A crucial role in the BRT transportation system’s planning, development, and operation is the prediction of passenger numbers. Using time-series data, it is necessary to develop careful prediction models, appropriate...
详细信息
ISBN:
(数字)9798350367492
ISBN:
(纸本)9798350367508
A crucial role in the BRT transportation system’s planning, development, and operation is the prediction of passenger numbers. Using time-series data, it is necessary to develop careful prediction models, appropriate techniques, and an indepth understanding of the number of BRT Transjakarta passengers. A prediction model is sought based on comparing combined LSTM and BiLSTM experiments using three evaluation matrices and time. Historical data used from daily passenger data for 13 BRT Transjakarta corridors (1/01/2021-31/12/2023). The best prediction model was obtained from the BiLSTM-CNN combination with the lowest MSLE (0.0425), MAPE (0.1598), and SMAPE (15.9387) evaluation matrix values. However, it required a longer time (00:02:14). Predictions of passenger numbers on the 13 Transjakarta BRT corridors for the next 12 months can be made simultaneously by predicting fluctuations occurring simultaneously. The strongest positive correlation is in corridor 9-6, while the strongest negative correlation is in corridor 12-5. The prediction results must be understood by stakeholders, managers, and technopreneurs to develop and support appropriate strategies to increase the number of BRT passengers.
Due to the difficulties of brain tumor segmentation, this paper proposes a strategy for extracting brain tumors from three-dimensional MagneticResonance Image (MRI) and Computed Tomography (CT) scans utilizing3D U-Net...
详细信息
Due to the difficulties of brain tumor segmentation, this paper proposes a strategy for extracting brain tumors from three-dimensional MagneticResonance Image (MRI) and Computed Tomography (CT) scans utilizing3D U-Net Design and ResNet50, taken after by conventional classificationstrategies. In this inquire, the ResNet50 picked up accuracy with 98.96%, andthe 3D U-Net scored 97.99% among the different methods of deep *** is to be mentioned that traditional Convolutional Neural Network (CNN)gives 97.90% accuracy on top of the 3D MRI. In expansion, the imagefusion approach combines the multimodal images and makes a fused image toextricate more highlights from the medical images. Other than that, we haveidentified the loss function by utilizing several dice measurements approachand received Dice Result on top of a specific test case. The average mean scoreof dice coefficient and soft dice loss for three test cases was 0.0980. At thesame time, for two test cases, the sensitivity and specification were recordedto be 0.0211 and 0.5867 using patch level predictions. On the other hand,a software integration pipeline was integrated to deploy the concentratedmodel into the webserver for accessing it from the softwaresystem using theRepresentational state transfer (REST) API. Eventually, the suggested modelswere validated through the Area Under the Curve–Receiver CharacteristicOperator (AUC–ROC) curve and Confusion Matrix and compared with theexisting research articles to understand the underlying problem. ThroughComparative Analysis, we have extracted meaningful insights regarding braintumour segmentation and figured out potential gaps. Nevertheless, the proposed model can be adjustable in daily life and the healthcare domain to identify the infected regions and cancer of the brain through various imagingmodalities.
Speech Recognition focuses on developing advanced technologies that can recognize and translate spoken language into text. Automatic Speech Recognition (ASR) is an Artificial Intelligence (AI) technology that captures...
Speech Recognition focuses on developing advanced technologies that can recognize and translate spoken language into text. Automatic Speech Recognition (ASR) is an Artificial Intelligence (AI) technology that captures human voice from a mi-crophone and analyzes it based on spoken words to comprehend natural language. In Ethiopia, ASR models have been developed for specific local languages such as Amharic, Tigrigna, Wolaytta, and Afaan Oromo, but there has been a lack of research on ASR models for the Hadiyyisa language, which is also spoken in Ethiopia. The research study designed and developed an ASR model for the Hadiyyisa language. The researchers collected data from native speakers of the Hadiyyisa language and used Python programming to design and develop the deep learning model for the Hadiyissa ASR model. Different methods and techniques were used in the study to achieve the research objectives and complete the entire research process. The proposed model utilized deep learning algorithms including RNN, LSTM, BiLSTM, and CNN, along with suitable feature extraction techniques such as Mel Frequency Cepstral Coefficients (MFCC). The accuracy of the proposed ASR model was evaluated through experimentation, which demonstrated that the BiLSTM model outperformed the other deep learning models with an overall accuracy of 90.95 % Based on the experimental evidence, the proposed model was found to be better suited for ASR for the Hadiyyisa language.
Background: Cloud Computing has drawn much attention in the industry due to its cost-efficient schema along with more prospects, such as elasticity and scalability nature of Cloud Com-puting. One of the main service m...
