계의 일련의 순차적 과정이 평가요소로 구성되었다. 또한 학습자의 인식, 학습, 행동, 결과에 대한 인지 적영역에 대한 평가가 구성되었으며, 학습자의 문제해결의 과정과 결과에 대하여 지식, 역량, 태도의 영역에 대하여 측정을 하게 됨으로써 AI교육에 대한 학습의 내재적인 인지영역의 변화와 결과에 대한 평가를 할 수 있도록 프레임 워크가 설계되었다. 연구의 결과는 교수학습의 맥락에 따른 개별화된 평가도구 개발에 대한 프레임워크를 구성하였 다는 점에서 의미가 있으며, 향후 AI교육의 다양한 영역에서 활용될 수 있는 기준으로서 활용될 수 있을 것이다.

The purpose of this study is to design the framework of evaluation on learner’s cognitive skill for artificial intelligence( AI) education through computational thinking. To design the rubric and framework for evaluating the change of leaner’s intrinsic thinking, the evaluation process was consisted of a sequential stage with a) agency that cognitive learning assistance for data collection, b) abstraction that recognizes the pattern of data and performs the categorization process by decomposing the characteristics of collected data, and c) modeling that constructing algorithms based on refined data through abstraction. The evaluating framework was designed for not only the cognitive domain of learners' perceptions, learning, behaviors, and outcomes but also the areas of knowledge, competencies, and attitudes about the problem-solving process and results of learners to evaluate the changes of inherent cognitive learning about AI education. The results of the research are meaningful in that the evaluating framework for AI education was developed for the development of individualized evaluation tools according to the context of teaching and learning, and it could be used as a standard in various areas of AI education in the future.

본 연구는 디지털 및 인공지능(AI) 교육의 중요성이 점차 부각되는 교육 환경 속에서, 중학교 영재 학생들을 위한 효과적인 교육 방안을 탐색하고자 수행되었다. 특히, 4차 산업혁명 시대에 요구되는 컴퓨팅 사고력(CT)과 AI 역량은 미래 인재 양성의 핵심 요소임에도 불구 하고, 이를 체계적으로 함양할 수 있는 교육 프로그램은 아직 부족한 실정이다. 본 연구는 피지컬 컴퓨팅 기반의 ‘디지털 새싹 캠프’를 설계·운영하고, 그 교육적 효과를 실증적으로 분석하는 데 목적을 두었다. 사전-사후 설문조사를 통해 수집된 데이터를 분석한 결과, CT는 평균 4.05에서 4.65로, AI 역량은 3.76에서 4.65로 각각 유의미하게 향상된 것으로 나타났다. 특히 팀 프로젝트와 실습 중심의 학습 활동은 학생들의 문제해결력과 창의성 증진에 긍정적인 영향을 미쳤다. 본 연구는 디지털 융합 교육의 실제 적용 가능성을 제시함 으로써, 미래 교육을 위한 실천적이고 통합적인 교수·학습 접근법의 필요성을 시사한다.

In response to the increasing emphasis on digital and artificial intelligence (AI) education, this study sought to explore effective educational interventions for gifted middle school students. As computational thinking (CT) and AI literacy have emerged as essential competencies in the context of the Fourth Industrial Revolution, there is a pressing need for structured programs that can foster these skills in a systematic and meaningful way. This study designed and implemented a physical computing-based initiative—the Digital Saessak Camp—and conducted an empirical evaluation of its educational impact. Pre- and post-program survey data indicated statistically significant improvements in both CT (from an average of 4.05 to 4.65) and AI competency (from 3.76 to 4.65). Notably, team-based projects and hands-on, experiential learning activities played a critical role in enhancing students’ problem-solving abilities and creative thinking. These findings highlight the practical value of integrated digital education and underscore the importance of adopting experiential, interdisciplinary teaching and learning approaches to prepare students for future societal and technological challenges.

