Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-a...Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-aided diagnosis system is highly required.Ultrasound is an important examination technique for breast cancer diagnosis due to its low cost.Recently,many learning-based techniques have been introduced to classify breast cancer using breast ultrasound imaging dataset(BUSI)datasets;however,the manual handling is not an easy process and time consuming.The authors propose an EfficientNet-integrated ResNet deep network and XAI-based framework for accurately classifying breast cancer(malignant and benign).In the initial step,data augmentation is performed to increase the number of training samples.For this purpose,three-pixel flip mathematical equations are introduced:horizontal,vertical,and 90°.Later,two pretrained deep learning models were employed,skipped some layers,and fine-tuned.Both fine-tuned models are later trained using a deep transfer learning process and extracted features from the deeper layer.Explainable artificial intelligence-based analysed the performance of trained models.After that,a new feature selection technique is proposed based on the cuckoo search algorithm called cuckoo search controlled standard error mean.This technique selects the best features and fuses using a new parallel zeropadding maximum correlated coefficient features.In the end,the selection algorithm is applied again to the fused feature vector and classified using machine learning algorithms.The experimental process of the proposed framework is conducted on a publicly available BUSI and obtained 98.4%and 98%accuracy in two different experiments.Comparing the proposed framework is also conducted with recent techniques and shows improved accuracy.In addition,the proposed framework was executed less than the original deep learning models.展开更多
The bidirectional convergence of artificial intelligence and nanophotonics drives photonic technologies toward unprecedented levels of intelligence and efficiency,fundamentally reshaping their design paradigms and app...The bidirectional convergence of artificial intelligence and nanophotonics drives photonic technologies toward unprecedented levels of intelligence and efficiency,fundamentally reshaping their design paradigms and application boundaries.With its powerful data-driven and nonlinear optimization capabilities,artificial intelligence has become a powerful tool for optical design,enabling the inverse design of nanophotonics devices while accelerating the forward computation of electromagnetic responses.Conversely,nanophotonics provides a wave-based computational platform,giving rise to novel optical neural networks that achieve high-speed parallel computing and efficient information processing.This paper reviews the latest progress in the bidirectional field of artificial intelligence and nanophotonics,analyzes the basic principles of various applications from a universal perspective,comprehensively evaluates the advantages and limitations of different research methods,and makes a forwardlooking outlook on the bidirectional integration of artificial intelligence and nanophotonics,focusing on analyzing future development trends,potential applications,and challenges.The deep integration of artificial intelligence and nanophotonics is ushering in a new era for photonic technologies,offering unparalleled opportunities for fundamental research and industrial applications.展开更多
ID-based public key cryptosystem can be a good alternative for certifieate-based public key setting. This paper provides an efficient ID-based proxy multi signature scheme from pairings. In the random oracle model, we...ID-based public key cryptosystem can be a good alternative for certifieate-based public key setting. This paper provides an efficient ID-based proxy multi signature scheme from pairings. In the random oracle model, we prove that our new scheme is secure against existential delegation forgery with the assumption that Hess＇s scheme-1 is existential unforgeable, and that our new scheme is secure against existential proxy multi-signature forgery under the hardness assumption of the computational Diffie-Hellman problem.展开更多
A novel classification algorithm based on abnormal magnetic signals is proposed for ground moving targets which are made of ferromagnetic material. According to the effect of diverse targets on earth's magnetism,t...A novel classification algorithm based on abnormal magnetic signals is proposed for ground moving targets which are made of ferromagnetic material. According to the effect of diverse targets on earth's magnetism,the moving targets are detected by a magnetic sensor and classified with a simple computation method. The detection sensor is used for collecting a disturbance signal of earth magnetic field from an undetermined target. An optimum category match pattern of target signature is tested by training some statistical samples and designing a classification machine. Three ordinary targets are researched in the paper. The experimental results show that the algorithm has a low computation cost and a better sorting accuracy. This classification method can be applied to ground reconnaissance and target intrusion detection.展开更多