详细信息
Background: Cloud Computing has drawn much attention in the industry due to its cost-efficient schema along with more prospects, such as elasticity and scalability nature of Cloud Com-puting. One of the main service models of a Cloud is software as a service, where many web services are published and hosted in the Cloud environment. Many web services offered in a Cloud have similar functionality, with different of characteristics non-functional requirements such as Quality of Service (QoS). In addition, as individual web services are limited in their capability. Therefore, there is a need for composing existing services to create new functionality in the form of composite service to fulfill the requirements of Cloud user for certain processes. Methods: This paper introduces a fuzzy rule approach to compose web service based on QoS from different Cloud Computing providers. The fuzzy rule is generated based on QoS of discovered web service from Cloud in order to compose web services that only match user requirements. The proposed model is based on an agent that is responsible for discovering and composing web service that only stratified user requirements Result: the experimental result shows that the proposed model is efficient in terms of time and the use of fuzzy rules to compose web services from different Cloud providers under different specifica-tions and configurations of Cloud Computing environment. Conclusion: In this paper, an agent-based model was proposed to compose web services based on fuzzy rule in Cloud environment. The agent is responsible for discovering web services and generat-ing composition plans based on offered QoS for each web service. The agent employs a set of fuzzy rules to carry out an intelligent selection to select the best composition plan that fulfills the requirements of the end user. The model was implemented on CloudSim to ensure the validity of the proposed model and performance time analysis was performed that showed good result i
software or application testing is a process of executing a program with the goal of finding defect to make better system. In software testing phase, writing test cases is one of the important activities. Manually wri...
详细信息
The integration of Internet of Things (IoT) technologies into modern homes has enhanced safety and comfort, particularly in detecting gas leaks, which pose serious fire hazards. Gas leaks can often be detected by smel...
详细信息
ISBN:
(数字)9798331517601
ISBN:
(纸本)9798331517618
The integration of Internet of Things (IoT) technologies into modern homes has enhanced safety and comfort, particularly in detecting gas leaks, which pose serious fire hazards. Gas leaks can often be detected by smell, but this method fails when no one is present. Previous research using microcontrollers and sensors to detect gas leaks faced challenges with accuracy due to noise interference. This paper proposes the use of a Kalman filter, developed by Rudolf Emil Kalman in 1960, to improve gas leak detection accuracy by filtering out noise. The system comprises an Arduino Nano, ESP8266 WiFi module, MQ-2 gas sensor, buzzer, and ThingSpeak cloud platform. By applying the Kalman filter, noise and data oscillations are reduced, enhancing detection accuracy. Experimental results show the system effectively detects gas leaks, provides real-time data, and triggers alarms. Future improvements could include additional sensors and features to further increase the system’s reliability and functionality.
Due to cloud security concerns, there is an increasing interest in information retrieval systems that can support private queries over public documents. It is desirable for oblivious document ranking and retrieval in ...
详细信息
ISBN:
(数字)9798350381993
ISBN:
(纸本)9798350382006
Due to cloud security concerns, there is an increasing interest in information retrieval systems that can support private queries over public documents. It is desirable for oblivious document ranking and retrieval in public cloud at lower cost and faster speed without revealing query-related information. Currently, the term frequency-inverse document frequency (TF-IDF) and private information retrieval (PIR) techniques are used to solve this problem, but the encryption operation time is over dominant. Motivated by the observation of the sparsity of the TF-IDF matrix, we propose an efficient approach for oblivious document ranking and retrieval, called E-Coeus. It takes advantage of the high sparsity of the TF-IDF matrix to rearrange the matrix. Our method accelerates the speed of PIR inadvertently retrieving documents and reduces the user retrieval delay time. In a stand-alone experiment for a TF-IDF matrix of 1.2M rows and 64K columns with the sparsity of 10%, E-Coeus improves the document ranking and retrieval performance by 23% over the state-of-the-art approach, Coeus. With cluster of 64 machines, E-Coeus improves the performance by 34% over Coeus when the TF-IDF matrix sparsity is 30%.
Erasure codes have been widely applied to in-memory key-value storage systems for high reliability and low redundancy. In distributed in-memory key-value storage systems, update operations are relatively frequent, esp...
详细信息
ISBN:
(数字)9798350381993
ISBN:
(纸本)9798350382006
Erasure codes have been widely applied to in-memory key-value storage systems for high reliability and low redundancy. In distributed in-memory key-value storage systems, update operations are relatively frequent, especially the partial-stripe update, which makes data update more challenging. Recently, existing research has been based on appending logs to accelerate parity data write. However, its logs are stored on disks, which decreases the system performance significantly. Therefore, we propose a novel in-memory key-value storage architecture, DNVPL, which utilizes NVRAM to log parity data. Our main idea is to design an appending-only update scheme to tradeoff the memory cost and the update overhead. We implement DNVPL with an in-memory key-value storage prototype, called LogKV. We evaluate it with different workloads. The experiments show that our scheme achieves high update performance from different metrics. Our scheme can reduce update latency by up to 49% and save storage space by 48% compared to the state-of-the-art schemes.
AlphaStar, a multi-agent intelligence program, is a new member of Alpha's gamer software. Rated at Grandmaster level in the empirical evaluation shows that AlphaStar has been a great success in engineering, which ...
详细信息
Link prediction analysis becomes vital to acquire a deeper understanding of events underlying social networks interactions and connections especially in current evolving and large-scale social networks. Traditional li...
详细信息
暂无评论