인공지능은 우리의 삶에 점차 많은 부분을 차지하고 있으며, 발전하는 속도도 빨라지고 있다. 학생들의 컴퓨 팅 사고력을 인공지능이 학습하는 방법대로 길러주는 것을 ACT(AI based Computational Thinking)라고 한다. ACT 중 패턴 인식은 문제를 효율적으로 해결하기 위해 필수적인 요소이다. 패턴 분석은 패턴 인식 과정의 일 부로 볼 수 있다. 실제로 넷플릭스의 개인 맞춤 영화 추천, 반복된 증상을 분석하여 코로나 바이러스로 명명하 는 것 등이 모두 패턴 분석의 결과이다. 패턴인식을 포함한 ACT의 중요성이 부각되는 것에 반면, 유치원과 초 등학교 저학년을 대상으로 한 소프트웨어 교육은 국외에 비해 많이 부족한 실정이다. 따라서 본 연구에서는 유 치원 학생들을 대상으로 하여 패턴 분석을 통한 인공지능 기반 컴퓨팅 사고력 계발을 위한 교재를 설계하고 개 발하였다.

AI(Artificial intelligence) is gradually taking up a large part of our lives, and the pace of AI development is accelerating. It is called ACT that develop students' computational thinking in the way artificial intelligence learns. Among ACTs, pattern recognition is an essential factor in efficiently solving problems. Pattern analysis is part of the pattern recognition process. In fact, Netflix's personalized movie recommendation service and what it named Covid-19 after repeated symptoms are all the results of pattern analysis. While the importance of ACT, including pattern recognition, is highlighted, software education for kindergarten and elementary school lower grades is much insufficient compared to foreign countries. Therefore, this study aims to design and develop textbooks for the development of artificial intelligence-based computational thinking through pattern analysis for kindergarten students.

4차 산업혁명 시대의 영향에 따라 범교과 학습 주제 중심의 인공지능 융합 교육이 초등학생의 컴퓨팅 사고력 에 미치는 영향을 알아보고자 한다. 이를 위해, 연구집단 24명, 통제집단 25명의 초등학교 6학년 학생들을 대상 으로 6개월간 37차시의 교육을 실시하였으며 연구집단에는 본 연구에서 설계한 범교과 학습 주제 중심의 인공지 능 융합 교육을, 통제집단에는 기존의 프로그래밍 수업을 포함한 전통적인 교과 교육을 시행하였다. 분석 결과, 연구 집단과 통제 집단의 차이는 사후 결과에서 유의하였으며, 연구 집단의 경우 컴퓨팅 사고력의 측정 요소 중 에서 알고리즘 및 프로그래밍 영역과 데이터 및 자료구조 영역에서 모두 유의하였다. 반면, 통제 집단의 경우 사 후 검사 결과에서 데이터 및 자료구조 영역에서는 유의하지 않았다. 본 연구의 결과는 향후 초등교육의 현장에 서 범교과 학습 주제 중심의 인공지능 융합 교육의 개선 방안을 제시하기 위한 기초자료로 활용될 수 있다.

This study explores the influence of artificial intelligence(AI) convergence education, centered on cross-curricular learning topics, on the computational thinking skills of elementary school students. Over six months, 37 educational sessions were conducted with 24 students in the experimental group and 25 in the control group. The experimental group received AI convergence education, while the control group followed traditional subject education, including existing programming classes. Results indicated significant improvement in computational thinking skills in the experimental group, particularly in algorithms & programming( ALP) and data structures & representation(DSR) areas. These findings suggest that AI convergence education can effectively enhance computational thinking skills, providing valuable data for future educational strategies in elementary schools.

본 연구는 ‘초등학교에서 IB PYP 기반 인공지능 교육이 컴퓨팅 사고력에 미치는 영향’에 초점을 맞추었다. 이를 바탕으로 ADDIE 모형을 이용하여 초등학생을 대상으로 한 인공지능 교육 프로그램을 설계하였다. 이후 실생활과 연계한 인공지능 교육 프로그램을 개발하고, 해당 프로그램이 IB PYP 교육 방식과 부합하는지 IB PYP 전문가에 게 검증받았다. 학습자들은 개발된 활동지를 기반으로 팀 프로젝트를 수행하며 주체적인 문제 해결 능력을 키웠 다. 교육 프로그램 참여 학생들의 컴퓨팅 사고력 변화를 파악하기 위해 사전 및 사후 검사를 실시하였고, 본 교육 프로그램이 컴퓨팅 사고력 향상에 긍정적인 효과를 가져다 주었음을 확인하였다.