Predicting the value of one or more variables using the values of other variables is a very important process in the various engineering experiments that include large data that are difficult to obtain using different...Predicting the value of one or more variables using the values of other variables is a very important process in the various engineering experiments that include large data that are difficult to obtain using different measurement processes.Regression is one of the most important types of supervised machine learning,in which labeled data is used to build a prediction model,regression can be classified into three different categories:linear,polynomial,and logistic.In this research paper,different methods will be implemented to solve the linear regression problem,where there is a linear relationship between the target and the predicted output.Various methods for linear regression will be analyzed using the calculated Mean Square Error(MSE)between the target values and the predicted outputs.A huge set of regression samples will be used to construct the training dataset with selected sizes.A detailed comparison will be performed between three methods,including least-square fit;Feed-Forward Artificial Neural Network(FFANN),and Cascade Feed-Forward Artificial Neural Network(CFFANN),and recommendations will be raised.The proposed method has been tested in this research on random data samples,and the results were compared with the results of the most common method,which is the linear multiple regression method.It should be noted here that the procedures for building and testing the neural network will remain constant even if another sample of data is used.展开更多
In this paper,the integer N = pkq is called a <k,1>-integer,if p and q are odd primes with almost the same size and k is a positive integer. Such integers were previously proposed for various cryptographic appli...In this paper,the integer N = pkq is called a <k,1>-integer,if p and q are odd primes with almost the same size and k is a positive integer. Such integers were previously proposed for various cryptographic applications. The conditional factorization based on lattice theory for n-bit <k,1>-integersis considered,and there is an algorithm in time polynomial in n to factor these integers if the least significant 「((2k-1)n)/((3k-1)(k+1))」bits of p are given.展开更多
Noncoherent communication receivers (differential-detectors) have simple design, however, they always incur bit error rate (BER) performance loss up to 3dB compared to coherent receivers. In this paper, a differential...Noncoherent communication receivers (differential-detectors) have simple design, however, they always incur bit error rate (BER) performance loss up to 3dB compared to coherent receivers. In this paper, a differential-detector is proposed for impulse radio ultra wideband (IR-UWB) communication systems. The system employs bit-level differential phase shift keying (DPSK) combined with code division (CD) for IR-UWB signals to support multiple-access (MA). It is analyzed under additive white Gaussian noise (AWGN) corrupted by multiple-access interference (MAI) channel. Its BER performance is compared against a reference coherent receiver using Monte-Carlo simulation method. A closed form expression for its average probability of error is derived analytically. Simulation results and theoretical analysis confirm the applicability of the proposed differential-detector for IR-UWB communication systems.展开更多
文摘Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-aided diagnosis system is highly required.Ultrasound is an important examination technique for breast cancer diagnosis due to its low cost.Recently,many learning-based techniques have been introduced to classify breast cancer using breast ultrasound imaging dataset(BUSI)datasets;however,the manual handling is not an easy process and time consuming.The authors propose an EfficientNet-integrated ResNet deep network and XAI-based framework for accurately classifying breast cancer(malignant and benign).In the initial step,data augmentation is performed to increase the number of training samples.For this purpose,three-pixel flip mathematical equations are introduced:horizontal,vertical,and 90°.Later,two pretrained deep learning models were employed,skipped some layers,and fine-tuned.Both fine-tuned models are later trained using a deep transfer learning process and extracted features from the deeper layer.Explainable artificial intelligence-based analysed the performance of trained models.After that,a new feature selection technique is proposed based on the cuckoo search algorithm called cuckoo search controlled standard error mean.This technique selects the best features and fuses using a new parallel zeropadding maximum correlated coefficient features.In the end,the selection algorithm is applied again to the fused feature vector and classified using machine learning algorithms.The experimental process of the proposed framework is conducted on a publicly available BUSI and obtained 98.4%and 98%accuracy in two different experiments.Comparing the proposed framework is also conducted with recent techniques and shows improved accuracy.In addition,the proposed framework was executed less than the original deep learning models.
