A Distinguishable Pseudo-Feature Synthesis Method for Generalized Zero-Shot LearningRead the full article
Computational Intelligence and Neuroscience is a forum for the interdisciplinary field of neural computing, neural engineering and artificial intelligence. The journal’s focus is on intelligent systems for computational neuroscience.
Chief Editor, Professor Cichocki, engages in world-leading research in the field of artificial intelligence and biomedical applications of advanced data analytics technologies.
Latest ArticlesMore articles
Research on Small Target Detection Technology Based on the MPH-SSD Algorithm
To address the problems of less semantic information and low measurement accuracy when the SSD (single shot multibox detector) algorithm detects small targets, an MPH-SSD (multiscale pyramid hybrid SSD) algorithm that integrates the attention mechanism and multiscale double pyramid feature enhancement is proposed in this paper. In this algorithm, firstly, the SSD algorithm is used to extract the feature map of small targets, and the shallow feature enhancement module is added to expand the receptive field of the shallow feature layer so as to enrich the semantic information in the feature layer for small targets and improve the expression ability of shallow features. The processed shallow feature layer and deep feature layer are fused at multiple scales, and the semantic information and location information are fused together to obtain a feature map with rich information. Secondly, the cascaded double pyramid structure is used to transfer from the deep layer to the shallow layer so that the context information between different feature layers can be effectively transferred and the feature information can be further strengthened. The hybrid attention mechanism can retain more context information in the network, adaptively adjust the feature map after addition and fusion, and reduce the background interference. The experimental analysis of MPH-SSD algorithm on Pascal VOC and MS COCO datasets shows that the map of this algorithm is 87.7% and 51.1%, respectively. The results show that the MPH-SSD algorithm can make better use of the feature information in the shallow feature layer in the process of small target detection and has better detection performance for small targets.
Enterprise Human Resource Management Model by Artificial Intelligence Digital Technology
Artificial intelligence (AI) is a potentially transformative force that is likely to change the role of management and organizational practices. AI is revolutionizing corporate decision-making and changing management structures. The visible effects of AI can be observed in key competencies and corporate processes such as knowledge management, as well as consumer outcomes including service quality perceptions and satisfaction. This study aims to optimize the human resource management (HRM) process, reduce the workload of human resource managers, and improve work efficiency. Based on AI digitization technology, a salary prediction model (SPM) is designed using a backpropagation neural network (BPNN), and the Nesterov and Adaptive Moment Estimation (Nadam) algorithms are integrated to optimize the model. Next, the content information of the resumes are used to predict the hiring salary of the candidates and validate the model. Results show that compared with other optimization algorithms, the final predicted result score of the Nadam optimization algorithm is 0.75%, and the training period is 186 s, providing the best optimization effect and the fastest convergence speed. Moreover, the BPNN-based SPM optimized by Nadam has good performance in the learning process and the accuracy rate can reach 79.4%, which verifies the validity of the SPM. The outcomes of this study can provide a reference for HRM systems based on data mining technology.
Cell Phenotype Classification Based on Joint of Texture Information and Multilayer Feature Extraction in DenseNet
Cell phenotype classification is a critical task in many medical applications, such as protein localization, gene effect identification, and cancer diagnosis in some types. Fluorescence imaging is the most efficient tool to analyze the biological characteristics of cells. So cell phenotype classification in fluorescence microscopy images has received increased attention from scientists in the last decade. The visible structures of cells are usually different in terms of shape, texture, relationship between intensities, etc. In this scope, most of the presented approaches use one type or joint of low-level and high-level features. In this paper, a new approach is proposed based on a combination of low-level and high-level features. An improved version of local quinary patterns is used to extract low-level texture features. Also, an innovative multilayer deep feature extraction method is performed to extract high-level features from DenseNet. In this respect, an output feature map of dense blocks is entered in a separate way to pooling and flatten layers, and finally, feature vectors are concatenated. The performance of the proposed approach is evaluated on the benchmark dataset 2D-HeLa in terms of accuracy. Also, the proposed approach is compared with state-of-the-art methods in terms of classification accuracy. Comparison of results demonstrates higher performance of the proposed approach in comparison with some efficient methods.