This study focused on the ‘Impact of IB PYP-based Artificial Intelligence Education on Computational Thinking Skills in Elementary Schools’. Based on this, an artificial intelligence education program targeting elementary students was designed using the ADDIE model. Subsequently, an AI education program integrated with real-life scenarios was developed and vetted for its adherence to the IB PYP teaching methodology by IB PYP experts. Students engaged in team projects using the devised activity sheets, fostering their proactive problem-solving abilities. Pre and post-tests were conducted to gauge the shift in students' computational thinking skills, and it was confirmed that the educational program had a positive effect on enhancing their computational thinking capabilities.

PGQ, a novel hybrid computational intelligence approach, in which Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and quantum computation are integrated, is proposed to solve the Vehicle Routing Problem (VRP). In PSO, a quantum approach called QUP is proposed to update the particles. GA operators are employed to improve population quality. The simulation results indicate that the PGQ algorithm is very effective and is better than simple PSO and GA as well as PSO and GA mixed algorithm.

In recent years improvement of new and effective medical domain applications has vital role in research. Computational Intelligence Systems (CIS) has profound influence in the enlargement of these effective medical field applications and tools. One of the prevalent diseases that world facing is heart disease. The Computational Intelligence Systems uses input clinical data from different knowledge resources throughout the world and applies this data on different computational intelligence tools that uses sophisticated algorithms. The sophisticated algorithms plays prominent role in the construction of medical clinical analysis tools. These tools may be used as an extra aid for the clinical diagnosis of the diseases for the doctors and clinicians. In this paper a novel method for the diagnosis of heart disease has been proposed using Genetic Algorithms. In this approach an effective association rules are inferred using Genetic Algorithm approach which uses tournament selection, crossover, mutation and new proposed fitness function. The Cleaveland data set is used for the experimentation. This data set is collected from the UCI machine learning repository experimental results are prominent when compared with some of the supervised learning techniques.

This paper examines the application of a support vector regression (SVR) approach to identifying relationships between land use characteristics and damages caused by natural hazards. Our empirical results show the outperformance of a SVR model over a multiple ordinary least squares (OLS) regression model in terms of the predictive performance. Nonlinear relationships between land use characteristics and damages are revealed by a SVR model.

Approaches to several recent issues in the operation of nuclear power plants using computational intelligence are discussed. These issues include 1) noise analysis techniques, 2) on-line monitoring and sensor validation, 3) regularization of ill-posed surveillance and diagnostic measurements, 4) transient identification, 5) artificial intelligence-based core monitoring and diagnostic system, 6) continuous efficiency improvement of nuclear power plants, and 7) autonomous anticipatory control and intelligent-agents. Several changes to the focus of Computational Intelligence in Nuclear Engineering have occurred in the past few years. With earlier activities focusing on the development of condition monitoring and diagnostic techniques for current nuclear power plants, recent activities have focused on the implementation of those methods and the development of methods for next generation plants and space reactors. These advanced techniques are expected to become increasingly important as current generation nuclear power plants have their licenses extended to 60 years and next generation reactors are being designed to operate for extended fuel cycles (up to 25 years), with less operator oversight, and especially for nuclear plants operating in severe environments such as space or ice-bound locations.

Nano drive control of five phase stepping motors is developed based on computational intelligence technology and it enables to drive into 5 million equiangular parts per revolution with keeping normal speed and torques. The experimental results of realizing high resolution/accuracy with low vibration and decreasing both heat loss and electric power consumption are mentioned.

This paper presents the rapid and accurate algorithm for fault discrimination in transmission lines. When faults occur in transmission lines, fault discrimination is very important. If high impedance faults occur in transmission lines, it cannot be detected by overcurrent relays. The method using current and voltage cannot discriminate high impedance fault. Because of this reason this paper uses voltage and zero sequence current, and the proposed algorithm uses fuzzy logic method. This algorithm uses voltage and zero sequence current per period in case of faults. Single line ground fault and three-phase fault can be detective using voltage. Two-line ground fault and line to line fault and high impedance can be detected using zero sequence current. To prove the performance of the algorithm, it test algorithm with signal obtained from ATPDraw simulation.