基金supported by the National Key R&D Program of China(Grant No.2024YFB3614600)the National Natural Science Foundation of China(Grant No.52402185)+1 种基金Guangzhou Basic and Applied Basic Research Foundation(Grant No.2025A1515011800)Shenzhen Science and Technology Program(Grant No.JCYJ20241202123712017)。
文摘The bidirectional convergence of artificial intelligence and nanophotonics drives photonic technologies toward unprecedented levels of intelligence and efficiency,fundamentally reshaping their design paradigms and application boundaries.With its powerful data-driven and nonlinear optimization capabilities,artificial intelligence has become a powerful tool for optical design,enabling the inverse design of nanophotonics devices while accelerating the forward computation of electromagnetic responses.Conversely,nanophotonics provides a wave-based computational platform,giving rise to novel optical neural networks that achieve high-speed parallel computing and efficient information processing.This paper reviews the latest progress in the bidirectional field of artificial intelligence and nanophotonics,analyzes the basic principles of various applications from a universal perspective,comprehensively evaluates the advantages and limitations of different research methods,and makes a forwardlooking outlook on the bidirectional integration of artificial intelligence and nanophotonics,focusing on analyzing future development trends,potential applications,and challenges.The deep integration of artificial intelligence and nanophotonics is ushering in a new era for photonic technologies,offering unparalleled opportunities for fundamental research and industrial applications.
基金Supported bythe National Key Basic Research andDevelopment Program (973 Program G1999035804),the NationalNatural Science Foundation of China (90204015 ,60473021) and theElitist Youth Foundation of Henan Province (021201400)
文摘ID-based public key cryptosystem can be a good alternative for certifieate-based public key setting. This paper provides an efficient ID-based proxy multi signature scheme from pairings. In the random oracle model, we prove that our new scheme is secure against existential delegation forgery with the assumption that Hess＇s scheme-1 is existential unforgeable, and that our new scheme is secure against existential proxy multi-signature forgery under the hardness assumption of the computational Diffie-Hellman problem.
基金Sponsored by the National Natural Science Foundation of China (60773129)the Excellent Youth Science and Technology Foundation of Anhui Province of China ( 08040106808)
文摘A novel classification algorithm based on abnormal magnetic signals is proposed for ground moving targets which are made of ferromagnetic material. According to the effect of diverse targets on earth's magnetism,the moving targets are detected by a magnetic sensor and classified with a simple computation method. The detection sensor is used for collecting a disturbance signal of earth magnetic field from an undetermined target. An optimum category match pattern of target signature is tested by training some statistical samples and designing a classification machine. Three ordinary targets are researched in the paper. The experimental results show that the algorithm has a low computation cost and a better sorting accuracy. This classification method can be applied to ground reconnaissance and target intrusion detection.
文摘Predicting the value of one or more variables using the values of other variables is a very important process in the various engineering experiments that include large data that are difficult to obtain using different measurement processes.Regression is one of the most important types of supervised machine learning,in which labeled data is used to build a prediction model,regression can be classified into three different categories:linear,polynomial,and logistic.In this research paper,different methods will be implemented to solve the linear regression problem,where there is a linear relationship between the target and the predicted output.Various methods for linear regression will be analyzed using the calculated Mean Square Error(MSE)between the target values and the predicted outputs.A huge set of regression samples will be used to construct the training dataset with selected sizes.A detailed comparison will be performed between three methods,including least-square fit;Feed-Forward Artificial Neural Network(FFANN),and Cascade Feed-Forward Artificial Neural Network(CFFANN),and recommendations will be raised.The proposed method has been tested in this research on random data samples,and the results were compared with the results of the most common method,which is the linear multiple regression method.It should be noted here that the procedures for building and testing the neural network will remain constant even if another sample of data is used.
基金the National Natural Science Foundation of China (No.60473021).
文摘In this paper,the integer N = pkq is called a <k,1>-integer,if p and q are odd primes with almost the same size and k is a positive integer. Such integers were previously proposed for various cryptographic applications. The conditional factorization based on lattice theory for n-bit <k,1>-integersis considered,and there is an algorithm in time polynomial in n to factor these integers if the least significant 「((2k-1)n)/((3k-1)(k+1))」bits of p are given.
文摘Noncoherent communication receivers (differential-detectors) have simple design, however, they always incur bit error rate (BER) performance loss up to 3dB compared to coherent receivers. In this paper, a differential-detector is proposed for impulse radio ultra wideband (IR-UWB) communication systems. The system employs bit-level differential phase shift keying (DPSK) combined with code division (CD) for IR-UWB signals to support multiple-access (MA). It is analyzed under additive white Gaussian noise (AWGN) corrupted by multiple-access interference (MAI) channel. Its BER performance is compared against a reference coherent receiver using Monte-Carlo simulation method. A closed form expression for its average probability of error is derived analytically. Simulation results and theoretical analysis confirm the applicability of the proposed differential-detector for IR-UWB communication systems.