Novel Decision Modeling for Manufacturing Sustainability under Single-Valued Neutrosophic Hesitant Fuzzy Rough Aggregation Information
We developed a multicriteria decision-making method based on the list of novel single-valued neutrosophic hesitant fuzzy rough (SV-NHFR) weighted averaging and geometric aggregation operators to address the uncertainty and achieve the sustainability of the manufacturing business. In addition, a case study on choosing the optimum elements for a sustainable manufacturing sector was carried out. The proposed decision support method is then compared to other relevant methodologies, and a validity test is performed to show the reliability and validity of the new methodology. Sustainability is one of the most important issues the world economy is facing today. Several industrial businesses have incurred large financial losses as a result of their ignorance of sustainability issues. Manufacturers in industrialized countries have done a decent job of making sure that their businesses are sustainable over the long run. Modern companies use a lot of modern technologies. These include blockchain, artificial intelligence (AI), the Internet of Things (IoT), big data analytics (BDA), and fuzzy logic (fuzziness). These modern technologies support the continuation of life, either directly or indirectly. Therefore, it is of utmost importance to concentrate on those elements that encourage the adoption of sustainability. The goal of this study is to provide a framework for using cutting-edge technology to increase the adoption of sustainability in manufacturing firms. Under the guidance of single-valued neutrosophic hesitant fuzzy rough (SV-NHFR) aggregate information, it was advised to place a strong emphasis on addressing sustainability, waste management, environmental protection, manufacturing cost savings, and chemicals and resources. The results suggest that the proposed technique can solve the inadequacy of the existing decision method by the SV-NHFR aggregation operators in terms of decision adaptability.
Detection of Middlebox-Based Attacks in Healthcare Internet of Things Using Multiple Machine Learning Models
The huge number of network traffic data, the abundance of available network features, and the diversity of cyber-attack patterns mean that intrusion detection remains difficult even though many earlier efforts have succeeded in building the Internet of Healthcare Things (IoHT). The implementation of an effective algorithm to filter out most of the probable outliers of Round Trip Time (RTT) of packets recorded in the Internet environment is urgently required. Congestion and interference in networks can arise when numerous biosensors in an IoHT system all attempt to communicate at once. Internet of Health Things networks are susceptible to both intra- and internetwork interference. In this research, the Server-Side Includes (SSI) attack is a key issue because it allows for network compromise as part of Internal Attacks. Despite recent advancements, SSI detection remains difficult due to the vast amounts of network traffic data, the abundance of network features, and the diversity of cyber-attack patterns (DDoS, DoS, Satan, spoofing, etc.). With the help of sensors, physiological data may be collected and sent to distant servers, where they can be analyzed in real time by doctors to help them catch diseases in their earliest stages. This is made possible by the Internet of medical things (IoMT). Wireless data transfer, however, leaves it vulnerable to hackers, especially if the data being transferred are particularly private or sensitive. Security measures designed for devices with more storage space and processing power will not work on those with less. However, machine learning for intrusion detection can give a tailored security response to the needs of IoMT systems. For SSI detection, current methods are either inefficient because of the large number of packets that need to be caught and analyzed or unsuccessful because of outlier values in the RTTs obtained from the captured TCP packets. To the same end, “downstream detection” refers to the process of calculating the total length of all connections made after a certain point. As a means of improving the SSI detection algorithm’s throughput in a network environment, packet RTT outliers will be eliminated. Flow records are used as inputs by flow-based NIDS to determine whether or not a given flow is malicious. In order to detect middlebox-based attacks from two Medical Health IoT datasets, this paper proposes a unique architecture of explainable neural networks (XNN). The model’s accuracy in classifying attacks in dataset 1 of the IoHT is 99.7%t, besides achieving 99.4% accuracy in categorising attacks on IoHT dataset 2.
The Diagnostic Value of Artificial Intelligence Ultrasound S-Detect Technology for Thyroid Nodules
This study aimed to evaluate the consistency of ultrasound TI-RADS classification used by sonographers with different ultrasound diagnosis experience in the diagnosis of thyroid nodules and the diagnostic value of using artificial intelligence ultrasound S-Detect technology in the differentiation of benign and malignant thyroid lesions. 100 patients who underwent ultrasound examination of thyroid masses in our hospital from June 2019 to June 2021 and were further punctured or operated on were included in the study. Pathological results were used as the gold standard to evaluate ultrasound S-Detect technology and the value of TI-RADS classification and the combined application of the two in diagnosing benign and malignant thyroid TI-RADS 4 types of nodules, and the consistency of judgments of doctors of different ages is assessed by a Kappa value. There were 128 nodules in 100 patients, 51 benign nodules, and 77 malignant nodules. For senior physicians, the sensitivity of diagnosis using TI-RADS classification combined with ultrasound S-Detect technology is 93.5%, specificity is 94.1%, and accuracy is 93.8%; for middle-aged physicians using TI-RADS classification combined with ultrasound S-Detect technology for diagnosis, the sensitivity is 89.6%, specificity is 92.2%, and accuracy is 90.6%; for junior doctors, the sensitivity of diagnosis using TI-RADS classification combined with ultrasound S-Detect technology is 83.1%, specificity is 88.2%, and accuracy is 85.1%. Regardless of seniority, the combined application of artificial intelligence ultrasound S-Detect technology and TI-RADS classification can improve the diagnostic ability of sonographers for thyroid nodules and at the same time improve the consistency of judgment among physicians, and this is especially important for radiologists.