Corrosion inhibition performance of Ataluren (ATA) on X80 steel in oilfield acid wash solution was investigated using a combination of experimental and computational techniques. Corrosion rates were quantified using weight loss analysis and electrochemical methods. Surface morphology and protection mechanisms were examined using spectroscopic and microscopic tools. Quantum chemical calculations and molecular dynamics simulations were performed to evaluate solvation, adsorption behavior, and binding affinity of ATA molecules at the steel interface. Experimental results demonstrated significant reductions of corrosion rates across various ATA concentrations, achieving inhibition efficiencies of 96.2%, 95.6%, and 96.3% as determined by impedance, polarization and weight loss measurements, respectively, while Monte Carlo simulations supported an inhibition efficiency of 76.1%. Analysis of Fukui indices, Mulliken charge distributions and interaction energies in both gas and aqueous phases, along with EDAX data, indicated that corrosion inhibition was primarily driven by spontaneous exothermic chemisorption involving N and O functionalities in ATA interacting with Fe d-orbitals. This adsorption led to formation of a protective ATA monolayer that significantly reduced surface roughness, as confirmed by SEM. These findings establish ATA as a highly effective corrosion inhibitor for X80 steel under investigated conditions.

정보 혁명 시대를 맞이하여 전 세계적인 변화의 흐름 속에서 인공지능 융합 교육의 필요성이 더욱 대두되고 있다. 이에 본 논문에서는 인공지능을 융합한 피지컬 컴퓨팅 프로그래밍 교육 방법을 개발 및 적용하였다. 통제집단에는 인공지능을 융합하지 않은 피지컬 컴퓨팅 프로그래밍 교육을 실시하였으며, 실험집단에는 인공지능을 융합한 피지컬 컴퓨팅 프로그래밍 교육 방법을 개발하여 적용한 후 초등학생의 컴퓨팅 사고력에 미치는 영향을 분석하였다. 그 결과, 인공지능을 융합한 피지컬 컴퓨팅 프로그래밍 교육이 인공지능을 융합하지 않은 피지컬 컴퓨팅 프로그래밍 교육과 비교하여 초등학생의 컴퓨팅 사고력 신장에 더욱 긍정적인 효과를 나타내었음에 대한 통계적으로 유의미한 결과를 확인할 수 있었다.

In the era of the information revolution, the need for artificial intelligence convergence education is emerging in the trend of global change. Therefore, in this paper, a physical computing programming education method that combines artificial intelligence was developed and applied. The control group was provided with physical computing programming education that did not converge with artificial intelligence, and the experimental group developed and applied a physical computing programming education method that fused artificial intelligence to analyze the impact on elementary school students' computing thinking ability. As a result, it was confirmed that physical computing programming education fused with artificial intelligence had a more positive effect on enhancing elementary school students' computational thinking skills compared to physical computing programming education without artificial intelligence.

Pathology is the motor that drives healthcare to understand diseases. The way pathologists diagnose diseases, which involves manual observation of images under a microscope has been used for the last 150 years, it's time to change. This paper is specifically based on tumor detection using deep learning techniques. Pathologist examine the specimen slides from the specific portion of body (e-g liver, breast, prostate region) and then examine it under the microscope to identify the effected cells among all the normal cells. This process is time consuming and not sufficiently accurate. So, there is a need of a system that can detect tumor automatically in less time. Solution to this problem is computational pathology: an approach to examine tissue data obtained through whole slide imaging using modern image analysis algorithms and to analyze clinically relevant information from these data. Artificial Intelligence models like machine learning and deep learning are used at the molecular levels to generate diagnostic inferences and predictions; and presents this clinically actionable knowledge to pathologist through dynamic and integrated reports. Which enables physicians, laboratory personnel, and other health care system to make the best possible medical decisions. I will discuss the techniques for the automated tumor detection system within the new discipline of computational pathology, which will be useful for the future practice of pathology and, more broadly, medical practice in general.